236 files changed, 2736 insertions, 2025 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index 4b0669cbb3b0..2505740b81d2 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -30,6 +30,10 @@ config OPROFILE_EVENT_MULTIPLEX
 config HAVE_OPROFILE
        bool
+config OPROFILE_NMI_TIMER
+        def_bool y
+        depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 config KPROBES
        bool "Kprobes"
        depends on MODULES
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e084b7e981e8..b259c7c644e3 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -220,8 +220,9 @@ config NEED_MACH_MEMORY_H
          be avoided when possible.
 config PHYS_OFFSET
-        hex "Physical address of main memory"
+        hex "Physical address of main memory" if MMU
        depends on !ARM_PATCH_PHYS_VIRT && !NEED_MACH_MEMORY_H
+        default DRAM_BASE if !MMU
        help
          Please provide the physical address corresponding to the
          location of main memory in your system.
@@ -1245,7 +1246,7 @@ config PL310_ERRATA_588369
 config ARM_ERRATA_720789
        bool "ARM errata: TLBIASIDIS and TLBIMVAIS operations can broadcast a faulty ASID"
-        depends on CPU_V7 && SMP
+        depends on CPU_V7
        help
          This option enables the workaround for the 720789 Cortex-A9 (prior to
          r2p0) erratum. A faulty ASID can be sent to the other CPUs for the
@@ -1281,7 +1282,7 @@ config ARM_ERRATA_743622
 config ARM_ERRATA_751472
        bool "ARM errata: Interrupted ICIALLUIS may prevent completion of broadcasted operation"
-        depends on CPU_V7 && SMP
+        depends on CPU_V7
        help
          This option enables the workaround for the 751472 Cortex-A9 (prior
          to r3p0) erratum. An interrupted ICIALLUIS operation may prevent the
diff --git a/arch/arm/common/pl330.c b/arch/arm/common/pl330.c
index f407a6b35d3d..8d8df744f7a5 100644
--- a/arch/arm/common/pl330.c
+++ b/arch/arm/common/pl330.c
@@ -221,17 +221,6 @@
 */
 #define MCODE_BUFF_PER_REQ      256
-/*
- * Mark a _pl330_req as free.
- * We do it by writing DMAEND as the first instruction
- * because no valid request is going to have DMAEND as
- * its first instruction to execute.
- */
-#define MARK_FREE(req)  do { \
-                                _emit_END(0, (req)->mc_cpu); \
-                                (req)->mc_len = 0; \
-                        } while (0)
 /* If the _pl330_req is available to the client */
 #define IS_FREE(req)    (*((u8 *)((req)->mc_cpu)) == CMD_DMAEND)
@@ -301,8 +290,10 @@ struct pl330_thread {
        struct pl330_dmac *dmac;
        /* Only two at a time */
        struct _pl330_req req[2];
-        /* Index of the last submitted request */
+        /* Index of the last enqueued request */
        unsigned lstenq;
+        /* Index of the last submitted request or -1 if the DMA is stopped */
+        int req_running;
 };
 enum pl330_dmac_state {
@@ -778,6 +769,22 @@ static inline void _execute_DBGINSN(struct pl330_thread *thrd,
        writel(0, regs + DBGCMD);
 }
+/*
+ * Mark a _pl330_req as free.
+ * We do it by writing DMAEND as the first instruction
+ * because no valid request is going to have DMAEND as
+ * its first instruction to execute.
+ */
+static void mark_free(struct pl330_thread *thrd, int idx)
+{
+        struct _pl330_req *req = &thrd->req[idx];
+        _emit_END(0, req->mc_cpu);
+        req->mc_len = 0;
+        thrd->req_running = -1;
+}
 static inline u32 _state(struct pl330_thread *thrd)
 {
        void __iomem *regs = thrd->dmac->pinfo->base;
@@ -836,31 +843,6 @@ static inline u32 _state(struct pl330_thread *thrd)
        }
 }
-/* If the request 'req' of thread 'thrd' is currently active */
-static inline bool _req_active(struct pl330_thread *thrd,
-                struct _pl330_req *req)
-{
-        void __iomem *regs = thrd->dmac->pinfo->base;
-        u32 buf = req->mc_bus, pc = readl(regs + CPC(thrd->id));
-        if (IS_FREE(req))
-                return false;
-        return (pc >= buf && pc <= buf + req->mc_len) ? true : false;
-}
-/* Returns 0 if the thread is inactive, ID of active req + 1 otherwise */
-static inline unsigned _thrd_active(struct pl330_thread *thrd)
-{
-        if (_req_active(thrd, &thrd->req[0]))
-                return 1; /* First req active */
-        if (_req_active(thrd, &thrd->req[1]))
-                return 2; /* Second req active */
-        return 0;
-}
 static void _stop(struct pl330_thread *thrd)
 {
        void __iomem *regs = thrd->dmac->pinfo->base;
@@ -892,17 +874,22 @@ static bool _trigger(struct pl330_thread *thrd)
        struct _arg_GO go;
        unsigned ns;
        u8 insn[6] = {0, 0, 0, 0, 0, 0};
+        int idx;
        /* Return if already ACTIVE */
        if (_state(thrd) != PL330_STATE_STOPPED)
                return true;
-        if (!IS_FREE(&thrd->req[1 - thrd->lstenq]))
+        idx = 1 - thrd->lstenq;
-                req = &thrd->req[1 - thrd->lstenq];
+        if (!IS_FREE(&thrd->req[idx]))
-        else if (!IS_FREE(&thrd->req[thrd->lstenq]))
+                req = &thrd->req[idx];
-                req = &thrd->req[thrd->lstenq];
+        else {
-        else
+                idx = thrd->lstenq;
-                req = NULL;
+                if (!IS_FREE(&thrd->req[idx]))
+                        req = &thrd->req[idx];
+                else
+                        req = NULL;
+        }
        /* Return if no request */
        if (!req || !req->r)
@@ -933,6 +920,8 @@ static bool _trigger(struct pl330_thread *thrd)
        /* Only manager can execute GO */
        _execute_DBGINSN(thrd, insn, true);
+        thrd->req_running = idx;
        return true;
 }
@@ -1382,8 +1371,8 @@ static void pl330_dotask(unsigned long data)
                        thrd->req[0].r = NULL;
                        thrd->req[1].r = NULL;
-                        MARK_FREE(&thrd->req[0]);
+                        mark_free(thrd, 0);
-                        MARK_FREE(&thrd->req[1]);
+                        mark_free(thrd, 1);
                        /* Clear the reset flag */
                        pl330->dmac_tbd.reset_chan &= ~(1 << i);
@@ -1461,14 +1450,12 @@ int pl330_update(const struct pl330_info *pi)
                        thrd = &pl330->channels[id];
-                        active = _thrd_active(thrd);
+                        active = thrd->req_running;
-                        if (!active) /* Aborted */
+                        if (active == -1) /* Aborted */
                                continue;
-                        active -= 1;
                        rqdone = &thrd->req[active];
-                        MARK_FREE(rqdone);
+                        mark_free(thrd, active);
                        /* Get going again ASAP */
                        _start(thrd);
@@ -1509,7 +1496,7 @@ int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op)
        struct pl330_thread *thrd = ch_id;
        struct pl330_dmac *pl330;
        unsigned long flags;
-        int ret = 0, active;
+        int ret = 0, active = thrd->req_running;
        if (!thrd || thrd->free || thrd->dmac->state == DYING)
                return -EINVAL;
@@ -1525,28 +1512,24 @@ int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op)
                thrd->req[0].r = NULL;
                thrd->req[1].r = NULL;
-                MARK_FREE(&thrd->req[0]);
+                mark_free(thrd, 0);
-                MARK_FREE(&thrd->req[1]);
+                mark_free(thrd, 1);
                break;
        case PL330_OP_ABORT:
-                active = _thrd_active(thrd);
                /* Make sure the channel is stopped */
                _stop(thrd);
                /* ABORT is only for the active req */
-                if (!active)
+                if (active == -1)
                        break;
-                active--;
                thrd->req[active].r = NULL;
-                MARK_FREE(&thrd->req[active]);
+                mark_free(thrd, active);
                /* Start the next */
        case PL330_OP_START:
-                if (!_thrd_active(thrd) && !_start(thrd))
+                if ((active == -1) && !_start(thrd))
                        ret = -EIO;
                break;
@@ -1587,14 +1570,13 @@ int pl330_chan_status(void *ch_id, struct pl330_chanstatus *pstatus)
        else
                pstatus->faulting = false;
-        active = _thrd_active(thrd);
+        active = thrd->req_running;
-        if (!active) {
+        if (active == -1) {
                /* Indicate that the thread is not running */
                pstatus->top_req = NULL;
                pstatus->wait_req = NULL;
        } else {
-                active--;
                pstatus->top_req = thrd->req[active].r;
                pstatus->wait_req = !IS_FREE(&thrd->req[1 - active])
                                        ? thrd->req[1 - active].r : NULL;
@@ -1659,9 +1641,9 @@ void *pl330_request_channel(const struct pl330_info *pi)
                                thrd->free = false;
                                thrd->lstenq = 1;
                                thrd->req[0].r = NULL;
-                                MARK_FREE(&thrd->req[0]);
+                                mark_free(thrd, 0);
                                thrd->req[1].r = NULL;
-                                MARK_FREE(&thrd->req[1]);
+                                mark_free(thrd, 1);
                                break;
                        }
                }
@@ -1767,14 +1749,14 @@ static inline void _reset_thread(struct pl330_thread *thrd)
        thrd->req[0].mc_bus = pl330->mcode_bus
                                + (thrd->id * pi->mcbufsz);
        thrd->req[0].r = NULL;
-        MARK_FREE(&thrd->req[0]);
+        mark_free(thrd, 0);
        thrd->req[1].mc_cpu = thrd->req[0].mc_cpu
                                + pi->mcbufsz / 2;
        thrd->req[1].mc_bus = thrd->req[0].mc_bus
                                + pi->mcbufsz / 2;
        thrd->req[1].r = NULL;
-        MARK_FREE(&thrd->req[1]);
+        mark_free(thrd, 1);
 }
 static int dmac_alloc_threads(struct pl330_dmac *pl330)
diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig
index 11a4192197c8..cf497ce41dfe 100644
--- a/arch/arm/configs/imx_v4_v5_defconfig
+++ b/arch/arm/configs/imx_v4_v5_defconfig
@@ -18,9 +18,10 @@ CONFIG_ARCH_MXC=y
 CONFIG_ARCH_IMX_V4_V5=y
 CONFIG_ARCH_MX1ADS=y
 CONFIG_MACH_SCB9328=y
+CONFIG_MACH_APF9328=y
 CONFIG_MACH_MX21ADS=y
 CONFIG_MACH_MX25_3DS=y
-CONFIG_MACH_EUKREA_CPUIMX25=y
+CONFIG_MACH_EUKREA_CPUIMX25SD=y
 CONFIG_MACH_MX27ADS=y
 CONFIG_MACH_PCM038=y
 CONFIG_MACH_CPUIMX27=y
@@ -72,17 +73,16 @@ CONFIG_MTD_CFI_GEOMETRY=y
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_PHYSMAP=y
 CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_MXC=y
 CONFIG_MTD_UBI=y
 CONFIG_MISC_DEVICES=y
 CONFIG_EEPROM_AT24=y
 CONFIG_EEPROM_AT25=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_SMC91X=y
 CONFIG_DM9000=y
+CONFIG_SMC91X=y
 CONFIG_SMC911X=y
-# CONFIG_NETDEV_1000 is not set
+CONFIG_SMSC_PHY=y
-# CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT_MOUSEDEV is not set
 CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_KEYBOARD is not set
@@ -100,6 +100,7 @@ CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_IMX=y
 CONFIG_SPI=y
 CONFIG_SPI_IMX=y
+CONFIG_SPI_SPIDEV=y
 CONFIG_W1=y
 CONFIG_W1_MASTER_MXC=y
 CONFIG_W1_SLAVE_THERM=y
@@ -139,6 +140,7 @@ CONFIG_MMC=y
 CONFIG_MMC_MXC=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
 CONFIG_LEDS_MC13783=y
 CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=y
diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig
index a7e777581378..945a34f2a34d 100644
--- a/arch/arm/configs/omap1_defconfig
+++ b/arch/arm/configs/omap1_defconfig
@@ -48,12 +48,7 @@ CONFIG_MACH_SX1=y
 CONFIG_MACH_NOKIA770=y
 CONFIG_MACH_AMS_DELTA=y
 CONFIG_MACH_OMAP_GENERIC=y
-CONFIG_OMAP_ARM_216MHZ=y
-CONFIG_OMAP_ARM_195MHZ=y
-CONFIG_OMAP_ARM_192MHZ=y
 CONFIG_OMAP_ARM_182MHZ=y
-CONFIG_OMAP_ARM_168MHZ=y
-# CONFIG_OMAP_ARM_60MHZ is not set
 # CONFIG_ARM_THUMB is not set
 CONFIG_PCCARD=y
 CONFIG_OMAP_CF=y
diff --git a/arch/arm/include/asm/unwind.h b/arch/arm/include/asm/unwind.h
index a5edf421005c..d1c3f3a71c94 100644
--- a/arch/arm/include/asm/unwind.h
+++ b/arch/arm/include/asm/unwind.h
@@ -30,14 +30,15 @@ enum unwind_reason_code {
 };
 struct unwind_idx {
-        unsigned long addr;
+        unsigned long addr_offset;
        unsigned long insn;
 };
 struct unwind_table {
        struct list_head list;
-        struct unwind_idx *start;
+        const struct unwind_idx *start;
-        struct unwind_idx *stop;
+        const struct unwind_idx *origin;
+        const struct unwind_idx *stop;
        unsigned long begin_addr;
        unsigned long end_addr;
 };
@@ -49,15 +50,6 @@ extern struct unwind_table *unwind_table_add(unsigned long start,
 extern void unwind_table_del(struct unwind_table *tab);
 extern void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk);
-#ifdef CONFIG_ARM_UNWIND
-extern int __init unwind_init(void);
-#else
-static inline int __init unwind_init(void)
-{
-        return 0;
-}
-#endif
 #endif  /* !__ASSEMBLY__ */
 #ifdef CONFIG_ARM_UNWIND
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index c475379199b1..88b0941ce51e 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -353,15 +353,15 @@ validate_group(struct perf_event *event)
        fake_pmu.used_mask = fake_used_mask;
        if (!validate_event(&fake_pmu, leader))
-                return -ENOSPC;
+                return -EINVAL;
        list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
                if (!validate_event(&fake_pmu, sibling))
-                        return -ENOSPC;
+                        return -EINVAL;
        }
        if (!validate_event(&fake_pmu, event))
-                return -ENOSPC;
+                return -EINVAL;
        return 0;
 }
@@ -640,6 +640,9 @@ static struct platform_device_id armpmu_plat_device_ids[] = {
 static int __devinit armpmu_device_probe(struct platform_device *pdev)
 {
+        if (!cpu_pmu)
+                return -ENODEV;
        cpu_pmu->plat_device = pdev;
        return 0;
 }
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 3d0c6fb74ae4..e8e8fe505df1 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -183,7 +183,8 @@ void cpu_idle(void)
        /* endless idle loop with no priority at all */
        while (1) {
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                leds_event(led_idle_start);
                while (!need_resched()) {
 #ifdef CONFIG_HOTPLUG_CPU
@@ -213,7 +214,8 @@ void cpu_idle(void)
                        }
                }
                leds_event(led_idle_end);
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
                schedule();
                preempt_disable();
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 3448a3f9cc8c..c0b59bff6be6 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -52,6 +52,7 @@
 #include <asm/mach/time.h>
 #include <asm/traps.h>
 #include <asm/unwind.h>
+#include <asm/memblock.h>
 #if defined(CONFIG_DEPRECATED_PARAM_STRUCT)
 #include "compat.h"
@@ -895,8 +896,6 @@ void __init setup_arch(char **cmdline_p)
 {
        struct machine_desc *mdesc;
-        unwind_init();
        setup_processor();
        mdesc = setup_machine_fdt(__atags_pointer);
        if (!mdesc)
@@ -904,6 +903,12 @@ void __init setup_arch(char **cmdline_p)
        machine_desc = mdesc;
        machine_name = mdesc->name;
+#ifdef CONFIG_ZONE_DMA
+        if (mdesc->dma_zone_size) {
+                extern unsigned long arm_dma_zone_size;
+                arm_dma_zone_size = mdesc->dma_zone_size;
+        }
+#endif
        if (mdesc->soft_reboot)
                reboot_setup("s");
@@ -934,12 +939,6 @@ void __init setup_arch(char **cmdline_p)
        tcm_init();
-#ifdef CONFIG_ZONE_DMA
-        if (mdesc->dma_zone_size) {
-                extern unsigned long arm_dma_zone_size;
-                arm_dma_zone_size = mdesc->dma_zone_size;
-        }
-#endif
 #ifdef CONFIG_MULTI_IRQ_HANDLER
        handle_arch_irq = mdesc->handle_irq;
 #endif
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index e7e8365795c3..00df012c4678 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -67,7 +67,7 @@ EXPORT_SYMBOL(__aeabi_unwind_cpp_pr2);
 struct unwind_ctrl_block {
        unsigned long vrs[16];          /* virtual register set */
-        unsigned long *insn;            /* pointer to the current instructions word */
+        const unsigned long *insn;      /* pointer to the current instructions word */
        int entries;                    /* number of entries left to interpret */
        int byte;                       /* current byte number in the instructions word */
 };
@@ -83,8 +83,9 @@ enum regs {
        PC = 15
 };
-extern struct unwind_idx __start_unwind_idx[];
+extern const struct unwind_idx __start_unwind_idx[];
-extern struct unwind_idx __stop_unwind_idx[];
+static const struct unwind_idx *__origin_unwind_idx;
+extern const struct unwind_idx __stop_unwind_idx[];
 static DEFINE_SPINLOCK(unwind_lock);
 static LIST_HEAD(unwind_tables);
@@ -98,45 +99,99 @@ static LIST_HEAD(unwind_tables);
 })
 /*
- * Binary search in the unwind index. The entries entries are
+ * Binary search in the unwind index. The entries are
 * guaranteed to be sorted in ascending order by the linker.
+ *
+ * start = first entry
+ * origin = first entry with positive offset (or stop if there is no such entry)
+ * stop - 1 = last entry
 */
-static struct unwind_idx *search_index(unsigned long addr,
+static const struct unwind_idx *search_index(unsigned long addr,
-                                       struct unwind_idx *first,
+                                       const struct unwind_idx *start,
-                                       struct unwind_idx *last)
+                                       const struct unwind_idx *origin,
+                                       const struct unwind_idx *stop)
 {
-        pr_debug("%s(%08lx, %p, %p)\n", __func__, addr, first, last);
+        unsigned long addr_prel31;
+        pr_debug("%s(%08lx, %p, %p, %p)\n",
+                        __func__, addr, start, origin, stop);
+        /*
+         * only search in the section with the matching sign. This way the
+         * prel31 numbers can be compared as unsigned longs.
+         */
+        if (addr < (unsigned long)start)
+                /* negative offsets: [start; origin) */
+                stop = origin;
+        else
+                /* positive offsets: [origin; stop) */
+                start = origin;
+        /* prel31 for address relavive to start */
+        addr_prel31 = (addr - (unsigned long)start) & 0x7fffffff;
-        if (addr < first->addr) {
+        while (start < stop - 1) {
+                const struct unwind_idx *mid = start + ((stop - start) >> 1);
+                /*
+                 * As addr_prel31 is relative to start an offset is needed to
+                 * make it relative to mid.
+                 */
+                if (addr_prel31 - ((unsigned long)mid - (unsigned long)start) <
+                                mid->addr_offset)
+                        stop = mid;
+                else {
+                        /* keep addr_prel31 relative to start */
+                        addr_prel31 -= ((unsigned long)mid -
+                                        (unsigned long)start);
+                        start = mid;
+                }
+        }
+        if (likely(start->addr_offset <= addr_prel31))
+                return start;
+        else {
                pr_warning("unwind: Unknown symbol address %08lx\n", addr);
                return NULL;
-        } else if (addr >= last->addr)
+        }
-                return last;
+}
-        while (first < last - 1) {
+static const struct unwind_idx *unwind_find_origin(
-                struct unwind_idx *mid = first + ((last - first + 1) >> 1);
+                const struct unwind_idx *start, const struct unwind_idx *stop)
+{
+        pr_debug("%s(%p, %p)\n", __func__, start, stop);
+        while (start < stop) {
+                const struct unwind_idx *mid = start + ((stop - start) >> 1);
-                if (addr < mid->addr)
+                if (mid->addr_offset >= 0x40000000)
-                        last = mid;
+                        /* negative offset */
+                        start = mid + 1;
                else
-                        first = mid;
+                        /* positive offset */
+                        stop = mid;
        }
+        pr_debug("%s -> %p\n", __func__, stop);
-        return first;
+        return stop;
 }
-static struct unwind_idx *unwind_find_idx(unsigned long addr)
+static const struct unwind_idx *unwind_find_idx(unsigned long addr)
 {
-        struct unwind_idx *idx = NULL;
+        const struct unwind_idx *idx = NULL;
        unsigned long flags;
        pr_debug("%s(%08lx)\n", __func__, addr);
-        if (core_kernel_text(addr))
+        if (core_kernel_text(addr)) {
+                if (unlikely(!__origin_unwind_idx))
+                        __origin_unwind_idx =
+                                unwind_find_origin(__start_unwind_idx,
+                                                __stop_unwind_idx);
                /* main unwind table */
                idx = search_index(addr, __start_unwind_idx,
-                                   __stop_unwind_idx - 1);
+                                   __origin_unwind_idx,
-        else {
+                                   __stop_unwind_idx);
+        } else {
                /* module unwind tables */
                struct unwind_table *table;
@@ -145,7 +200,8 @@ static struct unwind_idx *unwind_find_idx(unsigned long addr)
                        if (addr >= table->begin_addr &&
                            addr < table->end_addr) {
                                idx = search_index(addr, table->start,
-                                                   table->stop - 1);
+                                                   table->origin,
+                                                   table->stop);
                                /* Move-to-front to exploit common traces */
                                list_move(&table->list, &unwind_tables);
                                break;
@@ -274,7 +330,7 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 int unwind_frame(struct stackframe *frame)
 {
        unsigned long high, low;
-        struct unwind_idx *idx;
+        const struct unwind_idx *idx;
        struct unwind_ctrl_block ctrl;
        /* only go to a higher address on the stack */
@@ -399,7 +455,6 @@ struct unwind_table *unwind_table_add(unsigned long start, unsigned long size,
                                      unsigned long text_size)
 {
        unsigned long flags;
-        struct unwind_idx *idx;
        struct unwind_table *tab = kmalloc(sizeof(*tab), GFP_KERNEL);
        pr_debug("%s(%08lx, %08lx, %08lx, %08lx)\n", __func__, start, size,
@@ -408,15 +463,12 @@ struct unwind_table *unwind_table_add(unsigned long start, unsigned long size,
        if (!tab)
                return tab;
-        tab->start = (struct unwind_idx *)start;
+        tab->start = (const struct unwind_idx *)start;
-        tab->stop = (struct unwind_idx *)(start + size);
+        tab->stop = (const struct unwind_idx *)(start + size);
+        tab->origin = unwind_find_origin(tab->start, tab->stop);
        tab->begin_addr = text_addr;
        tab->end_addr = text_addr + text_size;
-        /* Convert the symbol addresses to absolute values */
-        for (idx = tab->start; idx < tab->stop; idx++)
-                idx->addr = prel31_to_addr(&idx->addr);
        spin_lock_irqsave(&unwind_lock, flags);
        list_add_tail(&tab->list, &unwind_tables);
        spin_unlock_irqrestore(&unwind_lock, flags);
@@ -437,16 +489,3 @@ void unwind_table_del(struct unwind_table *tab)
        kfree(tab);
 }
-int __init unwind_init(void)
-{
-        struct unwind_idx *idx;
-        /* Convert the symbol addresses to absolute values */
-        for (idx = __start_unwind_idx; idx < __stop_unwind_idx; idx++)
-                idx->addr = prel31_to_addr(&idx->addr);
-        pr_debug("unwind: ARM stack unwinding initialised\n");
-        return 0;
-}
diff --git a/arch/arm/mach-at91/at91rm9200_devices.c b/arch/arm/mach-at91/at91rm9200_devices.c
index 66591fa53e05..ad930688358c 100644
--- a/arch/arm/mach-at91/at91rm9200_devices.c
+++ b/arch/arm/mach-at91/at91rm9200_devices.c
@@ -83,7 +83,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data) {}
 *  USB Device (Gadget)
 * -------------------------------------------------------------------- */
-#ifdef CONFIG_USB_GADGET_AT91
+#ifdef CONFIG_USB_AT91
 static struct at91_udc_data udc_data;
 static struct resource udc_resources[] = {
diff --git a/arch/arm/mach-at91/at91sam9260.c b/arch/arm/mach-at91/at91sam9260.c
index b84a9f642f59..0d20677fbef0 100644
--- a/arch/arm/mach-at91/at91sam9260.c
+++ b/arch/arm/mach-at91/at91sam9260.c
@@ -195,9 +195,9 @@ static struct clk_lookup periph_clocks_lookups[] = {
        CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tc0_clk),
        CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.0", &tc1_clk),
        CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc2_clk),
-        CLKDEV_CON_DEV_ID("t3_clk", "atmel_tcb.1", &tc3_clk),
+        CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.1", &tc3_clk),
-        CLKDEV_CON_DEV_ID("t4_clk", "atmel_tcb.1", &tc4_clk),
+        CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.1", &tc4_clk),
-        CLKDEV_CON_DEV_ID("t5_clk", "atmel_tcb.1", &tc5_clk),
+        CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.1", &tc5_clk),
        CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc_clk),
        /* more usart lookup table for DT entries */
        CLKDEV_CON_DEV_ID("usart", "fffff200.serial", &mck),
diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c
index 25e3464fb07f..629fa9774972 100644
--- a/arch/arm/mach-at91/at91sam9260_devices.c
+++ b/arch/arm/mach-at91/at91sam9260_devices.c
@@ -84,7 +84,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data) {}
 *  USB Device (Gadget)
 * -------------------------------------------------------------------- */
-#ifdef CONFIG_USB_GADGET_AT91
+#ifdef CONFIG_USB_AT91
 static struct at91_udc_data udc_data;
 static struct resource udc_resources[] = {
diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
index ae78f4d03b73..a178b58b0b9c 100644
--- a/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/arch/arm/mach-at91/at91sam9261_devices.c
@@ -87,7 +87,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data) {}
 *  USB Device (Gadget)
 * -------------------------------------------------------------------- */
-#ifdef CONFIG_USB_GADGET_AT91
+#ifdef CONFIG_USB_AT91
 static struct at91_udc_data udc_data;
 static struct resource udc_resources[] = {
diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c
index ad017eb1f8df..d5fbac9ff4fa 100644
--- a/arch/arm/mach-at91/at91sam9263_devices.c
+++ b/arch/arm/mach-at91/at91sam9263_devices.c
@@ -92,7 +92,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data) {}
 *  USB Device (Gadget)
 * -------------------------------------------------------------------- */
-#ifdef CONFIG_USB_GADGET_AT91
+#ifdef CONFIG_USB_AT91
 static struct at91_udc_data udc_data;
 static struct resource udc_resources[] = {
diff --git a/arch/arm/mach-at91/include/mach/system_rev.h b/arch/arm/mach-at91/include/mach/system_rev.h
index 8f4866045b41..ec164a4124c9 100644
--- a/arch/arm/mach-at91/include/mach/system_rev.h
+++ b/arch/arm/mach-at91/include/mach/system_rev.h
@@ -19,7 +19,7 @@
 #define BOARD_HAVE_NAND_16BIT   (1 << 31)
 static inline int board_have_nand_16bit(void)
 {
-        return system_rev & BOARD_HAVE_NAND_16BIT;
+        return (system_rev & BOARD_HAVE_NAND_16BIT) ? 1 : 0;
 }
 #endif /* __ARCH_SYSTEM_REV_H__ */
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index 1d7d24995226..6659a90dbcad 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -753,7 +753,7 @@ static struct snd_platform_data da850_evm_snd_data = {
        .num_serializer = ARRAY_SIZE(da850_iis_serializer_direction),
        .tdm_slots      = 2,
        .serial_dir     = da850_iis_serializer_direction,
-        .asp_chan_q     = EVENTQ_1,
+        .asp_chan_q     = EVENTQ_0,
        .version        = MCASP_VERSION_2,
        .txnumevt       = 1,
        .rxnumevt       = 1,
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index 1918ae711428..46e1f4173b97 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -107,7 +107,7 @@ static struct mtd_partition davinci_nand_partitions[] = {
                /* UBL (a few copies) plus U-Boot */
                .name           = "bootloader",
                .offset         = 0,
-                .size           = 28 * NAND_BLOCK_SIZE,
+                .size           = 30 * NAND_BLOCK_SIZE,
                .mask_flags     = MTD_WRITEABLE, /* force read-only */
        }, {
                /* U-Boot environment */
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index e574d7f837a8..635bf7740157 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -564,7 +564,7 @@ static int setup_vpif_input_channel_mode(int mux_mode)
        int val;
        u32 value;
-        if (!vpif_vsclkdis_reg || !cpld_client)
+        if (!vpif_vidclkctl_reg || !cpld_client)
                return -ENXIO;
        val = i2c_smbus_read_byte(cpld_client);
@@ -572,7 +572,7 @@ static int setup_vpif_input_channel_mode(int mux_mode)
                return val;
        spin_lock_irqsave(&vpif_reg_lock, flags);
-        value = __raw_readl(vpif_vsclkdis_reg);
+        value = __raw_readl(vpif_vidclkctl_reg);
        if (mux_mode) {
                val &= VPIF_INPUT_TWO_CHANNEL;
                value |= VIDCH1CLK;
@@ -580,7 +580,7 @@ static int setup_vpif_input_channel_mode(int mux_mode)
                val |= VPIF_INPUT_ONE_CHANNEL;
                value &= ~VIDCH1CLK;
        }
-        __raw_writel(value, vpif_vsclkdis_reg);
+        __raw_writel(value, vpif_vidclkctl_reg);
        spin_unlock_irqrestore(&vpif_reg_lock, flags);
        err = i2c_smbus_write_byte(cpld_client, val);
diff --git a/arch/arm/mach-davinci/dm646x.c b/arch/arm/mach-davinci/dm646x.c
index 0b68ed534f8e..af27c130595f 100644
--- a/arch/arm/mach-davinci/dm646x.c
+++ b/arch/arm/mach-davinci/dm646x.c
@@ -161,7 +161,6 @@ static struct clk dsp_clk = {
        .name = "dsp",
        .parent = &pll1_sysclk1,
        .lpsc = DM646X_LPSC_C64X_CPU,
-        .flags = PSC_DSP,
        .usecount = 1,                  /* REVISIT how to disable? */
 };
diff --git a/arch/arm/mach-davinci/include/mach/psc.h b/arch/arm/mach-davinci/include/mach/psc.h
index fa59c097223d..8bc3fc256171 100644
--- a/arch/arm/mach-davinci/include/mach/psc.h
+++ b/arch/arm/mach-davinci/include/mach/psc.h
@@ -233,7 +233,7 @@
 #define PTCMD           0x120
 #define PTSTAT          0x128
 #define PDSTAT          0x200
-#define PDCTL1          0x304
+#define PDCTL           0x300
 #define MDSTAT          0x800
 #define MDCTL           0xA00
@@ -244,7 +244,10 @@
 #define PSC_STATE_ENABLE        3
 #define MDSTAT_STATE_MASK       0x3f
+#define PDSTAT_STATE_MASK       0x1f
 #define MDCTL_FORCE             BIT(31)
+#define PDCTL_NEXT              BIT(1)
+#define PDCTL_EPCGOOD           BIT(8)
 #ifndef __ASSEMBLER__
diff --git a/arch/arm/mach-davinci/psc.c b/arch/arm/mach-davinci/psc.c
index 1fb6bdff38c1..d7e210f4b55c 100644
--- a/arch/arm/mach-davinci/psc.c
+++ b/arch/arm/mach-davinci/psc.c
@@ -52,7 +52,7 @@ int __init davinci_psc_is_clk_active(unsigned int ctlr, unsigned int id)
 void davinci_psc_config(unsigned int domain, unsigned int ctlr,
                unsigned int id, bool enable, u32 flags)
 {
-        u32 epcpr, ptcmd, ptstat, pdstat, pdctl1, mdstat, mdctl;
+        u32 epcpr, ptcmd, ptstat, pdstat, pdctl, mdstat, mdctl;
        void __iomem *psc_base;
        struct davinci_soc_info *soc_info = &davinci_soc_info;
        u32 next_state = PSC_STATE_ENABLE;
@@ -79,11 +79,11 @@ void davinci_psc_config(unsigned int domain, unsigned int ctlr,
                mdctl |= MDCTL_FORCE;
        __raw_writel(mdctl, psc_base + MDCTL + 4 * id);
-        pdstat = __raw_readl(psc_base + PDSTAT);
+        pdstat = __raw_readl(psc_base + PDSTAT + 4 * domain);
-        if ((pdstat & 0x00000001) == 0) {
+        if ((pdstat & PDSTAT_STATE_MASK) == 0) {
-                pdctl1 = __raw_readl(psc_base + PDCTL1);
+                pdctl = __raw_readl(psc_base + PDCTL + 4 * domain);
-                pdctl1 |= 0x1;
+                pdctl |= PDCTL_NEXT;
-                __raw_writel(pdctl1, psc_base + PDCTL1);
+                __raw_writel(pdctl, psc_base + PDCTL + 4 * domain);
                ptcmd = 1 << domain;
                __raw_writel(ptcmd, psc_base + PTCMD);
@@ -92,9 +92,9 @@ void davinci_psc_config(unsigned int domain, unsigned int ctlr,
                        epcpr = __raw_readl(psc_base + EPCPR);
                } while ((((epcpr >> domain) & 1) == 0));
-                pdctl1 = __raw_readl(psc_base + PDCTL1);
+                pdctl = __raw_readl(psc_base + PDCTL + 4 * domain);
-                pdctl1 |= 0x100;
+                pdctl |= PDCTL_EPCGOOD;
-                __raw_writel(pdctl1, psc_base + PDCTL1);
+                __raw_writel(pdctl, psc_base + PDCTL + 4 * domain);
        } else {
                ptcmd = 1 << domain;
                __raw_writel(ptcmd, psc_base + PTCMD);
diff --git a/arch/arm/mach-exynos/cpu.c b/arch/arm/mach-exynos/cpu.c
index 90ec247f3b37..cc8d4bd6d0f7 100644
--- a/arch/arm/mach-exynos/cpu.c
+++ b/arch/arm/mach-exynos/cpu.c
@@ -111,11 +111,6 @@ static struct map_desc exynos4_iodesc[] __initdata = {
                .length         = SZ_4K,
                .type           = MT_DEVICE,
        }, {
-                .virtual        = (unsigned long)S5P_VA_SROMC,
-                .pfn            = __phys_to_pfn(EXYNOS4_PA_SROMC),
-                .length         = SZ_4K,
-                .type           = MT_DEVICE,
-        }, {
                .virtual        = (unsigned long)S3C_VA_USB_HSPHY,
                .pfn            = __phys_to_pfn(EXYNOS4_PA_HSPHY),
                .length         = SZ_4K,
diff --git a/arch/arm/mach-exynos/mct.c b/arch/arm/mach-exynos/mct.c
index 97343df8f132..85b5527d0918 100644
--- a/arch/arm/mach-exynos/mct.c
+++ b/arch/arm/mach-exynos/mct.c
@@ -44,8 +44,6 @@ struct mct_clock_event_device {
        char name[10];
 };
-static DEFINE_PER_CPU(struct mct_clock_event_device, percpu_mct_tick);
 static void exynos4_mct_write(unsigned int value, void *addr)
 {
        void __iomem *stat_addr;
@@ -264,6 +262,9 @@ static void exynos4_clockevent_init(void)
 }
 #ifdef CONFIG_LOCAL_TIMERS
+static DEFINE_PER_CPU(struct mct_clock_event_device, percpu_mct_tick);
 /* Clock event handling */
 static void exynos4_mct_tick_stop(struct mct_clock_event_device *mevt)
 {
@@ -428,9 +429,13 @@ int __cpuinit local_timer_setup(struct clock_event_device *evt)
 void local_timer_stop(struct clock_event_device *evt)
 {
+        unsigned int cpu = smp_processor_id();
        evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
        if (mct_int_type == MCT_INT_SPI)
-                disable_irq(evt->irq);
+                if (cpu == 0)
+                        remove_irq(evt->irq, &mct_tick0_event_irq);
+                else
+                        remove_irq(evt->irq, &mct_tick1_event_irq);
        else
                disable_percpu_irq(IRQ_MCT_LOCALTIMER);
 }
@@ -443,6 +448,7 @@ static void __init exynos4_timer_resources(void)
        clk_rate = clk_get_rate(mct_clk);
+#ifdef CONFIG_LOCAL_TIMERS
        if (mct_int_type == MCT_INT_PPI) {
                int err;
@@ -452,6 +458,7 @@ static void __init exynos4_timer_resources(void)
                WARN(err, "MCT: can't request IRQ %d (%d)\n",
                     IRQ_MCT_LOCALTIMER, err);
        }
+#endif /* CONFIG_LOCAL_TIMERS */
 }
 static void __init exynos4_timer_init(void)
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index c44aa974e79c..0e6f1af260b6 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -132,7 +132,7 @@ config MACH_MX25_3DS
        select IMX_HAVE_PLATFORM_MXC_NAND
        select IMX_HAVE_PLATFORM_SDHCI_ESDHC_IMX
-config MACH_EUKREA_CPUIMX25
+config MACH_EUKREA_CPUIMX25SD
        bool "Support Eukrea CPUIMX25 Platform"
        select SOC_IMX25
        select IMX_HAVE_PLATFORM_FLEXCAN
@@ -148,7 +148,7 @@ config MACH_EUKREA_CPUIMX25
 choice
        prompt "Baseboard"
-        depends on MACH_EUKREA_CPUIMX25
+        depends on MACH_EUKREA_CPUIMX25SD
        default MACH_EUKREA_MBIMXSD25_BASEBOARD
 config MACH_EUKREA_MBIMXSD25_BASEBOARD
@@ -542,7 +542,7 @@ config MACH_MX35_3DS
          Include support for MX35PDK platform. This includes specific
          configurations for the board and its peripherals.
