77 files changed, 4574 insertions, 2723 deletions
diff --git a/arch/um/sys-x86_64/syscall_table.c b/arch/um/sys-x86_64/syscall_table.c
index c128eb897008..32f5fbe2d0d2 100644
--- a/arch/um/sys-x86_64/syscall_table.c
+++ b/arch/um/sys-x86_64/syscall_table.c
@@ -41,12 +41,12 @@
 #define stub_rt_sigreturn sys_rt_sigreturn
 #define __SYSCALL(nr, sym) extern asmlinkage void sym(void) ;
-#undef _ASM_X86_64_UNISTD_H_
+#undef ASM_X86__UNISTD_64_H
 #include <asm-x86/unistd_64.h>
 #undef __SYSCALL
 #define __SYSCALL(nr, sym) [ nr ] = sym,
-#undef _ASM_X86_64_UNISTD_H_
+#undef ASM_X86__UNISTD_64_H
 typedef void (*sys_call_ptr_t)(void);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0d7cdbbfc1ee..44d4f2130d01 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1689,6 +1689,14 @@ config DMAR_FLOPPY_WA
         workaround will setup a 1:1 mapping for the first
         16M to make floppy (an ISA device) work.
+config INTR_REMAP
+        bool "Support for Interrupt Remapping (EXPERIMENTAL)"
+        depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI && EXPERIMENTAL
+        help
+         Supports Interrupt remapping for IO-APIC and MSI devices.
+         To use x2apic mode in the CPU's which support x2APIC enhancements or
+         to support platforms with CPU's having > 8 bit APIC ID, say Y.
 source "drivers/pci/pcie/Kconfig"
 source "drivers/pci/Kconfig"
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 60a85768cfcb..f8843c3ae77d 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -419,6 +419,60 @@ config X86_DEBUGCTLMSR
        def_bool y
        depends on !(MK6 || MWINCHIPC6 || MWINCHIP2 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486 || M386)
+menuconfig PROCESSOR_SELECT
+        default y
+        bool "Supported processor vendors" if EMBEDDED
+        help
+          This lets you choose what x86 vendor support code your kernel
+          will include.
+config CPU_SUP_INTEL
+        default y
+        bool "Support Intel processors" if PROCESSOR_SELECT
+        help
+          This enables extended support for Intel processors
+config CPU_SUP_CYRIX_32
+        default y
+        bool "Support Cyrix processors" if PROCESSOR_SELECT
+        depends on !64BIT
+        help
+          This enables extended support for Cyrix processors
+config CPU_SUP_AMD
+        default y
+        bool "Support AMD processors" if PROCESSOR_SELECT
+        help
+          This enables extended support for AMD processors
+config CPU_SUP_CENTAUR_32
+        default y
+        bool "Support Centaur processors" if PROCESSOR_SELECT
+        depends on !64BIT
+        help
+          This enables extended support for Centaur processors
+config CPU_SUP_CENTAUR_64
+        default y
+        bool "Support Centaur processors" if PROCESSOR_SELECT
+        depends on 64BIT
+        help
+          This enables extended support for Centaur processors
+config CPU_SUP_TRANSMETA_32
+        default y
+        bool "Support Transmeta processors" if PROCESSOR_SELECT
+        depends on !64BIT
+        help
+          This enables extended support for Transmeta processors
+config CPU_SUP_UMC_32
+        default y
+        bool "Support UMC processors" if PROCESSOR_SELECT
+        depends on !64BIT
+        help
+          This enables extended support for UMC processors
 config X86_DS
        bool "Debug Store support"
        default y
diff --git a/arch/x86/boot/cpu.c b/arch/x86/boot/cpu.c
index 75298fe2edca..6ec6bb6e9957 100644
--- a/arch/x86/boot/cpu.c
+++ b/arch/x86/boot/cpu.c
@@ -59,17 +59,18 @@ int validate_cpu(void)
                        u32 e = err_flags[i];
                        for (j = 0; j < 32; j++) {
-                                int n = (i << 5)+j;
+                                if (msg_strs[0] < i ||
-                                if (*msg_strs < n) {
+                                    (msg_strs[0] == i && msg_strs[1] < j)) {
                                        /* Skip to the next string */
-                                        do {
+                                        msg_strs += 2;
-                                                msg_strs++;
+                                        while (*msg_strs++)
-                                        } while (*msg_strs);
+                                                ;
-                                        msg_strs++;
                                }
                                if (e & 1) {
-                                        if (*msg_strs == n && msg_strs[1])
+                                        if (msg_strs[0] == i &&
-                                                printf("%s ", msg_strs+1);
+                                            msg_strs[1] == j &&
+                                            msg_strs[2])
+                                                printf("%s ", msg_strs+2);
                                        else
                                                printf("%d:%d ", i, j);
                                }
diff --git a/arch/x86/boot/mkcpustr.c b/arch/x86/boot/mkcpustr.c
index bbe76953bae9..8ef60f20b371 100644
--- a/arch/x86/boot/mkcpustr.c
+++ b/arch/x86/boot/mkcpustr.c
@@ -15,33 +15,33 @@
 #include <stdio.h>
-#include "../kernel/cpu/feature_names.c"
+#include "../kernel/cpu/capflags.c"
-#if NCAPFLAGS > 8
-# error "Need to adjust the boot code handling of CPUID strings"
-#endif
 int main(void)
 {
-        int i;
+        int i, j;
        const char *str;
        printf("static const char x86_cap_strs[] = \n");
-        for (i = 0; i < NCAPINTS*32; i++) {
+        for (i = 0; i < NCAPINTS; i++) {
-                str = x86_cap_flags[i];
+                for (j = 0; j < 32; j++) {
+                        str = x86_cap_flags[i*32+j];
-                if (i == NCAPINTS*32-1) {
-                        /* The last entry must be unconditional; this
+                        if (i == NCAPINTS-1 && j == 31) {
-                           also consumes the compiler-added null character */
+                                /* The last entry must be unconditional; this
-                        if (!str)
+                                   also consumes the compiler-added null
-                                str = "";
+                                   character */
-                        printf("\t\"\\x%02x\"\"%s\"\n", i, str);
+                                if (!str)
-                } else if (str) {
+                                        str = "";
-                        printf("#if REQUIRED_MASK%d & (1 << %d)\n"
+                                printf("\t\"\\x%02x\\x%02x\"\"%s\"\n",
-                               "\t\"\\x%02x\"\"%s\\0\"\n"
+                                       i, j, str);
-                               "#endif\n",
+                        } else if (str) {
-                               i >> 5, i & 31, i, str);
+                                printf("#if REQUIRED_MASK%d & (1 << %d)\n"
+                                       "\t\"\\x%02x\\x%02x\"\"%s\\0\"\n"
+                                       "#endif\n",
+                                       i, j, i, j, str);
+                        }
                }
        }
        printf("\t;\n");
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index f1a2ac777faf..8d64c1bc8474 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -179,9 +179,10 @@ struct sigframe
        u32 pretcode;
        int sig;
        struct sigcontext_ia32 sc;
-        struct _fpstate_ia32 fpstate;
+        struct _fpstate_ia32 fpstate_unused; /* look at kernel/sigframe.h */
        unsigned int extramask[_COMPAT_NSIG_WORDS-1];
        char retcode[8];
+        /* fp state follows here */
 };
 struct rt_sigframe
@@ -192,8 +193,8 @@ struct rt_sigframe
        u32 puc;
        compat_siginfo_t info;
        struct ucontext_ia32 uc;
-        struct _fpstate_ia32 fpstate;
        char retcode[8];
+        /* fp state follows here */
 };
 #define COPY(x)         {               \
@@ -215,7 +216,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
                                   unsigned int *peax)
 {
        unsigned int tmpflags, gs, oldgs, err = 0;
-        struct _fpstate_ia32 __user *buf;
+        void __user *buf;
        u32 tmp;
        /* Always make any pending restarted system calls return -EINTR */
@@ -259,26 +260,12 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
        err |= __get_user(tmp, &sc->fpstate);
        buf = compat_ptr(tmp);
-        if (buf) {
+        err |= restore_i387_xstate_ia32(buf);
-                if (!access_ok(VERIFY_READ, buf, sizeof(*buf)))
-                        goto badframe;
-                err |= restore_i387_ia32(buf);
-        } else {
-                struct task_struct *me = current;
-                if (used_math()) {
-                        clear_fpu(me);
-                        clear_used_math();
-                }
-        }
        err |= __get_user(tmp, &sc->ax);
        *peax = tmp;
        return err;
-badframe:
-        return 1;
 }
 asmlinkage long sys32_sigreturn(struct pt_regs *regs)
@@ -350,7 +337,7 @@ badframe:
 */
 static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
-                                 struct _fpstate_ia32 __user *fpstate,
+                                 void __user *fpstate,
                                 struct pt_regs *regs, unsigned int mask)
 {
        int tmp, err = 0;
@@ -380,7 +367,7 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
        err |= __put_user((u32)regs->flags, &sc->flags);
        err |= __put_user((u32)regs->sp, &sc->sp_at_signal);
-        tmp = save_i387_ia32(fpstate);
+        tmp = save_i387_xstate_ia32(fpstate);
        if (tmp < 0)
                err = -EFAULT;
        else {
@@ -401,7 +388,8 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
 * Determine which stack to use..
