55 files changed, 1248 insertions, 1070 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index efb42949cc09..67d6af3581bc 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
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/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/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/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 X86_PMC_IDX_FIXED_INSTRUCTIONS                  (X86_PMC_IDX_FIXED + 0)
+#define MSR_ARCH_PERFMON_FIXED_CTR0     0x309
+#define X86_PMC_IDX_FIXED_INSTRUCTIONS  (X86_PMC_IDX_FIXED + 0)
 
 /* CPU_CLK_Unhalted.Core: */
-#define MSR_ARCH_PERFMON_FIXED_CTR1                     0x30a
-#define X86_PMC_IDX_FIXED_CPU_CYCLES                    (X86_PMC_IDX_FIXED + 1)
+#define MSR_ARCH_PERFMON_FIXED_CTR1     0x30a
+#define X86_PMC_IDX_FIXED_CPU_CYCLES    (X86_PMC_IDX_FIXED + 1)
 
 /* CPU_CLK_Unhalted.Ref: */
-#define MSR_ARCH_PERFMON_FIXED_CTR2                     0x30b
-#define X86_PMC_IDX_FIXED_BUS_CYCLES                    (X86_PMC_IDX_FIXED + 2)
+#define MSR_ARCH_PERFMON_FIXED_CTR2     0x30b
+#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/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 f98d84caf94c..2cd2d93643dc 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -876,8 +876,8 @@ 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();
 
@@ -1809,8 +1809,8 @@ 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...
@@ -1846,8 +1846,8 @@ 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 6d939d7847e2..898055585516 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/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) {
-                u64 size;
-                addr = memblock_x86_find_in_range_size(addr, &size, PAGE_SIZE);
+        for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) {
+                start = clamp_t(phys_addr_t, round_up(start, 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)
-                        break;
-
-                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++;
+                memblock_reserve(start, end - start);
+                scan_areas[num_scan_areas].addr = start;
+                scan_areas[num_scan_areas].size = end - start;
 
                 /* 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/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2bda212a0010..5adce1040b11 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -484,18 +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);
         }
 
         /*
@@ -521,60 +698,12 @@ 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;
+        /* slow path */
+        if (i != n)
+                num = perf_assign_events(constraints, n, wmin, wmax, assign);
 
         /*
-         * 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) {
-                                if (!test_bit(j, used_mask))
-                                        break;
-                        }
-
-                        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
          */
@@ -1119,6 +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;
 
@@ -1147,8 +1277,8 @@ static int __init init_hw_perf_events(void)
 
         pr_cont("%s PMU driver.\n", x86_pmu.name);
 
-        if (x86_pmu.quirks)
-                x86_pmu.quirks();
+        for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next)
+                quirk->func();
 
         if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) {
                 WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
@@ -1171,12 +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;
@@ -1566,3 +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_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 8d601b18bf9f..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 */
-        /*
-         * 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 */
+        FIXED_EVENT_CONSTRAINT(0x0300, 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:
@@ -1545,19 +1541,60 @@ static void intel_clovertown_quirks(void)
         x86_pmu.pebs_constraints = NULL;
 }
 
-static void intel_sandybridge_quirks(void)
+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)) {
@@ -1574,8 +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);
-        if (eax.split.mask_length <= ARCH_PERFMON_BRANCH_MISSES_RETIRED)
+        cpuid(10, &eax.full, &ebx.full, &unused, &edx.full);
+        if (eax.split.mask_length < ARCH_PERFMON_EVENTS_COUNT)
                 return -ENODEV;
 
         version = eax.split.version_id;
@@ -1589,6 +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:
@@ -1608,6 +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:
          */
@@ -1617,7 +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" */
@@ -1651,17 +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) {
-                        /*
-                         * 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;
+                x86_add_quirk(intel_nehalem_quirk);
 
-                        pr_cont("erratum AAJ80 worked around, ");
-                }
                 pr_cont("Nehalem events, ");
                 break;
 
@@ -1701,7 +1734,7 @@ __init int intel_pmu_init(void)
                 break;
 
         case 42: /* SandyBridge */
-                x86_pmu.quirks = intel_sandybridge_quirks;
+                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));
@@ -1738,5 +1771,6 @@ __init int intel_pmu_init(void)
                         break;
                 }
         }
+
         return 0;
 }
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) {
-                start = memblock_x86_find_in_range_size(start, &size, align);
-                if (start == MEMBLOCK_ERROR)
-                        return 0;
-                if (size >= sizet)
-                        break;
+        addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
+        if (addr) {
+                e820_update_range_saved(addr, size, E820_RAM, E820_RESERVED);
+                printk(KERN_INFO "update e820_saved for early_reserve_e820\n");
+                update_e820_saved();
         }
 
-#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 mem_size_pfn;
+        u64 nr_pages = 0, nr_free_pages = 0;
+        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;
-        free_size_pfn = memblock_x86_free_memory_in_range(0, MAX_DMA_PFN << PAGE_SHIFT) >> PAGE_SHIFT;
-        set_dma_reserve(mem_size_pfn - free_size_pfn);
+        for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
+                start_pfn = min_t(unsigned long, start_pfn, MAX_DMA_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_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
+        memblock_reserve(__pa_symbol(&_text),
+                         __pa_symbol(&__bss_stop) - __pa_symbol(&_text));
 
 #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_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
+        memblock_reserve(__pa_symbol(&_text),
+                         __pa_symbol(&__bss_stop) - __pa_symbol(&_text));
 
 #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/irq.c b/arch/x86/kernel/irq.c
index 429e0c92924e..5d31e5bdbf85 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -181,8 +181,8 @@ 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]);
 
@@ -209,10 +209,10 @@ 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/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/mpparse.c b/arch/x86/kernel/mpparse.c
index 0741b062a304..ca470e4c92dc 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -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_x86_reserve_range(mpf->physptr, mpf->physptr+size, "* MP-table mpc");
+        memblock_reserve(mpf->physptr, get_mpc_size(mpf->physptr));
 }
 
 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) {
-                u64 startt = 0;
-                mpc_new_phys = early_reserve_e820(startt, mpc_new_length, 4);
-        }
+        if (enable_update_mptable && alloc_mptable)
+                mpc_new_phys = early_reserve_e820(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/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_x86_reserve_range(pa_data, pa_data+sizeof(*data)+data->len, buf);
+                memblock_reserve(pa_data, sizeof(*data) + data->len);
                 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/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 &&
-                best->function == 0x1) {
-                best->ecx |= bit(X86_FEATURE_TSC_DEADLINE_TIMER);
-                timer_mode_mask = 3 << 17;
-        } else
-                timer_mode_mask = 1 << 17;
-
-        if (apic)
-                apic->lapic_timer.timer_mode_mask = timer_mode_mask;
+        if (apic) {
+                if (best->ecx & bit(X86_FEATURE_TSC_DEADLINE_TIMER))
+                        apic->lapic_timer.timer_mode_mask = 3 << 17;
+                else
+                        apic->lapic_timer.timer_mode_mask = 1 << 17;
+        }
 }
 