-config MACH_EUKREA_CPUIMX35
+config MACH_EUKREA_CPUIMX35SD
        bool "Support Eukrea CPUIMX35 Platform"
        select SOC_IMX35
        select IMX_HAVE_PLATFORM_FLEXCAN
@@ -560,7 +560,7 @@ config MACH_EUKREA_CPUIMX35
 choice
        prompt "Baseboard"
-        depends on MACH_EUKREA_CPUIMX35
+        depends on MACH_EUKREA_CPUIMX35SD
        default MACH_EUKREA_MBIMXSD35_BASEBOARD
 config MACH_EUKREA_MBIMXSD35_BASEBOARD
diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile
index aba73214c2a8..d97f409ce98b 100644
--- a/arch/arm/mach-imx/Makefile
+++ b/arch/arm/mach-imx/Makefile
@@ -24,7 +24,7 @@ obj-$(CONFIG_MACH_MX21ADS) += mach-mx21ads.o
 # i.MX25 based machines
 obj-$(CONFIG_MACH_MX25_3DS) += mach-mx25_3ds.o
-obj-$(CONFIG_MACH_EUKREA_CPUIMX25) += mach-eukrea_cpuimx25.o
+obj-$(CONFIG_MACH_EUKREA_CPUIMX25SD) += mach-eukrea_cpuimx25.o
 obj-$(CONFIG_MACH_EUKREA_MBIMXSD25_BASEBOARD) += eukrea_mbimxsd25-baseboard.o
 # i.MX27 based machines
@@ -57,7 +57,7 @@ obj-$(CONFIG_MACH_BUG) += mach-bug.o
 # i.MX35 based machines
 obj-$(CONFIG_MACH_PCM043) += mach-pcm043.o
 obj-$(CONFIG_MACH_MX35_3DS) += mach-mx35_3ds.o
-obj-$(CONFIG_MACH_EUKREA_CPUIMX35) += mach-cpuimx35.o
+obj-$(CONFIG_MACH_EUKREA_CPUIMX35SD) += mach-cpuimx35.o
 obj-$(CONFIG_MACH_EUKREA_MBIMXSD35_BASEBOARD) += eukrea_mbimxsd35-baseboard.o
 obj-$(CONFIG_MACH_VPR200) += mach-vpr200.o
diff --git a/arch/arm/mach-imx/clock-imx35.c b/arch/arm/mach-imx/clock-imx35.c
index 8116f119517d..ac8238caecb9 100644
--- a/arch/arm/mach-imx/clock-imx35.c
+++ b/arch/arm/mach-imx/clock-imx35.c
@@ -507,7 +507,7 @@ static struct clk_lookup lookups[] = {
 int __init mx35_clocks_init()
 {
-        unsigned int cgr2 = 3 << 26, cgr3 = 0;
+        unsigned int cgr2 = 3 << 26;
 #if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_ICEDCC)
        cgr2 |= 3 << 16;
@@ -521,6 +521,12 @@ int __init mx35_clocks_init()
        __raw_writel((3 << 18), CCM_BASE + CCM_CGR0);
        __raw_writel((3 << 2) | (3 << 4) | (3 << 6) | (3 << 8) | (3 << 16),
                        CCM_BASE + CCM_CGR1);
+        __raw_writel(cgr2, CCM_BASE + CCM_CGR2);
+        __raw_writel(0, CCM_BASE + CCM_CGR3);
+        clk_enable(&iim_clk);
+        imx_print_silicon_rev("i.MX35", mx35_revision());
+        clk_disable(&iim_clk);
        /*
         * Check if we came up in internal boot mode. If yes, we need some
@@ -529,17 +535,11 @@ int __init mx35_clocks_init()
         */
        if (!(__raw_readl(CCM_BASE + CCM_RCSR) & (3 << 10))) {
                /* Additionally turn on UART1, SCC, and IIM clocks */
-                cgr2 |= 3 << 16 | 3 << 4;
+                clk_enable(&iim_clk);
-                cgr3 |= 3 << 2;
+                clk_enable(&uart1_clk);
+                clk_enable(&scc_clk);
        }
-        __raw_writel(cgr2, CCM_BASE + CCM_CGR2);
-        __raw_writel(cgr3, CCM_BASE + CCM_CGR3);
-        clk_enable(&iim_clk);
-        imx_print_silicon_rev("i.MX35", mx35_revision());
-        clk_disable(&iim_clk);
 #ifdef CONFIG_MXC_USE_EPIT
        epit_timer_init(&epit1_clk,
                        MX35_IO_ADDRESS(MX35_EPIT1_BASE_ADDR), MX35_INT_EPIT1);
diff --git a/arch/arm/mach-imx/mach-cpuimx35.c b/arch/arm/mach-imx/mach-cpuimx35.c
index 66af2e8f7e57..362aae780601 100644
--- a/arch/arm/mach-imx/mach-cpuimx35.c
+++ b/arch/arm/mach-imx/mach-cpuimx35.c
@@ -53,12 +53,18 @@ static const struct imxi2c_platform_data
        .bitrate =              100000,
 };
+#define TSC2007_IRQGPIO         IMX_GPIO_NR(3, 2)
+static int tsc2007_get_pendown_state(void)
+{
+        return !gpio_get_value(TSC2007_IRQGPIO);
+}
 static struct tsc2007_platform_data tsc2007_info = {
        .model                  = 2007,
        .x_plate_ohms           = 180,
+        .get_pendown_state = tsc2007_get_pendown_state,
 };
-#define TSC2007_IRQGPIO         IMX_GPIO_NR(3, 2)
 static struct i2c_board_info eukrea_cpuimx35_i2c_devices[] = {
        {
                I2C_BOARD_INFO("pcf8563", 0x51),
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index 9cd860a27af5..8deb012189b5 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -37,14 +37,15 @@ static void __init imx6q_map_io(void)
        imx6q_clock_map_io();
 }
-static void __init imx6q_gpio_add_irq_domain(struct device_node *np,
+static int __init imx6q_gpio_add_irq_domain(struct device_node *np,
                                struct device_node *interrupt_parent)
 {
-        static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS -
+        static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS;
-                                   32 * 7; /* imx6q gets 7 gpio ports */
+        gpio_irq_base -= 32;
        irq_domain_add_simple(np, gpio_irq_base);
-        gpio_irq_base += 32;
+        return 0;
 }
 static const struct of_device_id imx6q_irq_match[] __initconst = {
diff --git a/arch/arm/mach-msm/devices-iommu.c b/arch/arm/mach-msm/devices-iommu.c
index 24030d0da6e3..0fb7a17df398 100644
--- a/arch/arm/mach-msm/devices-iommu.c
+++ b/arch/arm/mach-msm/devices-iommu.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/bootmem.h>
+#include <linux/module.h>
 #include <mach/irqs.h>
 #include <mach/iommu.h>
diff --git a/arch/arm/mach-mx5/board-mx51_babbage.c b/arch/arm/mach-mx5/board-mx51_babbage.c
index 5c837603ff0f..24994bb52147 100644
--- a/arch/arm/mach-mx5/board-mx51_babbage.c
+++ b/arch/arm/mach-mx5/board-mx51_babbage.c
@@ -362,7 +362,7 @@ static void __init mx51_babbage_init(void)
 {
        iomux_v3_cfg_t usbh1stp = MX51_PAD_USBH1_STP__USBH1_STP;
        iomux_v3_cfg_t power_key = NEW_PAD_CTRL(MX51_PAD_EIM_A27__GPIO2_21,
-                PAD_CTL_SRE_FAST | PAD_CTL_DSE_HIGH | PAD_CTL_PUS_100K_UP);
+                PAD_CTL_SRE_FAST | PAD_CTL_DSE_HIGH);
        imx51_soc_init();
diff --git a/arch/arm/mach-mx5/board-mx53_evk.c b/arch/arm/mach-mx5/board-mx53_evk.c
index 6bea31ab8f85..64bbfcea6f35 100644
--- a/arch/arm/mach-mx5/board-mx53_evk.c
+++ b/arch/arm/mach-mx5/board-mx53_evk.c
@@ -106,7 +106,7 @@ static inline void mx53_evk_fec_reset(void)
        gpio_set_value(MX53_EVK_FEC_PHY_RST, 1);
 }
-static struct fec_platform_data mx53_evk_fec_pdata = {
+static const struct fec_platform_data mx53_evk_fec_pdata __initconst = {
        .phy = PHY_INTERFACE_MODE_RMII,
 };
diff --git a/arch/arm/mach-mx5/board-mx53_loco.c b/arch/arm/mach-mx5/board-mx53_loco.c
index 7678f7734db6..237bdecd9331 100644
--- a/arch/arm/mach-mx5/board-mx53_loco.c
+++ b/arch/arm/mach-mx5/board-mx53_loco.c
@@ -242,7 +242,7 @@ static inline void mx53_loco_fec_reset(void)
        gpio_set_value(LOCO_FEC_PHY_RST, 1);
 }
-static struct fec_platform_data mx53_loco_fec_data = {
+static const struct fec_platform_data mx53_loco_fec_data __initconst = {
        .phy = PHY_INTERFACE_MODE_RMII,
 };
diff --git a/arch/arm/mach-mx5/board-mx53_smd.c b/arch/arm/mach-mx5/board-mx53_smd.c
index 59c0845eb4a6..d42132a80e8f 100644
--- a/arch/arm/mach-mx5/board-mx53_smd.c
+++ b/arch/arm/mach-mx5/board-mx53_smd.c
@@ -104,7 +104,7 @@ static inline void mx53_smd_fec_reset(void)
        gpio_set_value(SMD_FEC_PHY_RST, 1);
 }
-static struct fec_platform_data mx53_smd_fec_data = {
+static const struct fec_platform_data mx53_smd_fec_data __initconst = {
        .phy = PHY_INTERFACE_MODE_RMII,
 };
diff --git a/arch/arm/mach-mx5/imx51-dt.c b/arch/arm/mach-mx5/imx51-dt.c
index ccc61585659b..596edd967dbf 100644
--- a/arch/arm/mach-mx5/imx51-dt.c
+++ b/arch/arm/mach-mx5/imx51-dt.c
@@ -44,20 +44,22 @@ static const struct of_dev_auxdata imx51_auxdata_lookup[] __initconst = {
        { /* sentinel */ }
 };
-static void __init imx51_tzic_add_irq_domain(struct device_node *np,
+static int __init imx51_tzic_add_irq_domain(struct device_node *np,
                                struct device_node *interrupt_parent)
 {
        irq_domain_add_simple(np, 0);
+        return 0;
 }
-static void __init imx51_gpio_add_irq_domain(struct device_node *np,
+static int __init imx51_gpio_add_irq_domain(struct device_node *np,
                                struct device_node *interrupt_parent)
 {
-        static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS -
+        static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS;
-                                   32 * 4; /* imx51 gets 4 gpio ports */
+        gpio_irq_base -= 32;
        irq_domain_add_simple(np, gpio_irq_base);
-        gpio_irq_base += 32;
+        return 0;
 }
 static const struct of_device_id imx51_irq_match[] __initconst = {
diff --git a/arch/arm/mach-mx5/imx53-dt.c b/arch/arm/mach-mx5/imx53-dt.c
index ccaa0b81b768..85bfd5ff21b0 100644
--- a/arch/arm/mach-mx5/imx53-dt.c
+++ b/arch/arm/mach-mx5/imx53-dt.c
@@ -48,20 +48,22 @@ static const struct of_dev_auxdata imx53_auxdata_lookup[] __initconst = {
        { /* sentinel */ }
 };
-static void __init imx53_tzic_add_irq_domain(struct device_node *np,
+static int __init imx53_tzic_add_irq_domain(struct device_node *np,
                                struct device_node *interrupt_parent)
 {
        irq_domain_add_simple(np, 0);
+        return 0;
 }
-static void __init imx53_gpio_add_irq_domain(struct device_node *np,
+static int __init imx53_gpio_add_irq_domain(struct device_node *np,
                                struct device_node *interrupt_parent)
 {
-        static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS -
+        static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS;
-                                   32 * 7; /* imx53 gets 7 gpio ports */
+        gpio_irq_base -= 32;
        irq_domain_add_simple(np, gpio_irq_base);
-        gpio_irq_base += 32;
+        return 0;
 }
 static const struct of_device_id imx53_irq_match[] __initconst = {
diff --git a/arch/arm/mach-mxs/include/mach/mx28.h b/arch/arm/mach-mxs/include/mach/mx28.h
index 75d86118b76a..30c7990f3c01 100644
--- a/arch/arm/mach-mxs/include/mach/mx28.h
+++ b/arch/arm/mach-mxs/include/mach/mx28.h
@@ -104,8 +104,8 @@
 #define MX28_INT_CAN1                   9
 #define MX28_INT_LRADC_TOUCH            10
 #define MX28_INT_HSADC                  13
-#define MX28_INT_IRADC_THRESH0          14
+#define MX28_INT_LRADC_THRESH0          14
-#define MX28_INT_IRADC_THRESH1          15
+#define MX28_INT_LRADC_THRESH1          15
 #define MX28_INT_LRADC_CH0              16
 #define MX28_INT_LRADC_CH1              17
 #define MX28_INT_LRADC_CH2              18
diff --git a/arch/arm/mach-mxs/include/mach/mxs.h b/arch/arm/mach-mxs/include/mach/mxs.h
index 0d2d2b470998..bde5f6634747 100644
--- a/arch/arm/mach-mxs/include/mach/mxs.h
+++ b/arch/arm/mach-mxs/include/mach/mxs.h
@@ -30,6 +30,7 @@
 */
 #define cpu_is_mx23()           (                                       \
                machine_is_mx23evk() ||                                 \
+                machine_is_stmp378x() ||                                \
                0)
 #define cpu_is_mx28()           (                                       \
                machine_is_mx28evk() ||                                 \
diff --git a/arch/arm/mach-mxs/mach-m28evk.c b/arch/arm/mach-mxs/mach-m28evk.c
index 3b1681e4f49a..6b00577b7025 100644
--- a/arch/arm/mach-mxs/mach-m28evk.c
+++ b/arch/arm/mach-mxs/mach-m28evk.c
@@ -361,6 +361,6 @@ static struct sys_timer m28evk_timer = {
 MACHINE_START(M28EVK, "DENX M28 EVK")
        .map_io         = mx28_map_io,
        .init_irq       = mx28_init_irq,
-        .init_machine   = m28evk_init,
        .timer          = &m28evk_timer,
+        .init_machine   = m28evk_init,
 MACHINE_END
diff --git a/arch/arm/mach-mxs/mach-stmp378x_devb.c b/arch/arm/mach-mxs/mach-stmp378x_devb.c
index 177e53123a02..6834dea38c04 100644
--- a/arch/arm/mach-mxs/mach-stmp378x_devb.c
+++ b/arch/arm/mach-mxs/mach-stmp378x_devb.c
@@ -115,6 +115,6 @@ static struct sys_timer stmp378x_dvb_timer = {
 MACHINE_START(STMP378X, "STMP378X")
        .map_io         = mx23_map_io,
        .init_irq       = mx23_init_irq,
-        .init_machine   = stmp378x_dvb_init,
        .timer          = &stmp378x_dvb_timer,
+        .init_machine   = stmp378x_dvb_init,
 MACHINE_END
diff --git a/arch/arm/mach-mxs/module-tx28.c b/arch/arm/mach-mxs/module-tx28.c
index 0fcff47009cf..9a7b08b2a925 100644
--- a/arch/arm/mach-mxs/module-tx28.c
+++ b/arch/arm/mach-mxs/module-tx28.c
@@ -66,11 +66,11 @@ static const iomux_cfg_t tx28_fec1_pads[] __initconst = {
        MX28_PAD_ENET0_CRS__ENET1_RX_EN,
 };
-static struct fec_platform_data tx28_fec0_data = {
+static const struct fec_platform_data tx28_fec0_data __initconst = {
        .phy = PHY_INTERFACE_MODE_RMII,
 };
-static struct fec_platform_data tx28_fec1_data = {
+static const struct fec_platform_data tx28_fec1_data __initconst = {
        .phy = PHY_INTERFACE_MODE_RMII,
 };
diff --git a/arch/arm/mach-omap1/clock_data.c b/arch/arm/mach-omap1/clock_data.c
index 1297bb58869c..9ff90a744a21 100644
--- a/arch/arm/mach-omap1/clock_data.c
+++ b/arch/arm/mach-omap1/clock_data.c
@@ -16,6 +16,8 @@
 #include <linux/kernel.h>
 #include <linux/clk.h>
+#include <linux/cpufreq.h>
+#include <linux/delay.h>
 #include <linux/io.h>
 #include <asm/mach-types.h>  /* for machine_is_* */
@@ -927,16 +929,22 @@ int __init omap1_clk_init(void)
 void __init omap1_clk_late_init(void)
 {
-        if (ck_dpll1.rate >= OMAP1_DPLL1_SANE_VALUE)
+        unsigned long rate = ck_dpll1.rate;
+        if (rate >= OMAP1_DPLL1_SANE_VALUE)
                return;
+        /* System booting at unusable rate, force reprogramming of DPLL1 */
+        ck_dpll1_p->rate = 0;
        /* Find the highest supported frequency and enable it */
        if (omap1_select_table_rate(&virtual_ck_mpu, ~0)) {
                pr_err("System frequencies not set, using default. Check your config.\n");
                omap_writew(0x2290, DPLL_CTL);
-                omap_writew(cpu_is_omap7xx() ? 0x3005 : 0x1005, ARM_CKCTL);
+                omap_writew(cpu_is_omap7xx() ? 0x2005 : 0x0005, ARM_CKCTL);
                ck_dpll1.rate = OMAP1_DPLL1_SANE_VALUE;
        }
        propagate_rate(&ck_dpll1);
        omap1_show_rates();
+        loops_per_jiffy = cpufreq_scale(loops_per_jiffy, rate, ck_dpll1.rate);
 }
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index ba1aa07bdb29..c15c5c9c9085 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -193,7 +193,7 @@ static struct platform_device rx51_charger_device = {
 static void __init rx51_charger_init(void)
 {
        WARN_ON(gpio_request_one(RX51_USB_TRANSCEIVER_RST_GPIO,
-                GPIOF_OUT_INIT_LOW, "isp1704_reset"));
+                GPIOF_OUT_INIT_HIGH, "isp1704_reset"));
        platform_device_register(&rx51_charger_device);
 }
diff --git a/arch/arm/mach-omap2/mcbsp.c b/arch/arm/mach-omap2/mcbsp.c
index 292eee3be15f..28fcb27005d2 100644
--- a/arch/arm/mach-omap2/mcbsp.c
+++ b/arch/arm/mach-omap2/mcbsp.c
@@ -145,6 +145,9 @@ static int omap_init_mcbsp(struct omap_hwmod *oh, void *unused)
                pdata->reg_size = 4;
                pdata->has_ccr = true;
        }
+        pdata->set_clk_src = omap2_mcbsp_set_clk_src;
+        if (id == 1)
+                pdata->mux_signal = omap2_mcbsp1_mux_rx_clk;
        if (oh->class->rev == MCBSP_CONFIG_TYPE3) {
                if (id == 2)
@@ -174,9 +177,6 @@ static int omap_init_mcbsp(struct omap_hwmod *oh, void *unused)
                                        name, oh->name);
                return PTR_ERR(pdev);
        }
-        pdata->set_clk_src = omap2_mcbsp_set_clk_src;
-        if (id == 1)
-                pdata->mux_signal = omap2_mcbsp1_mux_rx_clk;
        omap_mcbsp_count++;
        return 0;
 }
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index 7f8915ad5099..eef43e2e163e 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -3247,18 +3247,14 @@ static __initdata struct omap_hwmod *omap3xxx_hwmods[] = {
 /* 3430ES1-only hwmods */
 static __initdata struct omap_hwmod *omap3430es1_hwmods[] = {
-        &omap3xxx_iva_hwmod,
        &omap3430es1_dss_core_hwmod,
-        &omap3xxx_mailbox_hwmod,
        NULL
 };
 /* 3430ES2+-only hwmods */
 static __initdata struct omap_hwmod *omap3430es2plus_hwmods[] = {
-        &omap3xxx_iva_hwmod,
        &omap3xxx_dss_core_hwmod,
        &omap3xxx_usbhsotg_hwmod,
-        &omap3xxx_mailbox_hwmod,
        NULL
 };
diff --git a/arch/arm/mach-prima2/pm.c b/arch/arm/mach-prima2/pm.c
index cb53160f6c5d..26ebb57719df 100644
--- a/arch/arm/mach-prima2/pm.c
+++ b/arch/arm/mach-prima2/pm.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/suspend.h>
 #include <linux/slab.h>
+#include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
diff --git a/arch/arm/mach-prima2/prima2.c b/arch/arm/mach-prima2/prima2.c
index ef555c041962..a12b689a8702 100644
--- a/arch/arm/mach-prima2/prima2.c
+++ b/arch/arm/mach-prima2/prima2.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <asm/sizes.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <linux/of.h>
diff --git a/arch/arm/mach-s3c64xx/dev-spi.c b/arch/arm/mach-s3c64xx/dev-spi.c
index 5e6b42089eb4..3341fd118723 100644
--- a/arch/arm/mach-s3c64xx/dev-spi.c
+++ b/arch/arm/mach-s3c64xx/dev-spi.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <linux/export.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/gpio.h>
diff --git a/arch/arm/mach-s3c64xx/s3c6400.c b/arch/arm/mach-s3c64xx/s3c6400.c
index 7a3bc32df425..51c00f2453c6 100644
--- a/arch/arm/mach-s3c64xx/s3c6400.c
+++ b/arch/arm/mach-s3c64xx/s3c6400.c
@@ -70,7 +70,7 @@ void __init s3c6400_init_irq(void)
        s3c64xx_init_irq(~0 & ~(0xf << 5), ~0);
 }
-struct sysdev_class s3c6400_sysclass = {
+static struct sysdev_class s3c6400_sysclass = {
        .name   = "s3c6400-core",
 };
diff --git a/arch/arm/mach-s3c64xx/setup-fb-24bpp.c b/arch/arm/mach-s3c64xx/setup-fb-24bpp.c
index 83d2afb79e9f..2cf80026c58d 100644
--- a/arch/arm/mach-s3c64xx/setup-fb-24bpp.c
+++ b/arch/arm/mach-s3c64xx/setup-fb-24bpp.c
@@ -20,7 +20,7 @@
 #include <plat/fb.h>
 #include <plat/gpio-cfg.h>
-extern void s3c64xx_fb_gpio_setup_24bpp(void)
+void s3c64xx_fb_gpio_setup_24bpp(void)
 {
        s3c_gpio_cfgrange_nopull(S3C64XX_GPI(0), 16, S3C_GPIO_SFN(2));
        s3c_gpio_cfgrange_nopull(S3C64XX_GPJ(0), 12, S3C_GPIO_SFN(2));
diff --git a/arch/arm/mach-s5pv210/mach-smdkv210.c b/arch/arm/mach-s5pv210/mach-smdkv210.c
index a9106c392398..8662ef6e5681 100644
--- a/arch/arm/mach-s5pv210/mach-smdkv210.c
+++ b/arch/arm/mach-s5pv210/mach-smdkv210.c
@@ -273,6 +273,7 @@ static struct samsung_bl_gpio_info smdkv210_bl_gpio_info = {
 static struct platform_pwm_backlight_data smdkv210_bl_data = {
        .pwm_id = 3,
+        .pwm_period_ns = 1000,
 };
 static void __init smdkv210_map_io(void)
diff --git a/arch/arm/mach-sa1100/Makefile.boot b/arch/arm/mach-sa1100/Makefile.boot
index 5a616f6e5612..f7951aa04562 100644
--- a/arch/arm/mach-sa1100/Makefile.boot
+++ b/arch/arm/mach-sa1100/Makefile.boot
@@ -1,5 +1,5 @@
-ifeq ($(CONFIG_ARCH_SA1100),y)
+ifeq ($(CONFIG_SA1111),y)
-   zreladdr-$(CONFIG_SA1111)            += 0xc0208000
+   zreladdr-y   += 0xc0208000
 else
   zreladdr-y   += 0xc0008000
 endif
diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c
index b862e9f81e3e..7119b87cbfa0 100644
--- a/arch/arm/mach-shmobile/board-ag5evm.c
+++ b/arch/arm/mach-shmobile/board-ag5evm.c
@@ -607,6 +607,7 @@ struct sys_timer ag5evm_timer = {
 MACHINE_START(AG5EVM, "ag5evm")
        .map_io         = ag5evm_map_io,
+        .nr_irqs        = NR_IRQS_LEGACY,
        .init_irq       = sh73a0_init_irq,
        .handle_irq     = shmobile_handle_irq_gic,
        .init_machine   = ag5evm_init,
diff --git a/arch/arm/mach-shmobile/board-kota2.c b/arch/arm/mach-shmobile/board-kota2.c
index bd9a78424d6b..f44150b5ae46 100644
--- a/arch/arm/mach-shmobile/board-kota2.c
+++ b/arch/arm/mach-shmobile/board-kota2.c
@@ -33,6 +33,7 @@
 #include <linux/input/sh_keysc.h>
 #include <linux/gpio_keys.h>
 #include <linux/leds.h>
+#include <linux/platform_data/leds-renesas-tpu.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/sh_mmcif.h>
 #include <linux/mfd/tmio.h>
@@ -56,7 +57,7 @@ static struct resource smsc9220_resources[] = {
                .flags          = IORESOURCE_MEM,
        },
        [1] = {
-                .start          = gic_spi(33), /* PINTA2 @ PORT144 */
+                .start          = SH73A0_PINT0_IRQ(2), /* PINTA2 */
                .flags          = IORESOURCE_IRQ,
        },
 };
@@ -157,10 +158,6 @@ static struct platform_device gpio_keys_device = {
 #define GPIO_LED(n, g) { .name = n, .gpio = g }
 static struct gpio_led gpio_leds[] = {
-        GPIO_LED("V2513", GPIO_PORT153), /* PORT153 [TPU1T02] -> V2513 */
-        GPIO_LED("V2514", GPIO_PORT199), /* PORT199 [TPU4TO1] -> V2514 */
-        GPIO_LED("V2515", GPIO_PORT197), /* PORT197 [TPU2TO1] -> V2515 */
-        GPIO_LED("KEYLED", GPIO_PORT163), /* PORT163 [TPU3TO0] -> KEYLED */
        GPIO_LED("G", GPIO_PORT20), /* PORT20 [GPO0] -> LED7 -> "G" */
        GPIO_LED("H", GPIO_PORT21), /* PORT21 [GPO1] -> LED8 -> "H" */
        GPIO_LED("J", GPIO_PORT22), /* PORT22 [GPO2] -> LED9 -> "J" */
@@ -179,6 +176,119 @@ static struct platform_device gpio_leds_device = {
        },
 };
+/* TPU LED */
+static struct led_renesas_tpu_config led_renesas_tpu12_pdata = {
+        .name           = "V2513",
+        .pin_gpio_fn    = GPIO_FN_TPU1TO2,
+        .pin_gpio       = GPIO_PORT153,
+        .channel_offset = 0x90,
+        .timer_bit = 2,
+        .max_brightness = 1000,
+};
+static struct resource tpu12_resources[] = {
+        [0] = {
+                .name   = "TPU12",
+                .start  = 0xe6610090,
+                .end    = 0xe66100b5,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+static struct platform_device leds_tpu12_device = {
+        .name = "leds-renesas-tpu",
+        .id = 12,
+        .dev = {
+                .platform_data  = &led_renesas_tpu12_pdata,
+        },
+        .num_resources  = ARRAY_SIZE(tpu12_resources),
+        .resource       = tpu12_resources,
+};
+static struct led_renesas_tpu_config led_renesas_tpu41_pdata = {
+        .name           = "V2514",
+        .pin_gpio_fn    = GPIO_FN_TPU4TO1,
+        .pin_gpio       = GPIO_PORT199,
+        .channel_offset = 0x50,
+        .timer_bit = 1,
+        .max_brightness = 1000,
+};
+static struct resource tpu41_resources[] = {
+        [0] = {
+                .name   = "TPU41",
+                .start  = 0xe6640050,
+                .end    = 0xe6640075,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+static struct platform_device leds_tpu41_device = {
+        .name = "leds-renesas-tpu",
+        .id = 41,
+        .dev = {
+                .platform_data  = &led_renesas_tpu41_pdata,
+        },
+        .num_resources  = ARRAY_SIZE(tpu41_resources),
+        .resource       = tpu41_resources,
+};
+static struct led_renesas_tpu_config led_renesas_tpu21_pdata = {
+        .name           = "V2515",
+        .pin_gpio_fn    = GPIO_FN_TPU2TO1,
+        .pin_gpio       = GPIO_PORT197,
+        .channel_offset = 0x50,
+        .timer_bit = 1,
+        .max_brightness = 1000,
+};
+static struct resource tpu21_resources[] = {
+        [0] = {
+                .name   = "TPU21",
+                .start  = 0xe6620050,
+                .end    = 0xe6620075,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+static struct platform_device leds_tpu21_device = {
+        .name = "leds-renesas-tpu",
+        .id = 21,
+        .dev = {
+                .platform_data  = &led_renesas_tpu21_pdata,
+        },
+        .num_resources  = ARRAY_SIZE(tpu21_resources),
+        .resource       = tpu21_resources,
+};
+static struct led_renesas_tpu_config led_renesas_tpu30_pdata = {
+        .name           = "KEYLED",
+        .pin_gpio_fn    = GPIO_FN_TPU3TO0,
+        .pin_gpio       = GPIO_PORT163,
+        .channel_offset = 0x10,
+        .timer_bit = 0,
+        .max_brightness = 1000,
+};
+static struct resource tpu30_resources[] = {
+        [0] = {
+                .name   = "TPU30",
+                .start  = 0xe6630010,
+                .end    = 0xe6630035,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+static struct platform_device leds_tpu30_device = {
+        .name = "leds-renesas-tpu",
+        .id = 30,
+        .dev = {
+                .platform_data  = &led_renesas_tpu30_pdata,
+        },
+        .num_resources  = ARRAY_SIZE(tpu30_resources),
+        .resource       = tpu30_resources,
+};
 /* MMCIF */
 static struct resource mmcif_resources[] = {
        [0] = {
@@ -291,6 +401,10 @@ static struct platform_device *kota2_devices[] __initdata = {
        &keysc_device,
        &gpio_keys_device,
        &gpio_leds_device,
+        &leds_tpu12_device,
+        &leds_tpu41_device,
+        &leds_tpu21_device,
+        &leds_tpu30_device,
        &mmcif_device,
        &sdhi0_device,
        &sdhi1_device,
@@ -317,18 +431,6 @@ static void __init kota2_map_io(void)
        shmobile_setup_console();
 }
-#define PINTER0A        0xe69000a0
-#define PINTCR0A        0xe69000b0
-void __init kota2_init_irq(void)
-{
-        sh73a0_init_irq();
-        /* setup PINT: enable PINTA2 as active low */
-        __raw_writel(1 << 29, PINTER0A);
-        __raw_writew(2 << 10, PINTCR0A);
-}
 static void __init kota2_init(void)
 {
        sh73a0_pinmux_init();
@@ -447,7 +549,8 @@ struct sys_timer kota2_timer = {
 MACHINE_START(KOTA2, "kota2")
        .map_io         = kota2_map_io,
-        .init_irq       = kota2_init_irq,
+        .nr_irqs        = NR_IRQS_LEGACY,
+        .init_irq       = sh73a0_init_irq,
        .handle_irq     = shmobile_handle_irq_gic,
        .init_machine   = kota2_init,
        .timer          = &kota2_timer,
diff --git a/arch/arm/mach-shmobile/clock-sh73a0.c b/arch/arm/mach-shmobile/clock-sh73a0.c
index 61a846bb30f2..1370a89ca358 100644
--- a/arch/arm/mach-shmobile/clock-sh73a0.c
+++ b/arch/arm/mach-shmobile/clock-sh73a0.c
@@ -113,6 +113,12 @@ static struct clk main_clk = {
        .ops            = &main_clk_ops,
 };
+/* Divide Main clock by two */
+static struct clk main_div2_clk = {
+        .ops            = &div2_clk_ops,
+        .parent         = &main_clk,
+};
 /* PLL0, PLL1, PLL2, PLL3 */
 static unsigned long pll_recalc(struct clk *clk)
 {
@@ -181,6 +187,7 @@ static struct clk *main_clks[] = {
        &extal1_div2_clk,
        &extal2_div2_clk,
        &main_clk,
+        &main_div2_clk,
        &pll0_clk,
        &pll1_clk,
        &pll2_clk,
@@ -243,7 +250,7 @@ static struct clk div6_clks[DIV6_NR] = {
        [DIV6_VCK1] = SH_CLK_DIV6(&pll1_div2_clk, VCLKCR1, 0),
        [DIV6_VCK2] = SH_CLK_DIV6(&pll1_div2_clk, VCLKCR2, 0),
        [DIV6_VCK3] = SH_CLK_DIV6(&pll1_div2_clk, VCLKCR3, 0),
-        [DIV6_ZB1] = SH_CLK_DIV6(&pll1_div2_clk, ZBCKCR, 0),
+        [DIV6_ZB1] = SH_CLK_DIV6(&pll1_div2_clk, ZBCKCR, CLK_ENABLE_ON_INIT),
        [DIV6_FLCTL] = SH_CLK_DIV6(&pll1_div2_clk, FLCKCR, 0),
        [DIV6_SDHI0] = SH_CLK_DIV6(&pll1_div2_clk, SD0CKCR, 0),
        [DIV6_SDHI1] = SH_CLK_DIV6(&pll1_div2_clk, SD1CKCR, 0),
@@ -268,6 +275,7 @@ enum { MSTP001,
        MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
        MSTP331, MSTP329, MSTP325, MSTP323, MSTP318,
        MSTP314, MSTP313, MSTP312, MSTP311,
+        MSTP303, MSTP302, MSTP301, MSTP300,
        MSTP411, MSTP410, MSTP403,
        MSTP_NR };
@@ -301,6 +309,10 @@ static struct clk mstp_clks[MSTP_NR] = {
        [MSTP313] = MSTP(&div6_clks[DIV6_SDHI1], SMSTPCR3, 13, 0), /* SDHI1 */
        [MSTP312] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 12, 0), /* MMCIF0 */
        [MSTP311] = MSTP(&div6_clks[DIV6_SDHI2], SMSTPCR3, 11, 0), /* SDHI2 */
+        [MSTP303] = MSTP(&main_div2_clk, SMSTPCR3, 3, 0), /* TPU1 */
+        [MSTP302] = MSTP(&main_div2_clk, SMSTPCR3, 2, 0), /* TPU2 */
+        [MSTP301] = MSTP(&main_div2_clk, SMSTPCR3, 1, 0), /* TPU3 */
+        [MSTP300] = MSTP(&main_div2_clk, SMSTPCR3, 0, 0), /* TPU4 */
        [MSTP411] = MSTP(&div4_clks[DIV4_HP], SMSTPCR4, 11, 0), /* IIC3 */
        [MSTP410] = MSTP(&div4_clks[DIV4_HP], SMSTPCR4, 10, 0), /* IIC4 */
        [MSTP403] = MSTP(&r_clk, SMSTPCR4, 3, 0), /* KEYSC */
@@ -350,6 +362,10 @@ static struct clk_lookup lookups[] = {
        CLKDEV_DEV_ID("sh_mobile_sdhi.1", &mstp_clks[MSTP313]), /* SDHI1 */
        CLKDEV_DEV_ID("sh_mmcif.0", &mstp_clks[MSTP312]), /* MMCIF0 */
        CLKDEV_DEV_ID("sh_mobile_sdhi.2", &mstp_clks[MSTP311]), /* SDHI2 */
+        CLKDEV_DEV_ID("leds-renesas-tpu.12", &mstp_clks[MSTP303]), /* TPU1 */
+        CLKDEV_DEV_ID("leds-renesas-tpu.21", &mstp_clks[MSTP302]), /* TPU2 */
+        CLKDEV_DEV_ID("leds-renesas-tpu.30", &mstp_clks[MSTP301]), /* TPU3 */
+        CLKDEV_DEV_ID("leds-renesas-tpu.41", &mstp_clks[MSTP300]), /* TPU4 */
        CLKDEV_DEV_ID("i2c-sh_mobile.3", &mstp_clks[MSTP411]), /* I2C3 */
        CLKDEV_DEV_ID("i2c-sh_mobile.4", &mstp_clks[MSTP410]), /* I2C4 */
        CLKDEV_DEV_ID("sh_keysc.0", &mstp_clks[MSTP403]), /* KEYSC */
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index fbdd12ea3a58..7c38474e533a 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -32,6 +32,7 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
+#include <asm/memblock.h>
 #include "mm.h"
@@ -332,7 +333,6 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
        sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL);
-        memblock_init();
        for (i = 0; i < mi->nr_banks; i++)
                memblock_add(mi->bank[i].start, mi->bank[i].size);
@@ -371,7 +371,7 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
        if (mdesc->reserve)
                mdesc->reserve();
-        memblock_analyze();
+        memblock_allow_resize();
        memblock_dump_all();
 }
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 2c559ac38142..e70a73731eaa 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -363,11 +363,13 @@ __v7_setup:
        orreq   r10, r10, #1 << 6               @ set bit #6
        mcreq   p15, 0, r10, c15, c0, 1         @ write diagnostic register
 #endif
-#ifdef CONFIG_ARM_ERRATA_751472
+#if defined(CONFIG_ARM_ERRATA_751472) && defined(CONFIG_SMP)
-        cmp     r6, #0x30                       @ present prior to r3p0
+        ALT_SMP(cmp r6, #0x30)                  @ present prior to r3p0
+        ALT_UP_B(1f)
        mrclt   p15, 0, r10, c15, c0, 1         @ read diagnostic register
        orrlt   r10, r10, #1 << 11              @ set bit #11
        mcrlt   p15, 0, r10, c15, c0, 1         @ write diagnostic register
+1:
 #endif
 3:      mov     r10, #0
diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c
index c074e66ad224..4e0a371630b3 100644
--- a/arch/arm/oprofile/common.c
+++ b/arch/arm/oprofile/common.c
@@ -116,7 +116,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
        return oprofile_perf_init(ops);
 }
-void __exit oprofile_arch_exit(void)
+void oprofile_arch_exit(void)
 {
        oprofile_perf_exit();
 }
diff --git a/arch/arm/plat-mxc/cpufreq.c b/arch/arm/plat-mxc/cpufreq.c
index 74aac96cda20..73db34bf588a 100644
--- a/arch/arm/plat-mxc/cpufreq.c
+++ b/arch/arm/plat-mxc/cpufreq.c
@@ -17,6 +17,7 @@
 * the CPU clock speed on the fly.
 */
+#include <linux/module.h>
 #include <linux/cpufreq.h>
 #include <linux/clk.h>
 #include <linux/err.h>
@@ -97,7 +98,7 @@ static int mxc_set_target(struct cpufreq_policy *policy,
        return ret;
 }
-static int __init mxc_cpufreq_init(struct cpufreq_policy *policy)
+static int mxc_cpufreq_init(struct cpufreq_policy *policy)
 {
        int ret;
        int i;
diff --git a/arch/arm/plat-mxc/include/mach/uncompress.h b/arch/arm/plat-mxc/include/mach/uncompress.h
index 88fd40452567..477971b00930 100644
--- a/arch/arm/plat-mxc/include/mach/uncompress.h
+++ b/arch/arm/plat-mxc/include/mach/uncompress.h
@@ -98,6 +98,7 @@ static __inline__ void __arch_decomp_setup(unsigned long arch_id)
        case MACH_TYPE_PCM043:
        case MACH_TYPE_LILLY1131:
        case MACH_TYPE_VPR200:
+        case MACH_TYPE_EUKREA_CPUIMX35SD:
                uart_base = MX3X_UART1_BASE_ADDR;
                break;
        case MACH_TYPE_MAGX_ZN5:
diff --git a/arch/arm/plat-mxc/pwm.c b/arch/arm/plat-mxc/pwm.c
index 42d74ea59084..e032717f7d02 100644
--- a/arch/arm/plat-mxc/pwm.c
+++ b/arch/arm/plat-mxc/pwm.c
@@ -32,6 +32,9 @@
 #define MX3_PWMSAR                0x0C    /* PWM Sample Register */
 #define MX3_PWMPR                 0x10    /* PWM Period Register */
 #define MX3_PWMCR_PRESCALER(x)    (((x - 1) & 0xFFF) << 4)
+#define MX3_PWMCR_DOZEEN                (1 << 24)
+#define MX3_PWMCR_WAITEN                (1 << 23)
+#define MX3_PWMCR_DBGEN                 (1 << 22)
 #define MX3_PWMCR_CLKSRC_IPG_HIGH (2 << 16)
 #define MX3_PWMCR_CLKSRC_IPG      (1 << 16)
 #define MX3_PWMCR_EN              (1 << 0)
@@ -74,10 +77,21 @@ int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns)
                do_div(c, period_ns);
                duty_cycles = c;
+                /*
+                 * according to imx pwm RM, the real period value should be
+                 * PERIOD value in PWMPR plus 2.
+                 */
+                if (period_cycles > 2)
+                        period_cycles -= 2;
+                else
+                        period_cycles = 0;
                writel(duty_cycles, pwm->mmio_base + MX3_PWMSAR);
                writel(period_cycles, pwm->mmio_base + MX3_PWMPR);
-                cr = MX3_PWMCR_PRESCALER(prescale) | MX3_PWMCR_EN;
+                cr = MX3_PWMCR_PRESCALER(prescale) |
+                        MX3_PWMCR_DOZEEN | MX3_PWMCR_WAITEN |
+                        MX3_PWMCR_DBGEN | MX3_PWMCR_EN;
                if (cpu_is_mx25())
                        cr |= MX3_PWMCR_CLKSRC_IPG;
diff --git a/arch/arm/plat-orion/gpio.c b/arch/arm/plat-orion/gpio.c
index 41ab97ebe4cf..10d160888133 100644
--- a/arch/arm/plat-orion/gpio.c
+++ b/arch/arm/plat-orion/gpio.c
@@ -384,12 +384,16 @@ void __init orion_gpio_init(int gpio_base, int ngpio,
        struct orion_gpio_chip *ochip;
        struct irq_chip_generic *gc;
        struct irq_chip_type *ct;
+        char gc_label[16];
        if (orion_gpio_chip_count == ARRAY_SIZE(orion_gpio_chips))
                return;
+        snprintf(gc_label, sizeof(gc_label), "orion_gpio%d",
+                orion_gpio_chip_count);
        ochip = orion_gpio_chips + orion_gpio_chip_count;
-        ochip->chip.label = "orion_gpio";
+        ochip->chip.label = kstrdup(gc_label, GFP_KERNEL);
        ochip->chip.request = orion_gpio_request;
        ochip->chip.direction_input = orion_gpio_direction_input;
        ochip->chip.get = orion_gpio_get;
diff --git a/arch/arm/plat-samsung/dev-backlight.c b/arch/arm/plat-samsung/dev-backlight.c
index e657305644cc..a976c023b286 100644
--- a/arch/arm/plat-samsung/dev-backlight.c
+++ b/arch/arm/plat-samsung/dev-backlight.c
@@ -15,7 +15,6 @@
 #include <linux/slab.h>
 #include <linux/io.h>
 #include <linux/pwm_backlight.h>
-#include <linux/slab.h>
 #include <plat/devs.h>
 #include <plat/gpio-cfg.h>
diff --git a/arch/arm/plat-samsung/include/plat/cpu-freq-core.h b/arch/arm/plat-samsung/include/plat/cpu-freq-core.h
index dac4760c0f0a..95509d8eb140 100644
--- a/arch/arm/plat-samsung/include/plat/cpu-freq-core.h
+++ b/arch/arm/plat-samsung/include/plat/cpu-freq-core.h
@@ -202,14 +202,6 @@ extern int s3c_plltab_register(struct cpufreq_frequency_table *plls,
 extern struct s3c_cpufreq_config *s3c_cpufreq_getconfig(void);
 extern struct s3c_iotimings *s3c_cpufreq_getiotimings(void);
-extern void s3c2410_iotiming_debugfs(struct seq_file *seq,
-                                     struct s3c_cpufreq_config *cfg,
-                                     union s3c_iobank *iob);
-extern void s3c2412_iotiming_debugfs(struct seq_file *seq,
-                                     struct s3c_cpufreq_config *cfg,
-                                     union s3c_iobank *iob);
 #ifdef CONFIG_CPU_FREQ_S3C24XX_DEBUGFS
 #define s3c_cpufreq_debugfs_call(x) x
 #else
@@ -226,6 +218,10 @@ extern void s3c2410_cpufreq_setrefresh(struct s3c_cpufreq_config *cfg);
 extern void s3c2410_set_fvco(struct s3c_cpufreq_config *cfg);
 #ifdef CONFIG_S3C2410_IOTIMING
+extern void s3c2410_iotiming_debugfs(struct seq_file *seq,
+                                     struct s3c_cpufreq_config *cfg,
+                                     union s3c_iobank *iob);
 extern int s3c2410_iotiming_calc(struct s3c_cpufreq_config *cfg,
                                 struct s3c_iotimings *iot);
@@ -235,6 +231,7 @@ extern int s3c2410_iotiming_get(struct s3c_cpufreq_config *cfg,
 extern void s3c2410_iotiming_set(struct s3c_cpufreq_config *cfg,
                                 struct s3c_iotimings *iot);
 #else
+#define s3c2410_iotiming_debugfs NULL
 #define s3c2410_iotiming_calc NULL
 #define s3c2410_iotiming_get NULL
 #define s3c2410_iotiming_set NULL
@@ -242,8 +239,10 @@ extern void s3c2410_iotiming_set(struct s3c_cpufreq_config *cfg,
 /* S3C2412 compatible routines */
-extern int s3c2412_iotiming_get(struct s3c_cpufreq_config *cfg,
+#ifdef CONFIG_S3C2412_IOTIMING
-                                struct s3c_iotimings *timings);
+extern void s3c2412_iotiming_debugfs(struct seq_file *seq,
+                                     struct s3c_cpufreq_config *cfg,
+                                     union s3c_iobank *iob);
 extern int s3c2412_iotiming_get(struct s3c_cpufreq_config *cfg,
                                struct s3c_iotimings *timings);
@@ -253,6 +252,12 @@ extern int s3c2412_iotiming_calc(struct s3c_cpufreq_config *cfg,
 extern void s3c2412_iotiming_set(struct s3c_cpufreq_config *cfg,
                                 struct s3c_iotimings *iot);
+#else
+#define s3c2412_iotiming_debugfs NULL
+#define s3c2412_iotiming_calc NULL
+#define s3c2412_iotiming_get NULL
+#define s3c2412_iotiming_set NULL
+#endif /* CONFIG_S3C2412_IOTIMING */
 #ifdef CONFIG_CPU_FREQ_S3C24XX_DEBUG
 #define s3c_freq_dbg(x...) printk(KERN_INFO x)
diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c
index ef5a2a08fcca..ea3395750324 100644
--- a/arch/avr32/kernel/process.c
+++ b/arch/avr32/kernel/process.c
@@ -34,10 +34,12 @@ void cpu_idle(void)
 {
        /* endless idle loop with no priority at all */
        while (1) {
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                while (!need_resched())
                        cpu_idle_sleep();
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
                schedule();
                preempt_disable();
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index 6a80a9e9fc4a..8dd0416673cb 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -88,10 +88,12 @@ void cpu_idle(void)
 #endif
                if (!idle)
                        idle = default_idle;
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                while (!need_resched())
                        idle();
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
                schedule();
                preempt_disable();
diff --git a/arch/cris/arch-v32/kernel/time.c b/arch/cris/arch-v32/kernel/time.c
index bb978ede8985..6773fc83a670 100644
--- a/arch/cris/arch-v32/kernel/time.c
+++ b/arch/cris/arch-v32/kernel/time.c
@@ -47,14 +47,12 @@ static struct clocksource cont_rotime = {
        .rating = 300,
        .read   = read_cont_rotime,
        .mask   = CLOCKSOURCE_MASK(32),
-        .shift  = 10,
        .flags  = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 static int __init etrax_init_cont_rotime(void)
 {
-        cont_rotime.mult = clocksource_khz2mult(100000, cont_rotime.shift);
+        clocksource_register_khz(&cont_rotime, 100000);
-        clocksource_register(&cont_rotime);
        return 0;
 }
 arch_initcall(etrax_init_cont_rotime);
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 27489b6dd533..3b7a7c483785 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -23,6 +23,9 @@ config IA64
        select HAVE_ARCH_TRACEHOOK
        select HAVE_DMA_API_DEBUG
        select HAVE_GENERIC_HARDIRQS
+        select HAVE_MEMBLOCK
+        select HAVE_MEMBLOCK_NODE_MAP
+        select ARCH_DISCARD_MEMBLOCK
        select GENERIC_IRQ_PROBE
        select GENERIC_PENDING_IRQ if SMP
        select IRQ_PER_CPU
@@ -474,9 +477,6 @@ config NODES_SHIFT
          MAX_NUMNODES will be 2^(This value).
          If in doubt, use the default.
-config ARCH_POPULATES_NODE_MAP
-        def_bool y
 # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
 # VIRTUAL_MEM_MAP has been retained for historical reasons.
 config VIRTUAL_MEM_MAP
diff --git a/arch/ia64/include/asm/cputime.h b/arch/ia64/include/asm/cputime.h
index 6073b187528a..3deac956d325 100644
--- a/arch/ia64/include/asm/cputime.h
+++ b/arch/ia64/include/asm/cputime.h
@@ -26,59 +26,53 @@
 #include <linux/jiffies.h>
 #include <asm/processor.h>
-typedef u64 cputime_t;
+typedef u64 __nocast cputime_t;
-typedef u64 cputime64_t;
+typedef u64 __nocast cputime64_t;
-#define cputime_zero                    ((cputime_t)0)
 #define cputime_one_jiffy               jiffies_to_cputime(1)
-#define cputime_max                     ((~((cputime_t)0) >> 1) - 1)
-#define cputime_add(__a, __b)           ((__a) +  (__b))
-#define cputime_sub(__a, __b)           ((__a) -  (__b))
-#define cputime_div(__a, __n)           ((__a) /  (__n))
-#define cputime_halve(__a)              ((__a) >> 1)
-#define cputime_eq(__a, __b)            ((__a) == (__b))
-#define cputime_gt(__a, __b)            ((__a) >  (__b))
-#define cputime_ge(__a, __b)            ((__a) >= (__b))
-#define cputime_lt(__a, __b)            ((__a) <  (__b))
-#define cputime_le(__a, __b)            ((__a) <= (__b))
-#define cputime64_zero                  ((cputime64_t)0)
-#define cputime64_add(__a, __b)         ((__a) + (__b))
-#define cputime64_sub(__a, __b)         ((__a) - (__b))
-#define cputime_to_cputime64(__ct)      (__ct)
 /*
 * Convert cputime <-> jiffies (HZ)
 */
-#define cputime_to_jiffies(__ct)        ((__ct) / (NSEC_PER_SEC / HZ))
+#define cputime_to_jiffies(__ct)        \
-#define jiffies_to_cputime(__jif)       ((__jif) * (NSEC_PER_SEC / HZ))
+        ((__force u64)(__ct) / (NSEC_PER_SEC / HZ))
-#define cputime64_to_jiffies64(__ct)    ((__ct) / (NSEC_PER_SEC / HZ))
+#define jiffies_to_cputime(__jif)       \
-#define jiffies64_to_cputime64(__jif)   ((__jif) * (NSEC_PER_SEC / HZ))
+        (__force cputime_t)((__jif) * (NSEC_PER_SEC / HZ))
+#define cputime64_to_jiffies64(__ct)    \
+        ((__force u64)(__ct) / (NSEC_PER_SEC / HZ))
+#define jiffies64_to_cputime64(__jif)   \
+        (__force cputime64_t)((__jif) * (NSEC_PER_SEC / HZ))
 /*
 * Convert cputime <-> microseconds
 */
-#define cputime_to_usecs(__ct)          ((__ct) / NSEC_PER_USEC)
+#define cputime_to_usecs(__ct)          \
-#define usecs_to_cputime(__usecs)       ((__usecs) * NSEC_PER_USEC)
+        ((__force u64)(__ct) / NSEC_PER_USEC)
+#define usecs_to_cputime(__usecs)       \
+        (__force cputime_t)((__usecs) * NSEC_PER_USEC)
+#define usecs_to_cputime64(__usecs)     \
+        (__force cputime64_t)((__usecs) * NSEC_PER_USEC)
 /*
 * Convert cputime <-> seconds
 */
-#define cputime_to_secs(__ct)           ((__ct) / NSEC_PER_SEC)
+#define cputime_to_secs(__ct)           \
-#define secs_to_cputime(__secs)         ((__secs) * NSEC_PER_SEC)
+        ((__force u64)(__ct) / NSEC_PER_SEC)
+#define secs_to_cputime(__secs)         \
+        (__force cputime_t)((__secs) * NSEC_PER_SEC)
 /*
 * Convert cputime <-> timespec (nsec)
 */
 static inline cputime_t timespec_to_cputime(const struct timespec *val)
 {
-        cputime_t ret = val->tv_sec * NSEC_PER_SEC;
+        u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_nsec;
-        return (ret + val->tv_nsec);
+        return (__force cputime_t) ret;
 }
 static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
 {
-        val->tv_sec  = ct / NSEC_PER_SEC;
+        val->tv_sec  = (__force u64) ct / NSEC_PER_SEC;
-        val->tv_nsec = ct % NSEC_PER_SEC;
+        val->tv_nsec = (__force u64) ct % NSEC_PER_SEC;
 }
 /*
@@ -86,25 +80,28 @@ static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
 */
 static inline cputime_t timeval_to_cputime(struct timeval *val)
 {
-        cputime_t ret = val->tv_sec * NSEC_PER_SEC;
+        u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_usec * NSEC_PER_USEC;
-        return (ret + val->tv_usec * NSEC_PER_USEC);
+        return (__force cputime_t) ret;
 }
 static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val)
 {
-        val->tv_sec = ct / NSEC_PER_SEC;
+        val->tv_sec = (__force u64) ct / NSEC_PER_SEC;
-        val->tv_usec = (ct % NSEC_PER_SEC) / NSEC_PER_USEC;
+        val->tv_usec = ((__force u64) ct % NSEC_PER_SEC) / NSEC_PER_USEC;
 }
 /*
 * Convert cputime <-> clock (USER_HZ)
 */
-#define cputime_to_clock_t(__ct)        ((__ct) / (NSEC_PER_SEC / USER_HZ))
+#define cputime_to_clock_t(__ct)        \
-#define clock_t_to_cputime(__x)         ((__x) * (NSEC_PER_SEC / USER_HZ))
+        ((__force u64)(__ct) / (NSEC_PER_SEC / USER_HZ))
+#define clock_t_to_cputime(__x)         \
+        (__force cputime_t)((__x) * (NSEC_PER_SEC / USER_HZ))
 /*
 * Convert cputime64 to clock.