 */
 static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
-                                 size_t frame_size)
+                                 size_t frame_size,
+                                 void **fpstate)
 {
        unsigned long sp;
@@ -420,6 +408,11 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
                 ka->sa.sa_restorer)
                sp = (unsigned long) ka->sa.sa_restorer;
+        if (used_math()) {
+                sp = sp - sig_xstate_ia32_size;
+                *fpstate = (struct _fpstate_ia32 *) sp;
+        }
        sp -= frame_size;
        /* Align the stack pointer according to the i386 ABI,
         * i.e. so that on function entry ((sp + 4) & 15) == 0. */
@@ -433,6 +426,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
        struct sigframe __user *frame;
        void __user *restorer;
        int err = 0;
+        void __user *fpstate = NULL;
        /* copy_to_user optimizes that into a single 8 byte store */
        static const struct {
@@ -447,7 +441,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
                0,
        };
-        frame = get_sigframe(ka, regs, sizeof(*frame));
+        frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
        if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
                goto give_sigsegv;
@@ -456,8 +450,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
        if (err)
                goto give_sigsegv;
-        err |= ia32_setup_sigcontext(&frame->sc, &frame->fpstate, regs,
+        err |= ia32_setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0]);
-                                        set->sig[0]);
        if (err)
                goto give_sigsegv;
@@ -521,6 +514,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
        struct rt_sigframe __user *frame;
        void __user *restorer;
        int err = 0;
+        void __user *fpstate = NULL;
        /* __copy_to_user optimizes that into a single 8 byte store */
        static const struct {
@@ -536,7 +530,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
                0,
        };
-        frame = get_sigframe(ka, regs, sizeof(*frame));
+        frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
        if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
                goto give_sigsegv;
@@ -549,13 +543,16 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
                goto give_sigsegv;
        /* Create the ucontext.  */
-        err |= __put_user(0, &frame->uc.uc_flags);
+        if (cpu_has_xsave)
+                err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags);
+        else
+                err |= __put_user(0, &frame->uc.uc_flags);
        err |= __put_user(0, &frame->uc.uc_link);
        err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
        err |= __put_user(sas_ss_flags(regs->sp),
                          &frame->uc.uc_stack.ss_flags);
        err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
-        err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
+        err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
                                     regs, set->sig[0]);
        err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
        if (err)
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 3db651fc8ec5..c9be69fedb70 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -38,7 +38,7 @@ obj-y			+= tsc.o io_delay.o rtc.o
 obj-$(CONFIG_X86_TRAMPOLINE)    += trampoline.o
 obj-y                           += process.o
-obj-y                           += i387.o
+obj-y                           += i387.o xsave.o
 obj-y                           += ptrace.o
 obj-y                           += ds.o
 obj-$(CONFIG_X86_32)            += tls.o
@@ -69,6 +69,7 @@ obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)             += relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)        += crash_dump_$(BITS).o
 obj-$(CONFIG_X86_NUMAQ)         += numaq_32.o
+obj-$(CONFIG_X86_ES7000)        += es7000_32.o
 obj-$(CONFIG_X86_SUMMIT_NUMA)   += summit_32.o
 obj-y                           += vsmp_64.o
 obj-$(CONFIG_KPROBES)           += kprobes.o
@@ -104,6 +105,8 @@ obj-$(CONFIG_OLPC)		+= olpc.o
 ifeq ($(CONFIG_X86_64),y)
        obj-y                           += genapic_64.o genapic_flat_64.o genx2apic_uv_x.o tlb_uv.o
        obj-y                           += bios_uv.o
+        obj-y                           += genx2apic_cluster.o
+        obj-y                           += genx2apic_phys.o
        obj-$(CONFIG_X86_PM_TIMER)      += pmtimer_64.o
        obj-$(CONFIG_AUDIT)             += audit_64.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 7d40ef7b36e3..c2ac1b4515a0 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -252,10 +252,8 @@ static void __cpuinit acpi_register_lapic(int id, u8 enabled)
                return;
        }
-#ifdef CONFIG_X86_32
        if (boot_cpu_physical_apicid != -1U)
                ver = apic_version[boot_cpu_physical_apicid];
-#endif
        generic_processor_info(id, ver);
 }
@@ -774,11 +772,9 @@ static void __init acpi_register_lapic_address(unsigned long address)
        set_fixmap_nocache(FIX_APIC_BASE, address);
        if (boot_cpu_physical_apicid == -1U) {
-                boot_cpu_physical_apicid  = GET_APIC_ID(read_apic_id());
+                boot_cpu_physical_apicid  = read_apic_id();
-#ifdef CONFIG_X86_32
                apic_version[boot_cpu_physical_apicid] =
                         GET_APIC_VERSION(apic_read(APIC_LVR));
-#endif
        }
 }
@@ -1350,7 +1346,9 @@ static void __init acpi_process_madt(void)
                                acpi_ioapic = 1;
                                smp_found_config = 1;
+#ifdef CONFIG_X86_32
                                setup_apic_routing();
+#endif
                        }
                }
                if (error == -EINVAL) {
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index f88bd0d982b0..a91c57cb666a 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -60,10 +60,8 @@ unsigned long mp_lapic_addr;
 static int force_enable_local_apic;
 int disable_apic;
-/* Local APIC timer verification ok */
-static int local_apic_timer_verify_ok;
 /* Disable local APIC timer from the kernel commandline or via dmi quirk */
-static int local_apic_timer_disabled;
+static int disable_apic_timer __cpuinitdata;
 /* Local APIC timer works in C2 */
 int local_apic_timer_c2_ok;
 EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
@@ -130,7 +128,11 @@ static inline int lapic_get_version(void)
 */
 static inline int lapic_is_integrated(void)
 {
+#ifdef CONFIG_X86_64
+        return 1;
+#else
        return APIC_INTEGRATED(lapic_get_version());
+#endif
 }
 /*
@@ -145,13 +147,18 @@ static int modern_apic(void)
        return lapic_get_version() >= 0x14;
 }
-void apic_wait_icr_idle(void)
+/*
+ * Paravirt kernels also might be using these below ops. So we still
+ * use generic apic_read()/apic_write(), which might be pointing to different
+ * ops in PARAVIRT case.
+ */
+void xapic_wait_icr_idle(void)
 {
        while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
                cpu_relax();
 }
-u32 safe_apic_wait_icr_idle(void)
+u32 safe_xapic_wait_icr_idle(void)
 {
        u32 send_status;
        int timeout;
@@ -167,16 +174,48 @@ u32 safe_apic_wait_icr_idle(void)
        return send_status;
 }
+void xapic_icr_write(u32 low, u32 id)
+{
+        apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(id));
+        apic_write(APIC_ICR, low);
+}
+u64 xapic_icr_read(void)
+{
+        u32 icr1, icr2;
+        icr2 = apic_read(APIC_ICR2);
+        icr1 = apic_read(APIC_ICR);
+        return icr1 | ((u64)icr2 << 32);
+}
+static struct apic_ops xapic_ops = {
+        .read = native_apic_mem_read,
+        .write = native_apic_mem_write,
+        .icr_read = xapic_icr_read,
+        .icr_write = xapic_icr_write,
+        .wait_icr_idle = xapic_wait_icr_idle,
+        .safe_wait_icr_idle = safe_xapic_wait_icr_idle,
+};
+struct apic_ops __read_mostly *apic_ops = &xapic_ops;
+EXPORT_SYMBOL_GPL(apic_ops);
 /**
 * enable_NMI_through_LVT0 - enable NMI through local vector table 0
 */
 void __cpuinit enable_NMI_through_LVT0(void)
 {
-        unsigned int v = APIC_DM_NMI;
+        unsigned int v;
-        /* Level triggered for 82489DX */
+        /* unmask and set to NMI */
+        v = APIC_DM_NMI;
+        /* Level triggered for 82489DX (32bit mode) */
        if (!lapic_is_integrated())
                v |= APIC_LVT_LEVEL_TRIGGER;
        apic_write(APIC_LVT0, v);
 }
@@ -193,9 +232,13 @@ int get_physical_broadcast(void)
 */
 int lapic_get_maxlvt(void)
 {
-        unsigned int v = apic_read(APIC_LVR);
+        unsigned int v;
-        /* 82489DXs do not report # of LVT entries. */
+        v = apic_read(APIC_LVR);
+        /*
+         * - we always have APIC integrated on 64bit mode
+         * - 82489DXs do not report # of LVT entries
+         */
        return APIC_INTEGRATED(GET_APIC_VERSION(v)) ? GET_APIC_MAXLVT(v) : 2;
 }
@@ -203,8 +246,12 @@ int lapic_get_maxlvt(void)
 * Local APIC timer
 */
-/* Clock divisor is set to 16 */
+/* Clock divisor */
+#ifdef CONFG_X86_64
+#define APIC_DIVISOR 1
+#else
 #define APIC_DIVISOR 16
+#endif
 /*
 * This function sets up the local APIC timer, with a timeout of
@@ -212,6 +259,9 @@ int lapic_get_maxlvt(void)
 * this function twice on the boot CPU, once with a bogus timeout
 * value, second time for real. The other (noncalibrating) CPUs
 * call this function only once, with the real, calibrated value.