 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.
-#  (oVEX): this opcode requires VEX prefix.
-#  (o128): this opcode only supports 128bit VEX.
-#  (o256): this opcode only supports 256bit VEX.
+#  (v): this opcode requires VEX prefix.
+#  (v1): this opcode only supports 128bit 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
-a5: MOVS/W/D/Q Xv,Yv
+a4: MOVS/B Yb,Xb
+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)
-c5: LDS Gz,Mp (i64) | 2bytes-VEX (Prefix)
+c4: LES Gz,Mp (i64) | VEX+2byte (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)
-11: movups Wps,Vps (VEX) | movss Wss,Vss (F3),(VEX),(o128) | movupd Wpd,Vpd (66),(VEX) | movsd Wsd,Vsd (F2),(VEX),(o128)
-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)
-13: mpvlps Mq,Vq (VEX),(o128) | movlpd Mq,Vq (66),(VEX),(o128)
-14: unpcklps Vps,Wq (VEX) | unpcklpd Vpd,Wq (66),(VEX)
-15: unpckhps Vps,Wq (VEX) | unpckhpd Vpd,Wq (66),(VEX)
-16: movhps Vq,Mq (VEX),(o128) | movhpd Vq,Mq (66),(VEX),(o128) | movlsps Vq,Uq (VEX),(o128) | movshdup Vq,Wq (F3),(VEX)
-17: movhps Mq,Vq (VEX),(o128) | movhpd Mq,Vq (66),(VEX),(o128)
+# NOTE: According to Intel SDM opcode map, vmovups and vmovupd has no operands
+# but it actually has operands. And also, vmovss and vmovsd only accept 128bit.
+# MOVSS/MOVSD has too many forms(3) on SDM. This map just shows a typical form.
+# Many AVX instructions lack v1 superscript, according to Intel AVX-Prgramming
+# Reference A.1
+10: vmovups Vps,Wps | vmovupd Vpd,Wpd (66) | vmovss Vx,Hx,Wss (F3),(v1) | vmovsd Vx,Hx,Wsd (F2),(v1)
+11: vmovups Wps,Vps | vmovupd Wpd,Vpd (66) | vmovss Wss,Hx,Vss (F3),(v1) | vmovsd Wsd,Hx,Vsd (F2),(v1)
+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)
-29: movaps Wps,Vps (VEX) | movapd Wpd,Vpd (66),(VEX)
-2a: cvtpi2ps Vps,Qpi | cvtsi2ss Vss,Ed/q (F3),(VEX),(o128) | cvtpi2pd Vpd,Qpi (66) | cvtsi2sd Vsd,Ed/q (F2),(VEX),(o128)
-2b: movntps Mps,Vps (VEX) | movntpd Mpd,Vpd (66),(VEX)
-2c: cvttps2pi Ppi,Wps | cvttss2si  Gd/q,Wss (F3),(VEX),(o128) | cvttpd2pi Ppi,Wpd (66) | cvttsd2si Gd/q,Wsd (F2),(VEX),(o128)
-2d: cvtps2pi Ppi,Wps | cvtss2si Gd/q,Wss (F3),(VEX),(o128) | cvtpd2pi Qpi,Wpd (66) | cvtsd2si Gd/q,Wsd (F2),(VEX),(o128)
-2e: ucomiss Vss,Wss (VEX),(o128) | ucomisd  Vsd,Wsd (66),(VEX),(o128)
-2f: comiss Vss,Wss (VEX),(o128) | comisd  Vsd,Wsd (66),(VEX),(o128)
+28: vmovaps Vps,Wps | vmovapd Vpd,Wpd (66)
+29: vmovaps Wps,Vps | vmovapd Wpd,Vpd (66)
+2a: cvtpi2ps Vps,Qpi | cvtpi2pd Vpd,Qpi (66) | vcvtsi2ss Vss,Hss,Ey (F3),(v1) | vcvtsi2sd Vsd,Hsd,Ey (F2),(v1)
+2b: vmovntps Mps,Vps | vmovntpd Mpd,Vpd (66)
+2c: cvttps2pi Ppi,Wps | cvttpd2pi Ppi,Wpd (66) | vcvttss2si Gy,Wss (F3),(v1) | vcvttsd2si Gy,Wsd (F2),(v1)
+2d: cvtps2pi Ppi,Wps | cvtpd2pi Qpi,Wpd (66) | vcvtss2si Gy,Wss (F3),(v1) | vcvtsd2si Gy,Wsd (F2),(v1)
+2e: vucomiss Vss,Wss (v1) | vucomisd  Vsd,Wsd (66),(v1)
+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)
-51: sqrtps Vps,Wps (VEX) | sqrtss Vss,Wss (F3),(VEX),(o128) | sqrtpd Vpd,Wpd (66),(VEX) | sqrtsd Vsd,Wsd (F2),(VEX),(o128)
-52: rsqrtps Vps,Wps (VEX) | rsqrtss Vss,Wss (F3),(VEX),(o128)
-53: rcpps Vps,Wps (VEX) | rcpss Vss,Wss (F3),(VEX),(o128)
-54: andps Vps,Wps (VEX) | andpd Vpd,Wpd (66),(VEX)
-55: andnps Vps,Wps (VEX) | andnpd Vpd,Wpd (66),(VEX)
-56: orps Vps,Wps (VEX) | orpd Vpd,Wpd (66),(VEX)
-57: xorps Vps,Wps (VEX) | xorpd Vpd,Wpd (66),(VEX)
-58: addps Vps,Wps (VEX) | addss Vss,Wss (F3),(VEX),(o128) | addpd Vpd,Wpd (66),(VEX) | addsd Vsd,Wsd (F2),(VEX),(o128)
-59: mulps Vps,Wps (VEX) | mulss Vss,Wss (F3),(VEX),(o128) | mulpd Vpd,Wpd (66),(VEX) | mulsd Vsd,Wsd (F2),(VEX),(o128)
-5a: cvtps2pd Vpd,Wps (VEX) | cvtss2sd Vsd,Wss (F3),(VEX),(o128) | cvtpd2ps Vps,Wpd (66),(VEX) | cvtsd2ss Vsd,Wsd (F2),(VEX),(o128)
-5b: cvtdq2ps Vps,Wdq (VEX) | cvtps2dq Vdq,Wps (66),(VEX) | cvttps2dq Vdq,Wps (F3),(VEX)
-5c: subps Vps,Wps (VEX) | subss Vss,Wss (F3),(VEX),(o128) | subpd Vpd,Wpd (66),(VEX) | subsd Vsd,Wsd (F2),(VEX),(o128)
-5d: minps Vps,Wps (VEX) | minss Vss,Wss (F3),(VEX),(o128) | minpd Vpd,Wpd (66),(VEX) | minsd Vsd,Wsd (F2),(VEX),(o128)
-5e: divps Vps,Wps (VEX) | divss Vss,Wss (F3),(VEX),(o128) | divpd Vpd,Wpd (66),(VEX) | divsd Vsd,Wsd (F2),(VEX),(o128)
-5f: maxps Vps,Wps (VEX) | maxss Vss,Wss (F3),(VEX),(o128) | maxpd Vpd,Wpd (66),(VEX) | maxsd Vsd,Wsd (F2),(VEX),(o128)
+50: vmovmskps Gy,Ups | vmovmskpd Gy,Upd (66)
+51: vsqrtps Vps,Wps | vsqrtpd Vpd,Wpd (66) | vsqrtss Vss,Hss,Wss (F3),(v1) | vsqrtsd Vsd,Hsd,Wsd (F2),(v1)
+52: vrsqrtps Vps,Wps | vrsqrtss Vss,Hss,Wss (F3),(v1)
+53: vrcpps Vps,Wps | vrcpss Vss,Hss,Wss (F3),(v1)
+54: vandps Vps,Hps,Wps | vandpd Vpd,Hpd,Wpd (66)
+55: vandnps Vps,Hps,Wps | vandnpd Vpd,Hpd,Wpd (66)
+56: vorps Vps,Hps,Wps | vorpd Vpd,Hpd,Wpd (66)
+57: vxorps Vps,Hps,Wps | vxorpd Vpd,Hpd,Wpd (66)
+58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
+59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
+5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
+5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
+5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
+5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
+5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
+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)
-61: punpcklwd Pq,Qd | punpcklwd Vdq,Wdq (66),(VEX),(o128)
-62: punpckldq Pq,Qd | punpckldq Vdq,Wdq (66),(VEX),(o128)
-63: packsswb Pq,Qq | packsswb Vdq,Wdq (66),(VEX),(o128)
-64: pcmpgtb Pq,Qq | pcmpgtb Vdq,Wdq (66),(VEX),(o128)
-65: pcmpgtw Pq,Qq | pcmpgtw Vdq,Wdq (66),(VEX),(o128)
-66: pcmpgtd Pq,Qq | pcmpgtd Vdq,Wdq (66),(VEX),(o128)
-67: packuswb Pq,Qq | packuswb Vdq,Wdq (66),(VEX),(o128)
-68: punpckhbw Pq,Qd | punpckhbw Vdq,Wdq (66),(VEX),(o128)
-69: punpckhwd Pq,Qd | punpckhwd Vdq,Wdq (66),(VEX),(o128)
-6a: punpckhdq Pq,Qd | punpckhdq Vdq,Wdq (66),(VEX),(o128)
-6b: packssdw Pq,Qd | packssdw Vdq,Wdq (66),(VEX),(o128)
-6c: punpcklqdq Vdq,Wdq (66),(VEX),(o128)
-6d: punpckhqdq Vdq,Wdq (66),(VEX),(o128)
-6e: movd/q/ Pd,Ed/q | movd/q Vdq,Ed/q (66),(VEX),(o128)
-6f: movq Pq,Qq | movdqa Vdq,Wdq (66),(VEX) | movdqu Vdq,Wdq (F3),(VEX)
+60: punpcklbw Pq,Qd | vpunpcklbw Vx,Hx,Wx (66),(v1)
+61: punpcklwd Pq,Qd | vpunpcklwd Vx,Hx,Wx (66),(v1)