 */
-#define cputime64_to_clock_t(__ct)      cputime_to_clock_t((cputime_t)__ct)
+#define cputime64_to_clock_t(__ct)      \
+        cputime_to_clock_t((__force cputime_t)__ct)
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 #endif /* __IA64_CPUTIME_H */
diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index f114a3b14c6a..1516d1dc11fd 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -16,6 +16,7 @@
 */
 #include <linux/bootmem.h>
 #include <linux/efi.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/nmi.h>
 #include <linux/swap.h>
@@ -348,7 +349,7 @@ paging_init (void)
                printk("Virtual mem_map starts at 0x%p\n", mem_map);
        }
 #else /* !CONFIG_VIRTUAL_MEM_MAP */
-        add_active_range(0, 0, max_low_pfn);
+        memblock_add_node(0, PFN_PHYS(max_low_pfn), 0);
        free_area_init_nodes(max_zone_pfns);
 #endif /* !CONFIG_VIRTUAL_MEM_MAP */
        zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 00cb0e26c64e..13df239dbed1 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -10,6 +10,7 @@
 #include <linux/bootmem.h>
 #include <linux/efi.h>
 #include <linux/elf.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/module.h>
@@ -557,8 +558,7 @@ int __init register_active_ranges(u64 start, u64 len, int nid)
 #endif
        if (start < end)
-                add_active_range(nid, __pa(start) >> PAGE_SHIFT,
+                memblock_add_node(__pa(start), end - start, nid);
-                        __pa(end) >> PAGE_SHIFT);
        return 0;
 }
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index 43f984e93970..303192fc9260 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -350,10 +350,12 @@
 #define __NR_clock_adjtime      342
 #define __NR_syncfs             343
 #define __NR_setns              344
+#define __NR_process_vm_readv   345
+#define __NR_process_vm_writev  346
 #ifdef __KERNEL__
-#define NR_syscalls             345
+#define NR_syscalls             347
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index c468f2edaa85..ce827b376110 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -365,4 +365,6 @@ ENTRY(sys_call_table)
        .long sys_clock_adjtime
        .long sys_syncfs
        .long sys_setns
+        .long sys_process_vm_readv      /* 345 */
+        .long sys_process_vm_writev
diff --git a/arch/m68k/platform/68328/timers.c b/arch/m68k/platform/68328/timers.c
index 309f725995bf..f2678866067b 100644
--- a/arch/m68k/platform/68328/timers.c
+++ b/arch/m68k/platform/68328/timers.c
@@ -93,7 +93,6 @@ static struct clocksource m68328_clk = {
        .name   = "timer",
        .rating = 250,
        .read   = m68328_read_clk,
-        .shift  = 20,
        .mask   = CLOCKSOURCE_MASK(32),
        .flags  = CLOCK_SOURCE_IS_CONTINUOUS,
 };
@@ -115,8 +114,7 @@ void hw_timer_init(void)
        /* Enable timer 1 */
        TCTL |= TCTL_TEN;
-        m68328_clk.mult = clocksource_hz2mult(TICKS_PER_JIFFY*HZ, m68328_clk.shift);
+        clocksource_register_hz(&m68328_clk, TICKS_PER_JIFFY*HZ);
-        clocksource_register(&m68328_clk);
 }
 /***************************************************************************/
diff --git a/arch/m68k/platform/coldfire/dma_timer.c b/arch/m68k/platform/coldfire/dma_timer.c
index a5f562823d7a..235ad57c4707 100644
--- a/arch/m68k/platform/coldfire/dma_timer.c
+++ b/arch/m68k/platform/coldfire/dma_timer.c
@@ -44,7 +44,6 @@ static struct clocksource clocksource_cf_dt = {
        .rating         = 200,
        .read           = cf_dt_get_cycles,
        .mask           = CLOCKSOURCE_MASK(32),
-        .shift          = 20,
        .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 };
@@ -60,9 +59,7 @@ static int __init  init_cf_dt_clocksource(void)
        __raw_writeb(0x00, DTER0);
        __raw_writel(0x00000000, DTRR0);
        __raw_writew(DMA_DTMR_CLK_DIV_16 | DMA_DTMR_ENABLE, DTMR0);
-        clocksource_cf_dt.mult = clocksource_hz2mult(DMA_FREQ,
+        return clocksource_register_hz(&clocksource_cf_dt, DMA_FREQ);
-                                                     clocksource_cf_dt.shift);
-        return clocksource_register(&clocksource_cf_dt);
 }
 arch_initcall(init_cf_dt_clocksource);
diff --git a/arch/m68k/platform/coldfire/pit.c b/arch/m68k/platform/coldfire/pit.c
index c2b980926bec..02663d25822d 100644
--- a/arch/m68k/platform/coldfire/pit.c
+++ b/arch/m68k/platform/coldfire/pit.c
@@ -144,7 +144,6 @@ static struct clocksource pit_clk = {
        .name   = "pit",
        .rating = 100,
        .read   = pit_read_clk,
-        .shift  = 20,
        .mask   = CLOCKSOURCE_MASK(32),
 };
@@ -162,8 +161,7 @@ void hw_timer_init(void)
        setup_irq(MCFINT_VECBASE + MCFINT_PIT1, &pit_irq);
-        pit_clk.mult = clocksource_hz2mult(FREQ, pit_clk.shift);
+        clocksource_register_hz(&pit_clk, FREQ);
-        clocksource_register(&pit_clk);
 }
 /***************************************************************************/
diff --git a/arch/m68k/platform/coldfire/sltimers.c b/arch/m68k/platform/coldfire/sltimers.c
index 6a85daf9a7fd..b7f822b552bb 100644
--- a/arch/m68k/platform/coldfire/sltimers.c
+++ b/arch/m68k/platform/coldfire/sltimers.c
@@ -114,7 +114,6 @@ static struct clocksource mcfslt_clk = {
        .name   = "slt",
        .rating = 250,
        .read   = mcfslt_read_clk,
-        .shift  = 20,
        .mask   = CLOCKSOURCE_MASK(32),
        .flags  = CLOCK_SOURCE_IS_CONTINUOUS,
 };
@@ -136,8 +135,7 @@ void hw_timer_init(void)
        setup_irq(MCF_IRQ_TIMER, &mcfslt_timer_irq);
-        mcfslt_clk.mult = clocksource_hz2mult(MCF_BUSCLK, mcfslt_clk.shift);
+        clocksource_register_hz(&mcfslt_clk, MCF_BUSCLK);
-        clocksource_register(&mcfslt_clk);
 #ifdef CONFIG_HIGHPROFILE
        mcfslt_profile_init();
diff --git a/arch/m68k/platform/coldfire/timers.c b/arch/m68k/platform/coldfire/timers.c
index 60242f65fea9..0d90da32fcdb 100644
--- a/arch/m68k/platform/coldfire/timers.c
+++ b/arch/m68k/platform/coldfire/timers.c
@@ -88,7 +88,6 @@ static struct clocksource mcftmr_clk = {
        .name   = "tmr",
        .rating = 250,
        .read   = mcftmr_read_clk,
-        .shift  = 20,
        .mask   = CLOCKSOURCE_MASK(32),
        .flags  = CLOCK_SOURCE_IS_CONTINUOUS,
 };
@@ -109,8 +108,7 @@ void hw_timer_init(void)
        __raw_writew(MCFTIMER_TMR_ENORI | MCFTIMER_TMR_CLK16 |
                MCFTIMER_TMR_RESTART | MCFTIMER_TMR_ENABLE, TA(MCFTIMER_TMR));
-        mcftmr_clk.mult = clocksource_hz2mult(FREQ, mcftmr_clk.shift);
+        clocksource_register_hz(&mcftmr_clk, FREQ);
-        clocksource_register(&mcftmr_clk);
        setup_irq(MCF_IRQ_TIMER, &mcftmr_timer_irq);
diff --git a/arch/microblaze/include/asm/memblock.h b/arch/microblaze/include/asm/memblock.h
deleted file mode 100644
index 20a8e257c77f..000000000000
--- a/arch/microblaze/include/asm/memblock.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/*
- * Copyright (C) 2008 Michal Simek <monstr@monstr.eu>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#ifndef _ASM_MICROBLAZE_MEMBLOCK_H
-#define _ASM_MICROBLAZE_MEMBLOCK_H
-#endif /* _ASM_MICROBLAZE_MEMBLOCK_H */
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index 95cc295976a7..7dcb5bfffb75 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -103,10 +103,12 @@ void cpu_idle(void)
                if (!idle)
                        idle = default_idle;
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                while (!need_resched())
                        idle();
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
                schedule();
diff --git a/arch/microblaze/kernel/prom.c b/arch/microblaze/kernel/prom.c
index 977484add216..80d314e81901 100644
--- a/arch/microblaze/kernel/prom.c
+++ b/arch/microblaze/kernel/prom.c
@@ -122,7 +122,6 @@ void __init early_init_devtree(void *params)
        of_scan_flat_dt(early_init_dt_scan_chosen, cmd_line);
        /* Scan memory nodes and rebuild MEMBLOCKs */
-        memblock_init();
        of_scan_flat_dt(early_init_dt_scan_root, NULL);
        of_scan_flat_dt(early_init_dt_scan_memory, NULL);
@@ -130,7 +129,7 @@ void __init early_init_devtree(void *params)
        strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE);
        parse_early_param();
-        memblock_analyze();
+        memblock_allow_resize();
        pr_debug("Phys. mem: %lx\n", (unsigned long) memblock_phys_mem_size());
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index d46f1da18a3c..9c652eb68aaa 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -25,6 +25,9 @@ config MIPS
        select GENERIC_IRQ_SHOW
        select HAVE_ARCH_JUMP_LABEL
        select IRQ_FORCED_THREADING
+        select HAVE_MEMBLOCK
+        select HAVE_MEMBLOCK_NODE_MAP
+        select ARCH_DISCARD_MEMBLOCK
 menu "Machine selection"
@@ -2064,9 +2067,6 @@ config ARCH_DISCONTIGMEM_ENABLE
          or have huge holes in the physical address space for other reasons.
          See <file:Documentation/vm/numa> for more.
-config ARCH_POPULATES_NODE_MAP
-        def_bool y
 config ARCH_SPARSEMEM_ENABLE
        bool
        select SPARSEMEM_STATIC
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index 4f2971bcf8e5..315fc0b250f8 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -623,7 +623,7 @@ static int mipspmu_event_init(struct perf_event *event)
        if (!atomic_inc_not_zero(&active_events)) {
                if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) {
                        atomic_dec(&active_events);
-                        return -ENOSPC;
+                        return -EINVAL;
                }
                mutex_lock(&pmu_reserve_mutex);
@@ -732,15 +732,15 @@ static int validate_group(struct perf_event *event)
        memset(&fake_cpuc, 0, sizeof(fake_cpuc));
        if (!validate_event(&fake_cpuc, leader))
-                return -ENOSPC;
+                return -EINVAL;
        list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
                if (!validate_event(&fake_cpuc, sibling))
-                        return -ENOSPC;
+                        return -EINVAL;
        }
        if (!validate_event(&fake_cpuc, event))
-                return -ENOSPC;
+                return -EINVAL;
        return 0;
 }
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index c47f96e453c0..7955409051c4 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -56,7 +56,8 @@ void __noreturn cpu_idle(void)
        /* endless idle loop with no priority at all */
        while (1) {
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                while (!need_resched() && cpu_online(cpu)) {
 #ifdef CONFIG_MIPS_MT_SMTC
                        extern void smtc_idle_loop_hook(void);
@@ -77,7 +78,8 @@ void __noreturn cpu_idle(void)
                     system_state == SYSTEM_BOOTING))
                        play_dead();
 #endif
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
                schedule();
                preempt_disable();
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 84af26ab2212..b1cb8f87d7b4 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -14,6 +14,7 @@
 #include <linux/ioport.h>
 #include <linux/export.h>
 #include <linux/screen_info.h>
+#include <linux/memblock.h>
 #include <linux/bootmem.h>
 #include <linux/initrd.h>
 #include <linux/root_dev.h>
@@ -352,7 +353,7 @@ static void __init bootmem_init(void)
                        continue;
 #endif
-                add_active_range(0, start, end);
+                memblock_add_node(PFN_PHYS(start), PFN_PHYS(end - start), 0);
        }
        /*
diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
index bc1297109cc5..b105eca3c020 100644
--- a/arch/mips/sgi-ip27/ip27-memory.c
+++ b/arch/mips/sgi-ip27/ip27-memory.c
@@ -12,6 +12,7 @@
 */
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/module.h>
@@ -381,8 +382,8 @@ static void __init szmem(void)
                                continue;
                        }
                        num_physpages += slot_psize;
-                        add_active_range(node, slot_getbasepfn(node, slot),
+                        memblock_add_node(PFN_PHYS(slot_getbasepfn(node, slot)),
-                                         slot_getbasepfn(node, slot) + slot_psize);
+                                          PFN_PHYS(slot_psize), node);
                }
        }
 }
diff --git a/arch/openrisc/include/asm/memblock.h b/arch/openrisc/include/asm/memblock.h
deleted file mode 100644
index bbe5a1c788cb..000000000000
--- a/arch/openrisc/include/asm/memblock.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * OpenRISC Linux
- *
- * Linux architectural port borrowing liberally from similar works of
- * others.  All original copyrights apply as per the original source
- * declaration.
- *
- * OpenRISC implementation:
- * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
- * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
- * et al.
- *
- * 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.
- */
-#ifndef __ASM_OPENRISC_MEMBLOCK_H
-#define __ASM_OPENRISC_MEMBLOCK_H
-/* empty */
-#endif /* __ASM_OPENRISC_MEMBLOCK_H */
diff --git a/arch/openrisc/kernel/idle.c b/arch/openrisc/kernel/idle.c
index d5bc5f813e89..e5fc78877830 100644
--- a/arch/openrisc/kernel/idle.c
+++ b/arch/openrisc/kernel/idle.c
@@ -51,7 +51,8 @@ void cpu_idle(void)
        /* endless idle loop with no priority at all */
        while (1) {
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                while (!need_resched()) {
                        check_pgt_cache();
@@ -69,7 +70,8 @@ void cpu_idle(void)
                        set_thread_flag(TIF_POLLING_NRFLAG);
                }
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
                schedule();
                preempt_disable();
diff --git a/arch/openrisc/kernel/prom.c b/arch/openrisc/kernel/prom.c
index 1bb58ba89afa..3d4478f6c942 100644
--- a/arch/openrisc/kernel/prom.c
+++ b/arch/openrisc/kernel/prom.c
@@ -76,14 +76,13 @@ void __init early_init_devtree(void *params)
        of_scan_flat_dt(early_init_dt_scan_chosen, cmd_line);
        /* Scan memory nodes and rebuild MEMBLOCKs */
-        memblock_init();
        of_scan_flat_dt(early_init_dt_scan_root, NULL);
        of_scan_flat_dt(early_init_dt_scan_memory, NULL);
        /* Save command line for /proc/cmdline and then parse parameters */
        strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE);
-        memblock_analyze();
+        memblock_allow_resize();
        /* We must copy the flattend device tree from init memory to regular
         * memory because the device tree references the strings in it
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 45b7389d77aa..7c0774397b89 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -198,8 +198,6 @@ static struct clocksource clocksource_cr16 = {
        .rating                 = 300,
        .read                   = read_cr16,
        .mask                   = CLOCKSOURCE_MASK(BITS_PER_LONG),
-        .mult                   = 0, /* to be set */
-        .shift                  = 22,
        .flags                  = CLOCK_SOURCE_IS_CONTINUOUS,
 };
@@ -270,7 +268,5 @@ void __init time_init(void)
        /* register at clocksource framework */
        current_cr16_khz = PAGE0->mem_10msec/10;  /* kHz */
-        clocksource_cr16.mult = clocksource_khz2mult(current_cr16_khz,
+        clocksource_register_khz(&clocksource_cr16, current_cr16_khz);
-                                                clocksource_cr16.shift);
-        clocksource_register(&clocksource_cr16);
 }
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 951e18f5335b..ead0bc68439d 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -117,6 +117,7 @@ config PPC
        select HAVE_KRETPROBES
        select HAVE_ARCH_TRACEHOOK
        select HAVE_MEMBLOCK
+        select HAVE_MEMBLOCK_NODE_MAP
        select HAVE_DMA_ATTRS
        select HAVE_DMA_API_DEBUG
        select USE_GENERIC_SMP_HELPERS if SMP
@@ -421,9 +422,6 @@ config ARCH_SPARSEMEM_DEFAULT
        def_bool y
        depends on (SMP && PPC_PSERIES) || PPC_PS3
-config ARCH_POPULATES_NODE_MAP
-        def_bool y
 config SYS_SUPPORTS_HUGETLBFS
        bool
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 1cf20bdfbeca..6ec1c380a4d6 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -29,25 +29,8 @@ static inline void setup_cputime_one_jiffy(void) { }
 #include <asm/time.h>
 #include <asm/param.h>
-typedef u64 cputime_t;
+typedef u64 __nocast cputime_t;
-typedef u64 cputime64_t;
+typedef u64 __nocast cputime64_t;
-#define cputime_zero                    ((cputime_t)0)
-#define cputime_max                     ((~((cputime_t)0) >> 1) - 1)
-#define cputime_add(__a, __b)           ((__a) +  (__b))
-#define cputime_sub(__a, __b)           ((__a) -  (__b))
-#define cputime_div(__a, __n)           ((__a) /  (__n))
-#define cputime_halve(__a)              ((__a) >> 1)
-#define cputime_eq(__a, __b)            ((__a) == (__b))
-#define cputime_gt(__a, __b)            ((__a) >  (__b))
-#define cputime_ge(__a, __b)            ((__a) >= (__b))
-#define cputime_lt(__a, __b)            ((__a) <  (__b))
-#define cputime_le(__a, __b)            ((__a) <= (__b))
-#define cputime64_zero                  ((cputime64_t)0)
-#define cputime64_add(__a, __b)         ((__a) + (__b))
-#define cputime64_sub(__a, __b)         ((__a) - (__b))
-#define cputime_to_cputime64(__ct)      (__ct)
 #ifdef __KERNEL__
@@ -65,7 +48,7 @@ DECLARE_PER_CPU(unsigned long, cputime_scaled_last_delta);
 static inline unsigned long cputime_to_jiffies(const cputime_t ct)
 {
-        return mulhdu(ct, __cputime_jiffies_factor);
+        return mulhdu((__force u64) ct, __cputime_jiffies_factor);
 }
 /* Estimate the scaled cputime by scaling the real cputime based on
@@ -74,14 +57,15 @@ static inline cputime_t cputime_to_scaled(const cputime_t ct)
 {
        if (cpu_has_feature(CPU_FTR_SPURR) &&
            __get_cpu_var(cputime_last_delta))
-                return ct * __get_cpu_var(cputime_scaled_last_delta) /
+                return (__force u64) ct *
-                            __get_cpu_var(cputime_last_delta);
+                        __get_cpu_var(cputime_scaled_last_delta) /
+                        __get_cpu_var(cputime_last_delta);
        return ct;
 }
 static inline cputime_t jiffies_to_cputime(const unsigned long jif)
 {
-        cputime_t ct;
+        u64 ct;
        unsigned long sec;
        /* have to be a little careful about overflow */
@@ -93,7 +77,7 @@ static inline cputime_t jiffies_to_cputime(const unsigned long jif)
        }
        if (sec)
                ct += (cputime_t) sec * tb_ticks_per_sec;
-        return ct;
+        return (__force cputime_t) ct;
 }
 static inline void setup_cputime_one_jiffy(void)
@@ -103,7 +87,7 @@ static inline void setup_cputime_one_jiffy(void)
 static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
 {
-        cputime_t ct;
+        u64 ct;
        u64 sec;
        /* have to be a little careful about overflow */
@@ -114,13 +98,13 @@ static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
                do_div(ct, HZ);
        }
        if (sec)
-                ct += (cputime_t) sec * tb_ticks_per_sec;
+                ct += (u64) sec * tb_ticks_per_sec;
-        return ct;
+        return (__force cputime64_t) ct;
 }
 static inline u64 cputime64_to_jiffies64(const cputime_t ct)
 {
-        return mulhdu(ct, __cputime_jiffies_factor);
+        return mulhdu((__force u64) ct, __cputime_jiffies_factor);
 }
 /*
@@ -130,12 +114,12 @@ extern u64 __cputime_msec_factor;
 static inline unsigned long cputime_to_usecs(const cputime_t ct)
 {
-        return mulhdu(ct, __cputime_msec_factor) * USEC_PER_MSEC;
+        return mulhdu((__force u64) ct, __cputime_msec_factor) * USEC_PER_MSEC;
 }
 static inline cputime_t usecs_to_cputime(const unsigned long us)
 {
-        cputime_t ct;
+        u64 ct;
        unsigned long sec;
        /* have to be a little careful about overflow */
@@ -147,9 +131,11 @@ static inline cputime_t usecs_to_cputime(const unsigned long us)
        }
        if (sec)
                ct += (cputime_t) sec * tb_ticks_per_sec;
-        return ct;
+        return (__force cputime_t) ct;
 }
+#define usecs_to_cputime64(us)          usecs_to_cputime(us)
 /*
 * Convert cputime <-> seconds
 */
@@ -157,12 +143,12 @@ extern u64 __cputime_sec_factor;
 static inline unsigned long cputime_to_secs(const cputime_t ct)
 {
-        return mulhdu(ct, __cputime_sec_factor);
+        return mulhdu((__force u64) ct, __cputime_sec_factor);
 }
 static inline cputime_t secs_to_cputime(const unsigned long sec)
 {
-        return (cputime_t) sec * tb_ticks_per_sec;
+        return (__force cputime_t)((u64) sec * tb_ticks_per_sec);
 }
 /*
@@ -170,7 +156,7 @@ static inline cputime_t secs_to_cputime(const unsigned long sec)
 */
 static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p)
 {
-        u64 x = ct;
+        u64 x = (__force u64) ct;
        unsigned int frac;
        frac = do_div(x, tb_ticks_per_sec);
@@ -182,11 +168,11 @@ static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p)
 static inline cputime_t timespec_to_cputime(const struct timespec *p)
 {
-        cputime_t ct;
+        u64 ct;
        ct = (u64) p->tv_nsec * tb_ticks_per_sec;
        do_div(ct, 1000000000);
-        return ct + (u64) p->tv_sec * tb_ticks_per_sec;
+        return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec);
 }
 /*
@@ -194,7 +180,7 @@ static inline cputime_t timespec_to_cputime(const struct timespec *p)
 */
 static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p)
 {
-        u64 x = ct;
+        u64 x = (__force u64) ct;
        unsigned int frac;
        frac = do_div(x, tb_ticks_per_sec);
@@ -206,11 +192,11 @@ static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p)
 static inline cputime_t timeval_to_cputime(const struct timeval *p)
 {
-        cputime_t ct;
+        u64 ct;
        ct = (u64) p->tv_usec * tb_ticks_per_sec;
        do_div(ct, 1000000);
-        return ct + (u64) p->tv_sec * tb_ticks_per_sec;
+        return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec);
 }
 /*
@@ -220,12 +206,12 @@ extern u64 __cputime_clockt_factor;
 static inline unsigned long cputime_to_clock_t(const cputime_t ct)
 {
-        return mulhdu(ct, __cputime_clockt_factor);
+        return mulhdu((__force u64) ct, __cputime_clockt_factor);
 }
 static inline cputime_t clock_t_to_cputime(const unsigned long clk)
 {
-        cputime_t ct;
+        u64 ct;
        unsigned long sec;
        /* have to be a little careful about overflow */
@@ -236,8 +222,8 @@ static inline cputime_t clock_t_to_cputime(const unsigned long clk)
                do_div(ct, USER_HZ);
        }
        if (sec)
-                ct += (cputime_t) sec * tb_ticks_per_sec;
+                ct += (u64) sec * tb_ticks_per_sec;
-        return ct;
+        return (__force cputime_t) ct;
 }
 #define cputime64_to_clock_t(ct)        cputime_to_clock_t((cputime_t)(ct))
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index d4df013ad779..69c7377d2071 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -381,39 +381,6 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
 }
 #endif
-static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
-                                             unsigned long pte_index)
-{
-        unsigned long rb, va_low;
-        rb = (v & ~0x7fUL) << 16;               /* AVA field */
-        va_low = pte_index >> 3;
-        if (v & HPTE_V_SECONDARY)
-                va_low = ~va_low;
-        /* xor vsid from AVA */
-        if (!(v & HPTE_V_1TB_SEG))
-                va_low ^= v >> 12;
-        else
-                va_low ^= v >> 24;
-        va_low &= 0x7ff;
-        if (v & HPTE_V_LARGE) {
-                rb |= 1;                        /* L field */
-                if (cpu_has_feature(CPU_FTR_ARCH_206) &&
-                    (r & 0xff000)) {
-                        /* non-16MB large page, must be 64k */
-                        /* (masks depend on page size) */
-                        rb |= 0x1000;           /* page encoding in LP field */
-                        rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */
-                        rb |= (va_low & 0xfe);  /* AVAL field (P7 doesn't seem to care) */
-                }
-        } else {
-                /* 4kB page */
-                rb |= (va_low & 0x7ff) << 12;   /* remaining 11b of VA */
-        }
-        rb |= (v >> 54) & 0x300;                /* B field */
-        return rb;
-}
 /* Magic register values loaded into r3 and r4 before the 'sc' assembly
 * instruction for the OSI hypercalls */
 #define OSI_SC_MAGIC_R3                 0x113724FA
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index e43fe42b9875..d0ac94f98f9e 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -29,4 +29,37 @@ static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu)
 #define SPAPR_TCE_SHIFT         12
+static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
+                                             unsigned long pte_index)
+{
+        unsigned long rb, va_low;
+        rb = (v & ~0x7fUL) << 16;               /* AVA field */
+        va_low = pte_index >> 3;
+        if (v & HPTE_V_SECONDARY)
+                va_low = ~va_low;
+        /* xor vsid from AVA */
+        if (!(v & HPTE_V_1TB_SEG))
+                va_low ^= v >> 12;
+        else
+                va_low ^= v >> 24;
+        va_low &= 0x7ff;
+        if (v & HPTE_V_LARGE) {
+                rb |= 1;                        /* L field */
+                if (cpu_has_feature(CPU_FTR_ARCH_206) &&
+                    (r & 0xff000)) {
+                        /* non-16MB large page, must be 64k */
+                        /* (masks depend on page size) */
+                        rb |= 0x1000;           /* page encoding in LP field */
+                        rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */
+                        rb |= (va_low & 0xfe);  /* AVAL field (P7 doesn't seem to care) */
+                }
+        } else {
+                /* 4kB page */
+                rb |= (va_low & 0x7ff) << 12;   /* remaining 11b of VA */
+        }
+        rb |= (v >> 54) & 0x300;                /* B field */
+        return rb;
+}
 #endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/memblock.h b/arch/powerpc/include/asm/memblock.h
deleted file mode 100644
index 43efc345065e..000000000000
--- a/arch/powerpc/include/asm/memblock.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _ASM_POWERPC_MEMBLOCK_H
-#define _ASM_POWERPC_MEMBLOCK_H
-#include <asm/udbg.h>
-#define MEMBLOCK_DBG(fmt...) udbg_printf(fmt)
-#endif /* _ASM_POWERPC_MEMBLOCK_H */
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 39a2baa6ad58..9c3cd490b1bd 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -46,6 +46,12 @@ static int __init powersave_off(char *arg)
 }
 __setup("powersave=off", powersave_off);
+#if defined(CONFIG_PPC_PSERIES) && defined(CONFIG_TRACEPOINTS)
+static const bool idle_uses_rcu = 1;
+#else
+static const bool idle_uses_rcu;
+#endif
 /*
 * The body of the idle task.
 */
@@ -56,7 +62,10 @@ void cpu_idle(void)
        set_thread_flag(TIF_POLLING_NRFLAG);
        while (1) {
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                if (!idle_uses_rcu)
+                        rcu_idle_enter();
                while (!need_resched() && !cpu_should_die()) {
                        ppc64_runlatch_off();
@@ -93,7 +102,9 @@ void cpu_idle(void)
                HMT_medium();
                ppc64_runlatch_on();
-                tick_nohz_restart_sched_tick();
+                if (!idle_uses_rcu)
+                        rcu_idle_exit();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
                if (cpu_should_die())
                        cpu_die();
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index 9ce1672afb59..a2158a395d96 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -107,9 +107,6 @@ void __init reserve_crashkernel(void)
        unsigned long long crash_size, crash_base;
        int ret;
-        /* this is necessary because of memblock_phys_mem_size() */
-        memblock_analyze();
        /* use common parsing */
        ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
                        &crash_size, &crash_base);
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index fa1235b0503b..abe405dab34d 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -733,8 +733,6 @@ void __init early_init_devtree(void *params)
        of_scan_flat_dt(early_init_dt_scan_chosen_ppc, cmd_line);
        /* Scan memory nodes and rebuild MEMBLOCKs */
-        memblock_init();
        of_scan_flat_dt(early_init_dt_scan_root, NULL);
        of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL);
@@ -756,20 +754,14 @@ void __init early_init_devtree(void *params)
        early_reserve_mem();
        phyp_dump_reserve_mem();
-        limit = memory_limit;
+        /*
-        if (! limit) {
+         * Ensure that total memory size is page-aligned, because otherwise
-                phys_addr_t memsize;
+         * mark_bootmem() gets upset.
+         */
-                /* Ensure that total memory size is page-aligned, because
+        limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE);
-                 * otherwise mark_bootmem() gets upset. */
-                memblock_analyze();
-                memsize = memblock_phys_mem_size();
-                if ((memsize & PAGE_MASK) != memsize)
-                        limit = memsize & PAGE_MASK;
-        }
        memblock_enforce_memory_limit(limit);
-        memblock_analyze();
+        memblock_allow_resize();
        memblock_dump_all();
        DBG("Phys. mem: %llx\n", memblock_phys_mem_size());
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 0cb137a9b038..336983da9e72 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -538,7 +538,7 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
        tpaca->kvm_hstate.napping = 0;
        vcpu->cpu = vc->pcpu;
        smp_wmb();
-#ifdef CONFIG_PPC_ICP_NATIVE
+#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
        if (vcpu->arch.ptid) {
                tpaca->cpu_start = 0x80;
                wmb();
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 3c791e1eb675..e2cfb9e1e20e 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -658,10 +658,12 @@ program_interrupt:
                        ulong cmd = kvmppc_get_gpr(vcpu, 3);
                        int i;
+#ifdef CONFIG_KVM_BOOK3S_64_PR
                        if (kvmppc_h_pr(vcpu, cmd) == EMULATE_DONE) {
                                r = RESUME_GUEST;
                                break;
                        }
+#endif
                        run->papr_hcall.nr = cmd;
                        for (i = 0; i < 9; ++i) {
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 26d20903f2bc..8c0d45a6faf7 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -15,6 +15,7 @@
 #include <linux/kvm_host.h>
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/export.h>
 #include <asm/reg.h>
 #include <asm/cputable.h>
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 161cefde5c15..58861fa1220e 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -134,8 +134,7 @@ void __init MMU_init(void)
        if (memblock.memory.cnt > 1) {
 #ifndef CONFIG_WII
-                memblock.memory.cnt = 1;
+                memblock_enforce_memory_limit(memblock.memory.regions[0].size);
-                memblock_analyze();
                printk(KERN_WARNING "Only using first contiguous memory region");
 #else
                wii_memory_fixups();
@@ -158,7 +157,6 @@ void __init MMU_init(void)
 #ifndef CONFIG_HIGHMEM
                total_memory = total_lowmem;
                memblock_enforce_memory_limit(total_lowmem);
-                memblock_analyze();
 #endif /* CONFIG_HIGHMEM */
        }
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 2dd6bdd31fe1..8e2eb6611b0b 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -199,7 +199,7 @@ void __init do_init_bootmem(void)
                unsigned long start_pfn, end_pfn;
                start_pfn = memblock_region_memory_base_pfn(reg);
                end_pfn = memblock_region_memory_end_pfn(reg);
-                add_active_range(0, start_pfn, end_pfn);
+                memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
        }
        /* Add all physical memory to the bootmem map, mark each area
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index b22a83a91cb8..e6eea0ac80c8 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -127,45 +127,25 @@ static int __cpuinit fake_numa_create_new_node(unsigned long end_pfn,
 }
 /*
- * get_active_region_work_fn - A helper function for get_node_active_region
+ * get_node_active_region - Return active region containing pfn
- *      Returns datax set to the start_pfn and end_pfn if they contain
- *      the initial value of datax->start_pfn between them
- * @start_pfn: start page(inclusive) of region to check
- * @end_pfn: end page(exclusive) of region to check
- * @datax: comes in with ->start_pfn set to value to search for and
- *      goes out with active range if it contains it
- * Returns 1 if search value is in range else 0
- */
-static int __init get_active_region_work_fn(unsigned long start_pfn,
-                                        unsigned long end_pfn, void *datax)
-{
-        struct node_active_region *data;
-        data = (struct node_active_region *)datax;
-        if (start_pfn <= data->start_pfn && end_pfn > data->start_pfn) {
-                data->start_pfn = start_pfn;
-                data->end_pfn = end_pfn;
-                return 1;
-        }
-        return 0;
-}
-/*
- * get_node_active_region - Return active region containing start_pfn
 * Active range returned is empty if none found.
- * @start_pfn: The page to return the region for.
+ * @pfn: The page to return the region for
- * @node_ar: Returned set to the active region containing start_pfn
+ * @node_ar: Returned set to the active region containing @pfn
 */
-static void __init get_node_active_region(unsigned long start_pfn,
+static void __init get_node_active_region(unsigned long pfn,
-                       struct node_active_region *node_ar)
+                                          struct node_active_region *node_ar)
 {
-        int nid = early_pfn_to_nid(start_pfn);
+        unsigned long start_pfn, end_pfn;
+        int i, nid;
-        node_ar->nid = nid;
+        for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
-        node_ar->start_pfn = start_pfn;
+                if (pfn >= start_pfn && pfn < end_pfn) {
-        node_ar->end_pfn = start_pfn;
+                        node_ar->nid = nid;
-        work_with_active_regions(nid, get_active_region_work_fn, node_ar);
+                        node_ar->start_pfn = start_pfn;
+                        node_ar->end_pfn = end_pfn;
+                        break;
+                }
+        }
 }
 static void map_cpu_to_node(int cpu, int node)
@@ -710,9 +690,7 @@ static void __init parse_drconf_memory(struct device_node *memory)
                        node_set_online(nid);
                        sz = numa_enforce_memory_limit(base, size);
                        if (sz)
-                                add_active_range(nid, base >> PAGE_SHIFT,
+                                memblock_set_node(base, sz, nid);
-                                                 (base >> PAGE_SHIFT)
-                                                 + (sz >> PAGE_SHIFT));
                } while (--ranges);
        }
 }
@@ -802,8 +780,7 @@ new_range:
                                continue;
                }
-                add_active_range(nid, start >> PAGE_SHIFT,
+                memblock_set_node(start, size, nid);
-                                (start >> PAGE_SHIFT) + (size >> PAGE_SHIFT));
                if (--ranges)
                        goto new_range;
@@ -839,7 +816,8 @@ static void __init setup_nonnuma(void)
                end_pfn = memblock_region_memory_end_pfn(reg);
                fake_numa_create_new_node(end_pfn, &nid);
-                add_active_range(nid, start_pfn, end_pfn);
+                memblock_set_node(PFN_PHYS(start_pfn),
+                                  PFN_PHYS(end_pfn - start_pfn), nid);
                node_set_online(nid);
        }
 }
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 4e13d6f9023e..573ba3b69d1f 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -615,7 +615,6 @@ static void __early_init_mmu(int boot_cpu)
                /* limit memory so we dont have linear faults */
                memblock_enforce_memory_limit(linear_map_top);
-                memblock_analyze();
                patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e);
                patch_exception(0x1e0, exc_instruction_tlb_miss_bolted_book3e);
diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c
index 1b5dc1a2e145..6d8dadf19f0b 100644
--- a/arch/powerpc/platforms/embedded6xx/wii.c
+++ b/arch/powerpc/platforms/embedded6xx/wii.c
@@ -79,24 +79,19 @@ void __init wii_memory_fixups(void)
        BUG_ON(memblock.memory.cnt != 2);
        BUG_ON(!page_aligned(p[0].base) || !page_aligned(p[1].base));
-        p[0].size = _ALIGN_DOWN(p[0].size, PAGE_SIZE);
+        /* trim unaligned tail */
-        p[1].size = _ALIGN_DOWN(p[1].size, PAGE_SIZE);
+        memblock_remove(ALIGN(p[1].base + p[1].size, PAGE_SIZE),
+                        (phys_addr_t)ULLONG_MAX);
-        wii_hole_start = p[0].base + p[0].size;
+        /* determine hole, add & reserve them */
+        wii_hole_start = ALIGN(p[0].base + p[0].size, PAGE_SIZE);
        wii_hole_size = p[1].base - wii_hole_start;
+        memblock_add(wii_hole_start, wii_hole_size);
-        pr_info("MEM1: <%08llx %08llx>\n", p[0].base, p[0].size);
-        pr_info("HOLE: <%08lx %08lx>\n", wii_hole_start, wii_hole_size);
-        pr_info("MEM2: <%08llx %08llx>\n", p[1].base, p[1].size);
-        p[0].size += wii_hole_size + p[1].size;
-        memblock.memory.cnt = 1;
-        memblock_analyze();
-        /* reserve the hole */
        memblock_reserve(wii_hole_start, wii_hole_size);
+        BUG_ON(memblock.memory.cnt != 1);
+        __memblock_dump_all();
        /* allow ioremapping the address space in the hole */
        __allow_ioremap_reserved = 1;
 }
diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c
index ea0acbd8966d..8fc62586a973 100644
--- a/arch/powerpc/platforms/iseries/setup.c
+++ b/arch/powerpc/platforms/iseries/setup.c
@@ -563,7 +563,8 @@ static void yield_shared_processor(void)
 static void iseries_shared_idle(void)
 {
        while (1) {
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                while (!need_resched() && !hvlpevent_is_pending()) {
                        local_irq_disable();
                        ppc64_runlatch_off();
@@ -577,7 +578,8 @@ static void iseries_shared_idle(void)
                }
                ppc64_runlatch_on();
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
                if (hvlpevent_is_pending())
                        process_iSeries_events();
@@ -593,7 +595,8 @@ static void iseries_dedicated_idle(void)
        set_thread_flag(TIF_POLLING_NRFLAG);
        while (1) {
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                if (!need_resched()) {
                        while (!need_resched()) {
                                ppc64_runlatch_off();
@@ -610,7 +613,8 @@ static void iseries_dedicated_idle(void)
                }
                ppc64_runlatch_on();
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
                schedule();
                preempt_disable();
diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c
index 72714ad27842..8bd6ba542691 100644
--- a/arch/powerpc/platforms/ps3/mm.c
+++ b/arch/powerpc/platforms/ps3/mm.c
@@ -319,7 +319,6 @@ static int __init ps3_mm_add_memory(void)
        }
        memblock_add(start_addr, map.r1.size);
-        memblock_analyze();
        result = online_pages(start_pfn, nr_pages);
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 27a49508b410..52d429be6c76 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -555,6 +555,8 @@ void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
        (*depth)++;
        trace_hcall_entry(opcode, args);
+        if (opcode == H_CEDE)
+                rcu_idle_enter();
        (*depth)--;
 out:
@@ -575,6 +577,8 @@ void __trace_hcall_exit(long opcode, unsigned long retval,
                goto out;
        (*depth)++;
+        if (opcode == H_CEDE)
+                rcu_idle_exit();
        trace_hcall_exit(opcode, retval, retbuf);
        (*depth)--;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 373679b3744a..d48ede334434 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -92,6 +92,9 @@ config S390
        select HAVE_ARCH_JUMP_LABEL if !MARCH_G5
        select HAVE_RCU_TABLE_FREE if SMP
        select ARCH_SAVE_PAGE_KEYS if HIBERNATION
+        select HAVE_MEMBLOCK
+        select HAVE_MEMBLOCK_NODE_MAP
+        select ARCH_DISCARD_MEMBLOCK
        select ARCH_INLINE_SPIN_TRYLOCK
        select ARCH_INLINE_SPIN_TRYLOCK_BH
        select ARCH_INLINE_SPIN_LOCK
@@ -345,9 +348,6 @@ config WARN_DYNAMIC_STACK
          Say N if you are unsure.
-config ARCH_POPULATES_NODE_MAP
-        def_bool y
 comment "Kernel preemption"
 source "kernel/Kconfig.preempt"
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index 92f1cb745d69..4de031d6b76c 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -115,21 +115,21 @@ static void appldata_get_os_data(void *data)
        j = 0;
        for_each_online_cpu(i) {
                os_data->os_cpu[j].per_cpu_user =
-                        cputime_to_jiffies(kstat_cpu(i).cpustat.user);
+                        cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]);
                os_data->os_cpu[j].per_cpu_nice =
-                        cputime_to_jiffies(kstat_cpu(i).cpustat.nice);
+                        cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]);
                os_data->os_cpu[j].per_cpu_system =
-                        cputime_to_jiffies(kstat_cpu(i).cpustat.system);
+                        cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]);
                os_data->os_cpu[j].per_cpu_idle =
-                        cputime_to_jiffies(kstat_cpu(i).cpustat.idle);
+                        cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]);
                os_data->os_cpu[j].per_cpu_irq =
-                        cputime_to_jiffies(kstat_cpu(i).cpustat.irq);
+                        cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]);
                os_data->os_cpu[j].per_cpu_softirq =
-                        cputime_to_jiffies(kstat_cpu(i).cpustat.softirq);
+                        cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]);
                os_data->os_cpu[j].per_cpu_iowait =
-                        cputime_to_jiffies(kstat_cpu(i).cpustat.iowait);
+                        cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]);
                os_data->os_cpu[j].per_cpu_steal =
-                        cputime_to_jiffies(kstat_cpu(i).cpustat.steal);
+                        cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]);
                os_data->os_cpu[j].cpu_id = i;
                j++;
        }
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index 081434878296..c23c3900c304 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -16,114 +16,100 @@
 /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */
-typedef unsigned long long cputime_t;
+typedef unsigned long long __nocast cputime_t;
-typedef unsigned long long cputime64_t;
+typedef unsigned long long __nocast cputime64_t;
-#ifndef __s390x__
+static inline unsigned long __div(unsigned long long n, unsigned long base)
-static inline unsigned int
-__div(unsigned long long n, unsigned int base)
 {
+#ifndef __s390x__
        register_pair rp;
        rp.pair = n >> 1;
        asm ("dr %0,%1" : "+d" (rp) : "d" (base >> 1));
        return rp.subreg.odd;
+#else /* __s390x__ */
+        return n / base;
+#endif /* __s390x__ */
 }
-#else /* __s390x__ */
+#define cputime_one_jiffy               jiffies_to_cputime(1)
+/*
+ * Convert cputime to jiffies and back.
+ */
+static inline unsigned long cputime_to_jiffies(const cputime_t cputime)
+{
+        return __div((__force unsigned long long) cputime, 4096000000ULL / HZ);
+}
-static inline unsigned int
+static inline cputime_t jiffies_to_cputime(const unsigned int jif)
-__div(unsigned long long n, unsigned int base)
 {
-        return n / base;
+        return (__force cputime_t)(jif * (4096000000ULL / HZ));
 }
-#endif /* __s390x__ */
+static inline u64 cputime64_to_jiffies64(cputime64_t cputime)
+{
+        unsigned long long jif = (__force unsigned long long) cputime;
+        do_div(jif, 4096000000ULL / HZ);
+        return jif;
+}
-#define cputime_zero                    (0ULL)
+static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
-#define cputime_one_jiffy               jiffies_to_cputime(1)
+{
-#define cputime_max                     ((~0UL >> 1) - 1)
+        return (__force cputime64_t)(jif * (4096000000ULL / HZ));
-#define cputime_add(__a, __b)           ((__a) +  (__b))
-#define cputime_sub(__a, __b)           ((__a) -  (__b))
-#define cputime_div(__a, __n) ({                \
-        unsigned long long __div = (__a);       \
-        do_div(__div,__n);                      \
-        __div;                                  \
-})
-#define cputime_halve(__a)              ((__a) >> 1)
-#define cputime_eq(__a, __b)            ((__a) == (__b))
-#define cputime_gt(__a, __b)            ((__a) >  (__b))
-#define cputime_ge(__a, __b)            ((__a) >= (__b))
-#define cputime_lt(__a, __b)            ((__a) <  (__b))
-#define cputime_le(__a, __b)            ((__a) <= (__b))
-#define cputime_to_jiffies(__ct)        (__div((__ct), 4096000000ULL / HZ))
-#define cputime_to_scaled(__ct)         (__ct)
-#define jiffies_to_cputime(__hz)        ((cputime_t)(__hz) * (4096000000ULL / HZ))
-#define cputime64_zero                  (0ULL)
-#define cputime64_add(__a, __b)         ((__a) + (__b))
-#define cputime_to_cputime64(__ct)      (__ct)
-static inline u64
-cputime64_to_jiffies64(cputime64_t cputime)
-{
-        do_div(cputime, 4096000000ULL / HZ);
-        return cputime;
 }
 /*
 * Convert cputime to microseconds and back.