+ *
+ * We do reads before writes even if unnecessary, to get around the
+ * P5 APIC double write bug.
 */
 static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 {
@@ -233,14 +283,44 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
         */
        tmp_value = apic_read(APIC_TDCR);
        apic_write(APIC_TDCR,
-                   (tmp_value & ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE)) |
+                (tmp_value & ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE)) |
-                   APIC_TDR_DIV_16);
+                APIC_TDR_DIV_16);
        if (!oneshot)
                apic_write(APIC_TMICT, clocks / APIC_DIVISOR);
 }
 /*
+ * Setup extended LVT, AMD specific (K8, family 10h)
+ *
+ * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and
+ * MCE interrupts are supported. Thus MCE offset must be set to 0.
+ */
+#define APIC_EILVT_LVTOFF_MCE 0
+#define APIC_EILVT_LVTOFF_IBS 1
+static void setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask)
+{
+        unsigned long reg = (lvt_off << 4) + APIC_EILVT0;
+        unsigned int  v   = (mask << 16) | (msg_type << 8) | vector;
+        apic_write(reg, v);
+}
+u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask)
+{
+        setup_APIC_eilvt(APIC_EILVT_LVTOFF_MCE, vector, msg_type, mask);
+        return APIC_EILVT_LVTOFF_MCE;
+}
+u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask)
+{
+        setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask);
+        return APIC_EILVT_LVTOFF_IBS;
+}
+/*
 * Program the next event, relative to now
 */
 static int lapic_next_event(unsigned long delta,
@@ -259,8 +339,8 @@ static void lapic_timer_setup(enum clock_event_mode mode,
        unsigned long flags;
        unsigned int v;
-        /* Lapic used for broadcast ? */
+        /* Lapic used as dummy for broadcast ? */
-        if (!local_apic_timer_verify_ok)
+        if (evt->features & CLOCK_EVT_FEAT_DUMMY)
                return;
        local_irq_save(flags);
@@ -473,7 +553,7 @@ static int __init calibrate_APIC_clock(void)
                return -1;
        }
-        local_apic_timer_verify_ok = 1;
+        levt->features &= ~CLOCK_EVT_FEAT_DUMMY;
        /* We trust the pm timer based calibration */
        if (!pm_referenced) {
@@ -507,11 +587,11 @@ static int __init calibrate_APIC_clock(void)
                if (deltaj >= LAPIC_CAL_LOOPS-2 && deltaj <= LAPIC_CAL_LOOPS+2)
                        apic_printk(APIC_VERBOSE, "... jiffies result ok\n");
                else
-                        local_apic_timer_verify_ok = 0;
+                        levt->features |= CLOCK_EVT_FEAT_DUMMY;
        } else
                local_irq_enable();
-        if (!local_apic_timer_verify_ok) {
+        if (levt->features & CLOCK_EVT_FEAT_DUMMY) {
                printk(KERN_WARNING
                       "APIC timer disabled due to verification failure.\n");
                        return -1;
@@ -533,7 +613,8 @@ void __init setup_boot_APIC_clock(void)
         * timer as a dummy clock event source on SMP systems, so the
         * broadcast mechanism is used. On UP systems simply ignore it.
         */
-        if (local_apic_timer_disabled) {
+        if (disable_apic_timer) {
+                printk(KERN_INFO "Disabling APIC timer\n");
                /* No broadcast on UP ! */
                if (num_possible_cpus() > 1) {
                        lapic_clockevent.mult = 1;
@@ -602,7 +683,11 @@ static void local_apic_timer_interrupt(void)
        /*
         * the NMI deadlock-detector uses this.
         */
+#ifdef CONFIG_X86_64
+        add_pda(apic_timer_irqs, 1);
+#else
        per_cpu(irq_stat, cpu).apic_timer_irqs++;
+#endif
        evt->event_handler(evt);
 }
@@ -642,35 +727,6 @@ int setup_profiling_timer(unsigned int multiplier)
 }
 /*
- * Setup extended LVT, AMD specific (K8, family 10h)
- *
- * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and
- * MCE interrupts are supported. Thus MCE offset must be set to 0.
- */
-#define APIC_EILVT_LVTOFF_MCE 0
-#define APIC_EILVT_LVTOFF_IBS 1
-static void setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask)
-{
-        unsigned long reg = (lvt_off << 4) + APIC_EILVT0;
-        unsigned int  v   = (mask << 16) | (msg_type << 8) | vector;
-        apic_write(reg, v);
-}
-u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask)
-{
-        setup_APIC_eilvt(APIC_EILVT_LVTOFF_MCE, vector, msg_type, mask);
-        return APIC_EILVT_LVTOFF_MCE;
-}
-u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask)
-{
-        setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask);
-        return APIC_EILVT_LVTOFF_IBS;
-}
-/*
 * Local APIC start and shutdown
 */
@@ -715,7 +771,7 @@ void clear_local_APIC(void)
        }
        /* lets not touch this if we didn't frob it */
-#ifdef CONFIG_X86_MCE_P4THERMAL
+#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(X86_MCE_INTEL)
        if (maxlvt >= 5) {
                v = apic_read(APIC_LVTTHMR);
                apic_write(APIC_LVTTHMR, v | APIC_LVT_MASKED);
@@ -732,10 +788,6 @@ void clear_local_APIC(void)
        if (maxlvt >= 4)
                apic_write(APIC_LVTPC, APIC_LVT_MASKED);
-#ifdef CONFIG_X86_MCE_P4THERMAL
-        if (maxlvt >= 5)
-                apic_write(APIC_LVTTHMR, APIC_LVT_MASKED);
-#endif
        /* Integrated APIC (!82489DX) ? */
        if (lapic_is_integrated()) {
                if (maxlvt > 3)
@@ -750,7 +802,7 @@ void clear_local_APIC(void)
 */
 void disable_local_APIC(void)
 {
-        unsigned long value;
+        unsigned int value;
        clear_local_APIC();
@@ -762,6 +814,7 @@ void disable_local_APIC(void)
        value &= ~APIC_SPIV_APIC_ENABLED;
        apic_write(APIC_SPIV, value);
+#ifdef CONFIG_X86_32
        /*
         * When LAPIC was disabled by the BIOS and enabled by the kernel,
         * restore the disabled state.
@@ -773,6 +826,7 @@ void disable_local_APIC(void)
                l &= ~MSR_IA32_APICBASE_ENABLE;
                wrmsr(MSR_IA32_APICBASE, l, h);
        }
+#endif
 }
 /*
@@ -789,11 +843,15 @@ void lapic_shutdown(void)
                return;
        local_irq_save(flags);
-        clear_local_APIC();
-        if (enabled_via_apicbase)
+#ifdef CONFIG_X86_32
+        if (!enabled_via_apicbase)
+                clear_local_APIC();
+        else
+#endif
                disable_local_APIC();
        local_irq_restore(flags);
 }
@@ -838,6 +896,12 @@ int __init verify_local_APIC(void)
         */
        reg0 = apic_read(APIC_ID);
        apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0);
+        apic_write(APIC_ID, reg0 ^ APIC_ID_MASK);
+        reg1 = apic_read(APIC_ID);
+        apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1);
+        apic_write(APIC_ID, reg0);
+        if (reg1 != (reg0 ^ APIC_ID_MASK))
+                return 0;
        /*
         * The next two are just to see if we have sane values.
@@ -863,14 +927,15 @@ void __init sync_Arb_IDs(void)
         */
        if (modern_apic() || boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
                return;
        /*
         * Wait for idle.