+62: punpckldq Pq,Qd | vpunpckldq Vx,Hx,Wx (66),(v1)
+63: packsswb Pq,Qq | vpacksswb Vx,Hx,Wx (66),(v1)
+64: pcmpgtb Pq,Qq | vpcmpgtb Vx,Hx,Wx (66),(v1)
+65: pcmpgtw Pq,Qq | vpcmpgtw Vx,Hx,Wx (66),(v1)
+66: pcmpgtd Pq,Qq | vpcmpgtd Vx,Hx,Wx (66),(v1)
+67: packuswb Pq,Qq | vpackuswb Vx,Hx,Wx (66),(v1)
+68: punpckhbw Pq,Qd | vpunpckhbw Vx,Hx,Wx (66),(v1)
+69: punpckhwd Pq,Qd | vpunpckhwd Vx,Hx,Wx (66),(v1)
+6a: punpckhdq Pq,Qd | vpunpckhdq Vx,Hx,Wx (66),(v1)
+6b: packssdw Pq,Qd | vpackssdw Vx,Hx,Wx (66),(v1)
+6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
+6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
+6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
+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)
-75: pcmpeqw Pq,Qq | pcmpeqw Vdq,Wdq (66),(VEX),(o128)
-76: pcmpeqd Pq,Qq | pcmpeqd Vdq,Wdq (66),(VEX),(o128)
-77: emms/vzeroupper/vzeroall (VEX)
-78: VMREAD Ed/q,Gd/q
-79: VMWRITE Gd/q,Ed/q
+74: pcmpeqb Pq,Qq | vpcmpeqb Vx,Hx,Wx (66),(v1)
+75: pcmpeqw Pq,Qq | vpcmpeqw Vx,Hx,Wx (66),(v1)
+76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
+# Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
+77: emms | vzeroupper | vzeroall
+78: VMREAD Ey,Gy
+79: VMWRITE Gy,Ey
 7a:
 7b:
-7c: haddps Vps,Wps (F2),(VEX) | haddpd Vpd,Wpd (66),(VEX)
-7d: hsubps Vps,Wps (F2),(VEX) | hsubpd Vpd,Wpd (66),(VEX)
-7e: movd/q Ed/q,Pd | movd/q Ed/q,Vdq (66),(VEX),(o128) | movq Vq,Wq (F3),(VEX),(o128)
-7f: movq Qq,Pq | movdqa Wdq,Vdq (66),(VEX) | movdqu Wdq,Vdq (F3),(VEX)
+7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
+7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
+7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
+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)
-83: JNB/JAE/JNC Jz (f64)
-84: JZ/JE Jz (f64)
-85: JNZ/JNE Jz (f64)
+82: JB/JC/JNAE Jz (f64)
+83: JAE/JNB/JNC Jz (f64)
+84: JE/JZ 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
-bd: BSR Gv,Ev
+bc: BSF Gv,Ev | TZCNT Gv,Ev (F3)
+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)
-c3: movnti Md/q,Gd/q
-c4: pinsrw Pq,Rd/q/Mw,Ib | pinsrw Vdq,Rd/q/Mw,Ib (66),(VEX),(o128)
-c5: pextrw Gd,Nq,Ib | pextrw Gd,Udq,Ib (66),(VEX),(o128)
-c6: shufps Vps,Wps,Ib (VEX) | shufpd Vpd,Wpd,Ib (66),(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 My,Gy
+c4: pinsrw Pq,Ry/Mw,Ib | vpinsrw Vdq,Hdq,Ry/Mw,Ib (66),(v1)
+c5: pextrw Gd,Nq,Ib | vpextrw Gd,Udq,Ib (66),(v1)
+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)
-d1: psrlw Pq,Qq | psrlw Vdq,Wdq (66),(VEX),(o128)
-d2: psrld Pq,Qq | psrld Vdq,Wdq (66),(VEX),(o128)
-d3: psrlq Pq,Qq | psrlq Vdq,Wdq (66),(VEX),(o128)
-d4: paddq Pq,Qq | paddq Vdq,Wdq (66),(VEX),(o128)
-d5: pmullw Pq,Qq | pmullw Vdq,Wdq (66),(VEX),(o128)
-d6: movq Wq,Vq (66),(VEX),(o128) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2)
-d7: pmovmskb Gd,Nq | pmovmskb Gd,Udq (66),(VEX),(o128)
-d8: psubusb Pq,Qq | psubusb Vdq,Wdq (66),(VEX),(o128)
-d9: psubusw Pq,Qq | psubusw Vdq,Wdq (66),(VEX),(o128)
-da: pminub Pq,Qq | pminub Vdq,Wdq (66),(VEX),(o128)
-db: pand Pq,Qq | pand Vdq,Wdq (66),(VEX),(o128)
-dc: paddusb Pq,Qq | paddusb Vdq,Wdq (66),(VEX),(o128)
-dd: paddusw Pq,Qq | paddusw Vdq,Wdq (66),(VEX),(o128)
-de: pmaxub Pq,Qq | pmaxub Vdq,Wdq (66),(VEX),(o128)
-df: pandn Pq,Qq | pandn Vdq,Wdq (66),(VEX),(o128)
+d0: vaddsubpd Vpd,Hpd,Wpd (66) | vaddsubps Vps,Hps,Wps (F2)
+d1: psrlw Pq,Qq | vpsrlw Vx,Hx,Wx (66),(v1)
+d2: psrld Pq,Qq | vpsrld Vx,Hx,Wx (66),(v1)
+d3: psrlq Pq,Qq | vpsrlq Vx,Hx,Wx (66),(v1)
+d4: paddq Pq,Qq | vpaddq Vx,Hx,Wx (66),(v1)
+d5: pmullw Pq,Qq | vpmullw Vx,Hx,Wx (66),(v1)
+d6: vmovq Wq,Vq (66),(v1) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2)
+d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
+d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
+d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
+da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
+db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1)
+dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
+dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
+de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
+df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1)
 # 0x0f 0xe0-0xef
-e0: pavgb Pq,Qq | pavgb Vdq,Wdq (66),(VEX),(o128)
-e1: psraw Pq,Qq | psraw Vdq,Wdq (66),(VEX),(o128)
-e2: psrad Pq,Qq | psrad Vdq,Wdq (66),(VEX),(o128)
-e3: pavgw Pq,Qq | pavgw Vdq,Wdq (66),(VEX),(o128)
-e4: pmulhuw Pq,Qq | pmulhuw Vdq,Wdq (66),(VEX),(o128)
-e5: pmulhw Pq,Qq | pmulhw Vdq,Wdq (66),(VEX),(o128)
-e6: cvtpd2dq Vdq,Wpd (F2),(VEX) | cvttpd2dq Vdq,Wpd (66),(VEX) | cvtdq2pd Vpd,Wdq (F3),(VEX)
-e7: movntq Mq,Pq | movntdq Mdq,Vdq (66),(VEX)
-e8: psubsb Pq,Qq | psubsb Vdq,Wdq (66),(VEX),(o128)
-e9: psubsw Pq,Qq | psubsw Vdq,Wdq (66),(VEX),(o128)
-ea: pminsw Pq,Qq | pminsw Vdq,Wdq (66),(VEX),(o128)
-eb: por Pq,Qq | por Vdq,Wdq (66),(VEX),(o128)
-ec: paddsb Pq,Qq | paddsb Vdq,Wdq (66),(VEX),(o128)
-ed: paddsw Pq,Qq | paddsw Vdq,Wdq (66),(VEX),(o128)
-ee: pmaxsw Pq,Qq | pmaxsw Vdq,Wdq (66),(VEX),(o128)
-ef: pxor Pq,Qq | pxor Vdq,Wdq (66),(VEX),(o128)
+e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
+e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
+e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
+e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
+e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
+e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
+e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2)
+e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
+e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
+e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
+ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
+eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1)
+ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
+ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
+ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
+ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1)
 # 0x0f 0xf0-0xff
-f0: lddqu Vdq,Mdq (F2),(VEX)
-f1: psllw Pq,Qq | psllw Vdq,Wdq (66),(VEX),(o128)
-f2: pslld Pq,Qq | pslld Vdq,Wdq (66),(VEX),(o128)
-f3: psllq Pq,Qq | psllq Vdq,Wdq (66),(VEX),(o128)
-f4: pmuludq Pq,Qq | pmuludq Vdq,Wdq (66),(VEX),(o128)