 */
-static inline unsigned int
+static inline unsigned int cputime_to_usecs(const cputime_t cputime)
-cputime_to_usecs(const cputime_t cputime)
 {
-        return cputime_div(cputime, 4096);
+        return (__force unsigned long long) cputime >> 12;
 }
-static inline cputime_t
+static inline cputime_t usecs_to_cputime(const unsigned int m)
-usecs_to_cputime(const unsigned int m)
 {
-        return (cputime_t) m * 4096;
+        return (__force cputime_t)(m * 4096ULL);
 }
+#define usecs_to_cputime64(m)           usecs_to_cputime(m)
 /*
 * Convert cputime to milliseconds and back.
 */
-static inline unsigned int
+static inline unsigned int cputime_to_secs(const cputime_t cputime)
-cputime_to_secs(const cputime_t cputime)
 {
-        return __div(cputime, 2048000000) >> 1;
+        return __div((__force unsigned long long) cputime, 2048000000) >> 1;
 }
-static inline cputime_t
+static inline cputime_t secs_to_cputime(const unsigned int s)
-secs_to_cputime(const unsigned int s)
 {
-        return (cputime_t) s * 4096000000ULL;
+        return (__force cputime_t)(s * 4096000000ULL);
 }
 /*
 * Convert cputime to timespec and back.
 */
-static inline cputime_t
+static inline cputime_t timespec_to_cputime(const struct timespec *value)
-timespec_to_cputime(const struct timespec *value)
 {
-        return value->tv_nsec * 4096 / 1000 + (u64) value->tv_sec * 4096000000ULL;
+        unsigned long long ret = value->tv_sec * 4096000000ULL;
+        return (__force cputime_t)(ret + value->tv_nsec * 4096 / 1000);
 }
-static inline void
+static inline void cputime_to_timespec(const cputime_t cputime,
-cputime_to_timespec(const cputime_t cputime, struct timespec *value)
+                                       struct timespec *value)
 {
+        unsigned long long __cputime = (__force unsigned long long) cputime;
 #ifndef __s390x__
        register_pair rp;
-        rp.pair = cputime >> 1;
+        rp.pair = __cputime >> 1;
        asm ("dr %0,%1" : "+d" (rp) : "d" (2048000000UL));
        value->tv_nsec = rp.subreg.even * 1000 / 4096;
        value->tv_sec = rp.subreg.odd;
 #else
-        value->tv_nsec = (cputime % 4096000000ULL) * 1000 / 4096;
+        value->tv_nsec = (__cputime % 4096000000ULL) * 1000 / 4096;
-        value->tv_sec = cputime / 4096000000ULL;
+        value->tv_sec = __cputime / 4096000000ULL;
 #endif
 }
@@ -132,50 +118,52 @@ cputime_to_timespec(const cputime_t cputime, struct timespec *value)
 * Since cputime and timeval have the same resolution (microseconds)
 * this is easy.
 */
-static inline cputime_t
+static inline cputime_t timeval_to_cputime(const struct timeval *value)
-timeval_to_cputime(const struct timeval *value)
 {
-        return value->tv_usec * 4096 + (u64) value->tv_sec * 4096000000ULL;
+        unsigned long long ret = value->tv_sec * 4096000000ULL;
+        return (__force cputime_t)(ret + value->tv_usec * 4096ULL);
 }
-static inline void
+static inline void cputime_to_timeval(const cputime_t cputime,
-cputime_to_timeval(const cputime_t cputime, struct timeval *value)
+                                      struct timeval *value)
 {
+        unsigned long long __cputime = (__force unsigned long long) cputime;
 #ifndef __s390x__
        register_pair rp;
-        rp.pair = cputime >> 1;
+        rp.pair = __cputime >> 1;
        asm ("dr %0,%1" : "+d" (rp) : "d" (2048000000UL));
        value->tv_usec = rp.subreg.even / 4096;
        value->tv_sec = rp.subreg.odd;
 #else
-        value->tv_usec = (cputime % 4096000000ULL) / 4096;
+        value->tv_usec = (__cputime % 4096000000ULL) / 4096;
-        value->tv_sec = cputime / 4096000000ULL;
+        value->tv_sec = __cputime / 4096000000ULL;
 #endif
 }
 /*
 * Convert cputime to clock and back.
 */
-static inline clock_t
+static inline clock_t cputime_to_clock_t(cputime_t cputime)
-cputime_to_clock_t(cputime_t cputime)
 {
-        return cputime_div(cputime, 4096000000ULL / USER_HZ);
+        unsigned long long clock = (__force unsigned long long) cputime;
+        do_div(clock, 4096000000ULL / USER_HZ);
+        return clock;
 }
-static inline cputime_t
+static inline cputime_t clock_t_to_cputime(unsigned long x)
-clock_t_to_cputime(unsigned long x)
 {
-        return (cputime_t) x * (4096000000ULL / USER_HZ);
+        return (__force cputime_t)(x * (4096000000ULL / USER_HZ));
 }
 /*
 * Convert cputime64 to clock.
 */
-static inline clock_t
+static inline clock_t cputime64_to_clock_t(cputime64_t cputime)
-cputime64_to_clock_t(cputime64_t cputime)
 {
-       return cputime_div(cputime, 4096000000ULL / USER_HZ);
+        unsigned long long clock = (__force unsigned long long) cputime;
+        do_div(clock, 4096000000ULL / USER_HZ);
+        return clock;
 }
 struct s390_idle_data {
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 524d23b8610c..4f289ff0b7fe 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -599,10 +599,10 @@ static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
        skey = page_get_storage_key(address);
        bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
        /* Clear page changed & referenced bit in the storage key */
-        if (bits) {
+        if (bits & _PAGE_CHANGED)
-                skey ^= bits;
+                page_set_storage_key(address, skey ^ bits, 1);
-                page_set_storage_key(address, skey, 1);
+        else if (bits)
-        }
+                page_reset_referenced(address);
        /* Transfer page changed & referenced bit to guest bits in pgste */
        pgste_val(pgste) |= bits << 48;         /* RCP_GR_BIT & RCP_GC_BIT */
        /* Get host changed & referenced bits from pgste */
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 9451b210a1b4..3201ae447990 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -91,10 +91,12 @@ static void default_idle(void)
 void cpu_idle(void)
 {
        for (;;) {
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                while (!need_resched())
                        default_idle();
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
                schedule();
                preempt_disable();
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 450931a45b68..573bc29551ef 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -296,13 +296,6 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
                     ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA))))
                        /* Invalid psw mask. */
                        return -EINVAL;
-                if (addr == (addr_t) &dummy->regs.psw.addr)
-                        /*
-                         * The debugger changed the instruction address,
-                         * reset system call restart, see signal.c:do_signal
-                         */
-                        task_thread_info(child)->system_call = 0;
                *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
        } else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) {
@@ -614,11 +607,6 @@ static int __poke_user_compat(struct task_struct *child,
                        /* Transfer 31 bit amode bit to psw mask. */
                        regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) |
                                (__u64)(tmp & PSW32_ADDR_AMODE);
-                        /*
-                         * The debugger changed the instruction address,
-                         * reset system call restart, see signal.c:do_signal
-                         */
-                        task_thread_info(child)->system_call = 0;
                } else {
                        /* gpr 0-15 */
                        *(__u32*)((addr_t) &regs->psw + addr*2 + 4) = tmp;
@@ -905,6 +893,14 @@ static int s390_last_break_get(struct task_struct *target,
        return 0;
 }
+static int s390_last_break_set(struct task_struct *target,
+                               const struct user_regset *regset,
+                               unsigned int pos, unsigned int count,
+                               const void *kbuf, const void __user *ubuf)
+{
+        return 0;
+}
 #endif
 static int s390_system_call_get(struct task_struct *target,
@@ -951,6 +947,7 @@ static const struct user_regset s390_regsets[] = {
                .size = sizeof(long),
                .align = sizeof(long),
                .get = s390_last_break_get,
+                .set = s390_last_break_set,
        },
 #endif
        [REGSET_SYSTEM_CALL] = {
@@ -1116,6 +1113,14 @@ static int s390_compat_last_break_get(struct task_struct *target,
        return 0;
 }
+static int s390_compat_last_break_set(struct task_struct *target,
+                                      const struct user_regset *regset,
+                                      unsigned int pos, unsigned int count,
+                                      const void *kbuf, const void __user *ubuf)
+{
+        return 0;
+}
 static const struct user_regset s390_compat_regsets[] = {
        [REGSET_GENERAL] = {
                .core_note_type = NT_PRSTATUS,
@@ -1139,6 +1144,7 @@ static const struct user_regset s390_compat_regsets[] = {
                .size = sizeof(long),
                .align = sizeof(long),
                .get = s390_compat_last_break_get,
+                .set = s390_compat_last_break_set,
        },
        [REGSET_SYSTEM_CALL] = {
                .core_note_type = NT_S390_SYSTEM_CALL,
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index e58a462949b1..f11d1b037c50 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
@@ -579,7 +580,7 @@ static unsigned long __init find_crash_base(unsigned long crash_size,
                *msg = "first memory chunk must be at least crashkernel size";
                return 0;
        }
-        if (is_kdump_kernel() && (crash_size == OLDMEM_SIZE))
+        if (OLDMEM_BASE && crash_size == OLDMEM_SIZE)
                return OLDMEM_BASE;
        for (i = MEMORY_CHUNKS - 1; i >= 0; i--) {
@@ -820,7 +821,8 @@ setup_memory(void)
                end_chunk = min(end_chunk, end_pfn);
                if (start_chunk >= end_chunk)
                        continue;
-                add_active_range(0, start_chunk, end_chunk);
+                memblock_add_node(PFN_PHYS(start_chunk),
+                                  PFN_PHYS(end_chunk - start_chunk), 0);
                pfn = max(start_chunk, start_pfn);
                for (; pfn < end_chunk; pfn++)
                        page_set_storage_key(PFN_PHYS(pfn),
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 05a85bc14c98..7f6f9f354545 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -460,9 +460,9 @@ void do_signal(struct pt_regs *regs)
                                                     regs->svc_code >> 16);
                                break;
                        }
-                        /* No longer in a system call */
-                        clear_thread_flag(TIF_SYSCALL);
                }
+                /* No longer in a system call */
+                clear_thread_flag(TIF_SYSCALL);
                if ((is_compat_task() ?
                     handle_signal32(signr, &ka, &info, oldset, regs) :
@@ -486,6 +486,7 @@ void do_signal(struct pt_regs *regs)
        }
        /* No handlers present - check for system call restart */
+        clear_thread_flag(TIF_SYSCALL);
        if (current_thread_info()->system_call) {
                regs->svc_code = current_thread_info()->system_call;
                switch (regs->gprs[2]) {
@@ -500,9 +501,6 @@ void do_signal(struct pt_regs *regs)
                        regs->gprs[2] = regs->orig_gpr2;
                        set_thread_flag(TIF_SYSCALL);
                        break;
-                default:
-                        clear_thread_flag(TIF_SYSCALL);
-                        break;
                }
        }
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index f43c0e4282af..9daee91e6c3f 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -22,6 +22,7 @@
 #include <asm/irq.h>
 #include "hwsampler.h"
+#include "op_counter.h"
 #define MAX_NUM_SDB 511
 #define MIN_NUM_SDB 1
@@ -896,6 +897,8 @@ static void add_samples_to_oprofile(unsigned int cpu, unsigned long *sdbt,
                if (sample_data_ptr->P == 1) {
                        /* userspace sample */
                        unsigned int pid = sample_data_ptr->prim_asn;
+                        if (!counter_config.user)
+                                goto skip_sample;
                        rcu_read_lock();
                        tsk = pid_task(find_vpid(pid), PIDTYPE_PID);
                        if (tsk)
@@ -903,6 +906,8 @@ static void add_samples_to_oprofile(unsigned int cpu, unsigned long *sdbt,
                        rcu_read_unlock();
                } else {
                        /* kernelspace sample */
+                        if (!counter_config.kernel)
+                                goto skip_sample;
                        regs = task_pt_regs(current);
                }
@@ -910,7 +915,7 @@ static void add_samples_to_oprofile(unsigned int cpu, unsigned long *sdbt,
                oprofile_add_ext_hw_sample(sample_data_ptr->ia, regs, 0,
                                !sample_data_ptr->P, tsk);
                mutex_unlock(&hws_sem);
+        skip_sample:
                sample_data_ptr++;
        }
 }
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 6efc18b5e60a..2297be406c61 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -2,10 +2,11 @@
 * arch/s390/oprofile/init.c
 *
 * S390 Version
- *   Copyright (C) 2003 IBM Deutschland Entwicklung GmbH, IBM Corporation
+ *   Copyright (C) 2002-2011 IBM Deutschland Entwicklung GmbH, IBM Corporation
 *   Author(s): Thomas Spatzier (tspat@de.ibm.com)
 *   Author(s): Mahesh Salgaonkar (mahesh@linux.vnet.ibm.com)
 *   Author(s): Heinz Graalfs (graalfs@linux.vnet.ibm.com)
+ *   Author(s): Andreas Krebbel (krebbel@linux.vnet.ibm.com)
 *
 * @remark Copyright 2002-2011 OProfile authors
 */
@@ -14,6 +15,8 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/module.h>
+#include <asm/processor.h>
 #include "../../../drivers/oprofile/oprof.h"
@@ -22,6 +25,7 @@ extern void s390_backtrace(struct pt_regs * const regs, unsigned int depth);
 #ifdef CONFIG_64BIT
 #include "hwsampler.h"
+#include "op_counter.h"
 #define DEFAULT_INTERVAL        4127518
@@ -35,16 +39,41 @@ static unsigned long oprofile_max_interval;
 static unsigned long oprofile_sdbt_blocks = DEFAULT_SDBT_BLOCKS;
 static unsigned long oprofile_sdb_blocks = DEFAULT_SDB_BLOCKS;
-static int hwsampler_file;
+static int hwsampler_enabled;
 static int hwsampler_running;   /* start_mutex must be held to change */
+static int hwsampler_available;
 static struct oprofile_operations timer_ops;
+struct op_counter_config counter_config;
+enum __force_cpu_type {
+        reserved = 0,           /* do not force */
+        timer,
+};
+static int force_cpu_type;
+static int set_cpu_type(const char *str, struct kernel_param *kp)
+{
+        if (!strcmp(str, "timer")) {
+                force_cpu_type = timer;
+                printk(KERN_INFO "oprofile: forcing timer to be returned "
+                                 "as cpu type\n");
+        } else {
+                force_cpu_type = 0;
+        }
+        return 0;
+}
+module_param_call(cpu_type, set_cpu_type, NULL, NULL, 0);
+MODULE_PARM_DESC(cpu_type, "Force legacy basic mode sampling"
+                           "(report cpu_type \"timer\"");
 static int oprofile_hwsampler_start(void)
 {
        int retval;
-        hwsampler_running = hwsampler_file;
+        hwsampler_running = hwsampler_enabled;
        if (!hwsampler_running)
                return timer_ops.start();
@@ -72,10 +101,16 @@ static void oprofile_hwsampler_stop(void)
        return;
 }
+/*
+ * File ops used for:
+ * /dev/oprofile/0/enabled
+ * /dev/oprofile/hwsampling/hwsampler  (cpu_type = timer)
+ */
 static ssize_t hwsampler_read(struct file *file, char __user *buf,
                size_t count, loff_t *offset)
 {
-        return oprofilefs_ulong_to_user(hwsampler_file, buf, count, offset);
+        return oprofilefs_ulong_to_user(hwsampler_enabled, buf, count, offset);
 }
 static ssize_t hwsampler_write(struct file *file, char const __user *buf,
@@ -88,9 +123,12 @@ static ssize_t hwsampler_write(struct file *file, char const __user *buf,
                return -EINVAL;
        retval = oprofilefs_ulong_from_user(&val, buf, count);
-        if (retval)
+        if (retval <= 0)
                return retval;
+        if (val != 0 && val != 1)
+                return -EINVAL;
        if (oprofile_started)
                /*
                 * save to do without locking as we set
@@ -99,7 +137,7 @@ static ssize_t hwsampler_write(struct file *file, char const __user *buf,
                 */
                return -EBUSY;
-        hwsampler_file = val;
+        hwsampler_enabled = val;
        return count;
 }
@@ -109,38 +147,311 @@ static const struct file_operations hwsampler_fops = {
        .write          = hwsampler_write,
 };
+/*
+ * File ops used for:
+ * /dev/oprofile/0/count
+ * /dev/oprofile/hwsampling/hw_interval  (cpu_type = timer)
+ *
+ * Make sure that the value is within the hardware range.
+ */
+static ssize_t hw_interval_read(struct file *file, char __user *buf,
+                                size_t count, loff_t *offset)
+{
+        return oprofilefs_ulong_to_user(oprofile_hw_interval, buf,
+                                        count, offset);
+}
+static ssize_t hw_interval_write(struct file *file, char const __user *buf,
+                                 size_t count, loff_t *offset)
+{
+        unsigned long val;
+        int retval;
+        if (*offset)
+                return -EINVAL;
+        retval = oprofilefs_ulong_from_user(&val, buf, count);
+        if (retval)
+                return retval;
+        if (val < oprofile_min_interval)
+                oprofile_hw_interval = oprofile_min_interval;
+        else if (val > oprofile_max_interval)
+                oprofile_hw_interval = oprofile_max_interval;
+        else
+                oprofile_hw_interval = val;
+        return count;
+}
+static const struct file_operations hw_interval_fops = {
+        .read           = hw_interval_read,
+        .write          = hw_interval_write,
+};
+/*
+ * File ops used for:
+ * /dev/oprofile/0/event
+ * Only a single event with number 0 is supported with this counter.
+ *
+ * /dev/oprofile/0/unit_mask
+ * This is a dummy file needed by the user space tools.
+ * No value other than 0 is accepted or returned.
+ */
+static ssize_t hwsampler_zero_read(struct file *file, char __user *buf,
+                                    size_t count, loff_t *offset)
+{
+        return oprofilefs_ulong_to_user(0, buf, count, offset);
+}
+static ssize_t hwsampler_zero_write(struct file *file, char const __user *buf,
+                                     size_t count, loff_t *offset)
+{
+        unsigned long val;
+        int retval;
+        if (*offset)
+                return -EINVAL;
+        retval = oprofilefs_ulong_from_user(&val, buf, count);
+        if (retval)
+                return retval;
+        if (val != 0)
+                return -EINVAL;
+        return count;
+}
+static const struct file_operations zero_fops = {
+        .read           = hwsampler_zero_read,
+        .write          = hwsampler_zero_write,
+};
+/* /dev/oprofile/0/kernel file ops.  */
+static ssize_t hwsampler_kernel_read(struct file *file, char __user *buf,
+                                     size_t count, loff_t *offset)
+{
+        return oprofilefs_ulong_to_user(counter_config.kernel,
+                                        buf, count, offset);
+}
+static ssize_t hwsampler_kernel_write(struct file *file, char const __user *buf,
+                                      size_t count, loff_t *offset)
+{
+        unsigned long val;
+        int retval;
+        if (*offset)
+                return -EINVAL;
+        retval = oprofilefs_ulong_from_user(&val, buf, count);
+        if (retval)
+                return retval;
+        if (val != 0 && val != 1)
+                return -EINVAL;
+        counter_config.kernel = val;
+        return count;
+}
+static const struct file_operations kernel_fops = {
+        .read           = hwsampler_kernel_read,
+        .write          = hwsampler_kernel_write,
+};
+/* /dev/oprofile/0/user file ops. */
+static ssize_t hwsampler_user_read(struct file *file, char __user *buf,
+                                   size_t count, loff_t *offset)
+{
+        return oprofilefs_ulong_to_user(counter_config.user,
+                                        buf, count, offset);
+}
+static ssize_t hwsampler_user_write(struct file *file, char const __user *buf,
+                                    size_t count, loff_t *offset)
+{
+        unsigned long val;
+        int retval;
+        if (*offset)
+                return -EINVAL;
+        retval = oprofilefs_ulong_from_user(&val, buf, count);
+        if (retval)
+                return retval;
+        if (val != 0 && val != 1)
+                return -EINVAL;
+        counter_config.user = val;
+        return count;
+}
+static const struct file_operations user_fops = {
+        .read           = hwsampler_user_read,
+        .write          = hwsampler_user_write,
+};
+/*
+ * File ops used for: /dev/oprofile/timer/enabled
+ * The value always has to be the inverted value of hwsampler_enabled. So
+ * no separate variable is created. That way we do not need locking.
+ */
+static ssize_t timer_enabled_read(struct file *file, char __user *buf,
+                                  size_t count, loff_t *offset)
+{
+        return oprofilefs_ulong_to_user(!hwsampler_enabled, buf, count, offset);
+}
+static ssize_t timer_enabled_write(struct file *file, char const __user *buf,
+                                   size_t count, loff_t *offset)
+{
+        unsigned long val;
+        int retval;
+        if (*offset)
+                return -EINVAL;
+        retval = oprofilefs_ulong_from_user(&val, buf, count);
+        if (retval)
+                return retval;
+        if (val != 0 && val != 1)
+                return -EINVAL;
+        /* Timer cannot be disabled without having hardware sampling.  */
+        if (val == 0 && !hwsampler_available)
+                return -EINVAL;
+        if (oprofile_started)
+                /*
+                 * save to do without locking as we set
+                 * hwsampler_running in start() when start_mutex is
+                 * held
+                 */
+                return -EBUSY;
+        hwsampler_enabled = !val;
+        return count;
+}
+static const struct file_operations timer_enabled_fops = {
+        .read           = timer_enabled_read,
+        .write          = timer_enabled_write,
+};
 static int oprofile_create_hwsampling_files(struct super_block *sb,
-                                                struct dentry *root)
+                                            struct dentry *root)
 {
-        struct dentry *hw_dir;
+        struct dentry *dir;
+        dir = oprofilefs_mkdir(sb, root, "timer");
+        if (!dir)
+                return -EINVAL;
+        oprofilefs_create_file(sb, dir, "enabled", &timer_enabled_fops);
+        if (!hwsampler_available)
+                return 0;
        /* reinitialize default values */
-        hwsampler_file = 1;
+        hwsampler_enabled = 1;
+        counter_config.kernel = 1;
+        counter_config.user = 1;
-        hw_dir = oprofilefs_mkdir(sb, root, "hwsampling");
+        if (!force_cpu_type) {
-        if (!hw_dir)
+                /*
-                return -EINVAL;
+                 * Create the counter file system.  A single virtual
+                 * counter is created which can be used to
+                 * enable/disable hardware sampling dynamically from
+                 * user space.  The user space will configure a single
+                 * counter with a single event.  The value of 'event'
+                 * and 'unit_mask' are not evaluated by the kernel code
+                 * and can only be set to 0.
+                 */
+                dir = oprofilefs_mkdir(sb, root, "0");
+                if (!dir)
+                        return -EINVAL;
-        oprofilefs_create_file(sb, hw_dir, "hwsampler", &hwsampler_fops);
+                oprofilefs_create_file(sb, dir, "enabled", &hwsampler_fops);
-        oprofilefs_create_ulong(sb, hw_dir, "hw_interval",
+                oprofilefs_create_file(sb, dir, "event", &zero_fops);
-                                &oprofile_hw_interval);
+                oprofilefs_create_file(sb, dir, "count", &hw_interval_fops);
-        oprofilefs_create_ro_ulong(sb, hw_dir, "hw_min_interval",
+                oprofilefs_create_file(sb, dir, "unit_mask", &zero_fops);
-                                &oprofile_min_interval);
+                oprofilefs_create_file(sb, dir, "kernel", &kernel_fops);
-        oprofilefs_create_ro_ulong(sb, hw_dir, "hw_max_interval",
+                oprofilefs_create_file(sb, dir, "user", &user_fops);
-                                &oprofile_max_interval);
+                oprofilefs_create_ulong(sb, dir, "hw_sdbt_blocks",
-        oprofilefs_create_ulong(sb, hw_dir, "hw_sdbt_blocks",
+                                        &oprofile_sdbt_blocks);
-                                &oprofile_sdbt_blocks);
+        } else {
+                /*
+                 * Hardware sampling can be used but the cpu_type is
+                 * forced to timer in order to deal with legacy user
+                 * space tools.  The /dev/oprofile/hwsampling fs is
+                 * provided in that case.
+                 */
+                dir = oprofilefs_mkdir(sb, root, "hwsampling");
+                if (!dir)
+                        return -EINVAL;
+                oprofilefs_create_file(sb, dir, "hwsampler",
+                                       &hwsampler_fops);
+                oprofilefs_create_file(sb, dir, "hw_interval",
+                                       &hw_interval_fops);
+                oprofilefs_create_ro_ulong(sb, dir, "hw_min_interval",
+                                           &oprofile_min_interval);
+                oprofilefs_create_ro_ulong(sb, dir, "hw_max_interval",
+                                           &oprofile_max_interval);
+                oprofilefs_create_ulong(sb, dir, "hw_sdbt_blocks",
+                                        &oprofile_sdbt_blocks);
+        }
        return 0;
 }
 static int oprofile_hwsampler_init(struct oprofile_operations *ops)
 {
+        /*
+         * Initialize the timer mode infrastructure as well in order
+         * to be able to switch back dynamically.  oprofile_timer_init
+         * is not supposed to fail.
+         */
+        if (oprofile_timer_init(ops))
+                BUG();
+        memcpy(&timer_ops, ops, sizeof(timer_ops));
+        ops->create_files = oprofile_create_hwsampling_files;
+        /*
+         * If the user space tools do not support newer cpu types,
+         * the force_cpu_type module parameter
+         * can be used to always return \"timer\" as cpu type.
+         */
+        if (force_cpu_type != timer) {
+                struct cpuid id;
+                get_cpu_id (&id);
+                switch (id.machine) {
+                case 0x2097: case 0x2098: ops->cpu_type = "s390/z10"; break;
+                case 0x2817: case 0x2818: ops->cpu_type = "s390/z196"; break;
+                default: return -ENODEV;
+                }
+        }
        if (hwsampler_setup())
                return -ENODEV;
        /*
-         * create hwsampler files only if hwsampler_setup() succeeds.
+         * Query the range for the sampling interval from the
+         * hardware.
         */
        oprofile_min_interval = hwsampler_query_min_interval();
        if (oprofile_min_interval == 0)
@@ -155,23 +466,17 @@ static int oprofile_hwsampler_init(struct oprofile_operations *ops)
        if (oprofile_hw_interval > oprofile_max_interval)
                oprofile_hw_interval = oprofile_max_interval;
-        if (oprofile_timer_init(ops))
+        printk(KERN_INFO "oprofile: System z hardware sampling "
-                return -ENODEV;
+               "facility found.\n");
-        printk(KERN_INFO "oprofile: using hardware sampling\n");
-        memcpy(&timer_ops, ops, sizeof(timer_ops));
        ops->start = oprofile_hwsampler_start;
        ops->stop = oprofile_hwsampler_stop;
-        ops->create_files = oprofile_create_hwsampling_files;
        return 0;
 }
 static void oprofile_hwsampler_exit(void)
 {
-        oprofile_timer_exit();
        hwsampler_shutdown();
 }
@@ -182,7 +487,15 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
        ops->backtrace = s390_backtrace;
 #ifdef CONFIG_64BIT
-        return oprofile_hwsampler_init(ops);
+        /*
+         * -ENODEV is not reported to the caller.  The module itself
+         * will use the timer mode sampling as fallback and this is
+         * always available.
+         */
+        hwsampler_available = oprofile_hwsampler_init(ops) == 0;
+        return 0;
 #else
        return -ENODEV;
 #endif
diff --git a/arch/s390/oprofile/op_counter.h b/arch/s390/oprofile/op_counter.h
new file mode 100644
index 000000000000..1a8d3ca09014
--- /dev/null
+++ b/arch/s390/oprofile/op_counter.h
@@ -0,0 +1,23 @@
+/**
+ * arch/s390/oprofile/op_counter.h
+ *
+ *   Copyright (C) 2011 IBM Deutschland Entwicklung GmbH, IBM Corporation
+ *   Author(s): Andreas Krebbel (krebbel@linux.vnet.ibm.com)
+ *
+ * @remark Copyright 2011 OProfile authors
+ */
+#ifndef OP_COUNTER_H
+#define OP_COUNTER_H
+struct op_counter_config {
+        /* `enabled' maps to the hwsampler_file variable.  */
+        /* `count' maps to the oprofile_hw_interval variable.  */
+        /* `event' and `unit_mask' are unused. */
+        unsigned long kernel;
+        unsigned long user;
+};
+extern struct op_counter_config counter_config;
+#endif /* OP_COUNTER_H */
diff --git a/arch/score/Kconfig b/arch/score/Kconfig
index df169e84db4e..8b0c9464aa9d 100644
--- a/arch/score/Kconfig
+++ b/arch/score/Kconfig
@@ -4,6 +4,9 @@ config SCORE
       def_bool y
       select HAVE_GENERIC_HARDIRQS
       select GENERIC_IRQ_SHOW
+       select HAVE_MEMBLOCK
+       select HAVE_MEMBLOCK_NODE_MAP
+       select ARCH_DISCARD_MEMBLOCK
 choice
        prompt "System type"
@@ -60,9 +63,6 @@ config 32BIT
 config ARCH_FLATMEM_ENABLE
        def_bool y
-config ARCH_POPULATES_NODE_MAP
-        def_bool y
 source "mm/Kconfig"
 config MEMORY_START
diff --git a/arch/score/kernel/setup.c b/arch/score/kernel/setup.c
index 6f898c057878..b48459afefdd 100644
--- a/arch/score/kernel/setup.c
+++ b/arch/score/kernel/setup.c
@@ -26,6 +26,7 @@
 #include <linux/bootmem.h>
 #include <linux/initrd.h>
 #include <linux/ioport.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/seq_file.h>
 #include <linux/screen_info.h>
@@ -54,7 +55,8 @@ static void __init bootmem_init(void)
        /* Initialize the boot-time allocator with low memory only. */
        bootmap_size = init_bootmem_node(NODE_DATA(0), start_pfn,
                                         min_low_pfn, max_low_pfn);
-        add_active_range(0, min_low_pfn, max_low_pfn);
+        memblock_add_node(PFN_PHYS(min_low_pfn),
+                          PFN_PHYS(max_low_pfn - min_low_pfn), 0);
        free_bootmem(PFN_PHYS(start_pfn),
                     (max_low_pfn - start_pfn) << PAGE_SHIFT);
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 5629e2099130..47a2f1c2cb0d 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -4,6 +4,7 @@ config SUPERH
        select CLKDEV_LOOKUP
        select HAVE_IDE if HAS_IOPORT
        select HAVE_MEMBLOCK
+        select HAVE_MEMBLOCK_NODE_MAP
        select HAVE_OPROFILE
        select HAVE_GENERIC_DMA_COHERENT
        select HAVE_ARCH_TRACEHOOK
diff --git a/arch/sh/boards/board-sh7757lcr.c b/arch/sh/boards/board-sh7757lcr.c
index ec8c84c14b17..895e337c79b6 100644
--- a/arch/sh/boards/board-sh7757lcr.c
+++ b/arch/sh/boards/board-sh7757lcr.c
@@ -50,9 +50,9 @@ static struct platform_device heartbeat_device = {
 #define GBECONT         0xffc10100
 #define GBECONT_RMII1   BIT(17)
 #define GBECONT_RMII0   BIT(16)
-static void sh7757_eth_set_mdio_gate(unsigned long addr)
+static void sh7757_eth_set_mdio_gate(void *addr)
 {
-        if ((addr & 0x00000fff) < 0x0800)
+        if (((unsigned long)addr & 0x00000fff) < 0x0800)
                writel(readl(GBECONT) | GBECONT_RMII0, GBECONT);
        else
                writel(readl(GBECONT) | GBECONT_RMII1, GBECONT);
@@ -116,9 +116,9 @@ static struct platform_device sh7757_eth1_device = {
        },
 };
-static void sh7757_eth_giga_set_mdio_gate(unsigned long addr)
+static void sh7757_eth_giga_set_mdio_gate(void *addr)
 {
-        if ((addr & 0x00000fff) < 0x0800) {
+        if (((unsigned long)addr & 0x00000fff) < 0x0800) {
                gpio_set_value(GPIO_PTT4, 1);
                writel(readl(GBECONT) & ~GBECONT_RMII0, GBECONT);
        } else {
@@ -210,8 +210,12 @@ static struct resource sh_mmcif_resources[] = {
 };
 static struct sh_mmcif_dma sh7757lcr_mmcif_dma = {
-        .chan_priv_tx   = SHDMA_SLAVE_MMCIF_TX,
+        .chan_priv_tx   = {
-        .chan_priv_rx   = SHDMA_SLAVE_MMCIF_RX,
+                .slave_id = SHDMA_SLAVE_MMCIF_TX,
+        },
+        .chan_priv_rx   = {
+                .slave_id = SHDMA_SLAVE_MMCIF_RX,
+        }
 };
 static struct sh_mmcif_plat_data sh_mmcif_plat = {
diff --git a/arch/sh/include/asm/memblock.h b/arch/sh/include/asm/memblock.h
deleted file mode 100644
index e87063fad2ea..000000000000
--- a/arch/sh/include/asm/memblock.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef __ASM_SH_MEMBLOCK_H
-#define __ASM_SH_MEMBLOCK_H
-#endif /* __ASM_SH_MEMBLOCK_H */
diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
index db4ecd731a00..406508d4ce74 100644
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@@ -89,7 +89,8 @@ void cpu_idle(void)
        /* endless idle loop with no priority at all */
        while (1) {
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                while (!need_resched()) {
                        check_pgt_cache();
@@ -111,7 +112,8 @@ void cpu_idle(void)
                        start_critical_timings();
                }
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
                schedule();
                preempt_disable();
diff --git a/arch/sh/kernel/machine_kexec.c b/arch/sh/kernel/machine_kexec.c
index c5a33f007f88..9fea49f6e667 100644
--- a/arch/sh/kernel/machine_kexec.c
+++ b/arch/sh/kernel/machine_kexec.c
@@ -157,9 +157,6 @@ void __init reserve_crashkernel(void)
        unsigned long long crash_size, crash_base;
        int ret;
-        /* this is necessary because of memblock_phys_mem_size() */
-        memblock_analyze();
        ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
                        &crash_size, &crash_base);
        if (ret == 0 && crash_size > 0) {
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index 1a0e946679a4..7b57bf1dc855 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -230,7 +230,8 @@ void __init __add_active_range(unsigned int nid, unsigned long start_pfn,
        pmb_bolt_mapping((unsigned long)__va(start), start, end - start,
                         PAGE_KERNEL);
-        add_active_range(nid, start_pfn, end_pfn);
+        memblock_set_node(PFN_PHYS(start_pfn),
+                          PFN_PHYS(end_pfn - start_pfn), nid);
 }
 void __init __weak plat_early_device_setup(void)
diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig
index c3e61b366493..cb8f9920f4dd 100644
--- a/arch/sh/mm/Kconfig
+++ b/arch/sh/mm/Kconfig
@@ -143,9 +143,6 @@ config MAX_ACTIVE_REGIONS
                       CPU_SUBTYPE_SH7785)
        default "1"
-config ARCH_POPULATES_NODE_MAP
-        def_bool y
 config ARCH_SELECT_MEMORY_MODEL
        def_bool y
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 939ca0f356f6..82cc576fab15 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -324,7 +324,6 @@ void __init paging_init(void)
        unsigned long vaddr, end;
        int nid;
-        memblock_init();
        sh_mv.mv_mem_init();
        early_reserve_mem();
@@ -337,7 +336,7 @@ void __init paging_init(void)
                sh_mv.mv_mem_reserve();
        memblock_enforce_memory_limit(memory_limit);
-        memblock_analyze();
+        memblock_allow_resize();
        memblock_dump_all();
diff --git a/arch/sh/oprofile/common.c b/arch/sh/oprofile/common.c
index b4c2d2b946dd..e4dd5d5a1115 100644
--- a/arch/sh/oprofile/common.c
+++ b/arch/sh/oprofile/common.c
@@ -49,7 +49,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
        return oprofile_perf_init(ops);
 }
-void __exit oprofile_arch_exit(void)
+void oprofile_arch_exit(void)
 {
        oprofile_perf_exit();
        kfree(sh_pmu_op_name);
@@ -60,5 +60,5 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
        ops->backtrace = sh_backtrace;
        return -ENODEV;
 }
-void __exit oprofile_arch_exit(void) {}
+void oprofile_arch_exit(void) {}
 #endif /* CONFIG_HW_PERF_EVENTS */
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index f92602e86607..70ae9d81870e 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -43,6 +43,7 @@ config SPARC64
        select HAVE_KPROBES
        select HAVE_RCU_TABLE_FREE if SMP
        select HAVE_MEMBLOCK
+        select HAVE_MEMBLOCK_NODE_MAP
        select HAVE_SYSCALL_WRAPPERS
        select HAVE_DYNAMIC_FTRACE
        select HAVE_FTRACE_MCOUNT_RECORD
@@ -352,9 +353,6 @@ config NODES_SPAN_OTHER_NODES
        def_bool y
        depends on NEED_MULTIPLE_NODES
-config ARCH_POPULATES_NODE_MAP
-        def_bool y if SPARC64
 config ARCH_SELECT_MEMORY_MODEL
        def_bool y if SPARC64
diff --git a/arch/sparc/include/asm/memblock.h b/arch/sparc/include/asm/memblock.h
deleted file mode 100644
index c67b047ef85e..000000000000
--- a/arch/sparc/include/asm/memblock.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _SPARC64_MEMBLOCK_H
-#define _SPARC64_MEMBLOCK_H
-#include <asm/oplib.h>
-#define MEMBLOCK_DBG(fmt...) prom_printf(fmt)
-#endif /* !(_SPARC64_MEMBLOCK_H) */
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index 7429b47c3aca..381edcd5bc29 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -1181,13 +1181,11 @@ static int __devinit ds_probe(struct vio_dev *vdev,
        dp->rcv_buf_len = 4096;
-        dp->ds_states = kzalloc(sizeof(ds_states_template),
+        dp->ds_states = kmemdup(ds_states_template,
-                                GFP_KERNEL);
+                                sizeof(ds_states_template), GFP_KERNEL);
        if (!dp->ds_states)
                goto out_free_rcv_buf;
-        memcpy(dp->ds_states, ds_states_template,
-               sizeof(ds_states_template));
        dp->num_ds_states = ARRAY_SIZE(ds_states_template);
        for (i = 0; i < dp->num_ds_states; i++)
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index b272cda35a01..af5755d20fbe 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -849,10 +849,10 @@ static int pci_sun4v_msiq_build_irq(struct pci_pbm_info *pbm,
        if (!irq)
                return -ENOMEM;
-        if (pci_sun4v_msiq_setstate(pbm->devhandle, msiqid, HV_MSIQSTATE_IDLE))
-                return -EINVAL;
        if (pci_sun4v_msiq_setvalid(pbm->devhandle, msiqid, HV_MSIQ_VALID))
                return -EINVAL;
+        if (pci_sun4v_msiq_setstate(pbm->devhandle, msiqid, HV_MSIQSTATE_IDLE))
+                return -EINVAL;
        return irq;
 }
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 3739a06a76cb..39d8b05201a2 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -95,12 +95,14 @@ void cpu_idle(void)
        set_thread_flag(TIF_POLLING_NRFLAG);
        while(1) {
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                while (!need_resched() && !cpu_is_offline(cpu))
                        sparc64_yield(cpu);
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
diff --git a/arch/sparc/kernel/prom_common.c b/arch/sparc/kernel/prom_common.c
index 46614807a57f..741df916c124 100644
--- a/arch/sparc/kernel/prom_common.c
+++ b/arch/sparc/kernel/prom_common.c
@@ -58,12 +58,10 @@ int of_set_property(struct device_node *dp, const char *name, void *val, int len
        void *new_val;
        int err;
-        new_val = kmalloc(len, GFP_KERNEL);
+        new_val = kmemdup(val, len, GFP_KERNEL);
        if (!new_val)
                return -ENOMEM;
-        memcpy(new_val, val, len);
        err = -ENODEV;
        mutex_lock(&of_set_property_mutex);
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index fe1e3fc31bc5..ffb883ddd0f0 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -84,7 +84,7 @@ static void prom_sync_me(void)
        prom_printf("PROM SYNC COMMAND...\n");
        show_free_areas(0);
-        if(current->pid != 0) {
+        if (!is_idle_task(current)) {
                local_irq_enable();
                sys_sync();
                local_irq_disable();
diff --git a/arch/sparc/mm/btfixup.c b/arch/sparc/mm/btfixup.c
index 5175ac2f4820..8a7f81743c12 100644
--- a/arch/sparc/mm/btfixup.c
+++ b/arch/sparc/mm/btfixup.c
@@ -302,8 +302,7 @@ void __init btfixup(void)
                                case 'i':       /* INT */
                                        if ((insn & 0xc1c00000) == 0x01000000) /* %HI */
                                                set_addr(addr, q[1], fmangled, (insn & 0xffc00000) | (p[1] >> 10));
-                                        else if ((insn & 0x80002000) == 0x80002000 &&
+                                        else if ((insn & 0x80002000) == 0x80002000) /* %LO */
-                                                 (insn & 0x01800000) != 0x01800000) /* %LO */
                                                set_addr(addr, q[1], fmangled, (insn & 0xffffe000) | (p[1] & 0x3ff));
                                        else {
                                                prom_printf(insn_i, p, addr, insn);
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 8e073d802139..b3f5e7dfea51 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -790,7 +790,7 @@ static int find_node(unsigned long addr)
        return -1;
 }
-u64 memblock_nid_range(u64 start, u64 end, int *nid)
+static u64 memblock_nid_range(u64 start, u64 end, int *nid)
 {
        *nid = find_node(start);
        start += PAGE_SIZE;
@@ -808,7 +808,7 @@ u64 memblock_nid_range(u64 start, u64 end, int *nid)
        return start;
 }
 #else
-u64 memblock_nid_range(u64 start, u64 end, int *nid)
+static u64 memblock_nid_range(u64 start, u64 end, int *nid)
 {
        *nid = 0;
        return end;
@@ -816,7 +816,7 @@ u64 memblock_nid_range(u64 start, u64 end, int *nid)
 #endif
 /* This must be invoked after performing all of the necessary
- * add_active_range() calls for 'nid'.  We need to be able to get
+ * memblock_set_node() calls for 'nid'.  We need to be able to get
 * correct data from get_pfn_range_for_nid().
 */
 static void __init allocate_node_data(int nid)
@@ -987,14 +987,11 @@ static void __init add_node_ranges(void)
                        this_end = memblock_nid_range(start, end, &nid);
-                        numadbg("Adding active range nid[%d] "
+                        numadbg("Setting memblock NUMA node nid[%d] "
                                "start[%lx] end[%lx]\n",
                                nid, start, this_end);
-                        add_active_range(nid,
+                        memblock_set_node(start, this_end - start, nid);
-                                         start >> PAGE_SHIFT,
-                                         this_end >> PAGE_SHIFT);
                        start = this_end;
                }
        }
@@ -1282,7 +1279,6 @@ static void __init bootmem_init_nonnuma(void)
 {
        unsigned long top_of_ram = memblock_end_of_DRAM();
        unsigned long total_ram = memblock_phys_mem_size();
-        struct memblock_region *reg;
        numadbg("bootmem_init_nonnuma()\n");
@@ -1292,20 +1288,8 @@ static void __init bootmem_init_nonnuma(void)
               (top_of_ram - total_ram) >> 20);
        init_node_masks_nonnuma();
+        memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
-        for_each_memblock(memory, reg) {
-                unsigned long start_pfn, end_pfn;
-                if (!reg->size)
-                        continue;
-                start_pfn = memblock_region_memory_base_pfn(reg);
-                end_pfn = memblock_region_memory_end_pfn(reg);
-                add_active_range(0, start_pfn, end_pfn);
-        }
        allocate_node_data(0);
        node_set_online(0);
 }
@@ -1769,8 +1753,6 @@ void __init paging_init(void)
                sun4v_ktsb_init();
        }
-        memblock_init();
        /* Find available physical memory...
         *
         * Read it twice in order to work around a bug in openfirmware.
@@ -1796,7 +1778,7 @@ void __init paging_init(void)
        memblock_enforce_memory_limit(cmdline_memory_size);
-        memblock_analyze();
+        memblock_allow_resize();
        memblock_dump_all();
        set_bit(0, mmu_context_bmap);
diff --git a/arch/tile/include/asm/irq.h b/arch/tile/include/asm/irq.h
index 94e9a511de84..f80f8ceabc67 100644
--- a/arch/tile/include/asm/irq.h
+++ b/arch/tile/include/asm/irq.h
@@ -74,16 +74,6 @@ enum {
 */
 void tile_irq_activate(unsigned int irq, int tile_irq_type);
-/*
- * For onboard, non-PCI (e.g. TILE_IRQ_PERCPU) devices, drivers know
- * how to use enable/disable_percpu_irq() to manage interrupts on each
- * core.  We can't use the generic enable/disable_irq() because they
- * use a single reference count per irq, rather than per cpu per irq.
- */
-void enable_percpu_irq(unsigned int irq);
-void disable_percpu_irq(unsigned int irq);
 void setup_irq_regs(void);
 #endif /* _ASM_TILE_IRQ_H */
diff --git a/arch/tile/kernel/irq.c b/arch/tile/kernel/irq.c
index aa0134db2dd6..02e628065012 100644
--- a/arch/tile/kernel/irq.c
+++ b/arch/tile/kernel/irq.c
@@ -152,14 +152,13 @@ void tile_dev_intr(struct pt_regs *regs, int intnum)
 * Remove an irq from the disabled mask.  If we're in an interrupt
 * context, defer enabling the HW interrupt until we leave.
 */
-void enable_percpu_irq(unsigned int irq)
+static void tile_irq_chip_enable(struct irq_data *d)
 {
-        get_cpu_var(irq_disable_mask) &= ~(1UL << irq);
+        get_cpu_var(irq_disable_mask) &= ~(1UL << d->irq);
        if (__get_cpu_var(irq_depth) == 0)
-                unmask_irqs(1UL << irq);
+                unmask_irqs(1UL << d->irq);
        put_cpu_var(irq_disable_mask);
 }
-EXPORT_SYMBOL(enable_percpu_irq);
 /*
 * Add an irq to the disabled mask.  We disable the HW interrupt
@@ -167,13 +166,12 @@ EXPORT_SYMBOL(enable_percpu_irq);
 * in an interrupt context, the return path is careful to avoid
 * unmasking a newly disabled interrupt.