         */
        apic_wait_icr_idle();
        apic_printk(APIC_DEBUG, "Synchronizing Arb IDs.\n");
-        apic_write(APIC_ICR,
+        apic_write(APIC_ICR, APIC_DEST_ALLINC |
-                   APIC_DEST_ALLINC | APIC_INT_LEVELTRIG | APIC_DM_INIT);
+                        APIC_INT_LEVELTRIG | APIC_DM_INIT);
 }
 /*
@@ -878,7 +943,7 @@ void __init sync_Arb_IDs(void)
 */
 void __init init_bsp_APIC(void)
 {
-        unsigned long value;
+        unsigned int value;
        /*
         * Don't do the setup now if we have a SMP BIOS as the
@@ -899,11 +964,13 @@ void __init init_bsp_APIC(void)
        value &= ~APIC_VECTOR_MASK;
        value |= APIC_SPIV_APIC_ENABLED;
+#ifdef CONFIG_X86_32
        /* This bit is reserved on P4/Xeon and should be cleared */
        if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
            (boot_cpu_data.x86 == 15))
                value &= ~APIC_SPIV_FOCUS_DISABLED;
        else
+#endif
                value |= APIC_SPIV_FOCUS_DISABLED;
        value |= SPURIOUS_APIC_VECTOR;
        apic_write(APIC_SPIV, value);
@@ -922,6 +989,16 @@ static void __cpuinit lapic_setup_esr(void)
 {
        unsigned long oldvalue, value, maxlvt;
        if (lapic_is_integrated() && !esr_disable) {
+                if (esr_disable) {
+                        /*
+                         * Something untraceable is creating bad interrupts on
+                         * secondary quads ... for the moment, just leave the
+                         * ESR disabled - we can't do anything useful with the
+                         * errors anyway - mbligh
+                         */
+                        printk(KERN_INFO "Leaving ESR disabled.\n");
+                        return;
+                }
                /* !82489DX */
                maxlvt = lapic_get_maxlvt();
                if (maxlvt > 3)         /* Due to the Pentium erratum 3AP. */
@@ -942,16 +1019,7 @@ static void __cpuinit lapic_setup_esr(void)
                                "vector: 0x%08lx  after: 0x%08lx\n",
                                oldvalue, value);
        } else {
-                if (esr_disable)
+                printk(KERN_INFO "No ESR for 82489DX.\n");
-                        /*
-                         * Something untraceable is creating bad interrupts on
-                         * secondary quads ... for the moment, just leave the
-                         * ESR disabled - we can't do anything useful with the
-                         * errors anyway - mbligh
-                         */
-                        printk(KERN_INFO "Leaving ESR disabled.\n");
-                else
-                        printk(KERN_INFO "No ESR for 82489DX.\n");
        }
 }
@@ -1089,13 +1157,17 @@ void __cpuinit setup_local_APIC(void)
 void __cpuinit end_local_APIC_setup(void)
 {
-        unsigned long value;
        lapic_setup_esr();
-        /* Disable the local apic timer */
-        value = apic_read(APIC_LVTT);
+#ifdef CONFIG_X86_32
-        value |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
+        {
-        apic_write(APIC_LVTT, value);
+                unsigned int value;
+                /* Disable the local apic timer */
+                value = apic_read(APIC_LVTT);
+                value |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
+                apic_write(APIC_LVTT, value);
+        }
+#endif
        setup_apic_nmi_watchdog(NULL);
        apic_pm_activate();
@@ -1205,7 +1277,7 @@ void __init init_apic_mappings(void)
         * default configuration (or the MP table is broken).
         */
        if (boot_cpu_physical_apicid == -1U)
-                boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+                boot_cpu_physical_apicid = read_apic_id();
 }
@@ -1242,7 +1314,7 @@ int __init APIC_init_uniprocessor(void)
         * might be zero if read from MP tables. Get it from LAPIC.
         */
 #ifdef CONFIG_CRASH_DUMP
-        boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+        boot_cpu_physical_apicid = read_apic_id();
 #endif
        physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
@@ -1321,59 +1393,12 @@ void smp_error_interrupt(struct pt_regs *regs)
        irq_exit();
 }
-#ifdef CONFIG_SMP
-void __init smp_intr_init(void)
-{
-        /*
-         * IRQ0 must be given a fixed assignment and initialized,
-         * because it's used before the IO-APIC is set up.
-         */
-        set_intr_gate(FIRST_DEVICE_VECTOR, interrupt[0]);
-        /*
-         * The reschedule interrupt is a CPU-to-CPU reschedule-helper
-         * IPI, driven by wakeup.
-         */
-        alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
-        /* IPI for invalidation */
-        alloc_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt);
-        /* IPI for generic function call */
-        alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
-        /* IPI for single call function */
-        set_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
-                                call_function_single_interrupt);
-}
-#endif
-/*
- * Initialize APIC interrupts
- */
-void __init apic_intr_init(void)
-{
-#ifdef CONFIG_SMP
-        smp_intr_init();
-#endif
-        /* self generated IPI for local APIC timer */
-        alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
-        /* IPI vectors for APIC spurious and error interrupts */
-        alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
-        alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
-        /* thermal monitor LVT interrupt */
-#ifdef CONFIG_X86_MCE_P4THERMAL
-        alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
-#endif
-}
 /**
 * connect_bsp_APIC - attach the APIC to the interrupt system
 */
 void __init connect_bsp_APIC(void)
 {
+#ifdef CONFIG_X86_32
        if (pic_mode) {
                /*
                 * Do not trust the local APIC being empty at bootup.
@@ -1388,6 +1413,7 @@ void __init connect_bsp_APIC(void)
                outb(0x70, 0x22);
                outb(0x01, 0x23);
        }
+#endif
        enable_apic_mode();
 }
@@ -1400,6 +1426,9 @@ void __init connect_bsp_APIC(void)
 */
 void disconnect_bsp_APIC(int virt_wire_setup)
 {
+        unsigned int value;
+#ifdef CONFIG_X86_32
        if (pic_mode) {
                /*
                 * Put the board back into PIC mode (has an effect only on
@@ -1411,54 +1440,53 @@ void disconnect_bsp_APIC(int virt_wire_setup)
                                "entering PIC mode.\n");
                outb(0x70, 0x22);
                outb(0x00, 0x23);
-        } else {
+                return;
-                /* Go back to Virtual Wire compatibility mode */
+        }
-                unsigned long value;
+#endif
-                /* For the spurious interrupt use vector F, and enable it */
+        /* Go back to Virtual Wire compatibility mode */
-                value = apic_read(APIC_SPIV);
-                value &= ~APIC_VECTOR_MASK;
-                value |= APIC_SPIV_APIC_ENABLED;
-                value |= 0xf;
-                apic_write(APIC_SPIV, value);
-                if (!virt_wire_setup) {
+        /* For the spurious interrupt use vector F, and enable it */
-                        /*
+        value = apic_read(APIC_SPIV);
-                         * For LVT0 make it edge triggered, active high,
+        value &= ~APIC_VECTOR_MASK;
-                         * external and enabled
+        value |= APIC_SPIV_APIC_ENABLED;
-                         */
+        value |= 0xf;
-                        value = apic_read(APIC_LVT0);
+        apic_write(APIC_SPIV, value);
-                        value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
-                                APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
-                                APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED);
-                        value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
-                        value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_EXTINT);
-                        apic_write(APIC_LVT0, value);
-                } else {
-                        /* Disable LVT0 */
-                        apic_write(APIC_LVT0, APIC_LVT_MASKED);
-                }
+        if (!virt_wire_setup) {
                /*
-                 * For LVT1 make it edge triggered, active high, nmi and
+                 * For LVT0 make it edge triggered, active high,
-                 * enabled
+                 * external and enabled
                 */
-                value = apic_read(APIC_LVT1);
+                value = apic_read(APIC_LVT0);
-                value &= ~(
+                value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
-                        APIC_MODE_MASK | APIC_SEND_PENDING |
                        APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
                        APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED);
                value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
-                value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_NMI);
+                value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_EXTINT);
-                apic_write(APIC_LVT1, value);
+                apic_write(APIC_LVT0, value);
+        } else {
+                /* Disable LVT0 */
+                apic_write(APIC_LVT0, APIC_LVT_MASKED);
        }
+        /*
+         * For LVT1 make it edge triggered, active high,
+         * nmi and enabled
+         */
+        value = apic_read(APIC_LVT1);
+        value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
+                        APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
+                        APIC_LVT_LEVEL_TRIGGER | APIC_LVT_MASKED);
+        value |= APIC_LVT_REMOTE_IRR | APIC_SEND_PENDING;
+        value = SET_APIC_DELIVERY_MODE(value, APIC_MODE_NMI);
+        apic_write(APIC_LVT1, value);
 }
 void __cpuinit generic_processor_info(int apicid, int version)
 {
        int cpu;
        cpumask_t tmp_map;
-        physid_mask_t phys_cpu;
        /*
         * Validate version
@@ -1471,9 +1499,6 @@ void __cpuinit generic_processor_info(int apicid, int version)
        }
        apic_version[apicid] = version;
-        phys_cpu = apicid_to_cpu_present(apicid);
-        physids_or(phys_cpu_present_map, phys_cpu_present_map, phys_cpu);
        if (num_processors >= NR_CPUS) {
                printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached."
                        "  Processor ignored.\n", NR_CPUS);
@@ -1484,17 +1509,19 @@ void __cpuinit generic_processor_info(int apicid, int version)
        cpus_complement(tmp_map, cpu_present_map);
        cpu = first_cpu(tmp_map);
-        if (apicid == boot_cpu_physical_apicid)
+        physid_set(apicid, phys_cpu_present_map);
+        if (apicid == boot_cpu_physical_apicid) {
                /*
                 * x86_bios_cpu_apicid is required to have processors listed
                 * in same order as logical cpu numbers. Hence the first
                 * entry is BSP, and so on.