-f5: pmaddwd Pq,Qq | pmaddwd Vdq,Wdq (66),(VEX),(o128)
-f6: psadbw Pq,Qq | psadbw Vdq,Wdq (66),(VEX),(o128)
-f7: maskmovq Pq,Nq | maskmovdqu Vdq,Udq (66),(VEX),(o128)
-f8: psubb Pq,Qq | psubb Vdq,Wdq (66),(VEX),(o128)
-f9: psubw Pq,Qq | psubw Vdq,Wdq (66),(VEX),(o128)
-fa: psubd Pq,Qq | psubd Vdq,Wdq (66),(VEX),(o128)
-fb: psubq Pq,Qq | psubq Vdq,Wdq (66),(VEX),(o128)
-fc: paddb Pq,Qq | paddb Vdq,Wdq (66),(VEX),(o128)
-fd: paddw Pq,Qq | paddw Vdq,Wdq (66),(VEX),(o128)
-fe: paddd Pq,Qq | paddd Vdq,Wdq (66),(VEX),(o128)
+f0: vlddqu Vx,Mx (F2)
+f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
+f2: pslld Pq,Qq | vpslld Vx,Hx,Wx (66),(v1)
+f3: psllq Pq,Qq | vpsllq Vx,Hx,Wx (66),(v1)
+f4: pmuludq Pq,Qq | vpmuludq Vx,Hx,Wx (66),(v1)
+f5: pmaddwd Pq,Qq | vpmaddwd Vx,Hx,Wx (66),(v1)
+f6: psadbw Pq,Qq | vpsadbw Vx,Hx,Wx (66),(v1)
+f7: maskmovq Pq,Nq | vmaskmovdqu Vx,Ux (66),(v1)
+f8: psubb Pq,Qq | vpsubb Vx,Hx,Wx (66),(v1)
+f9: psubw Pq,Qq | vpsubw Vx,Hx,Wx (66),(v1)
+fa: psubd Pq,Qq | vpsubd Vx,Hx,Wx (66),(v1)
+fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
+fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
+fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
+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)
-01: phaddw Pq,Qq | phaddw Vdq,Wdq (66),(VEX),(o128)
-02: phaddd Pq,Qq | phaddd Vdq,Wdq (66),(VEX),(o128)
-03: phaddsw Pq,Qq | phaddsw Vdq,Wdq (66),(VEX),(o128)
-04: pmaddubsw Pq,Qq | pmaddubsw Vdq,Wdq (66),(VEX),(o128)
-05: phsubw Pq,Qq | phsubw Vdq,Wdq (66),(VEX),(o128)
-06: phsubd Pq,Qq | phsubd Vdq,Wdq (66),(VEX),(o128)
-07: phsubsw Pq,Qq | phsubsw Vdq,Wdq (66),(VEX),(o128)
-08: psignb Pq,Qq | psignb Vdq,Wdq (66),(VEX),(o128)
-09: psignw Pq,Qq | psignw Vdq,Wdq (66),(VEX),(o128)
-0a: psignd Pq,Qq | psignd Vdq,Wdq (66),(VEX),(o128)
-0b: pmulhrsw Pq,Qq | pmulhrsw Vdq,Wdq (66),(VEX),(o128)
-0c: Vpermilps /r (66),(oVEX)
-0d: Vpermilpd /r (66),(oVEX)
-0e: vtestps /r (66),(oVEX)
-0f: vtestpd /r (66),(oVEX)
+00: pshufb Pq,Qq | vpshufb Vx,Hx,Wx (66),(v1)
+01: phaddw Pq,Qq | vphaddw Vx,Hx,Wx (66),(v1)
+02: phaddd Pq,Qq | vphaddd Vx,Hx,Wx (66),(v1)
+03: phaddsw Pq,Qq | vphaddsw Vx,Hx,Wx (66),(v1)
+04: pmaddubsw Pq,Qq | vpmaddubsw Vx,Hx,Wx (66),(v1)
+05: phsubw Pq,Qq | vphsubw Vx,Hx,Wx (66),(v1)
+06: phsubd Pq,Qq | vphsubd Vx,Hx,Wx (66),(v1)
+07: phsubsw Pq,Qq | vphsubsw Vx,Hx,Wx (66),(v1)
+08: psignb Pq,Qq | vpsignb Vx,Hx,Wx (66),(v1)
+09: psignw Pq,Qq | vpsignw Vx,Hx,Wx (66),(v1)
+0a: psignd Pq,Qq | vpsignd Vx,Hx,Wx (66),(v1)
+0b: pmulhrsw Pq,Qq | vpmulhrsw Vx,Hx,Wx (66),(v1)
+0c: vpermilps Vx,Hx,Wx (66),(v)
+0d: vpermilpd Vx,Hx,Wx (66),(v)
+0e: vtestps Vx,Wx (66),(v)
+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:
-17: ptest Vdq,Wdq (66),(VEX)
-18: vbroadcastss /r (66),(oVEX)
-19: vbroadcastsd /r (66),(oVEX),(o256)
-1a: vbroadcastf128 /r (66),(oVEX),(o256)
+16: vpermps Vqq,Hqq,Wqq (66),(v)
+17: vptest Vx,Wx (66)
+18: vbroadcastss Vx,Wd (66),(v)
+19: vbroadcastsd Vqq,Wq (66),(v)
+1a: vbroadcastf128 Vqq,Mdq (66),(v)
 1b:
-1c: pabsb Pq,Qq | pabsb Vdq,Wdq (66),(VEX),(o128)
-1d: pabsw Pq,Qq | pabsw Vdq,Wdq (66),(VEX),(o128)
-1e: pabsd Pq,Qq | pabsd Vdq,Wdq (66),(VEX),(o128)
+1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
+1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
+1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
 1f:
 # 0x0f 0x38 0x20-0x2f
-20: pmovsxbw Vdq,Udq/Mq (66),(VEX),(o128)
-21: pmovsxbd Vdq,Udq/Md (66),(VEX),(o128)
-22: pmovsxbq Vdq,Udq/Mw (66),(VEX),(o128)
-23: pmovsxwd Vdq,Udq/Mq (66),(VEX),(o128)
-24: pmovsxwq Vdq,Udq/Md (66),(VEX),(o128)
-25: pmovsxdq Vdq,Udq/Mq (66),(VEX),(o128)
+20: vpmovsxbw Vx,Ux/Mq (66),(v1)
+21: vpmovsxbd Vx,Ux/Md (66),(v1)
+22: vpmovsxbq Vx,Ux/Mw (66),(v1)
+23: vpmovsxwd Vx,Ux/Mq (66),(v1)
+24: vpmovsxwq Vx,Ux/Md (66),(v1)
+25: vpmovsxdq Vx,Ux/Mq (66),(v1)
 26:
 27:
-28: pmuldq Vdq,Wdq (66),(VEX),(o128)
-29: pcmpeqq Vdq,Wdq (66),(VEX),(o128)
-2a: movntdqa Vdq,Mdq (66),(VEX),(o128)
-2b: packusdw Vdq,Wdq (66),(VEX),(o128)
-2c: vmaskmovps(ld) /r (66),(oVEX)
-2d: vmaskmovpd(ld) /r (66),(oVEX)
-2e: vmaskmovps(st) /r (66),(oVEX)
-2f: vmaskmovpd(st) /r (66),(oVEX)
+28: vpmuldq Vx,Hx,Wx (66),(v1)
+29: vpcmpeqq Vx,Hx,Wx (66),(v1)
+2a: vmovntdqa Vx,Mx (66),(v1)
+2b: vpackusdw Vx,Hx,Wx (66),(v1)
+2c: vmaskmovps Vx,Hx,Mx (66),(v)
+2d: vmaskmovpd Vx,Hx,Mx (66),(v)
+2e: vmaskmovps Mx,Hx,Vx (66),(v)
+2f: vmaskmovpd Mx,Hx,Vx (66),(v)
 # 0x0f 0x38 0x30-0x3f
-30: pmovzxbw Vdq,Udq/Mq (66),(VEX),(o128)
-31: pmovzxbd Vdq,Udq/Md (66),(VEX),(o128)
-32: pmovzxbq Vdq,Udq/Mw (66),(VEX),(o128)
-33: pmovzxwd Vdq,Udq/Mq (66),(VEX),(o128)
-34: pmovzxwq Vdq,Udq/Md (66),(VEX),(o128)
-35: pmovzxdq Vdq,Udq/Mq (66),(VEX),(o128)
-36:
-37: pcmpgtq Vdq,Wdq (66),(VEX),(o128)
-38: pminsb Vdq,Wdq (66),(VEX),(o128)
-39: pminsd Vdq,Wdq (66),(VEX),(o128)
-3a: pminuw Vdq,Wdq (66),(VEX),(o128)
-3b: pminud Vdq,Wdq (66),(VEX),(o128)
-3c: pmaxsb Vdq,Wdq (66),(VEX),(o128)
-3d: pmaxsd Vdq,Wdq (66),(VEX),(o128)
-3e: pmaxuw Vdq,Wdq (66),(VEX),(o128)
-3f: pmaxud Vdq,Wdq (66),(VEX),(o128)
+30: vpmovzxbw Vx,Ux/Mq (66),(v1)
+31: vpmovzxbd Vx,Ux/Md (66),(v1)
+32: vpmovzxbq Vx,Ux/Mw (66),(v1)
+33: vpmovzxwd Vx,Ux/Mq (66),(v1)
+34: vpmovzxwq Vx,Ux/Md (66),(v1)
+35: vpmovzxdq Vx,Ux/Mq (66),(v1)
+36: vpermd Vqq,Hqq,Wqq (66),(v)
+37: vpcmpgtq Vx,Hx,Wx (66),(v1)
+38: vpminsb Vx,Hx,Wx (66),(v1)
+39: vpminsd Vx,Hx,Wx (66),(v1)
+3a: vpminuw Vx,Hx,Wx (66),(v1)
+3b: vpminud Vx,Hx,Wx (66),(v1)
+3c: vpmaxsb Vx,Hx,Wx (66),(v1)
+3d: vpmaxsd Vx,Hx,Wx (66),(v1)
+3e: vpmaxuw Vx,Hx,Wx (66),(v1)
+3f: vpmaxud Vx,Hx,Wx (66),(v1)
 # 0x0f 0x38 0x40-0x8f
-40: pmulld Vdq,Wdq (66),(VEX),(o128)
-41: phminposuw Vdq,Wdq (66),(VEX),(o128)
-80: INVEPT Gd/q,Mdq (66)
-81: INVPID Gd/q,Mdq (66)
+40: vpmulld Vx,Hx,Wx (66),(v1)
+41: vphminposuw Vdq,Wdq (66),(v1)
+42:
+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)
-97: vfmsubadd132pd/ps /r (66),(VEX)
-98: vfmadd132pd/ps /r (66),(VEX)
-99: vfmadd132sd/ss /r (66),(VEX),(o128)
-9a: vfmsub132pd/ps /r (66),(VEX)
-9b: vfmsub132sd/ss /r (66),(VEX),(o128)
-9c: vfnmadd132pd/ps /r (66),(VEX)
-9d: vfnmadd132sd/ss /r (66),(VEX),(o128)
-9e: vfnmsub132pd/ps /r (66),(VEX)
-9f: vfnmsub132sd/ss /r (66),(VEX),(o128)
-a6: vfmaddsub213pd/ps /r (66),(VEX)