 */
-void disable_percpu_irq(unsigned int irq)
+static void tile_irq_chip_disable(struct irq_data *d)
 {
-        get_cpu_var(irq_disable_mask) |= (1UL << irq);
+        get_cpu_var(irq_disable_mask) |= (1UL << d->irq);
-        mask_irqs(1UL << irq);
+        mask_irqs(1UL << d->irq);
        put_cpu_var(irq_disable_mask);
 }
-EXPORT_SYMBOL(disable_percpu_irq);
 /* Mask an interrupt. */
 static void tile_irq_chip_mask(struct irq_data *d)
@@ -209,6 +207,8 @@ static void tile_irq_chip_eoi(struct irq_data *d)
 static struct irq_chip tile_irq_chip = {
        .name = "tile_irq_chip",
+        .irq_enable = tile_irq_chip_enable,
+        .irq_disable = tile_irq_chip_disable,
        .irq_ack = tile_irq_chip_ack,
        .irq_eoi = tile_irq_chip_eoi,
        .irq_mask = tile_irq_chip_mask,
diff --git a/arch/tile/kernel/pci-dma.c b/arch/tile/kernel/pci-dma.c
index 658f2ce426a4..b3ed19f8779c 100644
--- a/arch/tile/kernel/pci-dma.c
+++ b/arch/tile/kernel/pci-dma.c
@@ -15,6 +15,7 @@
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/vmalloc.h>
+#include <linux/export.h>
 #include <asm/tlbflush.h>
 #include <asm/homecache.h>
diff --git a/arch/tile/kernel/pci.c b/arch/tile/kernel/pci.c
index 2a8014cb1ff5..9d610d3fb11e 100644
--- a/arch/tile/kernel/pci.c
+++ b/arch/tile/kernel/pci.c
@@ -24,6 +24,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/uaccess.h>
+#include <linux/export.h>
 #include <asm/processor.h>
 #include <asm/sections.h>
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 9c45d8bbdf57..4c1ac6e5347a 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -85,7 +85,8 @@ void cpu_idle(void)
        /* endless idle loop with no priority at all */
        while (1) {
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                while (!need_resched()) {
                        if (cpu_is_offline(cpu))
                                BUG();  /* no HOTPLUG_CPU */
@@ -105,7 +106,8 @@ void cpu_idle(void)
                                local_irq_enable();
                        current_thread_info()->status |= TS_POLLING;
                }
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
                schedule();
                preempt_disable();
diff --git a/arch/tile/kernel/sysfs.c b/arch/tile/kernel/sysfs.c
index b671a86f4515..602908268093 100644
--- a/arch/tile/kernel/sysfs.c
+++ b/arch/tile/kernel/sysfs.c
@@ -18,6 +18,7 @@
 #include <linux/cpu.h>
 #include <linux/slab.h>
 #include <linux/smp.h>
+#include <linux/stat.h>
 #include <hv/hypervisor.h>
 /* Return a string queried from the hypervisor, truncated to page size. */
diff --git a/arch/tile/lib/exports.c b/arch/tile/lib/exports.c
index a87d2a859ba9..2a81d32de0da 100644
--- a/arch/tile/lib/exports.c
+++ b/arch/tile/lib/exports.c
@@ -39,6 +39,9 @@ EXPORT_SYMBOL(finv_user_asm);
 EXPORT_SYMBOL(current_text_addr);
 EXPORT_SYMBOL(dump_stack);
+/* arch/tile/kernel/head.S */
+EXPORT_SYMBOL(empty_zero_page);
 /* arch/tile/lib/, various memcpy files */
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(__copy_to_user_inatomic);
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 25b7b90fd620..c1eaaa1fcc20 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -54,7 +54,7 @@ static noinline void force_sig_info_fault(const char *type, int si_signo,
        if (unlikely(tsk->pid < 2)) {
                panic("Signal %d (code %d) at %#lx sent to %s!",
                      si_signo, si_code & 0xffff, address,
-                      tsk->pid ? "init" : "the idle task");
+                      is_idle_task(tsk) ? "the idle task" : "init");
        }
        info.si_signo = si_signo;
@@ -515,7 +515,7 @@ no_context:
        if (unlikely(tsk->pid < 2)) {
                panic("Kernel page fault running %s!",
-                      tsk->pid ? "init" : "the idle task");
+                      is_idle_task(tsk) ? "the idle task" : "init");
        }
        /*
diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c
index cbe6f4f9eca3..1cc6ae477c98 100644
--- a/arch/tile/mm/homecache.c
+++ b/arch/tile/mm/homecache.c
@@ -449,9 +449,12 @@ void homecache_free_pages(unsigned long addr, unsigned int order)
        VM_BUG_ON(!virt_addr_valid((void *)addr));
        page = virt_to_page((void *)addr);
        if (put_page_testzero(page)) {
-                int pages = (1 << order);
                homecache_change_page_home(page, order, initial_page_home());
-                while (pages--)
+                if (order == 0) {
-                        __free_page(page++);
+                        free_hot_cold_page(page, 0);
+                } else {
+                        init_page_count(page);
+                        __free_pages(page, order);
+                }
        }
 }
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index c5338351aecd..69f24905abdc 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -246,10 +246,12 @@ void default_idle(void)
                if (need_resched())
                        schedule();
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                nsecs = disable_timer();
                idle_sleep(nsecs);
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
        }
 }
diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
index a08d9fab81f2..82a6e22f1f35 100644
--- a/arch/um/kernel/time.c
+++ b/arch/um/kernel/time.c
@@ -75,8 +75,6 @@ static struct clocksource itimer_clocksource = {
        .rating         = 300,
        .read           = itimer_read,
        .mask           = CLOCKSOURCE_MASK(64),
-        .mult           = 1000,
-        .shift          = 0,
        .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 };
@@ -94,9 +92,9 @@ static void __init setup_itimer(void)
                clockevent_delta2ns(60 * HZ, &itimer_clockevent);
        itimer_clockevent.min_delta_ns =
                clockevent_delta2ns(1, &itimer_clockevent);
-        err = clocksource_register(&itimer_clocksource);
+        err = clocksource_register_hz(&itimer_clocksource, USEC_PER_SEC);
        if (err) {
-                printk(KERN_ERR "clocksource_register returned %d\n", err);
+                printk(KERN_ERR "clocksource_register_hz returned %d\n", err);
                return;
        }
        clockevents_register_device(&itimer_clockevent);
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index ba401df971ed..52edc2b62873 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -55,7 +55,8 @@ void cpu_idle(void)
 {
        /* endless idle loop with no priority at all */
        while (1) {
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                while (!need_resched()) {
                        local_irq_disable();
                        stop_critical_timings();
@@ -63,7 +64,8 @@ void cpu_idle(void)
                        local_irq_enable();
                        start_critical_timings();
                }
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
                schedule();
                preempt_disable();
diff --git a/arch/unicore32/kernel/setup.c b/arch/unicore32/kernel/setup.c
index 471b6bca8da4..673d7a89d8ff 100644
--- a/arch/unicore32/kernel/setup.c
+++ b/arch/unicore32/kernel/setup.c
@@ -37,6 +37,7 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/traps.h>
+#include <asm/memblock.h>
 #include "setup.h"
diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c
index 3b379cddbc64..de186bde8975 100644
--- a/arch/unicore32/mm/init.c
+++ b/arch/unicore32/mm/init.c
@@ -26,6 +26,7 @@
 #include <asm/setup.h>
 #include <asm/sizes.h>
 #include <asm/tlb.h>
+#include <asm/memblock.h>
 #include <mach/map.h>
 #include "mm.h"
@@ -245,7 +246,6 @@ void __init uc32_memblock_init(struct meminfo *mi)
        sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]),
                meminfo_cmp, NULL);
-        memblock_init();
        for (i = 0; i < mi->nr_banks; i++)
                memblock_add(mi->bank[i].start, mi->bank[i].size);
@@ -264,7 +264,7 @@ void __init uc32_memblock_init(struct meminfo *mi)
        uc32_mm_memblock_reserve();
-        memblock_analyze();
+        memblock_allow_resize();
        memblock_dump_all();
 }
diff --git a/arch/unicore32/mm/mmu.c b/arch/unicore32/mm/mmu.c
index 3e5c3e5a0b45..43c20b40e444 100644
--- a/arch/unicore32/mm/mmu.c
+++ b/arch/unicore32/mm/mmu.c
@@ -25,6 +25,7 @@
 #include <asm/setup.h>
 #include <asm/sizes.h>
 #include <asm/tlb.h>
+#include <asm/memblock.h>
 #include <mach/map.h>
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7b9eaa1ae10b..5731eb70e0a0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -26,6 +26,8 @@ config X86
        select HAVE_IOREMAP_PROT
        select HAVE_KPROBES
        select HAVE_MEMBLOCK
+        select HAVE_MEMBLOCK_NODE_MAP
+        select ARCH_DISCARD_MEMBLOCK
        select ARCH_WANT_OPTIONAL_GPIOLIB
        select ARCH_WANT_FRAME_POINTERS
        select HAVE_DMA_ATTRS
@@ -204,9 +206,6 @@ config ZONE_DMA32
        bool
        default X86_64
-config ARCH_POPULATES_NODE_MAP
-        def_bool y
 config AUDIT_ARCH
        bool
        default X86_64
@@ -403,7 +402,7 @@ config X86_INTEL_CE
          This option compiles in support for the CE4100 SOC for settop
          boxes and media devices.
-config X86_INTEL_MID
+config X86_WANT_INTEL_MID
        bool "Intel MID platform support"
        depends on X86_32
        depends on X86_EXTENDED_PLATFORM
@@ -412,7 +411,10 @@ config X86_INTEL_MID
          systems which do not have the PCI legacy interfaces (Moorestown,
          Medfield). If you are building for a PC class system say N here.
-if X86_INTEL_MID
+if X86_WANT_INTEL_MID
+config X86_INTEL_MID
+        bool
 config X86_MRST
       bool "Moorestown MID platform"
@@ -424,6 +426,7 @@ config X86_MRST
        select SPI
        select INTEL_SCU_IPC
        select X86_PLATFORM_DEVICES
+        select X86_INTEL_MID
        ---help---
          Moorestown is Intel's Low Power Intel Architecture (LPIA) based Moblin
          Internet Device(MID) platform. Moorestown consists of two chips:
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 908b96957d88..37782566af24 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -117,7 +117,7 @@ static inline void early_memtest(unsigned long start, unsigned long end)
 extern unsigned long e820_end_of_ram_pfn(void);
 extern unsigned long e820_end_of_low_ram_pfn(void);
-extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
+extern u64 early_reserve_e820(u64 sizet, u64 align);
 void memblock_x86_fill(void);
 void memblock_find_dma_reserve(void);
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index c9e09ea05644..6919e936345b 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -218,7 +218,7 @@ static inline void fpu_fxsave(struct fpu *fpu)
 #ifdef CONFIG_SMP
 #define safe_address (__per_cpu_offset[0])
 #else
-#define safe_address (kstat_cpu(0).cpustat.user)
+#define safe_address (__get_cpu_var(kernel_cpustat).cpustat[CPUTIME_USER])
 #endif
 /*
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 88c765e16410..74df3f1eddfd 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -137,6 +137,13 @@ static inline int insn_is_avx(struct insn *insn)
        return (insn->vex_prefix.value != 0);
 }
+/* Ensure this instruction is decoded completely */
+static inline int insn_complete(struct insn *insn)
+{
+        return insn->opcode.got && insn->modrm.got && insn->sib.got &&
+                insn->displacement.got && insn->immediate.got;
+}
 static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
 {
        if (insn->vex_prefix.nbytes == 2)       /* 2 bytes VEX */
diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h
index 4420993acc47..925b605eb5c6 100644
--- a/arch/x86/include/asm/intel_scu_ipc.h
+++ b/arch/x86/include/asm/intel_scu_ipc.h
@@ -3,11 +3,15 @@
 #include <linux/notifier.h>
-#define IPCMSG_VRTC     0xFA     /* Set vRTC device */
+#define IPCMSG_WARM_RESET       0xF0
+#define IPCMSG_COLD_RESET       0xF1
-/* Command id associated with message IPCMSG_VRTC */
+#define IPCMSG_SOFT_RESET       0xF2
-#define IPC_CMD_VRTC_SETTIME      1 /* Set time */
+#define IPCMSG_COLD_BOOT        0xF3
-#define IPC_CMD_VRTC_SETALARM     2 /* Set alarm */
+#define IPCMSG_VRTC             0xFA     /* Set vRTC device */
+        /* Command id associated with message IPCMSG_VRTC */
+        #define IPC_CMD_VRTC_SETTIME      1 /* Set time */
+        #define IPC_CMD_VRTC_SETALARM     2 /* Set alarm */
 /* Read single register */
 int intel_scu_ipc_ioread8(u16 addr, u8 *data);
diff --git a/arch/x86/include/asm/mach_timer.h b/arch/x86/include/asm/mach_timer.h
index 853728519ae9..88d0c3c74c13 100644
--- a/arch/x86/include/asm/mach_timer.h
+++ b/arch/x86/include/asm/mach_timer.h
@@ -15,7 +15,7 @@
 #define CALIBRATE_TIME_MSEC 30 /* 30 msecs */
 #define CALIBRATE_LATCH \
-        ((CLOCK_TICK_RATE * CALIBRATE_TIME_MSEC + 1000/2)/1000)
+        ((PIT_TICK_RATE * CALIBRATE_TIME_MSEC + 1000/2)/1000)
 static inline void mach_prepare_counter(void)
 {
diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h
deleted file mode 100644
index 0cd3800f33b9..000000000000
--- a/arch/x86/include/asm/memblock.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#ifndef _X86_MEMBLOCK_H
-#define _X86_MEMBLOCK_H
-#define ARCH_DISCARD_MEMBLOCK
-u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align);
-void memblock_x86_reserve_range(u64 start, u64 end, char *name);
-void memblock_x86_free_range(u64 start, u64 end);
-struct range;
-int __get_free_all_memory_range(struct range **range, int nodeid,
-                         unsigned long start_pfn, unsigned long end_pfn);
-int get_free_all_memory_range(struct range **rangep, int nodeid);
-void memblock_x86_register_active_regions(int nid, unsigned long start_pfn,
-                                         unsigned long last_pfn);
-u64 memblock_x86_hole_size(u64 start, u64 end);
-u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align);
-u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit);
-u64 memblock_x86_memory_in_range(u64 addr, u64 limit);
-bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align);
-#endif
diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h
index e6283129c821..93f79094c224 100644
--- a/arch/x86/include/asm/mrst.h
+++ b/arch/x86/include/asm/mrst.h
@@ -31,11 +31,20 @@ enum mrst_cpu_type {
 };
 extern enum mrst_cpu_type __mrst_cpu_chip;
+#ifdef CONFIG_X86_INTEL_MID
 static inline enum mrst_cpu_type mrst_identify_cpu(void)
 {
        return __mrst_cpu_chip;
 }
+#else /* !CONFIG_X86_INTEL_MID */
+#define mrst_identify_cpu()    (0)
+#endif /* !CONFIG_X86_INTEL_MID */
 enum mrst_timer_options {
        MRST_TIMER_DEFAULT,
        MRST_TIMER_APBT_ONLY,
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 084ef95274cd..95203d40ffdd 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -169,7 +169,14 @@ static inline int wrmsr_safe(unsigned msr, unsigned low, unsigned high)
        return native_write_msr_safe(msr, low, high);
 }
-/* rdmsr with exception handling */
+/*
+ * rdmsr with exception handling.
+ *
+ * Please note that the exception handling works only after we've
+ * switched to the "smart" #GP handler in trap_init() which knows about
+ * exception tables - using this macro earlier than that causes machine
+ * hangs on boxes which do not implement the @msr in the first argument.
+ */
 #define rdmsr_safe(msr, p1, p2)                                 \
 ({                                                              \
        int __err;                                              \
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index f61c62f7d5d8..096c975e099f 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -57,6 +57,7 @@
                (1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
 #define ARCH_PERFMON_BRANCH_MISSES_RETIRED              6
+#define ARCH_PERFMON_EVENTS_COUNT                       7
 /*
 * Intel "Architectural Performance Monitoring" CPUID
@@ -72,6 +73,19 @@ union cpuid10_eax {
        unsigned int full;
 };
+union cpuid10_ebx {
+        struct {
+                unsigned int no_unhalted_core_cycles:1;
+                unsigned int no_instructions_retired:1;
+                unsigned int no_unhalted_reference_cycles:1;
+                unsigned int no_llc_reference:1;
+                unsigned int no_llc_misses:1;
+                unsigned int no_branch_instruction_retired:1;
+                unsigned int no_branch_misses_retired:1;
+        } split;
+        unsigned int full;
+};
 union cpuid10_edx {
        struct {
                unsigned int num_counters_fixed:5;
@@ -81,6 +95,15 @@ union cpuid10_edx {
        unsigned int full;
 };
+struct x86_pmu_capability {
+        int             version;
+        int             num_counters_gp;
+        int             num_counters_fixed;
+        int             bit_width_gp;
+        int             bit_width_fixed;
+        unsigned int    events_mask;
+        int             events_mask_len;
+};
 /*
 * Fixed-purpose performance events:
@@ -89,23 +112,24 @@ union cpuid10_edx {
 /*
 * All 3 fixed-mode PMCs are configured via this single MSR:
 */
-#define MSR_ARCH_PERFMON_FIXED_CTR_CTRL                 0x38d
+#define MSR_ARCH_PERFMON_FIXED_CTR_CTRL 0x38d
 /*
 * The counts are available in three separate MSRs:
 */
 /* Instr_Retired.Any: */
-#define MSR_ARCH_PERFMON_FIXED_CTR0                     0x309
+#define MSR_ARCH_PERFMON_FIXED_CTR0     0x309
-#define X86_PMC_IDX_FIXED_INSTRUCTIONS                  (X86_PMC_IDX_FIXED + 0)
+#define X86_PMC_IDX_FIXED_INSTRUCTIONS  (X86_PMC_IDX_FIXED + 0)
 /* CPU_CLK_Unhalted.Core: */
-#define MSR_ARCH_PERFMON_FIXED_CTR1                     0x30a
+#define MSR_ARCH_PERFMON_FIXED_CTR1     0x30a
-#define X86_PMC_IDX_FIXED_CPU_CYCLES                    (X86_PMC_IDX_FIXED + 1)
+#define X86_PMC_IDX_FIXED_CPU_CYCLES    (X86_PMC_IDX_FIXED + 1)
 /* CPU_CLK_Unhalted.Ref: */
-#define MSR_ARCH_PERFMON_FIXED_CTR2                     0x30b
+#define MSR_ARCH_PERFMON_FIXED_CTR2     0x30b
-#define X86_PMC_IDX_FIXED_BUS_CYCLES                    (X86_PMC_IDX_FIXED + 2)
+#define X86_PMC_IDX_FIXED_REF_CYCLES    (X86_PMC_IDX_FIXED + 2)
+#define X86_PMC_MSK_FIXED_REF_CYCLES    (1ULL << X86_PMC_IDX_FIXED_REF_CYCLES)
 /*
 * We model BTS tracing as another fixed-mode PMC.
@@ -202,6 +226,7 @@ struct perf_guest_switch_msr {
 };
 extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
+extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
 #else
 static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
 {
@@ -209,6 +234,11 @@ static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
        return NULL;
 }
+static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
+{
+        memset(cap, 0, sizeof(*cap));
+}
 static inline void perf_events_lapic_init(void) { }
 #endif
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index fa7b9176b76c..431793e5d484 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -32,6 +32,22 @@ extern int no_timer_check;
 *  (mathieu.desnoyers@polymtl.ca)
 *
 *                      -johnstul@us.ibm.com "math is hard, lets go shopping!"
+ *
+ * In:
+ *
+ * ns = cycles * cyc2ns_scale / SC
+ *
+ * Although we may still have enough bits to store the value of ns,
+ * in some cases, we may not have enough bits to store cycles * cyc2ns_scale,
+ * leading to an incorrect result.
+ *
+ * To avoid this, we can decompose 'cycles' into quotient and remainder
+ * of division by SC.  Then,
+ *
+ * ns = (quot * SC + rem) * cyc2ns_scale / SC
+ *    = quot * cyc2ns_scale + (rem * cyc2ns_scale) / SC
+ *
+ *                      - sqazi@google.com
 */
 DECLARE_PER_CPU(unsigned long, cyc2ns);
@@ -41,9 +57,14 @@ DECLARE_PER_CPU(unsigned long long, cyc2ns_offset);
 static inline unsigned long long __cycles_2_ns(unsigned long long cyc)
 {
+        unsigned long long quot;
+        unsigned long long rem;
        int cpu = smp_processor_id();
        unsigned long long ns = per_cpu(cyc2ns_offset, cpu);
-        ns += cyc * per_cpu(cyc2ns, cpu) >> CYC2NS_SCALE_FACTOR;
+        quot = (cyc >> CYC2NS_SCALE_FACTOR);
+        rem = cyc & ((1ULL << CYC2NS_SCALE_FACTOR) - 1);
+        ns += quot * per_cpu(cyc2ns, cpu) +
+                ((rem * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR);
        return ns;
 }
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 83e2efd181e2..15d99153a96d 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -51,6 +51,8 @@ extern int unsynchronized_tsc(void);
 extern int check_tsc_unstable(void);
 extern unsigned long native_calibrate_tsc(void);
+extern int tsc_clocksource_reliable;
 /*
 * Boot-time check whether the TSCs are synchronized across
 * all CPUs/cores:
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index 10474fb1185d..cf1d73643f60 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -57,6 +57,7 @@
 #define UV1_HUB_PART_NUMBER     0x88a5
 #define UV2_HUB_PART_NUMBER     0x8eb8
+#define UV2_HUB_PART_NUMBER_X   0x1111
 /* Compat: if this #define is present, UV headers support UV2 */
 #define UV2_HUB_IS_SUPPORTED    1
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 3d2661ca6542..6e76c191a835 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -88,13 +88,13 @@ static u32 __init allocate_aperture(void)
         */
        addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR,
                                      aper_size, aper_size);
-        if (addr == MEMBLOCK_ERROR || addr + aper_size > GART_MAX_ADDR) {
+        if (!addr || addr + aper_size > GART_MAX_ADDR) {
                printk(KERN_ERR
                        "Cannot allocate aperture memory hole (%lx,%uK)\n",
                                addr, aper_size>>10);
                return 0;
        }
-        memblock_x86_reserve_range(addr, addr + aper_size, "aperture64");
+        memblock_reserve(addr, aper_size);
        /*
         * Kmemleak should not scan this block as it may not be mapped via the
         * kernel direct mapping.
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index ff69d5d79ca7..2eec05b6d1b8 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -887,8 +887,8 @@ void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs)
         * Besides, if we don't timer interrupts ignore the global
         * interrupt lock, which is the WrongThing (tm) to do.
         */
-        exit_idle();
        irq_enter();
+        exit_idle();
        local_apic_timer_interrupt();
        irq_exit();
@@ -1864,8 +1864,8 @@ void smp_spurious_interrupt(struct pt_regs *regs)
 {
        u32 v;
-        exit_idle();
        irq_enter();
+        exit_idle();
        /*
         * Check if this really is a spurious interrupt and ACK it
         * if it is a vectored one.  Just in case...
@@ -1901,8 +1901,8 @@ void smp_error_interrupt(struct pt_regs *regs)
                "Illegal register address",     /* APIC Error Bit 7 */
        };
-        exit_idle();
        irq_enter();
+        exit_idle();
        /* First tickle the hardware, only then report what went on. -- REW */
        v0 = apic_read(APIC_ESR);
        apic_write(APIC_ESR, 0);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 45b461fdb344..fb072754bc1d 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2421,8 +2421,8 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
        unsigned vector, me;
        ack_APIC_irq();
-        exit_idle();
        irq_enter();
+        exit_idle();
        me = smp_processor_id();
        for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 62ae3001ae02..9d59bbacd4e3 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -93,6 +93,8 @@ static int __init early_get_pnodeid(void)
        if (node_id.s.part_number == UV2_HUB_PART_NUMBER)
                uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1;
+        if (node_id.s.part_number == UV2_HUB_PART_NUMBER_X)
+                uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1;
        uv_hub_info->hub_revision = uv_min_hub_revision_id;
        pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1);
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index 452932d34730..5da1269e8ddc 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -62,7 +62,8 @@ early_param("memory_corruption_check_size", set_corruption_check_size);
 void __init setup_bios_corruption_check(void)
 {
-        u64 addr = PAGE_SIZE;   /* assume first page is reserved anyway */
+        phys_addr_t start, end;
+        u64 i;
        if (memory_corruption_check == -1) {
                memory_corruption_check =
@@ -82,28 +83,23 @@ void __init setup_bios_corruption_check(void)
        corruption_check_size = round_up(corruption_check_size, PAGE_SIZE);
-        while (addr < corruption_check_size && num_scan_areas < MAX_SCAN_AREAS) {
+        for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) {
-                u64 size;
+                start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE),
-                addr = memblock_x86_find_in_range_size(addr, &size, PAGE_SIZE);
+                                PAGE_SIZE, corruption_check_size);
+                end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE),
+                              PAGE_SIZE, corruption_check_size);
+                if (start >= end)
+                        continue;
-                if (addr == MEMBLOCK_ERROR)
+                memblock_reserve(start, end - start);
-                        break;
+                scan_areas[num_scan_areas].addr = start;
+                scan_areas[num_scan_areas].size = end - start;
-                if (addr >= corruption_check_size)
-                        break;
-                if ((addr + size) > corruption_check_size)
-                        size = corruption_check_size - addr;
-                memblock_x86_reserve_range(addr, addr + size, "SCAN RAM");
-                scan_areas[num_scan_areas].addr = addr;
-                scan_areas[num_scan_areas].size = size;
-                num_scan_areas++;
                /* Assume we've already mapped this early memory */
-                memset(__va(addr), 0, size);
+                memset(__va(start), 0, end - start);
-                addr += size;
+                if (++num_scan_areas >= MAX_SCAN_AREAS)
+                        break;
        }
        if (num_scan_areas)
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 787e06c84ea6..ce215616d5b9 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -397,8 +397,8 @@ static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;
 asmlinkage void smp_thermal_interrupt(struct pt_regs *regs)
 {
-        exit_idle();
        irq_enter();
+        exit_idle();
        inc_irq_stat(irq_thermal_count);
        smp_thermal_vector();
        irq_exit();
diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c
index d746df2909c9..aa578cadb940 100644
--- a/arch/x86/kernel/cpu/mcheck/threshold.c
+++ b/arch/x86/kernel/cpu/mcheck/threshold.c
@@ -19,8 +19,8 @@ void (*mce_threshold_vector)(void) = default_threshold_interrupt;
 asmlinkage void smp_threshold_interrupt(void)
 {
-        exit_idle();
        irq_enter();
+        exit_idle();
        inc_irq_stat(irq_threshold_count);
        mce_threshold_vector();
        irq_exit();
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index a71efcdbb092..97b26356e9ee 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -547,6 +547,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
                if (tmp != mask_lo) {
                        printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n");
+                        add_taint(TAINT_FIRMWARE_WORKAROUND);
                        mask_lo = tmp;
                }
        }
@@ -693,6 +694,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
        /* Disable MTRRs, and set the default type to uncached */
        mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi);
+        wbinvd();
 }
 static void post_set(void) __releases(set_atomicity_lock)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 640891014b2a..5adce1040b11 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -312,12 +312,8 @@ int x86_setup_perfctr(struct perf_event *event)
                        return -EOPNOTSUPP;
        }
-        /*
-         * Do not allow config1 (extended registers) to propagate,
-         * there's no sane user-space generalization yet:
-         */
        if (attr->type == PERF_TYPE_RAW)
-                return 0;
+                return x86_pmu_extra_regs(event->attr.config, event);
        if (attr->type == PERF_TYPE_HW_CACHE)
                return set_ext_hw_attr(hwc, event);
@@ -488,18 +484,195 @@ static inline int is_x86_event(struct perf_event *event)
        return event->pmu == &pmu;
 }
+/*
+ * Event scheduler state:
+ *
+ * Assign events iterating over all events and counters, beginning
+ * with events with least weights first. Keep the current iterator
+ * state in struct sched_state.
+ */
+struct sched_state {
+        int     weight;
+        int     event;          /* event index */
+        int     counter;        /* counter index */
+        int     unassigned;     /* number of events to be assigned left */
+        unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+};
+/* Total max is X86_PMC_IDX_MAX, but we are O(n!) limited */
+#define SCHED_STATES_MAX        2
+struct perf_sched {
+        int                     max_weight;
+        int                     max_events;
+        struct event_constraint **constraints;
+        struct sched_state      state;
+        int                     saved_states;
+        struct sched_state      saved[SCHED_STATES_MAX];
+};
+/*
+ * Initialize interator that runs through all events and counters.
+ */
+static void perf_sched_init(struct perf_sched *sched, struct event_constraint **c,
+                            int num, int wmin, int wmax)
+{
+        int idx;
+        memset(sched, 0, sizeof(*sched));
+        sched->max_events       = num;
+        sched->max_weight       = wmax;
+        sched->constraints      = c;
+        for (idx = 0; idx < num; idx++) {
+                if (c[idx]->weight == wmin)
+                        break;
+        }
+        sched->state.event      = idx;          /* start with min weight */
+        sched->state.weight     = wmin;
+        sched->state.unassigned = num;
+}
+static void perf_sched_save_state(struct perf_sched *sched)
+{
+        if (WARN_ON_ONCE(sched->saved_states >= SCHED_STATES_MAX))
+                return;
+        sched->saved[sched->saved_states] = sched->state;
+        sched->saved_states++;
+}
+static bool perf_sched_restore_state(struct perf_sched *sched)
+{
+        if (!sched->saved_states)
+                return false;
+        sched->saved_states--;
+        sched->state = sched->saved[sched->saved_states];
+        /* continue with next counter: */
+        clear_bit(sched->state.counter++, sched->state.used);
+        return true;
+}
+/*
+ * Select a counter for the current event to schedule. Return true on
+ * success.
+ */
+static bool __perf_sched_find_counter(struct perf_sched *sched)
+{
+        struct event_constraint *c;
+        int idx;
+        if (!sched->state.unassigned)
+                return false;
+        if (sched->state.event >= sched->max_events)
+                return false;
+        c = sched->constraints[sched->state.event];
+        /* Prefer fixed purpose counters */
+        if (x86_pmu.num_counters_fixed) {
+                idx = X86_PMC_IDX_FIXED;
+                for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_MAX) {
+                        if (!__test_and_set_bit(idx, sched->state.used))
+                                goto done;
+                }
+        }
+        /* Grab the first unused counter starting with idx */
+        idx = sched->state.counter;
+        for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_FIXED) {
+                if (!__test_and_set_bit(idx, sched->state.used))
+                        goto done;
+        }
+        return false;
+done:
+        sched->state.counter = idx;
+        if (c->overlap)
+                perf_sched_save_state(sched);
+        return true;
+}
+static bool perf_sched_find_counter(struct perf_sched *sched)
+{
+        while (!__perf_sched_find_counter(sched)) {
+                if (!perf_sched_restore_state(sched))
+                        return false;
+        }
+        return true;
+}
+/*
+ * Go through all unassigned events and find the next one to schedule.
+ * Take events with the least weight first. Return true on success.
+ */
+static bool perf_sched_next_event(struct perf_sched *sched)
+{
+        struct event_constraint *c;
+        if (!sched->state.unassigned || !--sched->state.unassigned)
+                return false;
+        do {
+                /* next event */
+                sched->state.event++;
+                if (sched->state.event >= sched->max_events) {
+                        /* next weight */
+                        sched->state.event = 0;
+                        sched->state.weight++;
+                        if (sched->state.weight > sched->max_weight)
+                                return false;
+                }
+                c = sched->constraints[sched->state.event];
+        } while (c->weight != sched->state.weight);
+        sched->state.counter = 0;       /* start with first counter */
+        return true;
+}
+/*
+ * Assign a counter for each event.
+ */
+static int perf_assign_events(struct event_constraint **constraints, int n,
+                              int wmin, int wmax, int *assign)
+{
+        struct perf_sched sched;
+        perf_sched_init(&sched, constraints, n, wmin, wmax);
+        do {
+                if (!perf_sched_find_counter(&sched))
+                        break;  /* failed */
+                if (assign)
+                        assign[sched.state.event] = sched.state.counter;
+        } while (perf_sched_next_event(&sched));
+        return sched.state.unassigned;
+}
 int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 {
        struct event_constraint *c, *constraints[X86_PMC_IDX_MAX];
        unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
-        int i, j, w, wmax, num = 0;
+        int i, wmin, wmax, num = 0;
        struct hw_perf_event *hwc;
        bitmap_zero(used_mask, X86_PMC_IDX_MAX);
-        for (i = 0; i < n; i++) {
+        for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
                c = x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]);
                constraints[i] = c;
+                wmin = min(wmin, c->weight);
+                wmax = max(wmax, c->weight);
        }
        /*
@@ -525,59 +698,11 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
                if (assign)
                        assign[i] = hwc->idx;
        }
-        if (i == n)
-                goto done;
-        /*
-         * begin slow path
-         */
-        bitmap_zero(used_mask, X86_PMC_IDX_MAX);
-        /*
-         * weight = number of possible counters
-         *
-         * 1    = most constrained, only works on one counter
-         * wmax = least constrained, works on any counter
-         *
-         * assign events to counters starting with most
-         * constrained events.
-         */
-        wmax = x86_pmu.num_counters;
-        /*
-         * when fixed event counters are present,
-         * wmax is incremented by 1 to account
-         * for one more choice
-         */
-        if (x86_pmu.num_counters_fixed)
-                wmax++;
-        for (w = 1, num = n; num && w <= wmax; w++) {
-                /* for each event */
-                for (i = 0; num && i < n; i++) {
-                        c = constraints[i];
-                        hwc = &cpuc->event_list[i]->hw;
-                        if (c->weight != w)
-                                continue;
-                        for_each_set_bit(j, c->idxmsk, X86_PMC_IDX_MAX) {
+        /* slow path */
-                                if (!test_bit(j, used_mask))
+        if (i != n)
-                                        break;
+                num = perf_assign_events(constraints, n, wmin, wmax, assign);
-                        }
-                        if (j == X86_PMC_IDX_MAX)
-                                break;
-                        __set_bit(j, used_mask);
-                        if (assign)
-                                assign[i] = j;
-                        num--;
-                }
-        }
-done:
        /*
         * scheduling failed or is just a simulation,
         * free resources if necessary
@@ -588,7 +713,7 @@ done:
                                x86_pmu.put_event_constraints(cpuc, cpuc->event_list[i]);
                }
        }
-        return num ? -ENOSPC : 0;
+        return num ? -EINVAL : 0;
 }
 /*
@@ -607,7 +732,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
        if (is_x86_event(leader)) {
                if (n >= max_count)
-                        return -ENOSPC;
+                        return -EINVAL;
                cpuc->event_list[n] = leader;
                n++;
        }
@@ -620,7 +745,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
                        continue;
                if (n >= max_count)
-                        return -ENOSPC;
+                        return -EINVAL;
                cpuc->event_list[n] = event;
                n++;
@@ -1123,6 +1248,7 @@ static void __init pmu_check_apic(void)
 static int __init init_hw_perf_events(void)
 {
+        struct x86_pmu_quirk *quirk;
        struct event_constraint *c;
        int err;
@@ -1151,8 +1277,8 @@ static int __init init_hw_perf_events(void)
        pr_cont("%s PMU driver.\n", x86_pmu.name);
-        if (x86_pmu.quirks)
+        for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next)
-                x86_pmu.quirks();
+                quirk->func();
        if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) {
                WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
@@ -1175,12 +1301,18 @@ 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, x86_pmu.num_counters, 0);
        if (x86_pmu.event_constraints) {
+                /*
+                 * event on fixed counter2 (REF_CYCLES) only works on this
+                 * counter, so do not extend mask to generic counters
+                 */
                for_each_event_constraint(c, x86_pmu.event_constraints) {
-                        if (c->cmask != X86_RAW_EVENT_MASK)
+                        if (c->cmask != X86_RAW_EVENT_MASK
+                            || c->idxmsk64 == X86_PMC_MSK_FIXED_REF_CYCLES) {
                                continue;
+                        }
                        c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
                        c->weight += x86_pmu.num_counters;
@@ -1316,7 +1448,7 @@ static int validate_event(struct perf_event *event)
        c = x86_pmu.get_event_constraints(fake_cpuc, event);
        if (!c || !c->weight)
-                ret = -ENOSPC;
+                ret = -EINVAL;
        if (x86_pmu.put_event_constraints)
                x86_pmu.put_event_constraints(fake_cpuc, event);
@@ -1341,7 +1473,7 @@ static int validate_group(struct perf_event *event)
 {
        struct perf_event *leader = event->group_leader;
        struct cpu_hw_events *fake_cpuc;
-        int ret = -ENOSPC, n;
+        int ret = -EINVAL, n;
        fake_cpuc = allocate_fake_cpuc();
        if (IS_ERR(fake_cpuc))
@@ -1570,3 +1702,15 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
        return misc;
 }
+void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
+{
+        cap->version            = x86_pmu.version;
+        cap->num_counters_gp    = x86_pmu.num_counters;
+        cap->num_counters_fixed = x86_pmu.num_counters_fixed;
+        cap->bit_width_gp       = x86_pmu.cntval_bits;
+        cap->bit_width_fixed    = x86_pmu.cntval_bits;
+        cap->events_mask        = (unsigned int)x86_pmu.events_maskl;
+        cap->events_mask_len    = x86_pmu.events_mask_len;
+}
+EXPORT_SYMBOL_GPL(perf_get_x86_pmu_capability);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index b9698d40ac4b..8944062f46e2 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -45,6 +45,7 @@ struct event_constraint {
        u64     code;
        u64     cmask;
        int     weight;
+        int     overlap;
 };
 struct amd_nb {
@@ -151,15 +152,40 @@ struct cpu_hw_events {
        void                            *kfree_on_online;
 };
-#define __EVENT_CONSTRAINT(c, n, m, w) {\
+#define __EVENT_CONSTRAINT(c, n, m, w, o) {\
        { .idxmsk64 = (n) },            \
        .code = (c),                    \
        .cmask = (m),                   \
        .weight = (w),                  \
+        .overlap = (o),                 \
 }
 #define EVENT_CONSTRAINT(c, n, m)       \
-        __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n))
+        __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0)
+/*
+ * The overlap flag marks event constraints with overlapping counter
+ * masks. This is the case if the counter mask of such an event is not
+ * a subset of any other counter mask of a constraint with an equal or
+ * higher weight, e.g.:
+ *
+ *  c_overlaps = EVENT_CONSTRAINT_OVERLAP(0, 0x09, 0);
+ *  c_another1 = EVENT_CONSTRAINT(0, 0x07, 0);
+ *  c_another2 = EVENT_CONSTRAINT(0, 0x38, 0);
+ *
+ * The event scheduler may not select the correct counter in the first
+ * cycle because it needs to know which subsequent events will be
+ * scheduled. It may fail to schedule the events then. So we set the
+ * overlap flag for such constraints to give the scheduler a hint which
+ * events to select for counter rescheduling.
+ *
+ * Care must be taken as the rescheduling algorithm is O(n!) which
+ * will increase scheduling cycles for an over-commited system
+ * dramatically.  The number of such EVENT_CONSTRAINT_OVERLAP() macros
+ * 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)
 /*
 * Constraint on the Event code.
@@ -235,6 +261,11 @@ union perf_capabilities {
        u64     capabilities;
 };
+struct x86_pmu_quirk {
+        struct x86_pmu_quirk *next;
+        void (*func)(void);
+};
 /*
 * struct x86_pmu - generic x86 pmu
 */
@@ -259,6 +290,11 @@ struct x86_pmu {
        int             num_counters_fixed;
        int             cntval_bits;
        u64             cntval_mask;
+        union {
+                        unsigned long events_maskl;
+                        unsigned long events_mask[BITS_TO_LONGS(ARCH_PERFMON_EVENTS_COUNT)];
+        };
+        int             events_mask_len;
        int             apic;
        u64             max_period;
        struct event_constraint *
@@ -268,7 +304,7 @@ struct x86_pmu {
        void            (*put_event_constraints)(struct cpu_hw_events *cpuc,
                                                 struct perf_event *event);
        struct event_constraint *event_constraints;
-        void            (*quirks)(void);
+        struct x86_pmu_quirk *quirks;
        int             perfctr_second_write;
        int             (*cpu_prepare)(int cpu);
@@ -309,6 +345,15 @@ struct x86_pmu {
        struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
 };
+#define x86_add_quirk(func_)                                            \
+do {                                                                    \
+        static struct x86_pmu_quirk __quirk __initdata = {              \
+                .func = func_,                                          \
+        };                                                              \
+        __quirk.next = x86_pmu.quirks;                                  \
+        x86_pmu.quirks = &__quirk;                                      \
+} while (0)
 #define ERF_NO_HT_SHARING       1
 #define ERF_HAS_RSP_1           2
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index aeefd45697a2..0397b23be8e9 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -492,7 +492,7 @@ static __initconst const struct x86_pmu amd_pmu = {
 static struct event_constraint amd_f15_PMC0  = EVENT_CONSTRAINT(0, 0x01, 0);
 static struct event_constraint amd_f15_PMC20 = EVENT_CONSTRAINT(0, 0x07, 0);
 static struct event_constraint amd_f15_PMC3  = EVENT_CONSTRAINT(0, 0x08, 0);
-static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT(0, 0x09, 0);
+static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT_OVERLAP(0, 0x09, 0);
 static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0);
 static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index ab6343d21825..3b8a2d30d14e 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -199,8 +199,7 @@ static int force_ibs_eilvt_setup(void)
                goto out;
        }
-        pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset);
+        pr_info("IBS: LVT offset %d assigned\n", offset);
-        pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
        return 0;
 out:
@@ -265,19 +264,23 @@ perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *h
 static __init int amd_ibs_init(void)
 {
        u32 caps;
-        int ret;
+        int ret = -EINVAL;
        caps = __get_ibs_caps();
        if (!caps)
                return -ENODEV; /* ibs not supported by the cpu */
-        if (!ibs_eilvt_valid()) {
+        /*
-                ret = force_ibs_eilvt_setup();
+         * Force LVT offset assignment for family 10h: The offsets are
-                if (ret) {
+         * not assigned by the BIOS for this family, so the OS is
-                        pr_err("Failed to setup IBS, %d\n", ret);
+         * responsible for doing it. If the OS assignment fails, fall
-                        return ret;
+         * back to BIOS settings and try to setup this.
-                }
+         */
-        }
+        if (boot_cpu_data.x86 == 0x10)
+                force_ibs_eilvt_setup();
+        if (!ibs_eilvt_valid())
+                goto out;
        get_online_cpus();
        ibs_caps = caps;
@@ -287,7 +290,11 @@ static __init int amd_ibs_init(void)
        smp_call_function(setup_APIC_ibs, NULL, 1);
        put_online_cpus();
-        return perf_event_ibs_init();
+        ret = perf_event_ibs_init();
+out:
+        if (ret)
+                pr_err("Failed to setup IBS, %d\n", ret);
+        return ret;
 }
 /* Since we need the pci subsystem to init ibs we can't do this earlier: */
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 2be5ebe99872..3bd37bdf1b8e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -28,6 +28,7 @@ static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly =
  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]   = 0x00c4,
  [PERF_COUNT_HW_BRANCH_MISSES]         = 0x00c5,
  [PERF_COUNT_HW_BUS_CYCLES]            = 0x013c,
+  [PERF_COUNT_HW_REF_CPU_CYCLES]        = 0x0300, /* pseudo-encoding */
 };
 static struct event_constraint intel_core_event_constraints[] __read_mostly =
@@ -45,12 +46,7 @@ static struct event_constraint intel_core2_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 */
-         * Core2 has Fixed Counter 2 listed as CPU_CLK_UNHALTED.REF and event
-         * 0x013c as CPU_CLK_UNHALTED.BUS and specifies there is a fixed
-         * ratio between these counters.