                 */
                cpu = 0;
+        }
        if (apicid > max_physical_apicid)
                max_physical_apicid = apicid;
+#ifdef CONFIG_X86_32
        /*
         * Would be preferable to switch to bigsmp when CONFIG_HOTPLUG_CPU=y
         * but we need to work other dependencies like SMP_SUSPEND etc
@@ -1514,7 +1541,9 @@ void __cpuinit generic_processor_info(int apicid, int version)
                        def_to_bigsmp = 1;
                }
        }
-#ifdef CONFIG_SMP
+#endif
+#if defined(CONFIG_X86_SMP) || defined(CONFIG_X86_64)
        /* are we being called early in kernel startup? */
        if (early_per_cpu_ptr(x86_cpu_to_apicid)) {
                u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
@@ -1527,6 +1556,7 @@ void __cpuinit generic_processor_info(int apicid, int version)
                per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
        }
 #endif
        cpu_set(cpu, cpu_possible_map);
        cpu_set(cpu, cpu_present_map);
 }
@@ -1537,6 +1567,11 @@ void __cpuinit generic_processor_info(int apicid, int version)
 #ifdef CONFIG_PM
 static struct {
+        /*
+         * 'active' is true if the local APIC was enabled by us and
+         * not the BIOS; this signifies that we are also responsible
+         * for disabling it before entering apm/acpi suspend
+         */
        int active;
        /* r/w apic fields */
        unsigned int apic_id;
@@ -1577,7 +1612,7 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
        apic_pm_state.apic_lvterr = apic_read(APIC_LVTERR);
        apic_pm_state.apic_tmict = apic_read(APIC_TMICT);
        apic_pm_state.apic_tdcr = apic_read(APIC_TDCR);
-#ifdef CONFIG_X86_MCE_P4THERMAL
+#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL)
        if (maxlvt >= 5)
                apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
 #endif
@@ -1601,16 +1636,23 @@ static int lapic_resume(struct sys_device *dev)
        local_irq_save(flags);
-        /*
+#ifdef CONFIG_X86_64
-         * Make sure the APICBASE points to the right address
+        if (x2apic)
-         *
+                enable_x2apic();
-         * FIXME! This will be wrong if we ever support suspend on
+        else
-         * SMP! We'll need to do this as part of the CPU restore!
+#endif
-         */
+        {
-        rdmsr(MSR_IA32_APICBASE, l, h);
+                /*
-        l &= ~MSR_IA32_APICBASE_BASE;
+                 * Make sure the APICBASE points to the right address
-        l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
+                 *
-        wrmsr(MSR_IA32_APICBASE, l, h);
+                 * FIXME! This will be wrong if we ever support suspend on
+                 * SMP! We'll need to do this as part of the CPU restore!
+                 */
+                rdmsr(MSR_IA32_APICBASE, l, h);
+                l &= ~MSR_IA32_APICBASE_BASE;
+                l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
+                wrmsr(MSR_IA32_APICBASE, l, h);
+        }
        apic_write(APIC_LVTERR, ERROR_APIC_VECTOR | APIC_LVT_MASKED);
        apic_write(APIC_ID, apic_pm_state.apic_id);
@@ -1620,7 +1662,7 @@ static int lapic_resume(struct sys_device *dev)
        apic_write(APIC_SPIV, apic_pm_state.apic_spiv);
        apic_write(APIC_LVT0, apic_pm_state.apic_lvt0);
        apic_write(APIC_LVT1, apic_pm_state.apic_lvt1);
-#ifdef CONFIG_X86_MCE_P4THERMAL
+#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL)
        if (maxlvt >= 5)
                apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr);
 #endif
@@ -1634,7 +1676,9 @@ static int lapic_resume(struct sys_device *dev)
        apic_write(APIC_LVTERR, apic_pm_state.apic_lvterr);
        apic_write(APIC_ESR, 0);
        apic_read(APIC_ESR);
        local_irq_restore(flags);
        return 0;
 }
@@ -1690,20 +1734,20 @@ static int __init parse_lapic(char *arg)
 }
 early_param("lapic", parse_lapic);
-static int __init parse_nolapic(char *arg)
+static int __init setup_disableapic(char *arg)
 {
        disable_apic = 1;
        setup_clear_cpu_cap(X86_FEATURE_APIC);
        return 0;
 }
-early_param("nolapic", parse_nolapic);
+early_param("disableapic", setup_disableapic);
-static int __init parse_disable_lapic_timer(char *arg)
+/* same as disableapic, for compatibility */
+static int __init setup_nolapic(char *arg)
 {
-        local_apic_timer_disabled = 1;
+        return setup_disableapic(arg);
-        return 0;
 }
-early_param("nolapic_timer", parse_disable_lapic_timer);
+early_param("nolapic", setup_nolapic);
 static int __init parse_lapic_timer_c2_ok(char *arg)
 {
@@ -1712,15 +1756,40 @@ static int __init parse_lapic_timer_c2_ok(char *arg)
 }
 early_param("lapic_timer_c2_ok", parse_lapic_timer_c2_ok);
+static int __init parse_disable_apic_timer(char *arg)
+{
+        disable_apic_timer = 1;
+        return 0;
+}
+early_param("noapictimer", parse_disable_apic_timer);
+static int __init parse_nolapic_timer(char *arg)
+{
+        disable_apic_timer = 1;
+        return 0;
+}
+early_param("nolapic_timer", parse_nolapic_timer);
 static int __init apic_set_verbosity(char *arg)
 {
-        if (!arg)
+        if (!arg)  {
+#ifdef CONFIG_X86_64
+                skip_ioapic_setup = 0;
+                ioapic_force = 1;
+                return 0;
+#endif
                return -EINVAL;
+        }
-        if (strcmp(arg, "debug") == 0)
+        if (strcmp("debug", arg) == 0)
                apic_verbosity = APIC_DEBUG;
-        else if (strcmp(arg, "verbose") == 0)
+        else if (strcmp("verbose", arg) == 0)
                apic_verbosity = APIC_VERBOSE;
+        else {
+                printk(KERN_WARNING "APIC Verbosity level %s not recognised"
+                        " use apic=verbose or apic=debug\n", arg);
+                return -EINVAL;
+        }
        return 0;
 }
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 446c062e831c..53898b65a6ae 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -27,6 +27,7 @@
 #include <linux/clockchips.h>
 #include <linux/acpi_pmtmr.h>
 #include <linux/module.h>
+#include <linux/dmar.h>
 #include <asm/atomic.h>
 #include <asm/smp.h>
@@ -39,13 +40,20 @@
 #include <asm/proto.h>
 #include <asm/timex.h>
 #include <asm/apic.h>
+#include <asm/i8259.h>
 #include <mach_ipi.h>
 #include <mach_apic.h>
+/* Disable local APIC timer from the kernel commandline or via dmi quirk */
 static int disable_apic_timer __cpuinitdata;
 static int apic_calibrate_pmtmr __initdata;
 int disable_apic;
+int disable_x2apic;
+int x2apic;
+/* x2apic enabled before OS handover */
+int x2apic_preenabled;
 /* Local APIC timer works in C2 */
 int local_apic_timer_c2_ok;
@@ -73,6 +81,9 @@ static void lapic_timer_setup(enum clock_event_mode mode,
 static void lapic_timer_broadcast(cpumask_t mask);
 static void apic_pm_activate(void);
+/*
+ * The local apic timer can be used for any function which is CPU local.
+ */
 static struct clock_event_device lapic_clockevent = {
        .name           = "lapic",
        .features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT
@@ -99,11 +110,15 @@ static inline int lapic_get_version(void)
 }
 /*
- * Check, if the APIC is integrated or a seperate chip
+ * Check, if the APIC is integrated or a separate chip
 */
 static inline int lapic_is_integrated(void)
 {
+#ifdef CONFIG_X86_64
        return 1;
+#else
+        return APIC_INTEGRATED(lapic_get_version());
+#endif
 }
 /*
@@ -118,13 +133,18 @@ static int modern_apic(void)
        return lapic_get_version() >= 0x14;
 }
-void apic_wait_icr_idle(void)
+/*
+ * Paravirt kernels also might be using these below ops. So we still
+ * use generic apic_read()/apic_write(), which might be pointing to different
+ * ops in PARAVIRT case.