-a7: vfmsubadd213pd/ps /r (66),(VEX)
-a8: vfmadd213pd/ps /r (66),(VEX)
-a9: vfmadd213sd/ss /r (66),(VEX),(o128)
-aa: vfmsub213pd/ps /r (66),(VEX)
-ab: vfmsub213sd/ss /r (66),(VEX),(o128)
-ac: vfnmadd213pd/ps /r (66),(VEX)
-ad: vfnmadd213sd/ss /r (66),(VEX),(o128)
-ae: vfnmsub213pd/ps /r (66),(VEX)
-af: vfnmsub213sd/ss /r (66),(VEX),(o128)
-b6: vfmaddsub231pd/ps /r (66),(VEX)
-b7: vfmsubadd231pd/ps /r (66),(VEX)
-b8: vfmadd231pd/ps /r (66),(VEX)
-b9: vfmadd231sd/ss /r (66),(VEX),(o128)
-ba: vfmsub231pd/ps /r (66),(VEX)
-bb: vfmsub231sd/ss /r (66),(VEX),(o128)
-bc: vfnmadd231pd/ps /r (66),(VEX)
-bd: vfnmadd231sd/ss /r (66),(VEX),(o128)
-be: vfnmsub231pd/ps /r (66),(VEX)
-bf: vfnmsub231sd/ss /r (66),(VEX),(o128)
+90: vgatherdd/q Vx,Hx,Wx (66),(v)
+91: vgatherqd/q Vx,Hx,Wx (66),(v)
+92: vgatherdps/d Vx,Hx,Wx (66),(v)
+93: vgatherqps/d Vx,Hx,Wx (66),(v)
+94:
+95:
+96: vfmaddsub132ps/d Vx,Hx,Wx (66),(v)
+97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v)
+98: vfmadd132ps/d Vx,Hx,Wx (66),(v)
+99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
+9a: vfmsub132ps/d Vx,Hx,Wx (66),(v)
+9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v)
+9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
+9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
+9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
+a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
+a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
+a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
+aa: vfmsub213ps/d Vx,Hx,Wx (66),(v)
+ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
+ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
+ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
+af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
+b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
+b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
+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)
-dc: aesenc Vdq,Wdq (66),(VEX),(o128)
-dd: aesenclast Vdq,Wdq (66),(VEX),(o128)
-de: aesdec Vdq,Wdq (66),(VEX),(o128)
-df: aesdeclast Vdq,Wdq (66),(VEX),(o128)
-f0: MOVBE Gv,Mv | CRC32 Gd,Eb (F2)
-f1: MOVBE Mv,Gv | CRC32 Gd,Ev (F2)
+db: VAESIMC Vdq,Wdq (66),(v1)
+dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
+dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
+de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
+df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
+f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (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)
-05: vpermilpd /r,Ib (66),(oVEX)
-06: vperm2f128 /r,Ib (66),(oVEX),(o256)
-08: roundps Vdq,Wdq,Ib (66),(VEX)
-09: roundpd Vdq,Wdq,Ib (66),(VEX)
-0a: roundss Vss,Wss,Ib (66),(VEX),(o128)
-0b: roundsd Vsd,Wsd,Ib (66),(VEX),(o128)
-0c: blendps Vdq,Wdq,Ib (66),(VEX)
-0d: blendpd Vdq,Wdq,Ib (66),(VEX)
-0e: pblendw Vdq,Wdq,Ib (66),(VEX),(o128)
-0f: palignr Pq,Qq,Ib | palignr Vdq,Wdq,Ib (66),(VEX),(o128)
-14: pextrb Rd/Mb,Vdq,Ib (66),(VEX),(o128)
-15: pextrw Rd/Mw,Vdq,Ib (66),(VEX),(o128)
-16: pextrd/pextrq Ed/q,Vdq,Ib (66),(VEX),(o128)
-17: extractps Ed,Vdq,Ib (66),(VEX),(o128)
-18: vinsertf128 /r,Ib (66),(oVEX),(o256)
-19: vextractf128 /r,Ib (66),(oVEX),(o256)
-20: pinsrb Vdq,Rd/q/Mb,Ib (66),(VEX),(o128)
-21: insertps Vdq,Udq/Md,Ib (66),(VEX),(o128)
-22: pinsrd/pinsrq Vdq,Ed/q,Ib (66),(VEX),(o128)
-40: dpps Vdq,Wdq,Ib (66),(VEX)
-41: dppd Vdq,Wdq,Ib (66),(VEX),(o128)
-42: mpsadbw Vdq,Wdq,Ib (66),(VEX),(o128)
-44: pclmulq Vdq,Wdq,Ib (66),(VEX),(o128)
-4a: vblendvps /r,Ib (66),(oVEX)
-4b: vblendvpd /r,Ib (66),(oVEX)
-4c: vpblendvb /r,Ib (66),(oVEX),(o128)
-60: pcmpestrm Vdq,Wdq,Ib (66),(VEX),(o128)
-61: pcmpestri Vdq,Wdq,Ib (66),(VEX),(o128)
-62: pcmpistrm Vdq,Wdq,Ib (66),(VEX),(o128)
-63: pcmpistri Vdq,Wdq,Ib (66),(VEX),(o128)
-df: aeskeygenassist Vdq,Wdq,Ib (66),(VEX),(o128)
+00: vpermq Vqq,Wqq,Ib (66),(v)
+01: vpermpd Vqq,Wqq,Ib (66),(v)
+02: vpblendd Vx,Hx,Wx,Ib (66),(v)
+03:
+04: vpermilps Vx,Wx,Ib (66),(v)
+05: vpermilpd Vx,Wx,Ib (66),(v)
+06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
+07:
+08: vroundps Vx,Wx,Ib (66)
+09: vroundpd Vx,Wx,Ib (66)
+0a: vroundss Vss,Wss,Ib (66),(v1)
+0b: vroundsd Vsd,Wsd,Ib (66),(v1)
+0c: vblendps Vx,Hx,Wx,Ib (66)
+0d: vblendpd Vx,Hx,Wx,Ib (66)
+0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
+0f: palignr Pq,Qq,Ib | vpalignr Vx,Hx,Wx,Ib (66),(v1)
+14: vpextrb Rd/Mb,Vdq,Ib (66),(v1)
+15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
+16: vpextrd/q Ey,Vdq,Ib (66),(v1)
+17: vextractps Ed,Vdq,Ib (66),(v1)
+18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v)
+19: vextractf128 Wdq,Vqq,Ib (66),(v)
+1d: vcvtps2ph Wx,Vx,Ib (66),(v)
+20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
+21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
+22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
+38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v)
+39: vextracti128 Wdq,Vqq,Ib (66),(v)
+40: vdpps Vx,Hx,Wx,Ib (66)
+41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
+42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1)
+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)
-7: VMPTRST Mq
+6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
+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)
-4: psraw Nq,Ib (11B) | psraw Udq,Ib (66),(11B),(VEX),(o128)
-6: psllw Nq,Ib (11B) | psllw Udq,Ib (66),(11B),(VEX),(o128)
+2: psrlw Nq,Ib (11B) | vpsrlw Hx,Ux,Ib (66),(11B),(v1)
+4: psraw Nq,Ib (11B) | vpsraw Hx,Ux,Ib (66),(11B),(v1)
+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)
-4: psrad Nq,Ib (11B) | psrad Udq,Ib (66),(11B),(VEX),(o128)
-6: pslld Nq,Ib (11B) | pslld Udq,Ib (66),(11B),(VEX),(o128)
+2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
+4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1)
+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)
-3: psrldq Udq,Ib (66),(11B),(VEX),(o128)
-6: psllq Nq,Ib (11B) | psllq Udq,Ib (66),(11B),(VEX),(o128)
-7: pslldq Udq,Ib (66),(11B),(VEX),(o128)
+2: psrlq Nq,Ib (11B) | vpsrlq Hx,Ux,Ib (66),(11B),(v1)
+3: vpsrldq Hx,Ux,Ib (66),(11B),(v1)
+6: psllq Nq,Ib (11B) | vpsllq Hx,Ux,Ib (66),(11B),(v1)
+7: vpslldq Hx,Ux,Ib (66),(11B),(v1)
 EndTable
 