-         */
-        /* FIXED_EVENT_CONSTRAINT(0x013c, 2),  CPU_CLK_UNHALTED.REF */
        INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */
        INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */
        INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
@@ -68,7 +64,7 @@ static struct event_constraint intel_nehalem_event_constraints[] __read_mostly =
 {
        FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
        FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
-        /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
+        FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
        INTEL_EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */
        INTEL_EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */
        INTEL_EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */
@@ -90,7 +86,7 @@ static struct event_constraint intel_westmere_event_constraints[] __read_mostly
 {
        FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
        FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
-        /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
+        FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
        INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */
        INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */
        INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */
@@ -102,7 +98,7 @@ 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(0x013c, 2), CPU_CLK_UNHALTED.REF */
+        FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
        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 */
@@ -125,7 +121,7 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly =
 {
        FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
        FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
-        /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
+        FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
        EVENT_CONSTRAINT_END
 };
@@ -1169,7 +1165,7 @@ again:
                 */
                c = &unconstrained;
        } else if (intel_try_alt_er(event, orig_idx)) {
-                raw_spin_unlock(&era->lock);
+                raw_spin_unlock_irqrestore(&era->lock, flags);
                goto again;
        }
        raw_spin_unlock_irqrestore(&era->lock, flags);
@@ -1519,7 +1515,7 @@ static __initconst const struct x86_pmu intel_pmu = {
        .guest_get_msrs         = intel_guest_get_msrs,
 };
-static void intel_clovertown_quirks(void)
+static __init void intel_clovertown_quirk(void)
 {
        /*
         * PEBS is unreliable due to:
@@ -1545,12 +1541,60 @@ static void intel_clovertown_quirks(void)
        x86_pmu.pebs_constraints = NULL;
 }
+static __init void intel_sandybridge_quirk(void)
+{
+        printk(KERN_WARNING "PEBS disabled due to CPU errata.\n");
+        x86_pmu.pebs = 0;
+        x86_pmu.pebs_constraints = NULL;
+}
+static const struct { int id; char *name; } intel_arch_events_map[] __initconst = {
+        { PERF_COUNT_HW_CPU_CYCLES, "cpu cycles" },
+        { PERF_COUNT_HW_INSTRUCTIONS, "instructions" },
+        { PERF_COUNT_HW_BUS_CYCLES, "bus cycles" },
+        { PERF_COUNT_HW_CACHE_REFERENCES, "cache references" },
+        { PERF_COUNT_HW_CACHE_MISSES, "cache misses" },
+        { PERF_COUNT_HW_BRANCH_INSTRUCTIONS, "branch instructions" },
+        { PERF_COUNT_HW_BRANCH_MISSES, "branch misses" },
+};
+static __init void intel_arch_events_quirk(void)
+{
+        int bit;
+        /* disable event that reported as not presend by cpuid */
+        for_each_set_bit(bit, x86_pmu.events_mask, ARRAY_SIZE(intel_arch_events_map)) {
+                intel_perfmon_event_map[intel_arch_events_map[bit].id] = 0;
+                printk(KERN_WARNING "CPUID marked event: \'%s\' unavailable\n",
+                                intel_arch_events_map[bit].name);
+        }
+}
+static __init void intel_nehalem_quirk(void)
+{
+        union cpuid10_ebx ebx;
+        ebx.full = x86_pmu.events_maskl;
+        if (ebx.split.no_branch_misses_retired) {
+                /*
+                 * Erratum AAJ80 detected, we work it around by using
+                 * the BR_MISP_EXEC.ANY event. This will over-count
+                 * branch-misses, but it's still much better than the
+                 * architectural event which is often completely bogus:
+                 */
+                intel_perfmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x7f89;
+                ebx.split.no_branch_misses_retired = 0;
+                x86_pmu.events_maskl = ebx.full;
+                printk(KERN_INFO "CPU erratum AAJ80 worked around\n");
+        }
+}
 __init int intel_pmu_init(void)
 {
        union cpuid10_edx edx;
        union cpuid10_eax eax;
+        union cpuid10_ebx ebx;
        unsigned int unused;
-        unsigned int ebx;
        int version;
        if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
@@ -1567,8 +1611,8 @@ __init int intel_pmu_init(void)
         * Check whether the Architectural PerfMon supports
         * Branch Misses Retired hw_event or not.
         */
-        cpuid(10, &eax.full, &ebx, &unused, &edx.full);
+        cpuid(10, &eax.full, &ebx.full, &unused, &edx.full);
-        if (eax.split.mask_length <= ARCH_PERFMON_BRANCH_MISSES_RETIRED)
+        if (eax.split.mask_length < ARCH_PERFMON_EVENTS_COUNT)
                return -ENODEV;
        version = eax.split.version_id;
@@ -1582,6 +1626,9 @@ __init int intel_pmu_init(void)
        x86_pmu.cntval_bits             = eax.split.bit_width;
        x86_pmu.cntval_mask             = (1ULL << eax.split.bit_width) - 1;
+        x86_pmu.events_maskl            = ebx.full;
+        x86_pmu.events_mask_len         = eax.split.mask_length;
        /*
         * Quirk: v2 perfmon does not report fixed-purpose events, so
         * assume at least 3 events:
@@ -1601,6 +1648,8 @@ __init int intel_pmu_init(void)
        intel_ds_init();
+        x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */
        /*
         * Install the hw-cache-events table:
         */
@@ -1610,7 +1659,7 @@ __init int intel_pmu_init(void)
                break;
        case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
-                x86_pmu.quirks = intel_clovertown_quirks;
+                x86_add_quirk(intel_clovertown_quirk);
        case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
        case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
        case 29: /* six-core 45 nm xeon "Dunnington" */
@@ -1644,17 +1693,8 @@ __init int intel_pmu_init(void)
                /* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
                intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
-                if (ebx & 0x40) {
+                x86_add_quirk(intel_nehalem_quirk);
-                        /*
-                         * Erratum AAJ80 detected, we work it around by using
-                         * the BR_MISP_EXEC.ANY event. This will over-count
-                         * branch-misses, but it's still much better than the
-                         * architectural event which is often completely bogus:
-                         */
-                        intel_perfmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x7f89;
-                        pr_cont("erratum AAJ80 worked around, ");
-                }
                pr_cont("Nehalem events, ");
                break;
@@ -1694,6 +1734,7 @@ __init int intel_pmu_init(void)
                break;
        case 42: /* SandyBridge */
+                x86_add_quirk(intel_sandybridge_quirk);
        case 45: /* SandyBridge, "Romely-EP" */
                memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
                       sizeof(hw_cache_event_ids));
@@ -1730,5 +1771,6 @@ __init int intel_pmu_init(void)
                        break;
                }
        }
        return 0;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index c0d238f49db8..73da6b64f5b7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -493,6 +493,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
        unsigned long from = cpuc->lbr_entries[0].from;
        unsigned long old_to, to = cpuc->lbr_entries[0].to;
        unsigned long ip = regs->ip;
+        int is_64bit = 0;
        /*
         * We don't need to fixup if the PEBS assist is fault like
@@ -544,7 +545,10 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
                } else
                        kaddr = (void *)to;
-                kernel_insn_init(&insn, kaddr);
+#ifdef CONFIG_X86_64
+                is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
+#endif
+                insn_init(&insn, kaddr, is_64bit);
                insn_get_length(&insn);
                to += insn.length;
        } while (to < ip);
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 492bf1358a7c..ef484d9d0a25 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1268,7 +1268,7 @@ reserve:
        }
 done:
-        return num ? -ENOSPC : 0;
+        return num ? -EINVAL : 0;
 }
 static __initconst const struct x86_pmu p4_pmu = {
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 3b97a80ce329..c99f9ed013d5 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -116,16 +116,16 @@ void show_registers(struct pt_regs *regs)
                for (i = 0; i < code_len; i++, ip++) {
                        if (ip < (u8 *)PAGE_OFFSET ||
                                        probe_kernel_address(ip, c)) {
-                                printk(" Bad EIP value.");
+                                printk(KERN_CONT " Bad EIP value.");
                                break;
                        }
                        if (ip == (u8 *)regs->ip)
-                                printk("<%02x> ", c);
+                                printk(KERN_CONT "<%02x> ", c);
                        else
-                                printk("%02x ", c);
+                                printk(KERN_CONT "%02x ", c);
                }
        }
-        printk("\n");
+        printk(KERN_CONT "\n");
 }
 int is_valid_bugaddr(unsigned long ip)
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 19853ad8afc5..6d728d9284bd 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -284,16 +284,16 @@ void show_registers(struct pt_regs *regs)
                for (i = 0; i < code_len; i++, ip++) {
                        if (ip < (u8 *)PAGE_OFFSET ||
                                        probe_kernel_address(ip, c)) {
-                                printk(" Bad RIP value.");
+                                printk(KERN_CONT " Bad RIP value.");
                                break;
                        }
                        if (ip == (u8 *)regs->ip)
-                                printk("<%02x> ", c);
+                                printk(KERN_CONT "<%02x> ", c);
                        else
-                                printk("%02x ", c);
+                                printk(KERN_CONT "%02x ", c);
                }
        }
-        printk("\n");
+        printk(KERN_CONT "\n");
 }
 int is_valid_bugaddr(unsigned long ip)
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 303a0e48f076..8071e2f3d6eb 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -738,35 +738,17 @@ core_initcall(e820_mark_nvs_memory);
 /*
 * pre allocated 4k and reserved it in memblock and e820_saved
 */
-u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
+u64 __init early_reserve_e820(u64 size, u64 align)
 {
-        u64 size = 0;
        u64 addr;
-        u64 start;
-        for (start = startt; ; start += size) {
+        addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
-                start = memblock_x86_find_in_range_size(start, &size, align);
+        if (addr) {
-                if (start == MEMBLOCK_ERROR)
+                e820_update_range_saved(addr, size, E820_RAM, E820_RESERVED);
-                        return 0;
+                printk(KERN_INFO "update e820_saved for early_reserve_e820\n");
-                if (size >= sizet)
+                update_e820_saved();
-                        break;
        }
-#ifdef CONFIG_X86_32
-        if (start >= MAXMEM)
-                return 0;
-        if (start + size > MAXMEM)
-                size = MAXMEM - start;
-#endif
-        addr = round_down(start + size - sizet, align);
-        if (addr < start)
-                return 0;
-        memblock_x86_reserve_range(addr, addr + sizet, "new next");
-        e820_update_range_saved(addr, sizet, E820_RAM, E820_RESERVED);
-        printk(KERN_INFO "update e820_saved for early_reserve_e820\n");
-        update_e820_saved();
        return addr;
 }
@@ -1090,7 +1072,7 @@ void __init memblock_x86_fill(void)
         * We are safe to enable resizing, beause memblock_x86_fill()
         * is rather later for x86
         */
-        memblock_can_resize = 1;
+        memblock_allow_resize();
        for (i = 0; i < e820.nr_map; i++) {
                struct e820entry *ei = &e820.map[i];
@@ -1105,22 +1087,36 @@ void __init memblock_x86_fill(void)
                memblock_add(ei->addr, ei->size);
        }
-        memblock_analyze();
        memblock_dump_all();
 }
 void __init memblock_find_dma_reserve(void)
 {
 #ifdef CONFIG_X86_64
-        u64 free_size_pfn;
+        u64 nr_pages = 0, nr_free_pages = 0;
-        u64 mem_size_pfn;
+        unsigned long start_pfn, end_pfn;
+        phys_addr_t start, end;
+        int i;
+        u64 u;
        /*
         * need to find out used area below MAX_DMA_PFN
         * need to use memblock to get free size in [0, MAX_DMA_PFN]
         * at first, and assume boot_mem will not take below MAX_DMA_PFN
         */
-        mem_size_pfn = memblock_x86_memory_in_range(0, MAX_DMA_PFN << PAGE_SHIFT) >> PAGE_SHIFT;
+        for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
-        free_size_pfn = memblock_x86_free_memory_in_range(0, MAX_DMA_PFN << PAGE_SHIFT) >> PAGE_SHIFT;
+                start_pfn = min_t(unsigned long, start_pfn, MAX_DMA_PFN);
-        set_dma_reserve(mem_size_pfn - free_size_pfn);
+                end_pfn = min_t(unsigned long, end_pfn, MAX_DMA_PFN);
+                nr_pages += end_pfn - start_pfn;
+        }
+        for_each_free_mem_range(u, MAX_NUMNODES, &start, &end, NULL) {
+                start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN);
+                end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN);
+                if (start_pfn < end_pfn)
+                        nr_free_pages += end_pfn - start_pfn;
+        }
+        set_dma_reserve(nr_pages - nr_free_pages);
 #endif
 }
diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c
index af0699ba48cf..48d9d4ea1020 100644
--- a/arch/x86/kernel/head.c
+++ b/arch/x86/kernel/head.c
@@ -52,5 +52,5 @@ void __init reserve_ebda_region(void)
                lowmem = 0x9f000;
        /* reserve all memory between lowmem and the 1MB mark */
-        memblock_x86_reserve_range(lowmem, 0x100000, "* BIOS reserved");
+        memblock_reserve(lowmem, 0x100000 - lowmem);
 }
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 3bb08509a7a1..51ff18616d50 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -31,9 +31,8 @@ static void __init i386_default_early_setup(void)
 void __init i386_start_kernel(void)
 {
-        memblock_init();
+        memblock_reserve(__pa_symbol(&_text),
+                         __pa_symbol(&__bss_stop) - __pa_symbol(&_text));
-        memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 #ifdef CONFIG_BLK_DEV_INITRD
        /* Reserve INITRD */
@@ -42,7 +41,7 @@ void __init i386_start_kernel(void)
                u64 ramdisk_image = boot_params.hdr.ramdisk_image;
                u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
                u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
-                memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK");
+                memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
        }
 #endif
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 5655c2272adb..3a3b779f41d3 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -98,9 +98,8 @@ void __init x86_64_start_reservations(char *real_mode_data)
 {
        copy_bootdata(__va(real_mode_data));
-        memblock_init();
+        memblock_reserve(__pa_symbol(&_text),
+                         __pa_symbol(&__bss_stop) - __pa_symbol(&_text));
-        memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 #ifdef CONFIG_BLK_DEV_INITRD
        /* Reserve INITRD */
@@ -109,7 +108,7 @@ void __init x86_64_start_reservations(char *real_mode_data)
                unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
                unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
                unsigned long ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
-                memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK");
+                memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
        }
 #endif
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index b946a9eac7d9..1bb0bf4d92cd 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1049,6 +1049,14 @@ int hpet_rtc_timer_init(void)
 }
 EXPORT_SYMBOL_GPL(hpet_rtc_timer_init);
+static void hpet_disable_rtc_channel(void)
+{
+        unsigned long cfg;
+        cfg = hpet_readl(HPET_T1_CFG);
+        cfg &= ~HPET_TN_ENABLE;
+        hpet_writel(cfg, HPET_T1_CFG);
+}
 /*
 * The functions below are called from rtc driver.
 * Return 0 if HPET is not being used.
@@ -1060,6 +1068,9 @@ int hpet_mask_rtc_irq_bit(unsigned long bit_mask)
                return 0;
        hpet_rtc_flags &= ~bit_mask;
+        if (unlikely(!hpet_rtc_flags))
+                hpet_disable_rtc_channel();
        return 1;
 }
 EXPORT_SYMBOL_GPL(hpet_mask_rtc_irq_bit);
@@ -1125,15 +1136,11 @@ EXPORT_SYMBOL_GPL(hpet_rtc_dropped_irq);
 static void hpet_rtc_timer_reinit(void)
 {
-        unsigned int cfg, delta;
+        unsigned int delta;
        int lost_ints = -1;
-        if (unlikely(!hpet_rtc_flags)) {
+        if (unlikely(!hpet_rtc_flags))
-                cfg = hpet_readl(HPET_T1_CFG);
+                hpet_disable_rtc_channel();
-                cfg &= ~HPET_TN_ENABLE;
-                hpet_writel(cfg, HPET_T1_CFG);
-                return;
-        }
        if (!(hpet_rtc_flags & RTC_PIE) || hpet_pie_limit)
                delta = hpet_default_delta;
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index ef54ed4e307d..7943e0c21bde 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -186,8 +186,8 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
        unsigned vector = ~regs->orig_ax;
        unsigned irq;
-        exit_idle();
        irq_enter();
+        exit_idle();
        irq = __this_cpu_read(vector_irq[vector]);
@@ -214,10 +214,10 @@ void smp_x86_platform_ipi(struct pt_regs *regs)
        ack_APIC_irq();
-        exit_idle();
        irq_enter();
+        exit_idle();
        inc_irq_stat(x86_platform_ipis);
        if (x86_platform_ipi_callback)
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index acf8fbf8fbda..69bca468c47a 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -38,6 +38,9 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
        u64 curbase = (u64)task_stack_page(current);
+        if (user_mode_vm(regs))
+                return;
        WARN_ONCE(regs->sp >= curbase &&
                  regs->sp <= curbase + THREAD_SIZE &&
                  regs->sp <  curbase + sizeof(struct thread_info) +
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index ea9d5f2f13ef..2889b3d43882 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -50,7 +50,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
        put_online_cpus();
 }
-void arch_jump_label_transform_static(struct jump_entry *entry,
+__init_or_module void arch_jump_label_transform_static(struct jump_entry *entry,
                                      enum jump_label_type type)
 {
        __jump_label_transform(entry, type, text_poke_early);
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index f2d2a664e797..9d46f5e43b51 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -256,7 +256,7 @@ static int __init microcode_dev_init(void)
        return 0;
 }
-static void microcode_dev_exit(void)
+static void __exit microcode_dev_exit(void)
 {
        misc_deregister(&microcode_dev);
 }
@@ -519,10 +519,8 @@ static int __init microcode_init(void)
        microcode_pdev = platform_device_register_simple("microcode", -1,
                                                         NULL, 0);
-        if (IS_ERR(microcode_pdev)) {
+        if (IS_ERR(microcode_pdev))
-                microcode_dev_exit();
                return PTR_ERR(microcode_pdev);
-        }
        get_online_cpus();
        mutex_lock(&microcode_mutex);
@@ -532,14 +530,12 @@ static int __init microcode_init(void)
        mutex_unlock(&microcode_mutex);
        put_online_cpus();
-        if (error) {
+        if (error)
-                platform_device_unregister(microcode_pdev);
+                goto out_pdev;
-                return error;
-        }
        error = microcode_dev_init();
        if (error)
-                return error;
+                goto out_sysdev_driver;
        register_syscore_ops(&mc_syscore_ops);
        register_hotcpu_notifier(&mc_cpu_notifier);
@@ -548,6 +544,20 @@ static int __init microcode_init(void)
                " <tigran@aivazian.fsnet.co.uk>, Peter Oruba\n");
        return 0;
+out_sysdev_driver:
+        get_online_cpus();
+        mutex_lock(&microcode_mutex);
+        sysdev_driver_unregister(&cpu_sysdev_class, &mc_sysdev_driver);
+        mutex_unlock(&microcode_mutex);
+        put_online_cpus();
+out_pdev:
+        platform_device_unregister(microcode_pdev);
+        return error;
 }
 module_init(microcode_init);
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 9103b89c145a..ca470e4c92dc 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -95,8 +95,8 @@ static void __init MP_bus_info(struct mpc_bus *m)
        }
 #endif
+        set_bit(m->busid, mp_bus_not_pci);
        if (strncmp(str, BUSTYPE_ISA, sizeof(BUSTYPE_ISA) - 1) == 0) {
-                set_bit(m->busid, mp_bus_not_pci);
 #if defined(CONFIG_EISA) || defined(CONFIG_MCA)
                mp_bus_id_to_type[m->busid] = MP_BUS_ISA;
 #endif
@@ -564,9 +564,7 @@ void __init default_get_smp_config(unsigned int early)
 static void __init smp_reserve_memory(struct mpf_intel *mpf)
 {
-        unsigned long size = get_mpc_size(mpf->physptr);
+        memblock_reserve(mpf->physptr, get_mpc_size(mpf->physptr));
-        memblock_x86_reserve_range(mpf->physptr, mpf->physptr+size, "* MP-table mpc");
 }
 static int __init smp_scan_config(unsigned long base, unsigned long length)
@@ -595,7 +593,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
                               mpf, (u64)virt_to_phys(mpf));
                        mem = virt_to_phys(mpf);
-                        memblock_x86_reserve_range(mem, mem + sizeof(*mpf), "* MP-table mpf");
+                        memblock_reserve(mem, sizeof(*mpf));
                        if (mpf->physptr)
                                smp_reserve_memory(mpf);
@@ -836,10 +834,8 @@ early_param("alloc_mptable", parse_alloc_mptable_opt);
 void __init early_reserve_e820_mpc_new(void)
 {
-        if (enable_update_mptable && alloc_mptable) {
+        if (enable_update_mptable && alloc_mptable)
-                u64 startt = 0;
+                mpc_new_phys = early_reserve_e820(mpc_new_length, 4);
-                mpc_new_phys = early_reserve_e820(startt, mpc_new_length, 4);
-        }
 }
 static int __init update_mp_table(void)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 795b79f984c2..485204f58cda 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -99,7 +99,8 @@ void cpu_idle(void)
        /* endless idle loop with no priority at all */
        while (1) {
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
+                rcu_idle_enter();
                while (!need_resched()) {
                        check_pgt_cache();
@@ -116,7 +117,8 @@ void cpu_idle(void)
                                pm_idle();
                        start_critical_timings();
                }
-                tick_nohz_restart_sched_tick();
+                rcu_idle_exit();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
                schedule();
                preempt_disable();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 3bd7e6eebf31..64e926c89a6f 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -122,7 +122,7 @@ void cpu_idle(void)
        /* endless idle loop with no priority at all */
        while (1) {
-                tick_nohz_stop_sched_tick(1);
+                tick_nohz_idle_enter();
                while (!need_resched()) {
                        rmb();
@@ -139,8 +139,14 @@ void cpu_idle(void)
                        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())
                                pm_idle();
+                        rcu_idle_exit();
                        start_critical_timings();
                        /* In many cases the interrupt that ended idle
@@ -149,7 +155,7 @@ void cpu_idle(void)
                        __exit_idle();
                }
-                tick_nohz_restart_sched_tick();
+                tick_nohz_idle_exit();
                preempt_enable_no_resched();
                schedule();
                preempt_disable();
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index b78643d0f9a5..03920a15a632 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -553,4 +553,17 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC,
                        quirk_amd_nb_node);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_LINK,
                        quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F0,
+                        quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F1,
+                        quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F2,
+                        quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3,
+                        quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4,
+                        quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F5,
+                        quirk_amd_nb_node);
 #endif
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index e334be1182b9..37a458b521a6 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -124,7 +124,7 @@ __setup("reboot=", reboot_setup);
 */
 /*
- * Some machines require the "reboot=b"  commandline option,
+ * Some machines require the "reboot=b" or "reboot=k"  commandline options,
 * this quirk makes that automatic.
 */
 static int __init set_bios_reboot(const struct dmi_system_id *d)
@@ -136,6 +136,15 @@ static int __init set_bios_reboot(const struct dmi_system_id *d)
        return 0;
 }
+static int __init set_kbd_reboot(const struct dmi_system_id *d)
+{
+        if (reboot_type != BOOT_KBD) {
+                reboot_type = BOOT_KBD;
+                printk(KERN_INFO "%s series board detected. Selecting KBD-method for reboot.\n", d->ident);
+        }
+        return 0;
+}
 static struct dmi_system_id __initdata reboot_dmi_table[] = {
        {       /* Handle problems with rebooting on Dell E520's */
                .callback = set_bios_reboot,
@@ -295,7 +304,7 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
                },
        },
        { /* Handle reboot issue on Acer Aspire one */
-                .callback = set_bios_reboot,
+                .callback = set_kbd_reboot,
                .ident = "Acer Aspire One A110",
                .matches = {
                        DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
@@ -443,6 +452,14 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = {
                        DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6420"),
                },
        },
+        {       /* Handle problems with rebooting on the OptiPlex 990. */
+                .callback = set_pci_reboot,
+                .ident = "Dell OptiPlex 990",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"),
+                },
+        },
        { }
 };
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 348ce016a835..af6db6ec5b2a 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -12,6 +12,7 @@
 #include <asm/vsyscall.h>
 #include <asm/x86_init.h>
 #include <asm/time.h>
+#include <asm/mrst.h>
 #ifdef CONFIG_X86_32
 /*
@@ -242,6 +243,10 @@ static __init int add_rtc_cmos(void)
        if (of_have_populated_dt())
                return 0;
+        /* Intel MID platforms don't have ioport rtc */
+        if (mrst_identify_cpu())
+                return -ENODEV;
        platform_device_register(&rtc_device);
        dev_info(&rtc_device.dev,
                 "registered platform RTC device (no PNP device found)\n");
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index cf0ef986cb6d..d05444ac2aea 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -306,7 +306,8 @@ static void __init cleanup_highmap(void)
 static void __init reserve_brk(void)
 {
        if (_brk_end > _brk_start)
-                memblock_x86_reserve_range(__pa(_brk_start), __pa(_brk_end), "BRK");
+                memblock_reserve(__pa(_brk_start),
+                                 __pa(_brk_end) - __pa(_brk_start));
        /* Mark brk area as locked down and no longer taking any
           new allocations */
@@ -331,13 +332,13 @@ static void __init relocate_initrd(void)
        ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size,
                                         PAGE_SIZE);
-        if (ramdisk_here == MEMBLOCK_ERROR)
+        if (!ramdisk_here)
                panic("Cannot find place for new RAMDISK of size %lld\n",
                         ramdisk_size);
        /* Note: this includes all the lowmem currently occupied by
           the initrd, we rely on that fact to keep the data intact. */
-        memblock_x86_reserve_range(ramdisk_here, ramdisk_here + area_size, "NEW RAMDISK");
+        memblock_reserve(ramdisk_here, area_size);
        initrd_start = ramdisk_here + PAGE_OFFSET;
        initrd_end   = initrd_start + ramdisk_size;
        printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
@@ -393,7 +394,7 @@ static void __init reserve_initrd(void)
        initrd_start = 0;
        if (ramdisk_size >= (end_of_lowmem>>1)) {
-                memblock_x86_free_range(ramdisk_image, ramdisk_end);
+                memblock_free(ramdisk_image, ramdisk_end - ramdisk_image);
                printk(KERN_ERR "initrd too large to handle, "
                       "disabling initrd\n");
                return;
@@ -416,7 +417,7 @@ static void __init reserve_initrd(void)
        relocate_initrd();
-        memblock_x86_free_range(ramdisk_image, ramdisk_end);
+        memblock_free(ramdisk_image, ramdisk_end - ramdisk_image);
 }
 #else
 static void __init reserve_initrd(void)
@@ -490,15 +491,13 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 {
        struct setup_data *data;
        u64 pa_data;
-        char buf[32];
        if (boot_params.hdr.version < 0x0209)
                return;
        pa_data = boot_params.hdr.setup_data;
        while (pa_data) {
                data = early_memremap(pa_data, sizeof(*data));
-                sprintf(buf, "setup data %x", data->type);
+                memblock_reserve(pa_data, sizeof(*data) + data->len);
-                memblock_x86_reserve_range(pa_data, pa_data+sizeof(*data)+data->len, buf);
                pa_data = data->next;
                early_iounmap(data, sizeof(*data));
        }
@@ -554,7 +553,7 @@ static void __init reserve_crashkernel(void)
                crash_base = memblock_find_in_range(alignment,
                               CRASH_KERNEL_ADDR_MAX, crash_size, alignment);
-                if (crash_base == MEMBLOCK_ERROR) {
+                if (!crash_base) {
                        pr_info("crashkernel reservation failed - No suitable area found.\n");
                        return;
                }
@@ -568,7 +567,7 @@ static void __init reserve_crashkernel(void)
                        return;
                }
        }
-        memblock_x86_reserve_range(crash_base, crash_base + crash_size, "CRASH KERNEL");
+        memblock_reserve(crash_base, crash_size);
        printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
                        "for crashkernel (System RAM: %ldMB)\n",
@@ -626,7 +625,7 @@ static __init void reserve_ibft_region(void)
        addr = find_ibft_region(&size);
        if (size)
-                memblock_x86_reserve_range(addr, addr + size, "* ibft");
+                memblock_reserve(addr, size);
 }
 static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index a91ae7709b49..a73b61055ad6 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -14,11 +14,11 @@ void __init setup_trampolines(void)
        /* Has to be in very low memory so we can execute real-mode AP code. */
        mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE);
-        if (mem == MEMBLOCK_ERROR)
+        if (!mem)
                panic("Cannot allocate trampoline\n");
        x86_trampoline_base = __va(mem);
-        memblock_x86_reserve_range(mem, mem + size, "TRAMPOLINE");
+        memblock_reserve(mem, size);
        printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n",
               x86_trampoline_base, (unsigned long long)mem, size);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index db483369f10b..2c9cf0fd78f5 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -35,7 +35,7 @@ static int __read_mostly tsc_unstable;
   erroneous rdtsc usage on !cpu_has_tsc processors */
 static int __read_mostly tsc_disabled = -1;
-static int tsc_clocksource_reliable;
+int tsc_clocksource_reliable;
 /*
 * Scheduler clock - returns current time in nanosec units.
 */
@@ -178,11 +178,11 @@ static unsigned long calc_pmtimer_ref(u64 deltatsc, u64 pm1, u64 pm2)
 }
 #define CAL_MS          10
-#define CAL_LATCH       (CLOCK_TICK_RATE / (1000 / CAL_MS))
+#define CAL_LATCH       (PIT_TICK_RATE / (1000 / CAL_MS))
 #define CAL_PIT_LOOPS   1000
 #define CAL2_MS         50
-#define CAL2_LATCH      (CLOCK_TICK_RATE / (1000 / CAL2_MS))
+#define CAL2_LATCH      (PIT_TICK_RATE / (1000 / CAL2_MS))
 #define CAL2_PIT_LOOPS  5000
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 0aa5fed8b9e6..9eba29b46cb7 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -113,7 +113,7 @@ void __cpuinit check_tsc_sync_source(int cpu)
        if (unsynchronized_tsc())
                return;
-        if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
+        if (tsc_clocksource_reliable) {
                if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING)
                        pr_info(
                        "Skipped synchronization checks as TSC is reliable.\n");
@@ -172,7 +172,7 @@ void __cpuinit check_tsc_sync_target(void)
 {
        int cpus = 2;
-        if (unsynchronized_tsc() || boot_cpu_has(X86_FEATURE_TSC_RELIABLE))
+        if (unsynchronized_tsc() || tsc_clocksource_reliable)
                return;
        /*
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 76e3f1cd0369..405f2620392f 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -338,11 +338,15 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
                return HRTIMER_NORESTART;
 }
-static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period)
+static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
 {
+        struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
        struct kvm_timer *pt = &ps->pit_timer;
        s64 interval;
+        if (!irqchip_in_kernel(kvm))
+                return;
        interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ);
        pr_debug("create pit timer, interval is %llu nsec\n", interval);
@@ -394,13 +398,13 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val)
        /* FIXME: enhance mode 4 precision */
        case 4:
                if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)) {
-                        create_pit_timer(ps, val, 0);
+                        create_pit_timer(kvm, val, 0);
                }
                break;
        case 2:
        case 3:
                if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)){
-                        create_pit_timer(ps, val, 1);
+                        create_pit_timer(kvm, val, 1);
                }
                break;
        default:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c38efd7b792e..4c938da2ba00 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -602,7 +602,6 @@ static void update_cpuid(struct kvm_vcpu *vcpu)
 {
        struct kvm_cpuid_entry2 *best;
        struct kvm_lapic *apic = vcpu->arch.apic;
-        u32 timer_mode_mask;
        best = kvm_find_cpuid_entry(vcpu, 1, 0);
        if (!best)
@@ -615,15 +614,12 @@ static void update_cpuid(struct kvm_vcpu *vcpu)
                        best->ecx |= bit(X86_FEATURE_OSXSAVE);
        }
-        if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+        if (apic) {
-                best->function == 0x1) {
+                if (best->ecx & bit(X86_FEATURE_TSC_DEADLINE_TIMER))
-                best->ecx |= bit(X86_FEATURE_TSC_DEADLINE_TIMER);
+                        apic->lapic_timer.timer_mode_mask = 3 << 17;
-                timer_mode_mask = 3 << 17;
+                else
-        } else
+                        apic->lapic_timer.timer_mode_mask = 1 << 17;
-                timer_mode_mask = 1 << 17;
+        }
-        if (apic)
-                apic->lapic_timer.timer_mode_mask = timer_mode_mask;
 }
 int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
@@ -2135,6 +2131,9 @@ int kvm_dev_ioctl_check_extension(long ext)
        case KVM_CAP_TSC_CONTROL:
                r = kvm_has_tsc_control;
                break;
+        case KVM_CAP_TSC_DEADLINE_TIMER:
+                r = boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER);
+                break;
        default:
                r = 0;
                break;
diff --git a/arch/x86/lib/inat.c b/arch/x86/lib/inat.c
index 46fc4ee09fc4..88ad5fbda6e1 100644
--- a/arch/x86/lib/inat.c
+++ b/arch/x86/lib/inat.c
@@ -82,9 +82,16 @@ insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m,
        const insn_attr_t *table;
        if (vex_m > X86_VEX_M_MAX || vex_p > INAT_LSTPFX_MAX)
                return 0;
-        table = inat_avx_tables[vex_m][vex_p];
+        /* At first, this checks the master table */
+        table = inat_avx_tables[vex_m][0];
        if (!table)
                return 0;
+        if (!inat_is_group(table[opcode]) && vex_p) {
+                /* If this is not a group, get attribute directly */
+                table = inat_avx_tables[vex_m][vex_p];
+                if (!table)
+                        return 0;
+        }
        return table[opcode];
 }
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 374562ed6704..5a1f9f3e3fbb 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -202,7 +202,7 @@ void insn_get_opcode(struct insn *insn)
                m = insn_vex_m_bits(insn);
                p = insn_vex_p_bits(insn);
                insn->attr = inat_get_avx_attribute(op, m, p);
-                if (!inat_accept_vex(insn->attr))
+                if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr))
                        insn->attr = 0; /* This instruction is bad */
                goto end;       /* VEX has only 1 byte for opcode */
        }
@@ -249,6 +249,8 @@ void insn_get_modrm(struct insn *insn)
                        pfx = insn_last_prefix(insn);
                        insn->attr = inat_get_group_attribute(mod, pfx,
                                                              insn->attr);
+                        if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
+                                insn->attr = 0; /* This is bad */
                }
        }
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index a793da5e560e..5b83c51c12e0 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -1,5 +1,11 @@
 # x86 Opcode Maps
 #
+# This is (mostly) based on following documentations.
+# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2
+#   (#325383-040US, October 2011)
+# - Intel(R) Advanced Vector Extensions Programming Reference
+#   (#319433-011,JUNE 2011).
+#
 #<Opcode maps>
 # Table: table-name
 # Referrer: escaped-name
@@ -15,10 +21,13 @@
 # EndTable
 #
 # AVX Superscripts
-#  (VEX): this opcode can accept VEX prefix.
+#  (v): this opcode requires VEX prefix.
-#  (oVEX): this opcode requires VEX prefix.
+#  (v1): this opcode only supports 128bit VEX.
-#  (o128): this opcode only supports 128bit VEX.
+#
-#  (o256): this opcode only supports 256bit VEX.
+# Last Prefix Superscripts
+#  - (66): the last prefix is 0x66
+#  - (F3): the last prefix is 0xF3
+#  - (F2): the last prefix is 0xF2
 #
 Table: one byte opcode
@@ -199,8 +208,8 @@ a0: MOV AL,Ob
 a1: MOV rAX,Ov
 a2: MOV Ob,AL
 a3: MOV Ov,rAX
-a4: MOVS/B Xb,Yb
+a4: MOVS/B Yb,Xb
-a5: MOVS/W/D/Q Xv,Yv
+a5: MOVS/W/D/Q Yv,Xv
 a6: CMPS/B Xb,Yb
 a7: CMPS/W/D Xv,Yv
 a8: TEST AL,Ib
@@ -233,8 +242,8 @@ c0: Grp2 Eb,Ib (1A)
 c1: Grp2 Ev,Ib (1A)
 c2: RETN Iw (f64)
 c3: RETN
-c4: LES Gz,Mp (i64) | 3bytes-VEX (Prefix)
+c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
-c5: LDS Gz,Mp (i64) | 2bytes-VEX (Prefix)
+c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
 c6: Grp11 Eb,Ib (1A)
 c7: Grp11 Ev,Iz (1A)
 c8: ENTER Iw,Ib
@@ -320,14 +329,19 @@ AVXcode: 1
 # 3DNow! uses the last imm byte as opcode extension.
 0f: 3DNow! Pq,Qq,Ib
 # 0x0f 0x10-0x1f
-10: movups Vps,Wps (VEX) | movss Vss,Wss (F3),(VEX),(o128) | movupd Vpd,Wpd (66),(VEX) | movsd Vsd,Wsd (F2),(VEX),(o128)
+# NOTE: According to Intel SDM opcode map, vmovups and vmovupd has no operands
-11: movups Wps,Vps (VEX) | movss Wss,Vss (F3),(VEX),(o128) | movupd Wpd,Vpd (66),(VEX) | movsd Wsd,Vsd (F2),(VEX),(o128)
+# but it actually has operands. And also, vmovss and vmovsd only accept 128bit.
-12: movlps Vq,Mq (VEX),(o128) | movlpd Vq,Mq (66),(VEX),(o128) | movhlps Vq,Uq (VEX),(o128) | movddup Vq,Wq (F2),(VEX) | movsldup Vq,Wq (F3),(VEX)
+# MOVSS/MOVSD has too many forms(3) on SDM. This map just shows a typical form.