+ */
+void xapic_wait_icr_idle(void)
 {
        while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
                cpu_relax();
 }
-u32 safe_apic_wait_icr_idle(void)
+u32 safe_xapic_wait_icr_idle(void)
 {
        u32 send_status;
        int timeout;
@@ -140,6 +160,68 @@ u32 safe_apic_wait_icr_idle(void)
        return send_status;
 }
+void xapic_icr_write(u32 low, u32 id)
+{
+        apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(id));
+        apic_write(APIC_ICR, low);
+}
+u64 xapic_icr_read(void)
+{
+        u32 icr1, icr2;
+        icr2 = apic_read(APIC_ICR2);
+        icr1 = apic_read(APIC_ICR);
+        return icr1 | ((u64)icr2 << 32);
+}
+static struct apic_ops xapic_ops = {
+        .read = native_apic_mem_read,
+        .write = native_apic_mem_write,
+        .icr_read = xapic_icr_read,
+        .icr_write = xapic_icr_write,
+        .wait_icr_idle = xapic_wait_icr_idle,
+        .safe_wait_icr_idle = safe_xapic_wait_icr_idle,
+};
+struct apic_ops __read_mostly *apic_ops = &xapic_ops;
+EXPORT_SYMBOL_GPL(apic_ops);
+static void x2apic_wait_icr_idle(void)
+{
+        /* no need to wait for icr idle in x2apic */
+        return;
+}
+static u32 safe_x2apic_wait_icr_idle(void)
+{
+        /* no need to wait for icr idle in x2apic */
+        return 0;
+}
+void x2apic_icr_write(u32 low, u32 id)
+{
+        wrmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), ((__u64) id) << 32 | low);
+}
+u64 x2apic_icr_read(void)
+{
+        unsigned long val;
+        rdmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), val);
+        return val;
+}
+static struct apic_ops x2apic_ops = {
+        .read = native_apic_msr_read,
+        .write = native_apic_msr_write,
+        .icr_read = x2apic_icr_read,
+        .icr_write = x2apic_icr_write,
+        .wait_icr_idle = x2apic_wait_icr_idle,
+        .safe_wait_icr_idle = safe_x2apic_wait_icr_idle,
+};
 /**
 * enable_NMI_through_LVT0 - enable NMI through local vector table 0
 */
@@ -149,6 +231,11 @@ void __cpuinit enable_NMI_through_LVT0(void)
        /* unmask and set to NMI */
        v = APIC_DM_NMI;
+        /* Level triggered for 82489DX (32bit mode) */
+        if (!lapic_is_integrated())
+                v |= APIC_LVT_LEVEL_TRIGGER;
        apic_write(APIC_LVT0, v);
 }
@@ -157,14 +244,28 @@ void __cpuinit enable_NMI_through_LVT0(void)
 */
 int lapic_get_maxlvt(void)
 {
-        unsigned int v, maxlvt;
+        unsigned int v;
        v = apic_read(APIC_LVR);
-        maxlvt = GET_APIC_MAXLVT(v);
+        /*
-        return maxlvt;
+         * - we always have APIC integrated on 64bit mode
+         * - 82489DXs do not report # of LVT entries
+         */
+        return APIC_INTEGRATED(GET_APIC_VERSION(v)) ? GET_APIC_MAXLVT(v) : 2;
 }
 /*
+ * Local APIC timer
+ */
+/* Clock divisor */
+#ifdef CONFG_X86_64
+#define APIC_DIVISOR 1
+#else
+#define APIC_DIVISOR 16
+#endif
+/*
 * This function sets up the local APIC timer, with a timeout of
 * 'clocks' APIC bus clock. During calibration we actually call
 * this function twice on the boot CPU, once with a bogus timeout
@@ -174,7 +275,6 @@ int lapic_get_maxlvt(void)
 * We do reads before writes even if unnecessary, to get around the
 * P5 APIC double write bug.
 */
 static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 {
        unsigned int lvtt_value, tmp_value;
@@ -182,6 +282,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
        lvtt_value = LOCAL_TIMER_VECTOR;
        if (!oneshot)
                lvtt_value |= APIC_LVT_TIMER_PERIODIC;
+        if (!lapic_is_integrated())
+                lvtt_value |= SET_APIC_TIMER_BASE(APIC_TIMER_BASE_DIV);
        if (!irqen)
                lvtt_value |= APIC_LVT_MASKED;
@@ -191,12 +294,12 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
         * Divide PICLK by 16
         */
        tmp_value = apic_read(APIC_TDCR);
-        apic_write(APIC_TDCR, (tmp_value
+        apic_write(APIC_TDCR,
-                                & ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE))
+                (tmp_value & ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE)) |
-                                | APIC_TDR_DIV_16);
+                APIC_TDR_DIV_16);
        if (!oneshot)
-                apic_write(APIC_TMICT, clocks);
+                apic_write(APIC_TMICT, clocks / APIC_DIVISOR);
 }
 /*
@@ -366,7 +469,7 @@ static int __init calibrate_APIC_clock(void)
        lapic_clockevent.min_delta_ns =
                clockevent_delta2ns(0xF, &lapic_clockevent);
-        calibration_result = result / HZ;
+        calibration_result = (result * APIC_DIVISOR) / HZ;
        /*
         * Do a sanity check on the APIC calibration result
@@ -388,10 +491,10 @@ static int __init calibrate_APIC_clock(void)
 void __init setup_boot_APIC_clock(void)
 {
        /*
-         * The local apic timer can be disabled via the kernel commandline.
+         * The local apic timer can be disabled via the kernel
-         * Register the lapic timer as a dummy clock event source on SMP
+         * commandline or from the CPU detection code. Register the lapic
-         * systems, so the broadcast mechanism is used. On UP systems simply
+         * timer as a dummy clock event source on SMP systems, so the
-         * ignore it.
+         * broadcast mechanism is used. On UP systems simply ignore it.
         */
        if (disable_apic_timer) {
                printk(KERN_INFO "Disabling APIC timer\n");
@@ -403,7 +506,9 @@ void __init setup_boot_APIC_clock(void)
                return;
        }
-        printk(KERN_INFO "Using local APIC timer interrupts.\n");
+        apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n"
+                    "calibrating APIC timer ...\n");
        if (calibrate_APIC_clock()) {
                /* No broadcast on UP ! */
                if (num_possible_cpus() > 1)
@@ -422,6 +527,7 @@ void __init setup_boot_APIC_clock(void)
                printk(KERN_WARNING "APIC timer registered as dummy,"
                        " due to nmi_watchdog=%d!\n", nmi_watchdog);
+        /* Setup the lapic or request the broadcast */
        setup_APIC_timer();
 }
@@ -460,7 +566,11 @@ static void local_apic_timer_interrupt(void)
        /*
         * the NMI deadlock-detector uses this.
         */
+#ifdef CONFIG_X86_64
        add_pda(apic_timer_irqs, 1);
+#else
+        per_cpu(irq_stat, cpu).apic_timer_irqs++;
+#endif
        evt->event_handler(evt);
 }
@@ -491,6 +601,7 @@ void smp_apic_timer_interrupt(struct pt_regs *regs)
        irq_enter();
        local_apic_timer_interrupt();
        irq_exit();
        set_irq_regs(old_regs);
 }
@@ -544,6 +655,13 @@ void clear_local_APIC(void)
                apic_write(APIC_LVTPC, v | APIC_LVT_MASKED);
        }
+        /* lets not touch this if we didn't frob it */
+#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(X86_MCE_INTEL)
+        if (maxlvt >= 5) {
+                v = apic_read(APIC_LVTTHMR);
+                apic_write(APIC_LVTTHMR, v | APIC_LVT_MASKED);
+        }
+#endif
        /*
         * Clean APIC state for other OSs:
         */
@@ -554,8 +672,14 @@ void clear_local_APIC(void)
                apic_write(APIC_LVTERR, APIC_LVT_MASKED);
        if (maxlvt >= 4)
                apic_write(APIC_LVTPC, APIC_LVT_MASKED);
-        apic_write(APIC_ESR, 0);
-        apic_read(APIC_ESR);
+        /* Integrated APIC (!82489DX) ? */
+        if (lapic_is_integrated()) {
+                if (maxlvt > 3)
+                        /* Clear ESR due to Pentium errata 3AP and 11AP */
+                        apic_write(APIC_ESR, 0);
+                apic_read(APIC_ESR);
+        }
 }
 /**
@@ -574,8 +698,28 @@ void disable_local_APIC(void)
        value = apic_read(APIC_SPIV);
        value &= ~APIC_SPIV_APIC_ENABLED;
        apic_write(APIC_SPIV, value);
+#ifdef CONFIG_X86_32
+        /*
+         * When LAPIC was disabled by the BIOS and enabled by the kernel,
+         * restore the disabled state.
+         */
+        if (enabled_via_apicbase) {
+                unsigned int l, h;
+                rdmsr(MSR_IA32_APICBASE, l, h);
+                l &= ~MSR_IA32_APICBASE_ENABLE;
+                wrmsr(MSR_IA32_APICBASE, l, h);
+        }
+#endif
 }
+/*
+ * If Linux enabled the LAPIC against the BIOS default disable it down before
+ * re-entering the BIOS on shutdown.  Otherwise the BIOS may get confused and
+ * not power-off.  Additionally clear all LVT entries before disable_local_APIC
+ * for the case where Linux didn't enable the LAPIC.
+ */
 void lapic_shutdown(void)
 {
        unsigned long flags;
@@ -585,7 +729,13 @@ void lapic_shutdown(void)
        local_irq_save(flags);
-        disable_local_APIC();
+#ifdef CONFIG_X86_32
+        if (!enabled_via_apicbase)
+                clear_local_APIC();
+        else
+#endif
+                disable_local_APIC();
        local_irq_restore(flags);
 }
@@ -629,10 +779,10 @@ int __init verify_local_APIC(void)
        /*
         * The ID register is read/write in a real APIC.