 GrpTable: Grp15
-0: fxsave
-1: fxstor
-2: ldmxcsr (VEX)
-3: stmxcsr (VEX)
+0: fxsave | RDFSBASE Ry (F3),(11B)
+1: fxstor | RDGSBASE Ry (F3),(11B)
+2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B)
+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/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
-         * also means marking RW the pagetable pages that we allocated before
+         * On native it just means calling memblock_reserve, on Xen it also
+         * 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;
-        int nr_range;
-        int i;
-
-        nr_range = __get_free_all_memory_range(&range, nid, start_pfn, end_pfn);
-
-        for (i = 0; i < nr_range; i++) {
-                struct page *page;
-                int node_pfn;
-
-                for (node_pfn = range[i].start; node_pfn < range[i].end;
-                     node_pfn++) {
-                        if (!pfn_valid(node_pfn))
-                                continue;
-                        page = pfn_to_page(node_pfn);
-                        add_one_highpage_init(page);
-                }
+        phys_addr_t start, end;
+        u64 i;
+
+        for_each_free_mem_range(i, nid, &start, &end, NULL) {
+                unsigned long pfn = clamp_t(unsigned long, PFN_UP(start),
+                                            start_pfn, end_pfn);
+                unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end),
+                                              start_pfn, end_pfn);
+                for ( ; pfn < e_pfn; pfn++)
+                        if (pfn_valid(pfn))
+                                add_one_highpage_init(pfn_to_page(pfn));
         }
 }
 #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;
-
-        while (start < end) {
-                start = memblock_x86_find_in_range_size(start, &size, 1);
-
-                /* done ? */
-                if (start >= end)
-                        break;
-                if (start + size > end)
-                        size = end - start;
-
-                printk(KERN_INFO "  %010llx - %010llx pattern %016llx\n",
-                       (unsigned long long) start,
-                       (unsigned long long) start + size,
-                       (unsigned long long) cpu_to_be64(pattern));
-                memtest(pattern, start, size);
-
-                start += size;
+        u64 i;
+        phys_addr_t this_start, this_end;
+
+        for_each_free_mem_range(i, MAX_NUMNODES, &this_start, &this_end, NULL) {
+                this_start = clamp_t(phys_addr_t, this_start, start, end);
+                this_end = clamp_t(phys_addr_t, this_end, start, end);
+                if (this_start < this_end) {
+                        printk(KERN_INFO "  %010llx - %010llx pattern %016llx\n",
+                               (unsigned long long)this_start,
+                               (unsigned long long)this_end,
+                               (unsigned long long)cpu_to_be64(pattern));
+                        memtest(pattern, this_start, this_end - this_start);
+                }
         }
 }
 