-13: mpvlps Mq,Vq (VEX),(o128) | movlpd Mq,Vq (66),(VEX),(o128)
+# Many AVX instructions lack v1 superscript, according to Intel AVX-Prgramming
-14: unpcklps Vps,Wq (VEX) | unpcklpd Vpd,Wq (66),(VEX)
+# Reference A.1
-15: unpckhps Vps,Wq (VEX) | unpckhpd Vpd,Wq (66),(VEX)
+10: vmovups Vps,Wps | vmovupd Vpd,Wpd (66) | vmovss Vx,Hx,Wss (F3),(v1) | vmovsd Vx,Hx,Wsd (F2),(v1)
-16: movhps Vq,Mq (VEX),(o128) | movhpd Vq,Mq (66),(VEX),(o128) | movlsps Vq,Uq (VEX),(o128) | movshdup Vq,Wq (F3),(VEX)
+11: vmovups Wps,Vps | vmovupd Wpd,Vpd (66) | vmovss Wss,Hx,Vss (F3),(v1) | vmovsd Wsd,Hx,Vsd (F2),(v1)
-17: movhps Mq,Vq (VEX),(o128) | movhpd Mq,Vq (66),(VEX),(o128)
+12: vmovlps Vq,Hq,Mq (v1) | vmovhlps Vq,Hq,Uq (v1) | vmovlpd Vq,Hq,Mq (66),(v1) | vmovsldup Vx,Wx (F3) | vmovddup Vx,Wx (F2)
+13: vmovlps Mq,Vq (v1) | vmovlpd Mq,Vq (66),(v1)
+14: vunpcklps Vx,Hx,Wx | vunpcklpd Vx,Hx,Wx (66)
+15: vunpckhps Vx,Hx,Wx | vunpckhpd Vx,Hx,Wx (66)
+16: vmovhps Vdq,Hq,Mq (v1) | vmovlhps Vdq,Hq,Uq (v1) | vmovhpd Vdq,Hq,Mq (66),(v1) | vmovshdup Vx,Wx (F3)
+17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1)
 18: Grp16 (1A)
 19:
 1a:
@@ -345,14 +359,14 @@ AVXcode: 1
 25:
 26:
 27:
-28: movaps Vps,Wps (VEX) | movapd Vpd,Wpd (66),(VEX)
+28: vmovaps Vps,Wps | vmovapd Vpd,Wpd (66)
-29: movaps Wps,Vps (VEX) | movapd Wpd,Vpd (66),(VEX)
+29: vmovaps Wps,Vps | vmovapd Wpd,Vpd (66)
-2a: cvtpi2ps Vps,Qpi | cvtsi2ss Vss,Ed/q (F3),(VEX),(o128) | cvtpi2pd Vpd,Qpi (66) | cvtsi2sd Vsd,Ed/q (F2),(VEX),(o128)
+2a: cvtpi2ps Vps,Qpi | cvtpi2pd Vpd,Qpi (66) | vcvtsi2ss Vss,Hss,Ey (F3),(v1) | vcvtsi2sd Vsd,Hsd,Ey (F2),(v1)
-2b: movntps Mps,Vps (VEX) | movntpd Mpd,Vpd (66),(VEX)
+2b: vmovntps Mps,Vps | vmovntpd Mpd,Vpd (66)
-2c: cvttps2pi Ppi,Wps | cvttss2si  Gd/q,Wss (F3),(VEX),(o128) | cvttpd2pi Ppi,Wpd (66) | cvttsd2si Gd/q,Wsd (F2),(VEX),(o128)
+2c: cvttps2pi Ppi,Wps | cvttpd2pi Ppi,Wpd (66) | vcvttss2si Gy,Wss (F3),(v1) | vcvttsd2si Gy,Wsd (F2),(v1)
-2d: cvtps2pi Ppi,Wps | cvtss2si Gd/q,Wss (F3),(VEX),(o128) | cvtpd2pi Qpi,Wpd (66) | cvtsd2si Gd/q,Wsd (F2),(VEX),(o128)
+2d: cvtps2pi Ppi,Wps | cvtpd2pi Qpi,Wpd (66) | vcvtss2si Gy,Wss (F3),(v1) | vcvtsd2si Gy,Wsd (F2),(v1)
-2e: ucomiss Vss,Wss (VEX),(o128) | ucomisd  Vsd,Wsd (66),(VEX),(o128)
+2e: vucomiss Vss,Wss (v1) | vucomisd  Vsd,Wsd (66),(v1)
-2f: comiss Vss,Wss (VEX),(o128) | comisd  Vsd,Wsd (66),(VEX),(o128)
+2f: vcomiss Vss,Wss (v1) | vcomisd  Vsd,Wsd (66),(v1)
 # 0x0f 0x30-0x3f
 30: WRMSR
 31: RDTSC
@@ -388,65 +402,66 @@ AVXcode: 1
 4e: CMOVLE/NG Gv,Ev
 4f: CMOVNLE/G Gv,Ev
 # 0x0f 0x50-0x5f
-50: movmskps Gd/q,Ups (VEX) | movmskpd Gd/q,Upd (66),(VEX)
+50: vmovmskps Gy,Ups | vmovmskpd Gy,Upd (66)
-51: sqrtps Vps,Wps (VEX) | sqrtss Vss,Wss (F3),(VEX),(o128) | sqrtpd Vpd,Wpd (66),(VEX) | sqrtsd Vsd,Wsd (F2),(VEX),(o128)
+51: vsqrtps Vps,Wps | vsqrtpd Vpd,Wpd (66) | vsqrtss Vss,Hss,Wss (F3),(v1) | vsqrtsd Vsd,Hsd,Wsd (F2),(v1)
-52: rsqrtps Vps,Wps (VEX) | rsqrtss Vss,Wss (F3),(VEX),(o128)
+52: vrsqrtps Vps,Wps | vrsqrtss Vss,Hss,Wss (F3),(v1)
-53: rcpps Vps,Wps (VEX) | rcpss Vss,Wss (F3),(VEX),(o128)
+53: vrcpps Vps,Wps | vrcpss Vss,Hss,Wss (F3),(v1)
-54: andps Vps,Wps (VEX) | andpd Vpd,Wpd (66),(VEX)
+54: vandps Vps,Hps,Wps | vandpd Vpd,Hpd,Wpd (66)
-55: andnps Vps,Wps (VEX) | andnpd Vpd,Wpd (66),(VEX)
+55: vandnps Vps,Hps,Wps | vandnpd Vpd,Hpd,Wpd (66)
-56: orps Vps,Wps (VEX) | orpd Vpd,Wpd (66),(VEX)
+56: vorps Vps,Hps,Wps | vorpd Vpd,Hpd,Wpd (66)
-57: xorps Vps,Wps (VEX) | xorpd Vpd,Wpd (66),(VEX)
+57: vxorps Vps,Hps,Wps | vxorpd Vpd,Hpd,Wpd (66)
-58: addps Vps,Wps (VEX) | addss Vss,Wss (F3),(VEX),(o128) | addpd Vpd,Wpd (66),(VEX) | addsd Vsd,Wsd (F2),(VEX),(o128)
+58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
-59: mulps Vps,Wps (VEX) | mulss Vss,Wss (F3),(VEX),(o128) | mulpd Vpd,Wpd (66),(VEX) | mulsd Vsd,Wsd (F2),(VEX),(o128)
+59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
-5a: cvtps2pd Vpd,Wps (VEX) | cvtss2sd Vsd,Wss (F3),(VEX),(o128) | cvtpd2ps Vps,Wpd (66),(VEX) | cvtsd2ss Vsd,Wsd (F2),(VEX),(o128)
+5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
-5b: cvtdq2ps Vps,Wdq (VEX) | cvtps2dq Vdq,Wps (66),(VEX) | cvttps2dq Vdq,Wps (F3),(VEX)
+5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
-5c: subps Vps,Wps (VEX) | subss Vss,Wss (F3),(VEX),(o128) | subpd Vpd,Wpd (66),(VEX) | subsd Vsd,Wsd (F2),(VEX),(o128)
+5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
-5d: minps Vps,Wps (VEX) | minss Vss,Wss (F3),(VEX),(o128) | minpd Vpd,Wpd (66),(VEX) | minsd Vsd,Wsd (F2),(VEX),(o128)
+5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
-5e: divps Vps,Wps (VEX) | divss Vss,Wss (F3),(VEX),(o128) | divpd Vpd,Wpd (66),(VEX) | divsd Vsd,Wsd (F2),(VEX),(o128)
+5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
-5f: maxps Vps,Wps (VEX) | maxss Vss,Wss (F3),(VEX),(o128) | maxpd Vpd,Wpd (66),(VEX) | maxsd Vsd,Wsd (F2),(VEX),(o128)
+5f: vmaxps Vps,Hps,Wps | vmaxpd Vpd,Hpd,Wpd (66) | vmaxss Vss,Hss,Wss (F3),(v1) | vmaxsd Vsd,Hsd,Wsd (F2),(v1)
 # 0x0f 0x60-0x6f
-60: punpcklbw Pq,Qd | punpcklbw Vdq,Wdq (66),(VEX),(o128)
+60: punpcklbw Pq,Qd | vpunpcklbw Vx,Hx,Wx (66),(v1)
-61: punpcklwd Pq,Qd | punpcklwd Vdq,Wdq (66),(VEX),(o128)
+61: punpcklwd Pq,Qd | vpunpcklwd Vx,Hx,Wx (66),(v1)
-62: punpckldq Pq,Qd | punpckldq Vdq,Wdq (66),(VEX),(o128)
+62: punpckldq Pq,Qd | vpunpckldq Vx,Hx,Wx (66),(v1)
-63: packsswb Pq,Qq | packsswb Vdq,Wdq (66),(VEX),(o128)
+63: packsswb Pq,Qq | vpacksswb Vx,Hx,Wx (66),(v1)
-64: pcmpgtb Pq,Qq | pcmpgtb Vdq,Wdq (66),(VEX),(o128)
+64: pcmpgtb Pq,Qq | vpcmpgtb Vx,Hx,Wx (66),(v1)
-65: pcmpgtw Pq,Qq | pcmpgtw Vdq,Wdq (66),(VEX),(o128)
+65: pcmpgtw Pq,Qq | vpcmpgtw Vx,Hx,Wx (66),(v1)
-66: pcmpgtd Pq,Qq | pcmpgtd Vdq,Wdq (66),(VEX),(o128)
+66: pcmpgtd Pq,Qq | vpcmpgtd Vx,Hx,Wx (66),(v1)
-67: packuswb Pq,Qq | packuswb Vdq,Wdq (66),(VEX),(o128)
+67: packuswb Pq,Qq | vpackuswb Vx,Hx,Wx (66),(v1)
-68: punpckhbw Pq,Qd | punpckhbw Vdq,Wdq (66),(VEX),(o128)
+68: punpckhbw Pq,Qd | vpunpckhbw Vx,Hx,Wx (66),(v1)
-69: punpckhwd Pq,Qd | punpckhwd Vdq,Wdq (66),(VEX),(o128)
+69: punpckhwd Pq,Qd | vpunpckhwd Vx,Hx,Wx (66),(v1)
-6a: punpckhdq Pq,Qd | punpckhdq Vdq,Wdq (66),(VEX),(o128)
+6a: punpckhdq Pq,Qd | vpunpckhdq Vx,Hx,Wx (66),(v1)
-6b: packssdw Pq,Qd | packssdw Vdq,Wdq (66),(VEX),(o128)
+6b: packssdw Pq,Qd | vpackssdw Vx,Hx,Wx (66),(v1)
-6c: punpcklqdq Vdq,Wdq (66),(VEX),(o128)
+6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
-6d: punpckhqdq Vdq,Wdq (66),(VEX),(o128)
+6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
-6e: movd/q/ Pd,Ed/q | movd/q Vdq,Ed/q (66),(VEX),(o128)
+6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
-6f: movq Pq,Qq | movdqa Vdq,Wdq (66),(VEX) | movdqu Vdq,Wdq (F3),(VEX)
+6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqu Vx,Wx (F3)
 # 0x0f 0x70-0x7f
-70: pshufw Pq,Qq,Ib | pshufd Vdq,Wdq,Ib (66),(VEX),(o128) | pshufhw Vdq,Wdq,Ib (F3),(VEX),(o128) | pshuflw VdqWdq,Ib (F2),(VEX),(o128)
+70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
 71: Grp12 (1A)
 72: Grp13 (1A)
 73: Grp14 (1A)
-74: pcmpeqb Pq,Qq | pcmpeqb Vdq,Wdq (66),(VEX),(o128)
+74: pcmpeqb Pq,Qq | vpcmpeqb Vx,Hx,Wx (66),(v1)
-75: pcmpeqw Pq,Qq | pcmpeqw Vdq,Wdq (66),(VEX),(o128)
+75: pcmpeqw Pq,Qq | vpcmpeqw Vx,Hx,Wx (66),(v1)
-76: pcmpeqd Pq,Qq | pcmpeqd Vdq,Wdq (66),(VEX),(o128)
+76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
-77: emms/vzeroupper/vzeroall (VEX)
+# Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
-78: VMREAD Ed/q,Gd/q
+77: emms | vzeroupper | vzeroall
-79: VMWRITE Gd/q,Ed/q
+78: VMREAD Ey,Gy
+79: VMWRITE Gy,Ey
 7a:
 7b:
-7c: haddps Vps,Wps (F2),(VEX) | haddpd Vpd,Wpd (66),(VEX)
+7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
-7d: hsubps Vps,Wps (F2),(VEX) | hsubpd Vpd,Wpd (66),(VEX)
+7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
-7e: movd/q Ed/q,Pd | movd/q Ed/q,Vdq (66),(VEX),(o128) | movq Vq,Wq (F3),(VEX),(o128)
+7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
-7f: movq Qq,Pq | movdqa Wdq,Vdq (66),(VEX) | movdqu Wdq,Vdq (F3),(VEX)
+7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3)
 # 0x0f 0x80-0x8f
 80: JO Jz (f64)
 81: JNO Jz (f64)
-82: JB/JNAE/JC Jz (f64)
+82: JB/JC/JNAE Jz (f64)
-83: JNB/JAE/JNC Jz (f64)
+83: JAE/JNB/JNC Jz (f64)
-84: JZ/JE Jz (f64)
+84: JE/JZ Jz (f64)
-85: JNZ/JNE Jz (f64)
+85: JNE/JNZ Jz (f64)
 86: JBE/JNA Jz (f64)
-87: JNBE/JA Jz (f64)
+87: JA/JNBE Jz (f64)
 88: JS Jz (f64)
 89: JNS Jz (f64)
 8a: JP/JPE Jz (f64)
@@ -502,18 +517,18 @@ b8: JMPE | POPCNT Gv,Ev (F3)
 b9: Grp10 (1A)
 ba: Grp8 Ev,Ib (1A)
 bb: BTC Ev,Gv
-bc: BSF Gv,Ev
+bc: BSF Gv,Ev | TZCNT Gv,Ev (F3)
-bd: BSR Gv,Ev
+bd: BSR Gv,Ev | LZCNT Gv,Ev (F3)
 be: MOVSX Gv,Eb
 bf: MOVSX Gv,Ew
 # 0x0f 0xc0-0xcf
 c0: XADD Eb,Gb
 c1: XADD Ev,Gv
-c2: cmpps Vps,Wps,Ib (VEX) | cmpss Vss,Wss,Ib (F3),(VEX),(o128) | cmppd Vpd,Wpd,Ib (66),(VEX) | cmpsd Vsd,Wsd,Ib (F2),(VEX)
+c2: vcmpps Vps,Hps,Wps,Ib | vcmppd Vpd,Hpd,Wpd,Ib (66) | vcmpss Vss,Hss,Wss,Ib (F3),(v1) | vcmpsd Vsd,Hsd,Wsd,Ib (F2),(v1)
-c3: movnti Md/q,Gd/q
+c3: movnti My,Gy
-c4: pinsrw Pq,Rd/q/Mw,Ib | pinsrw Vdq,Rd/q/Mw,Ib (66),(VEX),(o128)
+c4: pinsrw Pq,Ry/Mw,Ib | vpinsrw Vdq,Hdq,Ry/Mw,Ib (66),(v1)
-c5: pextrw Gd,Nq,Ib | pextrw Gd,Udq,Ib (66),(VEX),(o128)
+c5: pextrw Gd,Nq,Ib | vpextrw Gd,Udq,Ib (66),(v1)
-c6: shufps Vps,Wps,Ib (VEX) | shufpd Vpd,Wpd,Ib (66),(VEX)
+c6: vshufps Vps,Hps,Wps,Ib | vshufpd Vpd,Hpd,Wpd,Ib (66)
 c7: Grp9 (1A)
 c8: BSWAP RAX/EAX/R8/R8D
 c9: BSWAP RCX/ECX/R9/R9D
@@ -524,55 +539,55 @@ cd: BSWAP RBP/EBP/R13/R13D
 ce: BSWAP RSI/ESI/R14/R14D
 cf: BSWAP RDI/EDI/R15/R15D
 # 0x0f 0xd0-0xdf
-d0: addsubps Vps,Wps (F2),(VEX) | addsubpd Vpd,Wpd (66),(VEX)
+d0: vaddsubpd Vpd,Hpd,Wpd (66) | vaddsubps Vps,Hps,Wps (F2)
-d1: psrlw Pq,Qq | psrlw Vdq,Wdq (66),(VEX),(o128)
+d1: psrlw Pq,Qq | vpsrlw Vx,Hx,Wx (66),(v1)
-d2: psrld Pq,Qq | psrld Vdq,Wdq (66),(VEX),(o128)
+d2: psrld Pq,Qq | vpsrld Vx,Hx,Wx (66),(v1)
-d3: psrlq Pq,Qq | psrlq Vdq,Wdq (66),(VEX),(o128)
+d3: psrlq Pq,Qq | vpsrlq Vx,Hx,Wx (66),(v1)
-d4: paddq Pq,Qq | paddq Vdq,Wdq (66),(VEX),(o128)
+d4: paddq Pq,Qq | vpaddq Vx,Hx,Wx (66),(v1)
-d5: pmullw Pq,Qq | pmullw Vdq,Wdq (66),(VEX),(o128)
+d5: pmullw Pq,Qq | vpmullw Vx,Hx,Wx (66),(v1)
-d6: movq Wq,Vq (66),(VEX),(o128) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2)
+d6: vmovq Wq,Vq (66),(v1) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2)
-d7: pmovmskb Gd,Nq | pmovmskb Gd,Udq (66),(VEX),(o128)
+d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
-d8: psubusb Pq,Qq | psubusb Vdq,Wdq (66),(VEX),(o128)
+d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
-d9: psubusw Pq,Qq | psubusw Vdq,Wdq (66),(VEX),(o128)
+d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
-da: pminub Pq,Qq | pminub Vdq,Wdq (66),(VEX),(o128)
+da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
-db: pand Pq,Qq | pand Vdq,Wdq (66),(VEX),(o128)
+db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1)
-dc: paddusb Pq,Qq | paddusb Vdq,Wdq (66),(VEX),(o128)
+dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
-dd: paddusw Pq,Qq | paddusw Vdq,Wdq (66),(VEX),(o128)
+dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
-de: pmaxub Pq,Qq | pmaxub Vdq,Wdq (66),(VEX),(o128)
+de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
-df: pandn Pq,Qq | pandn Vdq,Wdq (66),(VEX),(o128)
+df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1)
 # 0x0f 0xe0-0xef
-e0: pavgb Pq,Qq | pavgb Vdq,Wdq (66),(VEX),(o128)
+e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
-e1: psraw Pq,Qq | psraw Vdq,Wdq (66),(VEX),(o128)
+e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
-e2: psrad Pq,Qq | psrad Vdq,Wdq (66),(VEX),(o128)
+e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
-e3: pavgw Pq,Qq | pavgw Vdq,Wdq (66),(VEX),(o128)
+e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
-e4: pmulhuw Pq,Qq | pmulhuw Vdq,Wdq (66),(VEX),(o128)
+e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
-e5: pmulhw Pq,Qq | pmulhw Vdq,Wdq (66),(VEX),(o128)
+e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
-e6: cvtpd2dq Vdq,Wpd (F2),(VEX) | cvttpd2dq Vdq,Wpd (66),(VEX) | cvtdq2pd Vpd,Wdq (F3),(VEX)
+e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2)
-e7: movntq Mq,Pq | movntdq Mdq,Vdq (66),(VEX)
+e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
-e8: psubsb Pq,Qq | psubsb Vdq,Wdq (66),(VEX),(o128)
+e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
-e9: psubsw Pq,Qq | psubsw Vdq,Wdq (66),(VEX),(o128)
+e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
-ea: pminsw Pq,Qq | pminsw Vdq,Wdq (66),(VEX),(o128)
+ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
-eb: por Pq,Qq | por Vdq,Wdq (66),(VEX),(o128)
+eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1)
-ec: paddsb Pq,Qq | paddsb Vdq,Wdq (66),(VEX),(o128)
+ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
-ed: paddsw Pq,Qq | paddsw Vdq,Wdq (66),(VEX),(o128)
+ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
-ee: pmaxsw Pq,Qq | pmaxsw Vdq,Wdq (66),(VEX),(o128)
+ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
-ef: pxor Pq,Qq | pxor Vdq,Wdq (66),(VEX),(o128)
+ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1)
 # 0x0f 0xf0-0xff
-f0: lddqu Vdq,Mdq (F2),(VEX)
+f0: vlddqu Vx,Mx (F2)
-f1: psllw Pq,Qq | psllw Vdq,Wdq (66),(VEX),(o128)
+f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
-f2: pslld Pq,Qq | pslld Vdq,Wdq (66),(VEX),(o128)
+f2: pslld Pq,Qq | vpslld Vx,Hx,Wx (66),(v1)
-f3: psllq Pq,Qq | psllq Vdq,Wdq (66),(VEX),(o128)
+f3: psllq Pq,Qq | vpsllq Vx,Hx,Wx (66),(v1)
-f4: pmuludq Pq,Qq | pmuludq Vdq,Wdq (66),(VEX),(o128)
+f4: pmuludq Pq,Qq | vpmuludq Vx,Hx,Wx (66),(v1)
-f5: pmaddwd Pq,Qq | pmaddwd Vdq,Wdq (66),(VEX),(o128)
+f5: pmaddwd Pq,Qq | vpmaddwd Vx,Hx,Wx (66),(v1)
-f6: psadbw Pq,Qq | psadbw Vdq,Wdq (66),(VEX),(o128)
+f6: psadbw Pq,Qq | vpsadbw Vx,Hx,Wx (66),(v1)
-f7: maskmovq Pq,Nq | maskmovdqu Vdq,Udq (66),(VEX),(o128)
+f7: maskmovq Pq,Nq | vmaskmovdqu Vx,Ux (66),(v1)
-f8: psubb Pq,Qq | psubb Vdq,Wdq (66),(VEX),(o128)
+f8: psubb Pq,Qq | vpsubb Vx,Hx,Wx (66),(v1)
-f9: psubw Pq,Qq | psubw Vdq,Wdq (66),(VEX),(o128)
+f9: psubw Pq,Qq | vpsubw Vx,Hx,Wx (66),(v1)
-fa: psubd Pq,Qq | psubd Vdq,Wdq (66),(VEX),(o128)
+fa: psubd Pq,Qq | vpsubd Vx,Hx,Wx (66),(v1)
-fb: psubq Pq,Qq | psubq Vdq,Wdq (66),(VEX),(o128)
+fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
-fc: paddb Pq,Qq | paddb Vdq,Wdq (66),(VEX),(o128)
+fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
-fd: paddw Pq,Qq | paddw Vdq,Wdq (66),(VEX),(o128)
+fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
-fe: paddd Pq,Qq | paddd Vdq,Wdq (66),(VEX),(o128)
+fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
 ff:
 EndTable
@@ -580,155 +595,193 @@ Table: 3-byte opcode 1 (0x0f 0x38)
 Referrer: 3-byte escape 1
 AVXcode: 2
 # 0x0f 0x38 0x00-0x0f
-00: pshufb Pq,Qq | pshufb Vdq,Wdq (66),(VEX),(o128)
+00: pshufb Pq,Qq | vpshufb Vx,Hx,Wx (66),(v1)
-01: phaddw Pq,Qq | phaddw Vdq,Wdq (66),(VEX),(o128)
+01: phaddw Pq,Qq | vphaddw Vx,Hx,Wx (66),(v1)
-02: phaddd Pq,Qq | phaddd Vdq,Wdq (66),(VEX),(o128)
+02: phaddd Pq,Qq | vphaddd Vx,Hx,Wx (66),(v1)
-03: phaddsw Pq,Qq | phaddsw Vdq,Wdq (66),(VEX),(o128)
+03: phaddsw Pq,Qq | vphaddsw Vx,Hx,Wx (66),(v1)
-04: pmaddubsw Pq,Qq | pmaddubsw Vdq,Wdq (66),(VEX),(o128)
+04: pmaddubsw Pq,Qq | vpmaddubsw Vx,Hx,Wx (66),(v1)
-05: phsubw Pq,Qq | phsubw Vdq,Wdq (66),(VEX),(o128)
+05: phsubw Pq,Qq | vphsubw Vx,Hx,Wx (66),(v1)
-06: phsubd Pq,Qq | phsubd Vdq,Wdq (66),(VEX),(o128)
+06: phsubd Pq,Qq | vphsubd Vx,Hx,Wx (66),(v1)
-07: phsubsw Pq,Qq | phsubsw Vdq,Wdq (66),(VEX),(o128)
+07: phsubsw Pq,Qq | vphsubsw Vx,Hx,Wx (66),(v1)
-08: psignb Pq,Qq | psignb Vdq,Wdq (66),(VEX),(o128)
+08: psignb Pq,Qq | vpsignb Vx,Hx,Wx (66),(v1)
-09: psignw Pq,Qq | psignw Vdq,Wdq (66),(VEX),(o128)
+09: psignw Pq,Qq | vpsignw Vx,Hx,Wx (66),(v1)
-0a: psignd Pq,Qq | psignd Vdq,Wdq (66),(VEX),(o128)
+0a: psignd Pq,Qq | vpsignd Vx,Hx,Wx (66),(v1)
-0b: pmulhrsw Pq,Qq | pmulhrsw Vdq,Wdq (66),(VEX),(o128)
+0b: pmulhrsw Pq,Qq | vpmulhrsw Vx,Hx,Wx (66),(v1)
-0c: Vpermilps /r (66),(oVEX)
+0c: vpermilps Vx,Hx,Wx (66),(v)
-0d: Vpermilpd /r (66),(oVEX)
+0d: vpermilpd Vx,Hx,Wx (66),(v)
-0e: vtestps /r (66),(oVEX)
+0e: vtestps Vx,Wx (66),(v)
-0f: vtestpd /r (66),(oVEX)
+0f: vtestpd Vx,Wx (66),(v)
 # 0x0f 0x38 0x10-0x1f
 10: pblendvb Vdq,Wdq (66)
 11:
 12:
-13:
+13: vcvtph2ps Vx,Wx,Ib (66),(v)
 14: blendvps Vdq,Wdq (66)
 15: blendvpd Vdq,Wdq (66)
-16:
+16: vpermps Vqq,Hqq,Wqq (66),(v)
-17: ptest Vdq,Wdq (66),(VEX)
+17: vptest Vx,Wx (66)
-18: vbroadcastss /r (66),(oVEX)
+18: vbroadcastss Vx,Wd (66),(v)
-19: vbroadcastsd /r (66),(oVEX),(o256)
+19: vbroadcastsd Vqq,Wq (66),(v)
-1a: vbroadcastf128 /r (66),(oVEX),(o256)
+1a: vbroadcastf128 Vqq,Mdq (66),(v)
 1b:
-1c: pabsb Pq,Qq | pabsb Vdq,Wdq (66),(VEX),(o128)
+1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
-1d: pabsw Pq,Qq | pabsw Vdq,Wdq (66),(VEX),(o128)
+1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
-1e: pabsd Pq,Qq | pabsd Vdq,Wdq (66),(VEX),(o128)
+1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
 1f:
 # 0x0f 0x38 0x20-0x2f
-20: pmovsxbw Vdq,Udq/Mq (66),(VEX),(o128)
+20: vpmovsxbw Vx,Ux/Mq (66),(v1)
-21: pmovsxbd Vdq,Udq/Md (66),(VEX),(o128)
+21: vpmovsxbd Vx,Ux/Md (66),(v1)
-22: pmovsxbq Vdq,Udq/Mw (66),(VEX),(o128)
+22: vpmovsxbq Vx,Ux/Mw (66),(v1)
-23: pmovsxwd Vdq,Udq/Mq (66),(VEX),(o128)
+23: vpmovsxwd Vx,Ux/Mq (66),(v1)
-24: pmovsxwq Vdq,Udq/Md (66),(VEX),(o128)
+24: vpmovsxwq Vx,Ux/Md (66),(v1)
-25: pmovsxdq Vdq,Udq/Mq (66),(VEX),(o128)
+25: vpmovsxdq Vx,Ux/Mq (66),(v1)
 26:
 27:
-28: pmuldq Vdq,Wdq (66),(VEX),(o128)
+28: vpmuldq Vx,Hx,Wx (66),(v1)
-29: pcmpeqq Vdq,Wdq (66),(VEX),(o128)
+29: vpcmpeqq Vx,Hx,Wx (66),(v1)
-2a: movntdqa Vdq,Mdq (66),(VEX),(o128)
+2a: vmovntdqa Vx,Mx (66),(v1)
-2b: packusdw Vdq,Wdq (66),(VEX),(o128)
+2b: vpackusdw Vx,Hx,Wx (66),(v1)
-2c: vmaskmovps(ld) /r (66),(oVEX)
+2c: vmaskmovps Vx,Hx,Mx (66),(v)
-2d: vmaskmovpd(ld) /r (66),(oVEX)
+2d: vmaskmovpd Vx,Hx,Mx (66),(v)
-2e: vmaskmovps(st) /r (66),(oVEX)
+2e: vmaskmovps Mx,Hx,Vx (66),(v)
-2f: vmaskmovpd(st) /r (66),(oVEX)
+2f: vmaskmovpd Mx,Hx,Vx (66),(v)
 # 0x0f 0x38 0x30-0x3f
-30: pmovzxbw Vdq,Udq/Mq (66),(VEX),(o128)
+30: vpmovzxbw Vx,Ux/Mq (66),(v1)
-31: pmovzxbd Vdq,Udq/Md (66),(VEX),(o128)
+31: vpmovzxbd Vx,Ux/Md (66),(v1)
-32: pmovzxbq Vdq,Udq/Mw (66),(VEX),(o128)
+32: vpmovzxbq Vx,Ux/Mw (66),(v1)
-33: pmovzxwd Vdq,Udq/Mq (66),(VEX),(o128)
+33: vpmovzxwd Vx,Ux/Mq (66),(v1)
-34: pmovzxwq Vdq,Udq/Md (66),(VEX),(o128)
+34: vpmovzxwq Vx,Ux/Md (66),(v1)
-35: pmovzxdq Vdq,Udq/Mq (66),(VEX),(o128)
+35: vpmovzxdq Vx,Ux/Mq (66),(v1)
-36:
+36: vpermd Vqq,Hqq,Wqq (66),(v)
-37: pcmpgtq Vdq,Wdq (66),(VEX),(o128)
+37: vpcmpgtq Vx,Hx,Wx (66),(v1)
-38: pminsb Vdq,Wdq (66),(VEX),(o128)
+38: vpminsb Vx,Hx,Wx (66),(v1)
-39: pminsd Vdq,Wdq (66),(VEX),(o128)
+39: vpminsd Vx,Hx,Wx (66),(v1)
-3a: pminuw Vdq,Wdq (66),(VEX),(o128)
+3a: vpminuw Vx,Hx,Wx (66),(v1)
-3b: pminud Vdq,Wdq (66),(VEX),(o128)
+3b: vpminud Vx,Hx,Wx (66),(v1)
-3c: pmaxsb Vdq,Wdq (66),(VEX),(o128)
+3c: vpmaxsb Vx,Hx,Wx (66),(v1)
-3d: pmaxsd Vdq,Wdq (66),(VEX),(o128)
+3d: vpmaxsd Vx,Hx,Wx (66),(v1)
-3e: pmaxuw Vdq,Wdq (66),(VEX),(o128)
+3e: vpmaxuw Vx,Hx,Wx (66),(v1)
-3f: pmaxud Vdq,Wdq (66),(VEX),(o128)
+3f: vpmaxud Vx,Hx,Wx (66),(v1)
 # 0x0f 0x38 0x40-0x8f
-40: pmulld Vdq,Wdq (66),(VEX),(o128)
+40: vpmulld Vx,Hx,Wx (66),(v1)
-41: phminposuw Vdq,Wdq (66),(VEX),(o128)
+41: vphminposuw Vdq,Wdq (66),(v1)
-80: INVEPT Gd/q,Mdq (66)
+42:
-81: INVPID Gd/q,Mdq (66)
+43:
+44:
+45: vpsrlvd/q Vx,Hx,Wx (66),(v)
+46: vpsravd Vx,Hx,Wx (66),(v)
+47: vpsllvd/q Vx,Hx,Wx (66),(v)
+# Skip 0x48-0x57
+58: vpbroadcastd Vx,Wx (66),(v)
+59: vpbroadcastq Vx,Wx (66),(v)
+5a: vbroadcasti128 Vqq,Mdq (66),(v)
+# Skip 0x5b-0x77
+78: vpbroadcastb Vx,Wx (66),(v)
+79: vpbroadcastw Vx,Wx (66),(v)
+# Skip 0x7a-0x7f
+80: INVEPT Gy,Mdq (66)
+81: INVPID Gy,Mdq (66)
+82: INVPCID Gy,Mdq (66)
+8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
+8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
 # 0x0f 0x38 0x90-0xbf (FMA)
-96: vfmaddsub132pd/ps /r (66),(VEX)
+90: vgatherdd/q Vx,Hx,Wx (66),(v)
-97: vfmsubadd132pd/ps /r (66),(VEX)
+91: vgatherqd/q Vx,Hx,Wx (66),(v)
-98: vfmadd132pd/ps /r (66),(VEX)
+92: vgatherdps/d Vx,Hx,Wx (66),(v)
-99: vfmadd132sd/ss /r (66),(VEX),(o128)
+93: vgatherqps/d Vx,Hx,Wx (66),(v)
-9a: vfmsub132pd/ps /r (66),(VEX)
+94:
-9b: vfmsub132sd/ss /r (66),(VEX),(o128)
+95:
-9c: vfnmadd132pd/ps /r (66),(VEX)
+96: vfmaddsub132ps/d Vx,Hx,Wx (66),(v)
-9d: vfnmadd132sd/ss /r (66),(VEX),(o128)
+97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v)
-9e: vfnmsub132pd/ps /r (66),(VEX)
+98: vfmadd132ps/d Vx,Hx,Wx (66),(v)
-9f: vfnmsub132sd/ss /r (66),(VEX),(o128)
+99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
-a6: vfmaddsub213pd/ps /r (66),(VEX)
+9a: vfmsub132ps/d Vx,Hx,Wx (66),(v)
-a7: vfmsubadd213pd/ps /r (66),(VEX)
+9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
-a8: vfmadd213pd/ps /r (66),(VEX)
+9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v)
-a9: vfmadd213sd/ss /r (66),(VEX),(o128)
+9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
-aa: vfmsub213pd/ps /r (66),(VEX)
+9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
-ab: vfmsub213sd/ss /r (66),(VEX),(o128)
+9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
-ac: vfnmadd213pd/ps /r (66),(VEX)
+a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
-ad: vfnmadd213sd/ss /r (66),(VEX),(o128)
+a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
-ae: vfnmsub213pd/ps /r (66),(VEX)
+a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
-af: vfnmsub213sd/ss /r (66),(VEX),(o128)
+a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
-b6: vfmaddsub231pd/ps /r (66),(VEX)
+aa: vfmsub213ps/d Vx,Hx,Wx (66),(v)
-b7: vfmsubadd231pd/ps /r (66),(VEX)
+ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
-b8: vfmadd231pd/ps /r (66),(VEX)
+ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
-b9: vfmadd231sd/ss /r (66),(VEX),(o128)
+ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
-ba: vfmsub231pd/ps /r (66),(VEX)
+ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
-bb: vfmsub231sd/ss /r (66),(VEX),(o128)
+af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
-bc: vfnmadd231pd/ps /r (66),(VEX)
+b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
-bd: vfnmadd231sd/ss /r (66),(VEX),(o128)
+b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
-be: vfnmsub231pd/ps /r (66),(VEX)
+b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
-bf: vfnmsub231sd/ss /r (66),(VEX),(o128)
+b9: vfmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
+ba: vfmsub231ps/d Vx,Hx,Wx (66),(v)
+bb: vfmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
+bc: vfnmadd231ps/d Vx,Hx,Wx (66),(v)
+bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
+be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
+bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
 # 0x0f 0x38 0xc0-0xff
-db: aesimc Vdq,Wdq (66),(VEX),(o128)
+db: VAESIMC Vdq,Wdq (66),(v1)
-dc: aesenc Vdq,Wdq (66),(VEX),(o128)
+dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
-dd: aesenclast Vdq,Wdq (66),(VEX),(o128)
+dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
-de: aesdec Vdq,Wdq (66),(VEX),(o128)
+de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
-df: aesdeclast Vdq,Wdq (66),(VEX),(o128)
+df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
-f0: MOVBE Gv,Mv | CRC32 Gd,Eb (F2)
+f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2)
-f1: MOVBE Mv,Gv | CRC32 Gd,Ev (F2)
+f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2)
+f3: ANDN Gy,By,Ey (v)
+f4: Grp17 (1A)
+f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
+f6: MULX By,Gy,rDX,Ey (F2),(v)
+f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
 EndTable
 Table: 3-byte opcode 2 (0x0f 0x3a)
 Referrer: 3-byte escape 2
 AVXcode: 3
 # 0x0f 0x3a 0x00-0xff
-04: vpermilps /r,Ib (66),(oVEX)
+00: vpermq Vqq,Wqq,Ib (66),(v)
-05: vpermilpd /r,Ib (66),(oVEX)
+01: vpermpd Vqq,Wqq,Ib (66),(v)
-06: vperm2f128 /r,Ib (66),(oVEX),(o256)
+02: vpblendd Vx,Hx,Wx,Ib (66),(v)
-08: roundps Vdq,Wdq,Ib (66),(VEX)
+03:
-09: roundpd Vdq,Wdq,Ib (66),(VEX)
+04: vpermilps Vx,Wx,Ib (66),(v)
-0a: roundss Vss,Wss,Ib (66),(VEX),(o128)
+05: vpermilpd Vx,Wx,Ib (66),(v)
-0b: roundsd Vsd,Wsd,Ib (66),(VEX),(o128)
+06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
-0c: blendps Vdq,Wdq,Ib (66),(VEX)
+07:
-0d: blendpd Vdq,Wdq,Ib (66),(VEX)
+08: vroundps Vx,Wx,Ib (66)
-0e: pblendw Vdq,Wdq,Ib (66),(VEX),(o128)
+09: vroundpd Vx,Wx,Ib (66)
-0f: palignr Pq,Qq,Ib | palignr Vdq,Wdq,Ib (66),(VEX),(o128)
+0a: vroundss Vss,Wss,Ib (66),(v1)
-14: pextrb Rd/Mb,Vdq,Ib (66),(VEX),(o128)
+0b: vroundsd Vsd,Wsd,Ib (66),(v1)
-15: pextrw Rd/Mw,Vdq,Ib (66),(VEX),(o128)
+0c: vblendps Vx,Hx,Wx,Ib (66)
-16: pextrd/pextrq Ed/q,Vdq,Ib (66),(VEX),(o128)
+0d: vblendpd Vx,Hx,Wx,Ib (66)
-17: extractps Ed,Vdq,Ib (66),(VEX),(o128)
+0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
-18: vinsertf128 /r,Ib (66),(oVEX),(o256)
+0f: palignr Pq,Qq,Ib | vpalignr Vx,Hx,Wx,Ib (66),(v1)
-19: vextractf128 /r,Ib (66),(oVEX),(o256)
+14: vpextrb Rd/Mb,Vdq,Ib (66),(v1)
-20: pinsrb Vdq,Rd/q/Mb,Ib (66),(VEX),(o128)
+15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
-21: insertps Vdq,Udq/Md,Ib (66),(VEX),(o128)
+16: vpextrd/q Ey,Vdq,Ib (66),(v1)
-22: pinsrd/pinsrq Vdq,Ed/q,Ib (66),(VEX),(o128)
+17: vextractps Ed,Vdq,Ib (66),(v1)
-40: dpps Vdq,Wdq,Ib (66),(VEX)
+18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v)
-41: dppd Vdq,Wdq,Ib (66),(VEX),(o128)
+19: vextractf128 Wdq,Vqq,Ib (66),(v)
-42: mpsadbw Vdq,Wdq,Ib (66),(VEX),(o128)
+1d: vcvtps2ph Wx,Vx,Ib (66),(v)
-44: pclmulq Vdq,Wdq,Ib (66),(VEX),(o128)
+20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
-4a: vblendvps /r,Ib (66),(oVEX)
+21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
-4b: vblendvpd /r,Ib (66),(oVEX)
+22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
-4c: vpblendvb /r,Ib (66),(oVEX),(o128)
+38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v)
-60: pcmpestrm Vdq,Wdq,Ib (66),(VEX),(o128)
+39: vextracti128 Wdq,Vqq,Ib (66),(v)
-61: pcmpestri Vdq,Wdq,Ib (66),(VEX),(o128)
+40: vdpps Vx,Hx,Wx,Ib (66)
-62: pcmpistrm Vdq,Wdq,Ib (66),(VEX),(o128)
+41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
-63: pcmpistri Vdq,Wdq,Ib (66),(VEX),(o128)
+42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1)
-df: aeskeygenassist Vdq,Wdq,Ib (66),(VEX),(o128)
+44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
+46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
+4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
+4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
+4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
+60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
+61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
+62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
+63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
+df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
+f0: RORX Gy,Ey,Ib (F2),(v)
 EndTable
 GrpTable: Grp1
@@ -790,7 +843,7 @@ GrpTable: Grp5
 2: CALLN Ev (f64)
 3: CALLF Ep
 4: JMPN Ev (f64)
-5: JMPF Ep
+5: JMPF Mp
 6: PUSH Ev (d64)
 7:
 EndTable
@@ -807,7 +860,7 @@ EndTable
 GrpTable: Grp7
 0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
 1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001)
-2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B)
+2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B)
 3: LIDT Ms
 4: SMSW Mw/Rv
 5:
@@ -824,44 +877,45 @@ EndTable
 GrpTable: Grp9
 1: CMPXCHG8B/16B Mq/Mdq
-6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3)
+6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
-7: VMPTRST Mq
+7: VMPTRST Mq | VMPTRST Mq (F3)
 EndTable
 GrpTable: Grp10
 EndTable
 GrpTable: Grp11
+# Note: the operands are given by group opcode
 0: MOV
 EndTable
 GrpTable: Grp12
-2: psrlw Nq,Ib (11B) | psrlw Udq,Ib (66),(11B),(VEX),(o128)
+2: psrlw Nq,Ib (11B) | vpsrlw Hx,Ux,Ib (66),(11B),(v1)
-4: psraw Nq,Ib (11B) | psraw Udq,Ib (66),(11B),(VEX),(o128)
+4: psraw Nq,Ib (11B) | vpsraw Hx,Ux,Ib (66),(11B),(v1)
-6: psllw Nq,Ib (11B) | psllw Udq,Ib (66),(11B),(VEX),(o128)
+6: psllw Nq,Ib (11B) | vpsllw Hx,Ux,Ib (66),(11B),(v1)
 EndTable
 GrpTable: Grp13
-2: psrld Nq,Ib (11B) | psrld Udq,Ib (66),(11B),(VEX),(o128)
+2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
-4: psrad Nq,Ib (11B) | psrad Udq,Ib (66),(11B),(VEX),(o128)
+4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1)
-6: pslld Nq,Ib (11B) | pslld Udq,Ib (66),(11B),(VEX),(o128)
+6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
 EndTable
 GrpTable: Grp14
-2: psrlq Nq,Ib (11B) | psrlq Udq,Ib (66),(11B),(VEX),(o128)
+2: psrlq Nq,Ib (11B) | vpsrlq Hx,Ux,Ib (66),(11B),(v1)
-3: psrldq Udq,Ib (66),(11B),(VEX),(o128)
+3: vpsrldq Hx,Ux,Ib (66),(11B),(v1)
-6: psllq Nq,Ib (11B) | psllq Udq,Ib (66),(11B),(VEX),(o128)
+6: psllq Nq,Ib (11B) | vpsllq Hx,Ux,Ib (66),(11B),(v1)
-7: pslldq Udq,Ib (66),(11B),(VEX),(o128)
+7: vpslldq Hx,Ux,Ib (66),(11B),(v1)
 EndTable
 GrpTable: Grp15
-0: fxsave
+0: fxsave | RDFSBASE Ry (F3),(11B)
-1: fxstor
+1: fxstor | RDGSBASE Ry (F3),(11B)
-2: ldmxcsr (VEX)
+2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B)
-3: stmxcsr (VEX)
+3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
 4: XSAVE
 5: XRSTOR | lfence (11B)
-6: mfence (11B)
+6: XSAVEOPT | mfence (11B)
 7: clflush | sfence (11B)
 EndTable
@@ -872,6 +926,12 @@ GrpTable: Grp16
 3: prefetch T2
 EndTable
+GrpTable: Grp17
+1: BLSR By,Ey (v)
+2: BLSMSK By,Ey (v)
+3: BLSI By,Ey (v)
+EndTable
 # AMD's Prefetch Group
 GrpTable: GrpP
 0: PREFETCH
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 3d11327c9ab4..23d8e5fecf76 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -27,6 +27,4 @@ obj-$(CONFIG_AMD_NUMA)		+= amdtopology.o
 obj-$(CONFIG_ACPI_NUMA)         += srat.o
 obj-$(CONFIG_NUMA_EMU)          += numa_emulation.o
-obj-$(CONFIG_HAVE_MEMBLOCK)             += memblock.o
 obj-$(CONFIG_MEMTEST)           += memtest.o
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index ea305856151c..dd74e46828c0 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -201,6 +201,8 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr,
        do {
                VM_BUG_ON(compound_head(page) != head);
                pages[*nr] = page;
+                if (PageTail(page))
+                        get_huge_page_tail(page);
                (*nr)++;
                page++;
                refs++;
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index b49962662101..f4f29b19fac5 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -45,6 +45,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
        vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
        BUG_ON(!pte_none(*(kmap_pte-idx)));
        set_pte(kmap_pte-idx, mk_pte(page, prot));
+        arch_flush_lazy_mmu_mode();
        return (void *)vaddr;
 }
@@ -88,6 +89,7 @@ void __kunmap_atomic(void *kvaddr)
                 */
                kpte_clear_flush(kmap_pte-idx, vaddr);
                kmap_atomic_idx_pop();
+                arch_flush_lazy_mmu_mode();
        }
 #ifdef CONFIG_DEBUG_HIGHMEM
        else {
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 87488b93a65c..a298914058f9 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -67,7 +67,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
        good_end = max_pfn_mapped << PAGE_SHIFT;
        base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE);
-        if (base == MEMBLOCK_ERROR)
+        if (!base)
                panic("Cannot find space for the kernel page tables");
        pgt_buf_start = base >> PAGE_SHIFT;
@@ -80,7 +80,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 void __init native_pagetable_reserve(u64 start, u64 end)
 {
-        memblock_x86_reserve_range(start, end, "PGTABLE");
+        memblock_reserve(start, end - start);
 }
 struct map_range {
@@ -279,8 +279,8 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
         * pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top)
         * so that they can be reused for other purposes.
         *
-         * On native it just means calling memblock_x86_reserve_range, on Xen it
+         * On native it just means calling memblock_reserve, on Xen it also
-         * also means marking RW the pagetable pages that we allocated before
+         * means marking RW the pagetable pages that we allocated before
         * but that haven't been used.
         *
         * In fact on xen we mark RO the whole range pgt_buf_start -
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 29f7c6d98179..0c1da394a634 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -427,23 +427,17 @@ static void __init add_one_highpage_init(struct page *page)
 void __init add_highpages_with_active_regions(int nid,
                         unsigned long start_pfn, unsigned long end_pfn)
 {
-        struct range *range;
+        phys_addr_t start, end;
-        int nr_range;
+        u64 i;
-        int i;
+        for_each_free_mem_range(i, nid, &start, &end, NULL) {
-        nr_range = __get_free_all_memory_range(&range, nid, start_pfn, end_pfn);
+                unsigned long pfn = clamp_t(unsigned long, PFN_UP(start),
+                                            start_pfn, end_pfn);
-        for (i = 0; i < nr_range; i++) {
+                unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end),
-                struct page *page;
+                                              start_pfn, end_pfn);
-                int node_pfn;
+                for ( ; pfn < e_pfn; pfn++)
+                        if (pfn_valid(pfn))
-                for (node_pfn = range[i].start; node_pfn < range[i].end;
+                                add_one_highpage_init(pfn_to_page(pfn));
-                     node_pfn++) {
-                        if (!pfn_valid(node_pfn))
-                                continue;
-                        page = pfn_to_page(node_pfn);
-                        add_one_highpage_init(page);
-                }
        }
 }
 #else
@@ -650,18 +644,18 @@ void __init initmem_init(void)
        highstart_pfn = highend_pfn = max_pfn;
        if (max_pfn > max_low_pfn)
                highstart_pfn = max_low_pfn;
-        memblock_x86_register_active_regions(0, 0, highend_pfn);
-        sparse_memory_present_with_active_regions(0);
        printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
                pages_to_mb(highend_pfn - highstart_pfn));
        num_physpages = highend_pfn;
        high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
 #else
-        memblock_x86_register_active_regions(0, 0, max_low_pfn);
-        sparse_memory_present_with_active_regions(0);
        num_physpages = max_low_pfn;
        high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
 #endif
+        memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
+        sparse_memory_present_with_active_regions(0);
 #ifdef CONFIG_FLATMEM
        max_mapnr = num_physpages;
 #endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index bbaaa005bf0e..a8a56ce3a962 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -608,7 +608,7 @@ kernel_physical_mapping_init(unsigned long start,
 #ifndef CONFIG_NUMA
 void __init initmem_init(void)
 {
-        memblock_x86_register_active_regions(0, 0, max_pfn);
+        memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
 }
 #endif
diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c
deleted file mode 100644
index 992da5ec5a64..000000000000
--- a/arch/x86/mm/memblock.c
+++ /dev/null
@@ -1,348 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/bitops.h>
-#include <linux/memblock.h>
-#include <linux/bootmem.h>
-#include <linux/mm.h>
-#include <linux/range.h>
-/* Check for already reserved areas */
-bool __init memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align)
-{
-        struct memblock_region *r;
-        u64 addr = *addrp, last;
-        u64 size = *sizep;
-        bool changed = false;
-again:
-        last = addr + size;
-        for_each_memblock(reserved, r) {
-                if (last > r->base && addr < r->base) {
-                        size = r->base - addr;
-                        changed = true;
-                        goto again;
-                }
-                if (last > (r->base + r->size) && addr < (r->base + r->size)) {
-                        addr = round_up(r->base + r->size, align);
-                        size = last - addr;
-                        changed = true;
-                        goto again;
-                }
-                if (last <= (r->base + r->size) && addr >= r->base) {
-                        *sizep = 0;
-                        return false;
-                }
-        }
-        if (changed) {
-                *addrp = addr;
-                *sizep = size;
-        }
-        return changed;
-}
-/*
- * Find next free range after start, and size is returned in *sizep
- */
-u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align)
-{
-        struct memblock_region *r;
-        for_each_memblock(memory, r) {
-                u64 ei_start = r->base;
-                u64 ei_last = ei_start + r->size;
-                u64 addr;
-                addr = round_up(ei_start, align);
-                if (addr < start)
-                        addr = round_up(start, align);
-                if (addr >= ei_last)
-                        continue;
-                *sizep = ei_last - addr;
-                while (memblock_x86_check_reserved_size(&addr, sizep, align))
-                        ;
-                if (*sizep)
-                        return addr;
-        }
-        return MEMBLOCK_ERROR;
-}
-static __init struct range *find_range_array(int count)
-{
-        u64 end, size, mem;
-        struct range *range;
-        size = sizeof(struct range) * count;
-        end = memblock.current_limit;
-        mem = memblock_find_in_range(0, end, size, sizeof(struct range));
-        if (mem == MEMBLOCK_ERROR)
-                panic("can not find more space for range array");
-        /*
-         * This range is tempoaray, so don't reserve it, it will not be
-         * overlapped because We will not alloccate new buffer before
-         * We discard this one
-         */
-        range = __va(mem);
-        memset(range, 0, size);
-        return range;
-}
-static void __init memblock_x86_subtract_reserved(struct range *range, int az)
-{
-        u64 final_start, final_end;
-        struct memblock_region *r;
-        /* Take out region array itself at first*/
-        memblock_free_reserved_regions();
-        memblock_dbg("Subtract (%ld early reservations)\n", memblock.reserved.cnt);
-        for_each_memblock(reserved, r) {
-                memblock_dbg("  [%010llx-%010llx]\n", (u64)r->base, (u64)r->base + r->size - 1);
-                final_start = PFN_DOWN(r->base);
-                final_end = PFN_UP(r->base + r->size);
-                if (final_start >= final_end)
-                        continue;
-                subtract_range(range, az, final_start, final_end);
-        }
-        /* Put region array back ? */
-        memblock_reserve_reserved_regions();
-}
-struct count_data {
-        int nr;
-};
-static int __init count_work_fn(unsigned long start_pfn,
-                                unsigned long end_pfn, void *datax)
-{
-        struct count_data *data = datax;
-        data->nr++;
-        return 0;
-}
-static int __init count_early_node_map(int nodeid)
-{
-        struct count_data data;
-        data.nr = 0;
-        work_with_active_regions(nodeid, count_work_fn, &data);
-        return data.nr;
-}
-int __init __get_free_all_memory_range(struct range **rangep, int nodeid,
-                         unsigned long start_pfn, unsigned long end_pfn)
-{
-        int count;
-        struct range *range;
-        int nr_range;
-        count = (memblock.reserved.cnt + count_early_node_map(nodeid)) * 2;
-        range = find_range_array(count);
-        nr_range = 0;
-        /*
-         * Use early_node_map[] and memblock.reserved.region to get range array
-         * at first
-         */
-        nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
-        subtract_range(range, count, 0, start_pfn);
-        subtract_range(range, count, end_pfn, -1ULL);
-        memblock_x86_subtract_reserved(range, count);
-        nr_range = clean_sort_range(range, count);
-        *rangep = range;
-        return nr_range;
-}
-int __init get_free_all_memory_range(struct range **rangep, int nodeid)
-{
-        unsigned long end_pfn = -1UL;
-#ifdef CONFIG_X86_32
-        end_pfn = max_low_pfn;
-#endif
-        return __get_free_all_memory_range(rangep, nodeid, 0, end_pfn);
-}
-static u64 __init __memblock_x86_memory_in_range(u64 addr, u64 limit, bool get_free)
-{
-        int i, count;
-        struct range *range;
-        int nr_range;
-        u64 final_start, final_end;
-        u64 free_size;
-        struct memblock_region *r;
-        count = (memblock.reserved.cnt + memblock.memory.cnt) * 2;
-        range = find_range_array(count);
-        nr_range = 0;
-        addr = PFN_UP(addr);
-        limit = PFN_DOWN(limit);
-        for_each_memblock(memory, r) {
-                final_start = PFN_UP(r->base);
-                final_end = PFN_DOWN(r->base + r->size);
-                if (final_start >= final_end)
-                        continue;
-                if (final_start >= limit || final_end <= addr)
-                        continue;
-                nr_range = add_range(range, count, nr_range, final_start, final_end);
-        }
-        subtract_range(range, count, 0, addr);
-        subtract_range(range, count, limit, -1ULL);
-        /* Subtract memblock.reserved.region in range ? */
-        if (!get_free)
-                goto sort_and_count_them;
-        for_each_memblock(reserved, r) {
-                final_start = PFN_DOWN(r->base);
-                final_end = PFN_UP(r->base + r->size);
-                if (final_start >= final_end)
-                        continue;
-                if (final_start >= limit || final_end <= addr)
-                        continue;
-                subtract_range(range, count, final_start, final_end);
-        }
-sort_and_count_them:
-        nr_range = clean_sort_range(range, count);
-        free_size = 0;
-        for (i = 0; i < nr_range; i++)
-                free_size += range[i].end - range[i].start;
-        return free_size << PAGE_SHIFT;
-}
-u64 __init memblock_x86_free_memory_in_range(u64 addr, u64 limit)
-{
-        return __memblock_x86_memory_in_range(addr, limit, true);
-}
-u64 __init memblock_x86_memory_in_range(u64 addr, u64 limit)
-{
-        return __memblock_x86_memory_in_range(addr, limit, false);
-}
-void __init memblock_x86_reserve_range(u64 start, u64 end, char *name)
-{
-        if (start == end)
-                return;
-        if (WARN_ONCE(start > end, "memblock_x86_reserve_range: wrong range [%#llx, %#llx)\n", start, end))
-                return;
-        memblock_dbg("    memblock_x86_reserve_range: [%#010llx-%#010llx] %16s\n", start, end - 1, name);
-        memblock_reserve(start, end - start);
-}
-void __init memblock_x86_free_range(u64 start, u64 end)
-{
-        if (start == end)
-                return;
-        if (WARN_ONCE(start > end, "memblock_x86_free_range: wrong range [%#llx, %#llx)\n", start, end))
-                return;
-        memblock_dbg("       memblock_x86_free_range: [%#010llx-%#010llx]\n", start, end - 1);
-        memblock_free(start, end - start);
-}
-/*
- * Need to call this function after memblock_x86_register_active_regions,
- * so early_node_map[] is filled already.