         */
-        reg0 = read_apic_id();
+        reg0 = apic_read(APIC_ID);
        apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0);
        apic_write(APIC_ID, reg0 ^ APIC_ID_MASK);
-        reg1 = read_apic_id();
+        reg1 = apic_read(APIC_ID);
        apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1);
        apic_write(APIC_ID, reg0);
        if (reg1 != (reg0 ^ APIC_ID_MASK))
@@ -656,8 +806,11 @@ int __init verify_local_APIC(void)
 */
 void __init sync_Arb_IDs(void)
 {
-        /* Unsupported on P4 - see Intel Dev. Manual Vol. 3, Ch. 8.6.1 */
+        /*
-        if (modern_apic())
+         * Unsupported on P4 - see Intel Dev. Manual Vol. 3, Ch. 8.6.1 And not
+         * needed on AMD.
+         */
+        if (modern_apic() || boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
                return;
        /*
@@ -666,8 +819,8 @@ void __init sync_Arb_IDs(void)
        apic_wait_icr_idle();
        apic_printk(APIC_DEBUG, "Synchronizing Arb IDs.\n");
-        apic_write(APIC_ICR, APIC_DEST_ALLINC | APIC_INT_LEVELTRIG
+        apic_write(APIC_ICR, APIC_DEST_ALLINC |
-                                | APIC_DM_INIT);
+                        APIC_INT_LEVELTRIG | APIC_DM_INIT);
 }
 /*
@@ -684,8 +837,6 @@ void __init init_bsp_APIC(void)
        if (smp_found_config || !cpu_has_apic)
                return;
-        value = apic_read(APIC_LVR);
        /*
         * Do not trust the local APIC being empty at bootup.
         */
@@ -697,7 +848,15 @@ void __init init_bsp_APIC(void)
        value = apic_read(APIC_SPIV);
        value &= ~APIC_VECTOR_MASK;
        value |= APIC_SPIV_APIC_ENABLED;
-        value |= APIC_SPIV_FOCUS_DISABLED;
+#ifdef CONFIG_X86_32
+        /* This bit is reserved on P4/Xeon and should be cleared */
+        if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
+            (boot_cpu_data.x86 == 15))
+                value &= ~APIC_SPIV_FOCUS_DISABLED;
+        else
+#endif
+                value |= APIC_SPIV_FOCUS_DISABLED;
        value |= SPURIOUS_APIC_VECTOR;
        apic_write(APIC_SPIV, value);
@@ -706,9 +865,50 @@ void __init init_bsp_APIC(void)
         */
        apic_write(APIC_LVT0, APIC_DM_EXTINT);
        value = APIC_DM_NMI;
+        if (!lapic_is_integrated())             /* 82489DX */
+                value |= APIC_LVT_LEVEL_TRIGGER;
        apic_write(APIC_LVT1, value);
 }
+static void __cpuinit lapic_setup_esr(void)
+{
+        unsigned long oldvalue, value, maxlvt;
+        if (lapic_is_integrated() && !esr_disable) {
+                if (esr_disable) {
+                        /*
+                         * Something untraceable is creating bad interrupts on
+                         * secondary quads ... for the moment, just leave the
+                         * ESR disabled - we can't do anything useful with the
+                         * errors anyway - mbligh
+                         */
+                        printk(KERN_INFO "Leaving ESR disabled.\n");
+                        return;
+                }
+                /* !82489DX */
+                maxlvt = lapic_get_maxlvt();
+                if (maxlvt > 3)         /* Due to the Pentium erratum 3AP. */
+                        apic_write(APIC_ESR, 0);
+                oldvalue = apic_read(APIC_ESR);
+                /* enables sending errors */
+                value = ERROR_APIC_VECTOR;
+                apic_write(APIC_LVTERR, value);
+                /*
+                 * spec says clear errors after enabling vector.
+                 */
+                if (maxlvt > 3)
+                        apic_write(APIC_ESR, 0);
+                value = apic_read(APIC_ESR);
+                if (value != oldvalue)
+                        apic_printk(APIC_VERBOSE, "ESR value before enabling "
+                                "vector: 0x%08lx  after: 0x%08lx\n",
+                                oldvalue, value);
+        } else {
+                printk(KERN_INFO "No ESR for 82489DX.\n");
+        }
+}
 /**
 * setup_local_APIC - setup the local APIC
 */
@@ -814,25 +1014,143 @@ void __cpuinit setup_local_APIC(void)
        preempt_enable();
 }
-static void __cpuinit lapic_setup_esr(void)
-{
-        unsigned maxlvt = lapic_get_maxlvt();
-        apic_write(APIC_LVTERR, ERROR_APIC_VECTOR);
-        /*
-         * spec says clear errors after enabling vector.
-         */
-        if (maxlvt > 3)
-                apic_write(APIC_ESR, 0);
-}
 void __cpuinit end_local_APIC_setup(void)
 {
        lapic_setup_esr();
+#ifdef CONFIG_X86_32
+        {
+                unsigned int value;
+                /* Disable the local apic timer */
+                value = apic_read(APIC_LVTT);
+                value |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
+                apic_write(APIC_LVTT, value);
+        }
+#endif
        setup_apic_nmi_watchdog(NULL);
        apic_pm_activate();
 }
+void check_x2apic(void)
+{
+        int msr, msr2;
+        rdmsr(MSR_IA32_APICBASE, msr, msr2);
+        if (msr & X2APIC_ENABLE) {
+                printk("x2apic enabled by BIOS, switching to x2apic ops\n");
+                x2apic_preenabled = x2apic = 1;
+                apic_ops = &x2apic_ops;
+        }
+}
+void enable_x2apic(void)
+{
+        int msr, msr2;
+        rdmsr(MSR_IA32_APICBASE, msr, msr2);
+        if (!(msr & X2APIC_ENABLE)) {
+                printk("Enabling x2apic\n");
+                wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
+        }
+}
+void enable_IR_x2apic(void)
+{
+#ifdef CONFIG_INTR_REMAP
+        int ret;
+        unsigned long flags;
+        if (!cpu_has_x2apic)
+                return;
+        if (!x2apic_preenabled && disable_x2apic) {
+                printk(KERN_INFO
+                       "Skipped enabling x2apic and Interrupt-remapping "
+                       "because of nox2apic\n");
+                return;
+        }
+        if (x2apic_preenabled && disable_x2apic)
+                panic("Bios already enabled x2apic, can't enforce nox2apic");
+        if (!x2apic_preenabled && skip_ioapic_setup) {
+                printk(KERN_INFO
+                       "Skipped enabling x2apic and Interrupt-remapping "
+                       "because of skipping io-apic setup\n");
+                return;
+        }
+        ret = dmar_table_init();
+        if (ret) {
+                printk(KERN_INFO
+                       "dmar_table_init() failed with %d:\n", ret);
+                if (x2apic_preenabled)
+                        panic("x2apic enabled by bios. But IR enabling failed");
+                else
+                        printk(KERN_INFO
+                               "Not enabling x2apic,Intr-remapping\n");
+                return;
+        }
+        local_irq_save(flags);
+        mask_8259A();
+        save_mask_IO_APIC_setup();
+        ret = enable_intr_remapping(1);
+        if (ret && x2apic_preenabled) {
+                local_irq_restore(flags);
+                panic("x2apic enabled by bios. But IR enabling failed");
+        }
+        if (ret)
+                goto end;
+        if (!x2apic) {
+                x2apic = 1;
+                apic_ops = &x2apic_ops;
+                enable_x2apic();
+        }
+end:
+        if (ret)
+                /*
+                 * IR enabling failed
+                 */
+                restore_IO_APIC_setup();
+        else
+                reinit_intr_remapped_IO_APIC(x2apic_preenabled);
+        unmask_8259A();
+        local_irq_restore(flags);
+        if (!ret) {
+                if (!x2apic_preenabled)
+                        printk(KERN_INFO
+                               "Enabled x2apic and interrupt-remapping\n");
+                else
+                        printk(KERN_INFO
+                               "Enabled Interrupt-remapping\n");
+        } else
+                printk(KERN_ERR
+                       "Failed to enable Interrupt-remapping and x2apic\n");
+#else
+        if (!cpu_has_x2apic)
+                return;
+        if (x2apic_preenabled)
+                panic("x2apic enabled prior OS handover,"
+                      " enable CONFIG_INTR_REMAP");
+        printk(KERN_INFO "Enable CONFIG_INTR_REMAP for enabling intr-remapping "
+               " and x2apic\n");
+#endif
+        return;
+}
 /*
 * Detect and enable local APICs on non-SMP boards.
 * Original code written by Keir Fraser.
@@ -872,7 +1190,7 @@ void __init early_init_lapic_mapping(void)
         * Fetch the APIC ID of the BSP in case we have a
         * default configuration (or the MP table is broken).
         */
-        boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+        boot_cpu_physical_apicid = read_apic_id();
 }
 /**
@@ -880,6 +1198,11 @@ void __init early_init_lapic_mapping(void)
 */
 void __init init_apic_mappings(void)
 {
+        if (x2apic) {
+                boot_cpu_physical_apicid = read_apic_id();
+                return;
+        }
        /*
         * If no local APIC can be found then set up a fake all
         * zeroes page to simulate the local APIC and another
@@ -899,13 +1222,15 @@ void __init init_apic_mappings(void)
         * Fetch the APIC ID of the BSP in case we have a
         * default configuration (or the MP table is broken).