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_size, SMP_CACHE_BYTES);
-                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) {
+                nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
+                if (!nd_pa) {
                         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),
-                                        __pa(numa_distance) + size);
+                memblock_free(__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,
-                                        PFN_PHYS(max_pfn)) >> PAGE_SHIFT);
+        e820ram = max_pfn - absent_pages_in_range(0, max_pfn);
+
         /* 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++)
-                memblock_x86_register_active_regions(mi->blk[i].nid,
-                                        mi->blk[i].start >> PAGE_SHIFT,
-                                        mi->blk[i].end >> PAGE_SHIFT);
-
-        /* for out of order entries */
-        sort_node_map();
+        for (i = 0; i < mi->nr_blks; i++) {
+                struct numa_memblk *mb = &mi->blk[i];
+                memblock_set_node(mb->start, mb->end - mb->start, mb->nid);
+        }
 
         /*
          * 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 -
-                               memblock_x86_hole_size(start, end) < size) {
+                        while (end - start - mem_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 -
-                            memblock_x86_hole_size(end, limit) < size)
+                        if (limit - end - mem_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)) /
-                                                MAX_NUMNODES;
+        min_size = (max_addr - addr - mem_hole_size(addr, max_addr)) / 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 -
-                            memblock_x86_hole_size(end, limit) < size)
+                        if (limit - end - mem_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)
-                                                t_offset += is_near(f_offset) ? 2 : 6;
+                                        if (filter[i].jf && f_offset)
+                                                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 f148cf652678..9e138d00ad36 100644
--- a/arch/x86/oprofile/init.c
+++ b/arch/x86/oprofile/init.c
@@ -16,37 +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
 