- */
-u64 __init memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align)
-{
-        u64 addr;
-        addr = find_memory_core_early(nid, size, align, start, end);
-        if (addr != MEMBLOCK_ERROR)
-                return addr;
-        /* Fallback, should already have start end within node range */
-        return memblock_find_in_range(start, end, size, align);
-}
-/*
- * Finds an active region in the address range from start_pfn to last_pfn and
- * returns its range in ei_startpfn and ei_endpfn for the memblock entry.
- */
-static int __init memblock_x86_find_active_region(const struct memblock_region *ei,
-                                  unsigned long start_pfn,
-                                  unsigned long last_pfn,
-                                  unsigned long *ei_startpfn,
-                                  unsigned long *ei_endpfn)
-{
-        u64 align = PAGE_SIZE;
-        *ei_startpfn = round_up(ei->base, align) >> PAGE_SHIFT;
-        *ei_endpfn = round_down(ei->base + ei->size, align) >> PAGE_SHIFT;
-        /* Skip map entries smaller than a page */
-        if (*ei_startpfn >= *ei_endpfn)
-                return 0;
-        /* Skip if map is outside the node */
-        if (*ei_endpfn <= start_pfn || *ei_startpfn >= last_pfn)
-                return 0;
-        /* Check for overlaps */
-        if (*ei_startpfn < start_pfn)
-                *ei_startpfn = start_pfn;
-        if (*ei_endpfn > last_pfn)
-                *ei_endpfn = last_pfn;
-        return 1;
-}
-/* Walk the memblock.memory map and register active regions within a node */
-void __init memblock_x86_register_active_regions(int nid, unsigned long start_pfn,
-                                         unsigned long last_pfn)
-{
-        unsigned long ei_startpfn;
-        unsigned long ei_endpfn;
-        struct memblock_region *r;
-        for_each_memblock(memory, r)
-                if (memblock_x86_find_active_region(r, start_pfn, last_pfn,
-                                           &ei_startpfn, &ei_endpfn))
-                        add_active_range(nid, ei_startpfn, ei_endpfn);
-}
-/*
- * Find the hole size (in bytes) in the memory range.
- * @start: starting address of the memory range to scan
- * @end: ending address of the memory range to scan
- */
-u64 __init memblock_x86_hole_size(u64 start, u64 end)
-{
-        unsigned long start_pfn = start >> PAGE_SHIFT;
-        unsigned long last_pfn = end >> PAGE_SHIFT;
-        unsigned long ei_startpfn, ei_endpfn, ram = 0;
-        struct memblock_region *r;
-        for_each_memblock(memory, r)
-                if (memblock_x86_find_active_region(r, start_pfn, last_pfn,
-                                           &ei_startpfn, &ei_endpfn))
-                        ram += ei_endpfn - ei_startpfn;
-        return end - start - ((u64)ram << PAGE_SHIFT);
-}
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 92faf3a1c53e..c80b9fb95734 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -34,7 +34,7 @@ static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad)
               (unsigned long long) pattern,
               (unsigned long long) start_bad,
               (unsigned long long) end_bad);
-        memblock_x86_reserve_range(start_bad, end_bad, "BAD RAM");
+        memblock_reserve(start_bad, end_bad - start_bad);
 }
 static void __init memtest(u64 pattern, u64 start_phys, u64 size)
@@ -70,24 +70,19 @@ static void __init memtest(u64 pattern, u64 start_phys, u64 size)
 static void __init do_one_pass(u64 pattern, u64 start, u64 end)
 {
-        u64 size = 0;
+        u64 i;
+        phys_addr_t this_start, this_end;
-        while (start < end) {
-                start = memblock_x86_find_in_range_size(start, &size, 1);
+        for_each_free_mem_range(i, MAX_NUMNODES, &this_start, &this_end, NULL) {
+                this_start = clamp_t(phys_addr_t, this_start, start, end);
-                /* done ? */
+                this_end = clamp_t(phys_addr_t, this_end, start, end);
-                if (start >= end)
+                if (this_start < this_end) {
-                        break;
+                        printk(KERN_INFO "  %010llx - %010llx pattern %016llx\n",
-                if (start + size > end)
+                               (unsigned long long)this_start,
-                        size = end - start;
+                               (unsigned long long)this_end,
+                               (unsigned long long)cpu_to_be64(pattern));
-                printk(KERN_INFO "  %010llx - %010llx pattern %016llx\n",
+                        memtest(pattern, this_start, this_end - this_start);
-                       (unsigned long long) start,
+                }
-                       (unsigned long long) start + size,
-                       (unsigned long long) cpu_to_be64(pattern));
-                memtest(pattern, start, size);
-                start += size;
        }
 }
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index fbeaaf416610..496f494593bf 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -192,8 +192,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 /* Initialize NODE_DATA for a node on the local memory */
 static void __init setup_node_data(int nid, u64 start, u64 end)
 {
-        const u64 nd_low = PFN_PHYS(MAX_DMA_PFN);
-        const u64 nd_high = PFN_PHYS(max_pfn_mapped);
        const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
        bool remapped = false;
        u64 nd_pa;
@@ -224,17 +222,12 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
                nd_pa = __pa(nd);
                remapped = true;
        } else {
-                nd_pa = memblock_x86_find_in_range_node(nid, nd_low, nd_high,
+                nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
-                                                nd_size, SMP_CACHE_BYTES);
+                if (!nd_pa) {
-                if (nd_pa == MEMBLOCK_ERROR)
-                        nd_pa = memblock_find_in_range(nd_low, nd_high,
-                                                nd_size, SMP_CACHE_BYTES);
-                if (nd_pa == MEMBLOCK_ERROR) {
                        pr_err("Cannot find %zu bytes in node %d\n",
                               nd_size, nid);
                        return;
                }
-                memblock_x86_reserve_range(nd_pa, nd_pa + nd_size, "NODE_DATA");
                nd = __va(nd_pa);
        }
@@ -371,8 +364,7 @@ void __init numa_reset_distance(void)
        /* numa_distance could be 1LU marking allocation failure, test cnt */
        if (numa_distance_cnt)
-                memblock_x86_free_range(__pa(numa_distance),
+                memblock_free(__pa(numa_distance), size);
-                                        __pa(numa_distance) + size);
        numa_distance_cnt = 0;
        numa_distance = NULL;   /* enable table creation */
 }
@@ -395,13 +387,13 @@ static int __init numa_alloc_distance(void)
        phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
                                      size, PAGE_SIZE);
-        if (phys == MEMBLOCK_ERROR) {
+        if (!phys) {
                pr_warning("NUMA: Warning: can't allocate distance table!\n");
                /* don't retry until explicitly reset */
                numa_distance = (void *)1LU;
                return -ENOMEM;
        }
-        memblock_x86_reserve_range(phys, phys + size, "NUMA DIST");
+        memblock_reserve(phys, size);
        numa_distance = __va(phys);
        numa_distance_cnt = cnt;
@@ -482,8 +474,8 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
                        numaram = 0;
        }
-        e820ram = max_pfn - (memblock_x86_hole_size(0,
+        e820ram = max_pfn - absent_pages_in_range(0, max_pfn);
-                                        PFN_PHYS(max_pfn)) >> PAGE_SHIFT);
        /* We seem to lose 3 pages somewhere. Allow 1M of slack. */
        if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) {
                printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n",
@@ -505,13 +497,10 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
        if (WARN_ON(nodes_empty(node_possible_map)))
                return -EINVAL;
-        for (i = 0; i < mi->nr_blks; i++)
+        for (i = 0; i < mi->nr_blks; i++) {
-                memblock_x86_register_active_regions(mi->blk[i].nid,
+                struct numa_memblk *mb = &mi->blk[i];
-                                        mi->blk[i].start >> PAGE_SHIFT,
+                memblock_set_node(mb->start, mb->end - mb->start, mb->nid);
-                                        mi->blk[i].end >> PAGE_SHIFT);
+        }
-        /* for out of order entries */
-        sort_node_map();
        /*
         * If sections array is gonna be used for pfn -> nid mapping, check
@@ -545,6 +534,8 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
                        setup_node_data(nid, start, end);
        }
+        /* Dump memblock with node info and return. */
+        memblock_dump_all();
        return 0;
 }
@@ -582,7 +573,7 @@ static int __init numa_init(int (*init_func)(void))
        nodes_clear(node_possible_map);
        nodes_clear(node_online_map);
        memset(&numa_meminfo, 0, sizeof(numa_meminfo));
-        remove_all_active_ranges();
+        WARN_ON(memblock_set_node(0, ULLONG_MAX, MAX_NUMNODES));
        numa_reset_distance();
        ret = init_func();
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 3adebe7e536a..534255a36b6b 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -199,23 +199,23 @@ void __init init_alloc_remap(int nid, u64 start, u64 end)
        /* allocate node memory and the lowmem remap area */
        node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES);
-        if (node_pa == MEMBLOCK_ERROR) {
+        if (!node_pa) {
                pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n",
                           size, nid);
                return;
        }
-        memblock_x86_reserve_range(node_pa, node_pa + size, "KVA RAM");
+        memblock_reserve(node_pa, size);
        remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT,
                                          max_low_pfn << PAGE_SHIFT,
                                          size, LARGE_PAGE_BYTES);
-        if (remap_pa == MEMBLOCK_ERROR) {
+        if (!remap_pa) {
                pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n",
                           size, nid);
-                memblock_x86_free_range(node_pa, node_pa + size);
+                memblock_free(node_pa, size);
                return;
        }
-        memblock_x86_reserve_range(remap_pa, remap_pa + size, "KVA PG");
+        memblock_reserve(remap_pa, size);
        remap_va = phys_to_virt(remap_pa);
        /* perform actual remap */
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index dd27f401f0a0..92e27119ee1a 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -19,7 +19,7 @@ unsigned long __init numa_free_all_bootmem(void)
        for_each_online_node(i)
                pages += free_all_bootmem_node(NODE_DATA(i));
-        pages += free_all_memory_core_early(MAX_NUMNODES);
+        pages += free_low_memory_core_early(MAX_NUMNODES);
        return pages;
 }
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index d0ed086b6247..46db56845f18 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -28,6 +28,16 @@ static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi)
        return -ENOENT;
 }
+static u64 mem_hole_size(u64 start, u64 end)
+{
+        unsigned long start_pfn = PFN_UP(start);
+        unsigned long end_pfn = PFN_DOWN(end);
+        if (start_pfn < end_pfn)
+                return PFN_PHYS(absent_pages_in_range(start_pfn, end_pfn));
+        return 0;
+}
 /*
 * Sets up nid to range from @start to @end.  The return value is -errno if
 * something went wrong, 0 otherwise.
@@ -89,7 +99,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
         * Calculate target node size.  x86_32 freaks on __udivdi3() so do
         * the division in ulong number of pages and convert back.
         */
-        size = max_addr - addr - memblock_x86_hole_size(addr, max_addr);
+        size = max_addr - addr - mem_hole_size(addr, max_addr);
        size = PFN_PHYS((unsigned long)(size >> PAGE_SHIFT) / nr_nodes);
        /*
@@ -135,8 +145,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
                         * Continue to add memory to this fake node if its
                         * non-reserved memory is less than the per-node size.
                         */
-                        while (end - start -
+                        while (end - start - mem_hole_size(start, end) < size) {
-                               memblock_x86_hole_size(start, end) < size) {
                                end += FAKE_NODE_MIN_SIZE;
                                if (end > limit) {
                                        end = limit;
@@ -150,7 +159,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
                         * this one must extend to the boundary.
                         */
                        if (end < dma32_end && dma32_end - end -
-                            memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+                            mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
                                end = dma32_end;
                        /*
@@ -158,8 +167,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
                         * next node, this one must extend to the end of the
                         * physical node.
                         */
-                        if (limit - end -
+                        if (limit - end - mem_hole_size(end, limit) < size)
-                            memblock_x86_hole_size(end, limit) < size)
                                end = limit;
                        ret = emu_setup_memblk(ei, pi, nid++ % nr_nodes,
@@ -180,7 +188,7 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
 {
        u64 end = start + size;
-        while (end - start - memblock_x86_hole_size(start, end) < size) {
+        while (end - start - mem_hole_size(start, end) < size) {
                end += FAKE_NODE_MIN_SIZE;
                if (end > max_addr) {
                        end = max_addr;
@@ -211,8 +219,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
         * creates a uniform distribution of node sizes across the entire
         * machine (but not necessarily over physical nodes).
         */
-        min_size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) /
+        min_size = (max_addr - addr - mem_hole_size(addr, max_addr)) / MAX_NUMNODES;
-                                                MAX_NUMNODES;
        min_size = max(min_size, FAKE_NODE_MIN_SIZE);
        if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
                min_size = (min_size + FAKE_NODE_MIN_SIZE) &
@@ -252,7 +259,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
                         * this one must extend to the boundary.
                         */
                        if (end < dma32_end && dma32_end - end -
-                            memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+                            mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
                                end = dma32_end;
                        /*
@@ -260,8 +267,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
                         * next node, this one must extend to the end of the
                         * physical node.
                         */
-                        if (limit - end -
+                        if (limit - end - mem_hole_size(end, limit) < size)
-                            memblock_x86_hole_size(end, limit) < size)
                                end = limit;
                        ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES,
@@ -351,11 +357,11 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
                phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
                                              phys_size, PAGE_SIZE);
-                if (phys == MEMBLOCK_ERROR) {
+                if (!phys) {
                        pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
                        goto no_emu;
                }
-                memblock_x86_reserve_range(phys, phys + phys_size, "TMP NUMA DIST");
+                memblock_reserve(phys, phys_size);
                phys_dist = __va(phys);
                for (i = 0; i < numa_dist_cnt; i++)
@@ -424,7 +430,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
        /* free the copied physical distance table */
        if (phys_dist)
-                memblock_x86_free_range(__pa(phys_dist), __pa(phys_dist) + phys_size);
+                memblock_free(__pa(phys_dist), phys_size);
        return;
 no_emu:
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index bfab3fa10edc..7b65f752c5f8 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -568,8 +568,8 @@ cond_branch:			f_offset = addrs[i + filter[i].jf] - addrs[i];
                                        break;
                                }
                                if (filter[i].jt != 0) {
-                                        if (filter[i].jf)
+                                        if (filter[i].jf && f_offset)
-                                                t_offset += is_near(f_offset) ? 2 : 6;
+                                                t_offset += is_near(f_offset) ? 2 : 5;
                                        EMIT_COND_JMP(t_op, t_offset);
                                        if (filter[i].jf)
                                                EMIT_JMP(f_offset);
diff --git a/arch/x86/oprofile/Makefile b/arch/x86/oprofile/Makefile
index 446902b2a6b6..1599f568f0e2 100644
--- a/arch/x86/oprofile/Makefile
+++ b/arch/x86/oprofile/Makefile
@@ -4,9 +4,8 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
                oprof.o cpu_buffer.o buffer_sync.o \
                event_buffer.o oprofile_files.o \
                oprofilefs.o oprofile_stats.o  \
-                timer_int.o )
+                timer_int.o nmi_timer_int.o )
 oprofile-y                              := $(DRIVER_OBJS) init.o backtrace.o
 oprofile-$(CONFIG_X86_LOCAL_APIC)       += nmi_int.o op_model_amd.o \
                                           op_model_ppro.o op_model_p4.o
-oprofile-$(CONFIG_X86_IO_APIC)          += nmi_timer_int.o
diff --git a/arch/x86/oprofile/init.c b/arch/x86/oprofile/init.c
index cdfe4c54deca..9e138d00ad36 100644
--- a/arch/x86/oprofile/init.c
+++ b/arch/x86/oprofile/init.c
@@ -16,34 +16,23 @@
 * with the NMI mode driver.
 */
+#ifdef CONFIG_X86_LOCAL_APIC
 extern int op_nmi_init(struct oprofile_operations *ops);
-extern int op_nmi_timer_init(struct oprofile_operations *ops);
 extern void op_nmi_exit(void);
-extern void x86_backtrace(struct pt_regs * const regs, unsigned int depth);
+#else
+static int op_nmi_init(struct oprofile_operations *ops) { return -ENODEV; }
+static void op_nmi_exit(void) { }
+#endif
+extern void x86_backtrace(struct pt_regs * const regs, unsigned int depth);
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
-        int ret;
-        ret = -ENODEV;
-#ifdef CONFIG_X86_LOCAL_APIC
-        ret = op_nmi_init(ops);
-#endif
-#ifdef CONFIG_X86_IO_APIC
-        if (ret < 0)
-                ret = op_nmi_timer_init(ops);
-#endif
        ops->backtrace = x86_backtrace;
+        return op_nmi_init(ops);
-        return ret;
 }
 void oprofile_arch_exit(void)
 {
-#ifdef CONFIG_X86_LOCAL_APIC
        op_nmi_exit();
-#endif
 }
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 75f9528e0372..26b8a8514ee5 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -595,24 +595,36 @@ static int __init p4_init(char **cpu_type)
        return 0;
 }
-static int force_arch_perfmon;
+enum __force_cpu_type {
-static int force_cpu_type(const char *str, struct kernel_param *kp)
+        reserved = 0,           /* do not force */
+        timer,
+        arch_perfmon,
+};
+static int force_cpu_type;
+static int set_cpu_type(const char *str, struct kernel_param *kp)
 {
-        if (!strcmp(str, "arch_perfmon")) {
+        if (!strcmp(str, "timer")) {
-                force_arch_perfmon = 1;
+                force_cpu_type = timer;
+                printk(KERN_INFO "oprofile: forcing NMI timer mode\n");
+        } else if (!strcmp(str, "arch_perfmon")) {
+                force_cpu_type = arch_perfmon;
                printk(KERN_INFO "oprofile: forcing architectural perfmon\n");
+        } else {
+                force_cpu_type = 0;
        }
        return 0;
 }
-module_param_call(cpu_type, force_cpu_type, NULL, NULL, 0);
+module_param_call(cpu_type, set_cpu_type, NULL, NULL, 0);
 static int __init ppro_init(char **cpu_type)
 {
        __u8 cpu_model = boot_cpu_data.x86_model;
        struct op_x86_model_spec *spec = &op_ppro_spec; /* default */
-        if (force_arch_perfmon && cpu_has_arch_perfmon)
+        if (force_cpu_type == arch_perfmon && cpu_has_arch_perfmon)
                return 0;
        /*
@@ -679,6 +691,9 @@ int __init op_nmi_init(struct oprofile_operations *ops)
        if (!cpu_has_apic)
                return -ENODEV;
+        if (force_cpu_type == timer)
+                return -ENODEV;
        switch (vendor) {
        case X86_VENDOR_AMD:
                /* Needs to be at least an Athlon (or hammer in 32bit mode) */
diff --git a/arch/x86/oprofile/nmi_timer_int.c b/arch/x86/oprofile/nmi_timer_int.c
deleted file mode 100644
index 7f8052cd6620..000000000000
--- a/arch/x86/oprofile/nmi_timer_int.c
+++ /dev/null
@@ -1,50 +0,0 @@
-/**
- * @file nmi_timer_int.c
- *
- * @remark Copyright 2003 OProfile authors
- * @remark Read the file COPYING
- *
- * @author Zwane Mwaikambo <zwane@linuxpower.ca>
- */
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/errno.h>
-#include <linux/oprofile.h>
-#include <linux/rcupdate.h>
-#include <linux/kdebug.h>
-#include <asm/nmi.h>
-#include <asm/apic.h>
-#include <asm/ptrace.h>
-static int profile_timer_exceptions_notify(unsigned int val, struct pt_regs *regs)
-{
-        oprofile_add_sample(regs, 0);
-        return NMI_HANDLED;
-}
-static int timer_start(void)
-{
-        if (register_nmi_handler(NMI_LOCAL, profile_timer_exceptions_notify,
-                                        0, "oprofile-timer"))
-                return 1;
-        return 0;
-}
-static void timer_stop(void)
-{
-        unregister_nmi_handler(NMI_LOCAL, "oprofile-timer");
-        synchronize_sched();  /* Allow already-started NMIs to complete. */
-}
-int __init op_nmi_timer_init(struct oprofile_operations *ops)
-{
-        ops->start = timer_start;
-        ops->stop = timer_stop;
-        ops->cpu_type = "timer";
-        printk(KERN_INFO "oprofile: using NMI timer interrupt.\n");
-        return 0;
-}
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 37718f0f053d..4a01967f02e7 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -352,8 +352,7 @@ void __init efi_memblock_x86_reserve_range(void)
                boot_params.efi_info.efi_memdesc_size;
        memmap.desc_version = boot_params.efi_info.efi_memdesc_version;
        memmap.desc_size = boot_params.efi_info.efi_memdesc_size;
-        memblock_x86_reserve_range(pmap, pmap + memmap.nr_map * memmap.desc_size,
+        memblock_reserve(pmap, memmap.nr_map * memmap.desc_size);
-                      "EFI memmap");
 }
 #if EFI_DEBUG
@@ -397,16 +396,14 @@ void __init efi_reserve_boot_services(void)
                if ((start+size >= virt_to_phys(_text)
                                && start <= virt_to_phys(_end)) ||
                        !e820_all_mapped(start, start+size, E820_RAM) ||
-                        memblock_x86_check_reserved_size(&start, &size,
+                        memblock_is_region_reserved(start, size)) {
-                                                        1<<EFI_PAGE_SHIFT)) {
                        /* Could not reserve, skip it */
                        md->num_pages = 0;
                        memblock_dbg(PFX "Could not reserve boot range "
                                        "[0x%010llx-0x%010llx]\n",
                                                start, start+size-1);
                } else
-                        memblock_x86_reserve_range(start, start+size,
+                        memblock_reserve(start, size);
-                                                        "EFI Boot");
        }
 }
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index e36bf714cb77..40e446941dd7 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -39,43 +39,14 @@
 */
 static unsigned long efi_rt_eflags;
-static pgd_t efi_bak_pg_dir_pointer[2];
 void efi_call_phys_prelog(void)
 {
-        unsigned long cr4;
-        unsigned long temp;
        struct desc_ptr gdt_descr;
        local_irq_save(efi_rt_eflags);
-        /*
+        load_cr3(initial_page_table);
-         * If I don't have PAE, I should just duplicate two entries in page
-         * directory. If I have PAE, I just need to duplicate one entry in
-         * page directory.
-         */
-        cr4 = read_cr4_safe();
-        if (cr4 & X86_CR4_PAE) {
-                efi_bak_pg_dir_pointer[0].pgd =
-                    swapper_pg_dir[pgd_index(0)].pgd;
-                swapper_pg_dir[0].pgd =
-                    swapper_pg_dir[pgd_index(PAGE_OFFSET)].pgd;
-        } else {
-                efi_bak_pg_dir_pointer[0].pgd =
-                    swapper_pg_dir[pgd_index(0)].pgd;
-                efi_bak_pg_dir_pointer[1].pgd =
-                    swapper_pg_dir[pgd_index(0x400000)].pgd;
-                swapper_pg_dir[pgd_index(0)].pgd =
-                    swapper_pg_dir[pgd_index(PAGE_OFFSET)].pgd;
-                temp = PAGE_OFFSET + 0x400000;
-                swapper_pg_dir[pgd_index(0x400000)].pgd =
-                    swapper_pg_dir[pgd_index(temp)].pgd;
-        }
-        /*
-         * After the lock is released, the original page table is restored.
-         */
        __flush_tlb_all();
        gdt_descr.address = __pa(get_cpu_gdt_table(0));
@@ -85,28 +56,13 @@ void efi_call_phys_prelog(void)
 void efi_call_phys_epilog(void)
 {
-        unsigned long cr4;
        struct desc_ptr gdt_descr;
        gdt_descr.address = (unsigned long)get_cpu_gdt_table(0);
        gdt_descr.size = GDT_SIZE - 1;
        load_gdt(&gdt_descr);
-        cr4 = read_cr4_safe();
+        load_cr3(swapper_pg_dir);
-        if (cr4 & X86_CR4_PAE) {
-                swapper_pg_dir[pgd_index(0)].pgd =
-                    efi_bak_pg_dir_pointer[0].pgd;
-        } else {
-                swapper_pg_dir[pgd_index(0)].pgd =
-                    efi_bak_pg_dir_pointer[0].pgd;
-                swapper_pg_dir[pgd_index(0x400000)].pgd =
-                    efi_bak_pg_dir_pointer[1].pgd;
-        }
-        /*
-         * After the lock is released, the original page table is restored.
-         */
        __flush_tlb_all();
        local_irq_restore(efi_rt_eflags);
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index b1489a06a49d..ad4ec1cb097e 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -76,6 +76,20 @@ struct sfi_rtc_table_entry sfi_mrtc_array[SFI_MRTC_MAX];
 EXPORT_SYMBOL_GPL(sfi_mrtc_array);
 int sfi_mrtc_num;
+static void mrst_power_off(void)
+{
+        if (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT)
+                intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 1);
+}
+static void mrst_reboot(void)
+{
+        if (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT)
+                intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0);
+        else
+                intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0);
+}
 /* parse all the mtimer info to a static mtimer array */
 static int __init sfi_parse_mtmr(struct sfi_table_header *table)
 {
@@ -265,17 +279,6 @@ static int mrst_i8042_detect(void)
        return 0;
 }
-/* Reboot and power off are handled by the SCU on a MID device */
-static void mrst_power_off(void)
-{
-        intel_scu_ipc_simple_command(0xf1, 1);
-}
-static void mrst_reboot(void)
-{
-        intel_scu_ipc_simple_command(0xf1, 0);
-}
 /*
 * Moorestown does not have external NMI source nor port 0x61 to report
 * NMI status. The possible NMI sources are from pmu as a result of NMI
@@ -484,6 +487,46 @@ static void __init *max7315_platform_data(void *info)
        return max7315;
 }
+static void *tca6416_platform_data(void *info)
+{
+        static struct pca953x_platform_data tca6416;
+        struct i2c_board_info *i2c_info = info;
+        int gpio_base, intr;
+        char base_pin_name[SFI_NAME_LEN + 1];
+        char intr_pin_name[SFI_NAME_LEN + 1];
+        strcpy(i2c_info->type, "tca6416");
+        strcpy(base_pin_name, "tca6416_base");
+        strcpy(intr_pin_name, "tca6416_int");
+        gpio_base = get_gpio_by_name(base_pin_name);
+        intr = get_gpio_by_name(intr_pin_name);
+        if (gpio_base == -1)
+                return NULL;
+        tca6416.gpio_base = gpio_base;
+        if (intr != -1) {
+                i2c_info->irq = intr + MRST_IRQ_OFFSET;
+                tca6416.irq_base = gpio_base + MRST_IRQ_OFFSET;
+        } else {
+                i2c_info->irq = -1;
+                tca6416.irq_base = -1;
+        }
+        return &tca6416;
+}
+static void *mpu3050_platform_data(void *info)
+{
+        struct i2c_board_info *i2c_info = info;
+        int intr = get_gpio_by_name("mpu3050_int");
+        if (intr == -1)
+                return NULL;
+        i2c_info->irq = intr + MRST_IRQ_OFFSET;
+        return NULL;
+}
 static void __init *emc1403_platform_data(void *info)
 {
        static short intr2nd_pdata;
@@ -646,12 +689,15 @@ static void *msic_ocd_platform_data(void *info)
 static const struct devs_id __initconst device_ids[] = {
        {"bma023", SFI_DEV_TYPE_I2C, 1, &no_platform_data},
        {"pmic_gpio", SFI_DEV_TYPE_SPI, 1, &pmic_gpio_platform_data},
+        {"pmic_gpio", SFI_DEV_TYPE_IPC, 1, &pmic_gpio_platform_data},
        {"spi_max3111", SFI_DEV_TYPE_SPI, 0, &max3111_platform_data},
        {"i2c_max7315", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data},
        {"i2c_max7315_2", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data},
+        {"tca6416", SFI_DEV_TYPE_I2C, 1, &tca6416_platform_data},
        {"emc1403", SFI_DEV_TYPE_I2C, 1, &emc1403_platform_data},
        {"i2c_accel", SFI_DEV_TYPE_I2C, 0, &lis331dl_platform_data},
        {"pmic_audio", SFI_DEV_TYPE_IPC, 1, &no_platform_data},
+        {"mpu3050", SFI_DEV_TYPE_I2C, 1, &mpu3050_platform_data},
        /* MSIC subdevices */
        {"msic_battery", SFI_DEV_TYPE_IPC, 1, &msic_battery_platform_data},
diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
index f82082677337..d511aa97533a 100644
--- a/arch/x86/tools/Makefile
+++ b/arch/x86/tools/Makefile
@@ -18,14 +18,21 @@ chkobjdump = $(srctree)/arch/x86/tools/chkobjdump.awk
 quiet_cmd_posttest = TEST    $@
      cmd_posttest = ($(OBJDUMP) -v | $(AWK) -f $(chkobjdump)) || $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(distill_awk) | $(obj)/test_get_len $(posttest_64bit) $(posttest_verbose)
-posttest: $(obj)/test_get_len vmlinux
+quiet_cmd_sanitytest = TEST    $@
+      cmd_sanitytest = $(obj)/insn_sanity $(posttest_64bit) -m 1000000
+posttest: $(obj)/test_get_len vmlinux $(obj)/insn_sanity
        $(call cmd,posttest)
+        $(call cmd,sanitytest)
-hostprogs-y     := test_get_len
+hostprogs-y     += test_get_len insn_sanity
 # -I needed for generated C source and C source which in the kernel tree.
 HOSTCFLAGS_test_get_len.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/
+HOSTCFLAGS_insn_sanity.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/
 # Dependencies are also needed.
 $(obj)/test_get_len.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
+$(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index eaf11f52fc0b..5f6a5b6c3a15 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -47,7 +47,7 @@ BEGIN {
        sep_expr = "^\\|$"
        group_expr = "^Grp[0-9A-Za-z]+"
-        imm_expr = "^[IJAO][a-z]"
+        imm_expr = "^[IJAOL][a-z]"
        imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
        imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
        imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)"
@@ -59,6 +59,7 @@ BEGIN {
        imm_flag["Iv"] = "INAT_MAKE_IMM(INAT_IMM_VWORD)"
        imm_flag["Ob"] = "INAT_MOFFSET"
        imm_flag["Ov"] = "INAT_MOFFSET"
+        imm_flag["Lx"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
        modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
        force64_expr = "\\([df]64\\)"
@@ -70,8 +71,12 @@ BEGIN {
        lprefix3_expr = "\\(F2\\)"
        max_lprefix = 4
-        vexok_expr = "\\(VEX\\)"
+        # All opcodes starting with lower-case 'v' or with (v1) superscript
-        vexonly_expr = "\\(oVEX\\)"
+        # accepts VEX prefix
+        vexok_opcode_expr = "^v.*"
+        vexok_expr = "\\(v1\\)"
+        # All opcodes with (v) superscript supports *only* VEX prefix
+        vexonly_expr = "\\(v\\)"
        prefix_expr = "\\(Prefix\\)"
        prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
@@ -85,8 +90,8 @@ BEGIN {
        prefix_num["SEG=GS"] = "INAT_PFX_GS"
        prefix_num["SEG=SS"] = "INAT_PFX_SS"
        prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
-        prefix_num["2bytes-VEX"] = "INAT_PFX_VEX2"
+        prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
-        prefix_num["3bytes-VEX"] = "INAT_PFX_VEX3"
+        prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
        clear_vars()
 }
@@ -310,12 +315,10 @@ function convert_operands(count,opnd,       i,j,imm,mod)
                if (match(opcode, fpu_expr))
                        flags = add_flags(flags, "INAT_MODRM")
-                # check VEX only code
+                # check VEX codes
                if (match(ext, vexonly_expr))
                        flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
+                else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
-                # check VEX only code
-                if (match(ext, vexok_expr))
                        flags = add_flags(flags, "INAT_VEXOK")
                # check prefixes
diff --git a/arch/x86/tools/insn_sanity.c b/arch/x86/tools/insn_sanity.c
new file mode 100644
index 000000000000..cc2f8c131286
--- /dev/null
+++ b/arch/x86/tools/insn_sanity.c
@@ -0,0 +1,275 @@
+/*
+ * x86 decoder sanity test - based on test_get_insn.c
+ *
+ * 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.
+ *
+ * Copyright (C) IBM Corporation, 2009
+ * Copyright (C) Hitachi, Ltd., 2011
+ */
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <assert.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#define unlikely(cond) (cond)
+#define ARRAY_SIZE(a)   (sizeof(a)/sizeof(a[0]))
+#include <asm/insn.h>
+#include <inat.c>
+#include <insn.c>
+/*
+ * Test of instruction analysis against tampering.
+ * Feed random binary to instruction decoder and ensure not to
+ * access out-of-instruction-buffer.
+ */
+#define DEFAULT_MAX_ITER        10000
+#define INSN_NOP 0x90
+static const char       *prog;          /* Program name */
+static int              verbose;        /* Verbosity */
+static int              x86_64;         /* x86-64 bit mode flag */
+static unsigned int     seed;           /* Random seed */
+static unsigned long    iter_start;     /* Start of iteration number */
+static unsigned long    iter_end = DEFAULT_MAX_ITER;    /* End of iteration number */
+static FILE             *input_file;    /* Input file name */
+static void usage(const char *err)
+{
+        if (err)
+                fprintf(stderr, "Error: %s\n\n", err);
+        fprintf(stderr, "Usage: %s [-y|-n|-v] [-s seed[,no]] [-m max] [-i input]\n", prog);
+        fprintf(stderr, "\t-y   64bit mode\n");
+        fprintf(stderr, "\t-n   32bit mode\n");
+        fprintf(stderr, "\t-v   Verbosity(-vv dumps any decoded result)\n");
+        fprintf(stderr, "\t-s   Give a random seed (and iteration number)\n");
+        fprintf(stderr, "\t-m   Give a maximum iteration number\n");
+        fprintf(stderr, "\t-i   Give an input file with decoded binary\n");
+        exit(1);
+}
+static void dump_field(FILE *fp, const char *name, const char *indent,
+                       struct insn_field *field)
+{
+        fprintf(fp, "%s.%s = {\n", indent, name);
+        fprintf(fp, "%s\t.value = %d, bytes[] = {%x, %x, %x, %x},\n",
+                indent, field->value, field->bytes[0], field->bytes[1],
+                field->bytes[2], field->bytes[3]);
+        fprintf(fp, "%s\t.got = %d, .nbytes = %d},\n", indent,
+                field->got, field->nbytes);
+}
+static void dump_insn(FILE *fp, struct insn *insn)
+{
+        fprintf(fp, "Instruction = {\n");
+        dump_field(fp, "prefixes", "\t",        &insn->prefixes);
+        dump_field(fp, "rex_prefix", "\t",      &insn->rex_prefix);
+        dump_field(fp, "vex_prefix", "\t",      &insn->vex_prefix);
+        dump_field(fp, "opcode", "\t",          &insn->opcode);
+        dump_field(fp, "modrm", "\t",           &insn->modrm);
+        dump_field(fp, "sib", "\t",             &insn->sib);
+        dump_field(fp, "displacement", "\t",    &insn->displacement);
+        dump_field(fp, "immediate1", "\t",      &insn->immediate1);
+        dump_field(fp, "immediate2", "\t",      &insn->immediate2);
+        fprintf(fp, "\t.attr = %x, .opnd_bytes = %d, .addr_bytes = %d,\n",
+                insn->attr, insn->opnd_bytes, insn->addr_bytes);
+        fprintf(fp, "\t.length = %d, .x86_64 = %d, .kaddr = %p}\n",
+                insn->length, insn->x86_64, insn->kaddr);
+}
+static void dump_stream(FILE *fp, const char *msg, unsigned long nr_iter,
+                        unsigned char *insn_buf, struct insn *insn)
+{
+        int i;
+        fprintf(fp, "%s:\n", msg);
+        dump_insn(fp, insn);
+        fprintf(fp, "You can reproduce this with below command(s);\n");
+        /* Input a decoded instruction sequence directly */
+        fprintf(fp, " $ echo ");
+        for (i = 0; i < MAX_INSN_SIZE; i++)
+                fprintf(fp, " %02x", insn_buf[i]);
+        fprintf(fp, " | %s -i -\n", prog);
+        if (!input_file) {
+                fprintf(fp, "Or \n");
+                /* Give a seed and iteration number */
+                fprintf(fp, " $ %s -s 0x%x,%lu\n", prog, seed, nr_iter);
+        }
+}
+static void init_random_seed(void)
+{
+        int fd;
+        fd = open("/dev/urandom", O_RDONLY);
+        if (fd < 0)
+                goto fail;
+        if (read(fd, &seed, sizeof(seed)) != sizeof(seed))
+                goto fail;
+        close(fd);
+        return;
+fail:
+        usage("Failed to open /dev/urandom");
+}
+/* Read given instruction sequence from the input file */
+static int read_next_insn(unsigned char *insn_buf)
+{
+        char buf[256]  = "", *tmp;
+        int i;
+        tmp = fgets(buf, ARRAY_SIZE(buf), input_file);
+        if (tmp == NULL || feof(input_file))
+                return 0;
+        for (i = 0; i < MAX_INSN_SIZE; i++) {
+                insn_buf[i] = (unsigned char)strtoul(tmp, &tmp, 16);
+                if (*tmp != ' ')
+                        break;
+        }
+        return i;
+}
+static int generate_insn(unsigned char *insn_buf)
+{
+        int i;
+        if (input_file)
+                return read_next_insn(insn_buf);
+        /* Fills buffer with random binary up to MAX_INSN_SIZE */
+        for (i = 0; i < MAX_INSN_SIZE - 1; i += 2)
+                *(unsigned short *)(&insn_buf[i]) = random() & 0xffff;
+        while (i < MAX_INSN_SIZE)
+                insn_buf[i++] = random() & 0xff;
+        return i;
+}
+static void parse_args(int argc, char **argv)
+{
+        int c;
+        char *tmp = NULL;
+        int set_seed = 0;
+        prog = argv[0];
+        while ((c = getopt(argc, argv, "ynvs:m:i:")) != -1) {
+                switch (c) {
+                case 'y':
+                        x86_64 = 1;
+                        break;
+                case 'n':
+                        x86_64 = 0;
+                        break;
+                case 'v':
+                        verbose++;
+                        break;
+                case 'i':
+                        if (strcmp("-", optarg) == 0)
+                                input_file = stdin;
+                        else
+                                input_file = fopen(optarg, "r");
+                        if (!input_file)
+                                usage("Failed to open input file");
+                        break;
+                case 's':
+                        seed = (unsigned int)strtoul(optarg, &tmp, 0);
+                        if (*tmp == ',') {
+                                optarg = tmp + 1;
+                                iter_start = strtoul(optarg, &tmp, 0);
+                        }
+                        if (*tmp != '\0' || tmp == optarg)
+                                usage("Failed to parse seed");
+                        set_seed = 1;
+                        break;
+                case 'm':
+                        iter_end = strtoul(optarg, &tmp, 0);
+                        if (*tmp != '\0' || tmp == optarg)
+                                usage("Failed to parse max_iter");
+                        break;
+                default:
+                        usage(NULL);
+                }
+        }
+        /* Check errors */
+        if (iter_end < iter_start)
+                usage("Max iteration number must be bigger than iter-num");
+        if (set_seed && input_file)
+                usage("Don't use input file (-i) with random seed (-s)");
+        /* Initialize random seed */
+        if (!input_file) {
+                if (!set_seed)  /* No seed is given */
+                        init_random_seed();
+                srand(seed);
+        }
+}
+int main(int argc, char **argv)
+{
+        struct insn insn;
+        int insns = 0;
+        int errors = 0;
+        unsigned long i;
+        unsigned char insn_buf[MAX_INSN_SIZE * 2];
+        parse_args(argc, argv);
+        /* Prepare stop bytes with NOPs */
+        memset(insn_buf + MAX_INSN_SIZE, INSN_NOP, MAX_INSN_SIZE);
+        for (i = 0; i < iter_end; i++) {
+                if (generate_insn(insn_buf) <= 0)
+                        break;
+                if (i < iter_start)     /* Skip to given iteration number */
+                        continue;
+                /* Decode an instruction */
+                insn_init(&insn, insn_buf, x86_64);
+                insn_get_length(&insn);
+                if (insn.next_byte <= insn.kaddr ||
+                    insn.kaddr + MAX_INSN_SIZE < insn.next_byte) {
+                        /* Access out-of-range memory */
+                        dump_stream(stderr, "Error: Found an access violation", i, insn_buf, &insn);
+                        errors++;
+                } else if (verbose && !insn_complete(&insn))
+                        dump_stream(stdout, "Info: Found an undecodable input", i, insn_buf, &insn);
+                else if (verbose >= 2)
+                        dump_insn(stdout, &insn);
+                insns++;
+        }
+        fprintf(stdout, "%s: decoded and checked %d %s instructions with %d errors (seed:0x%x)\n", (errors) ? "Failure" : "Success", insns, (input_file) ? "given" : "random", errors, seed);
+        return errors ? 1 : 0;
+}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 1f928659c338..12eb07bfb267 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1215,8 +1215,6 @@ asmlinkage void __init xen_start_kernel(void)
        local_irq_disable();
        early_boot_irqs_disabled = true;
-        memblock_init();
        xen_raw_console_write("mapping kernel into physical memory\n");
        pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
        xen_ident_map_ISA();
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 87f6673b1207..f4bf8aa574f4 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1774,10 +1774,8 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
        __xen_write_cr3(true, __pa(pgd));
        xen_mc_issue(PARAVIRT_LAZY_CPU);
-        memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
+        memblock_reserve(__pa(xen_start_info->pt_base),
-                      __pa(xen_start_info->pt_base +
+                         xen_start_info->nr_pt_frames * PAGE_SIZE);
-                           xen_start_info->nr_pt_frames * PAGE_SIZE),
-                      "XEN PAGETABLES");
        return pgd;
 }
@@ -1853,10 +1851,8 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
                          PFN_DOWN(__pa(initial_page_table)));
        xen_write_cr3(__pa(initial_page_table));
-        memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
+        memblock_reserve(__pa(xen_start_info->pt_base),
-                      __pa(xen_start_info->pt_base +
+                         xen_start_info->nr_pt_frames * PAGE_SIZE));
-                           xen_start_info->nr_pt_frames * PAGE_SIZE),
-                      "XEN PAGETABLES");
        return initial_page_table;
 }
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 1093f80c162d..e03c63692176 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -75,7 +75,7 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
        if (i == XEN_EXTRA_MEM_MAX_REGIONS)
                printk(KERN_WARNING "Warning: not enough extra memory regions\n");
-        memblock_x86_reserve_range(start, start + size, "XEN EXTRA");
+        memblock_reserve(start, size);
        xen_max_p2m_pfn = PFN_DOWN(start + size);
@@ -173,9 +173,21 @@ static unsigned long __init xen_get_max_pages(void)
        domid_t domid = DOMID_SELF;
        int ret;
-        ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid);
+        /*
-        if (ret > 0)
+         * For the initial domain we use the maximum reservation as
-                max_pages = ret;
+         * the maximum page.
+         *
+         * For guest domains the current maximum reservation reflects
+         * the current maximum rather than the static maximum. In this
+         * case the e820 map provided to us will cover the static
+         * maximum region.
+         */
+        if (xen_initial_domain()) {
+                ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid);
+                if (ret > 0)
+                        max_pages = ret;
+        }
        return min(max_pages, MAX_DOMAIN_PAGES);
 }
@@ -299,9 +311,8 @@ char * __init xen_memory_setup(void)
         *  - xen_start_info
         * See comment above "struct start_info" in <xen/interface/xen.h>
         */
-        memblock_x86_reserve_range(__pa(xen_start_info->mfn_list),
+        memblock_reserve(__pa(xen_start_info->mfn_list),
-                      __pa(xen_start_info->pt_base),
+                         xen_start_info->pt_base - xen_start_info->mfn_list);
-                        "XEN START INFO");
        sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index f3e5eb43f71c..ac62f9cf1e10 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -41,14 +41,6 @@ static struct clocksource ccount_clocksource = {
        .rating = 200,
        .read = ccount_read,
        .mask = CLOCKSOURCE_MASK(32),
-        /*
-         * With a shift of 22 the lower limit of the cpu clock is
-         * 1MHz, where NSEC_PER_CCOUNT is 1000 or a bit less than
-         * 2^10: Since we have 32 bits and the multiplicator can
-         * already take up as much as 10 bits, this leaves us with
-         * remaining upper 22 bits.
-         */
-        .shift = 22,
 };
 static irqreturn_t timer_interrupt(int irq, void *dev_id);
@@ -66,10 +58,7 @@ void __init time_init(void)
        printk("%d.%02d MHz\n", (int)ccount_per_jiffy/(1000000/HZ),
                        (int)(ccount_per_jiffy/(10000/HZ))%100);
 #endif
-        ccount_clocksource.mult =
+        clocksource_register_hz(&ccount_clocksource, CCOUNT_PER_JIFFY * HZ);
-                clocksource_hz2mult(CCOUNT_PER_JIFFY * HZ,
-                                ccount_clocksource.shift);
-        clocksource_register(&ccount_clocksource);
        /* Initialize the linux timer interrupt. */