-static int nmi_timer;
+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
-        nmi_timer = (ret != 0);
-#ifdef CONFIG_X86_IO_APIC
-        if (nmi_timer)
-                ret = op_nmi_timer_init(ops);
-#endif
         ops->backtrace = x86_backtrace;
-
-        return ret;
+        return op_nmi_init(ops);
 }
 
-
 void oprofile_arch_exit(void)
 {
-#ifdef CONFIG_X86_LOCAL_APIC
-        if (!nmi_timer)
-                op_nmi_exit();
-#endif
+        op_nmi_exit();
 }
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;
-static int force_cpu_type(const char *str, struct kernel_param *kp)
+enum __force_cpu_type {
+        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")) {
-                force_arch_perfmon = 1;
+        if (!strcmp(str, "timer")) {
+                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,
-                      "EFI memmap");
+        memblock_reserve(pmap, memmap.nr_map * memmap.desc_size);
 }
 
 #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,
-                                                        1<<EFI_PAGE_SHIFT)) {
+                        memblock_is_region_reserved(start, size)) {
                         /* 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,
-                                                        "EFI Boot");
+                        memblock_reserve(start, size);
         }
 }
 
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\\)"
-        vexonly_expr = "\\(oVEX\\)"
+        # All opcodes starting with lower-case 'v' or with (v1) superscript
+        # 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["3bytes-VEX"] = "INAT_PFX_VEX3"
+        prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
+        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")
-
-                # check VEX only code
-                if (match(ext, vexok_expr))
+                else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_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),
-                      __pa(xen_start_info->pt_base +
-                           xen_start_info->nr_pt_frames * PAGE_SIZE),
-                      "XEN PAGETABLES");
+        memblock_reserve(__pa(xen_start_info->pt_base),
+                         xen_start_info->nr_pt_frames * PAGE_SIZE);
 
         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),
-                      __pa(xen_start_info->pt_base +
-                           xen_start_info->nr_pt_frames * PAGE_SIZE),
-                      "XEN PAGETABLES");
+        memblock_reserve(__pa(xen_start_info->pt_base),
+                         xen_start_info->nr_pt_frames * PAGE_SIZE));
 
         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)
-                max_pages = ret;
+        /*
+         * For the initial domain we use the maximum reservation as
+         * 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),
-                      __pa(xen_start_info->pt_base),
-                        "XEN START INFO");
+        memblock_reserve(__pa(xen_start_info->mfn_list),
+                         xen_start_info->pt_base - xen_start_info->mfn_list);
 
         sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);