         */
-        boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
+        boot_cpu_physical_apicid = read_apic_id();
 }
 /*
 * This initializes the IO-APIC and APIC hardware if this is
 * a UP kernel.
 */
+int apic_version[MAX_APICS];
 int __init APIC_init_uniprocessor(void)
 {
        if (disable_apic) {
@@ -918,6 +1243,9 @@ int __init APIC_init_uniprocessor(void)
                return -1;
        }
+        enable_IR_x2apic();
+        setup_apic_routing();
        verify_local_APIC();
        connect_bsp_APIC();
@@ -1004,17 +1332,57 @@ asmlinkage void smp_error_interrupt(void)
 }
 /**
- *  * connect_bsp_APIC - attach the APIC to the interrupt system
+ * connect_bsp_APIC - attach the APIC to the interrupt system
- *   */
+ */
 void __init connect_bsp_APIC(void)
 {
+#ifdef CONFIG_X86_32
+        if (pic_mode) {
+                /*
+                 * Do not trust the local APIC being empty at bootup.
+                 */
+                clear_local_APIC();
+                /*
+                 * PIC mode, enable APIC mode in the IMCR, i.e.  connect BSP's
+                 * local APIC to INT and NMI lines.
+                 */
+                apic_printk(APIC_VERBOSE, "leaving PIC mode, "
+                                "enabling APIC mode.\n");
+                outb(0x70, 0x22);
+                outb(0x01, 0x23);
+        }
+#endif
        enable_apic_mode();
 }
+/**
+ * disconnect_bsp_APIC - detach the APIC from the interrupt system
+ * @virt_wire_setup:    indicates, whether virtual wire mode is selected
+ *
+ * Virtual wire mode is necessary to deliver legacy interrupts even when the
+ * APIC is disabled.
+ */
 void disconnect_bsp_APIC(int virt_wire_setup)
 {
+        unsigned int value;
+#ifdef CONFIG_X86_32
+        if (pic_mode) {
+                /*
+                 * Put the board back into PIC mode (has an effect only on
+                 * certain older boards).  Note that APIC interrupts, including
+                 * IPIs, won't work beyond this point!  The only exception are
+                 * INIT IPIs.
+                 */
+                apic_printk(APIC_VERBOSE, "disabling APIC mode, "
+                                "entering PIC mode.\n");
+                outb(0x70, 0x22);
+                outb(0x00, 0x23);
+                return;
+        }
+#endif
        /* Go back to Virtual Wire compatibility mode */
-        unsigned long value;
        /* For the spurious interrupt use vector F, and enable it */
        value = apic_read(APIC_SPIV);
@@ -1040,7 +1408,10 @@ void disconnect_bsp_APIC(int virt_wire_setup)
                apic_write(APIC_LVT0, APIC_LVT_MASKED);
        }
-        /* For LVT1 make it edge triggered, active high, nmi and enabled */
+        /*
+         * For LVT1 make it edge triggered, active high,
+         * nmi and enabled
+         */
        value = apic_read(APIC_LVT1);
        value &= ~(APIC_MODE_MASK | APIC_SEND_PENDING |
                        APIC_INPUT_POLARITY | APIC_LVT_REMOTE_IRR |
@@ -1055,9 +1426,20 @@ void __cpuinit generic_processor_info(int apicid, int version)
        int cpu;
        cpumask_t tmp_map;
+        /*
+         * Validate version
+         */
+        if (version == 0x0) {
+                printk(KERN_WARNING "BIOS bug, APIC version is 0 for CPU#%d! "
+                                "fixing up to 0x10. (tell your hw vendor)\n",
+                                version);
+                version = 0x10;
+        }
+        apic_version[apicid] = version;
        if (num_processors >= NR_CPUS) {
                printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached."
-                       " Processor ignored.\n", NR_CPUS);
+                        "  Processor ignored.\n", NR_CPUS);
                return;
        }
@@ -1077,6 +1459,29 @@ void __cpuinit generic_processor_info(int apicid, int version)
        if (apicid > max_physical_apicid)
                max_physical_apicid = apicid;
+#ifdef CONFIG_X86_32
+        /*
+         * Would be preferable to switch to bigsmp when CONFIG_HOTPLUG_CPU=y
+         * but we need to work other dependencies like SMP_SUSPEND etc
+         * before this can be done without some confusion.
+         * if (CPU_HOTPLUG_ENABLED || num_processors > 8)
+         *       - Ashok Raj <ashok.raj@intel.com>
+         */
+        if (max_physical_apicid >= 8) {
+                switch (boot_cpu_data.x86_vendor) {
+                case X86_VENDOR_INTEL:
+                        if (!APIC_XAPIC(version)) {
+                                def_to_bigsmp = 0;
+                                break;
+                        }
+                        /* If P4 and above fall through */
+                case X86_VENDOR_AMD:
+                        def_to_bigsmp = 1;
+                }
+        }
+#endif
+#if defined(CONFIG_X86_SMP) || defined(CONFIG_X86_64)
        /* are we being called early in kernel startup? */
        if (early_per_cpu_ptr(x86_cpu_to_apicid)) {
                u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
@@ -1088,20 +1493,28 @@ void __cpuinit generic_processor_info(int apicid, int version)
                per_cpu(x86_cpu_to_apicid, cpu) = apicid;
                per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
        }
+#endif
        cpu_set(cpu, cpu_possible_map);
        cpu_set(cpu, cpu_present_map);
 }
+int hard_smp_processor_id(void)
+{
+        return read_apic_id();
+}
 /*
 * Power management
 */
 #ifdef CONFIG_PM
 static struct {
-        /* 'active' is true if the local APIC was enabled by us and
+        /*
-           not the BIOS; this signifies that we are also responsible
+         * 'active' is true if the local APIC was enabled by us and
-           for disabling it before entering apm/acpi suspend */
+         * not the BIOS; this signifies that we are also responsible
+         * for disabling it before entering apm/acpi suspend
+         */
        int active;
        /* r/w apic fields */
        unsigned int apic_id;
@@ -1129,7 +1542,7 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
        maxlvt = lapic_get_maxlvt();
-        apic_pm_state.apic_id = read_apic_id();
+        apic_pm_state.apic_id = apic_read(APIC_ID);
        apic_pm_state.apic_taskpri = apic_read(APIC_TASKPRI);
        apic_pm_state.apic_ldr = apic_read(APIC_LDR);
        apic_pm_state.apic_dfr = apic_read(APIC_DFR);
@@ -1142,10 +1555,11 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
        apic_pm_state.apic_lvterr = apic_read(APIC_LVTERR);
        apic_pm_state.apic_tmict = apic_read(APIC_TMICT);
        apic_pm_state.apic_tdcr = apic_read(APIC_TDCR);
-#ifdef CONFIG_X86_MCE_INTEL
+#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL)
        if (maxlvt >= 5)
                apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
 #endif
        local_irq_save(flags);
        disable_local_APIC();
        local_irq_restore(flags);
@@ -1164,10 +1578,25 @@ static int lapic_resume(struct sys_device *dev)
        maxlvt = lapic_get_maxlvt();
        local_irq_save(flags);
-        rdmsr(MSR_IA32_APICBASE, l, h);
-        l &= ~MSR_IA32_APICBASE_BASE;
+#ifdef CONFIG_X86_64
-        l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
+        if (x2apic)
-        wrmsr(MSR_IA32_APICBASE, l, h);
+                enable_x2apic();
+        else
+#endif
+        {
+                /*
+                 * Make sure the APICBASE points to the right address
+                 *
+                 * FIXME! This will be wrong if we ever support suspend on
+                 * SMP! We'll need to do this as part of the CPU restore!
+                 */
+                rdmsr(MSR_IA32_APICBASE, l, h);
+                l &= ~MSR_IA32_APICBASE_BASE;
+                l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
+                wrmsr(MSR_IA32_APICBASE, l, h);
+        }
        apic_write(APIC_LVTERR, ERROR_APIC_VECTOR | APIC_LVT_MASKED);
        apic_write(APIC_ID, apic_pm_state.apic_id);
        apic_write(APIC_DFR, apic_pm_state.apic_dfr);
@@ -1176,7 +1605,7 @@ static int lapic_resume(struct sys_device *dev)
        apic_write(APIC_SPIV, apic_pm_state.apic_spiv);
        apic_write(APIC_LVT0, apic_pm_state.apic_lvt0);
        apic_write(APIC_LVT1, apic_pm_state.apic_lvt1);
-#ifdef CONFIG_X86_MCE_INTEL
+#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL)
        if (maxlvt >= 5)
                apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr);
 #endif
@@ -1190,10 +1619,17 @@ static int lapic_resume(struct sys_device *dev)
        apic_write(APIC_LVTERR, apic_pm_state.apic_lvterr);
        apic_write(APIC_ESR, 0);
        apic_read(APIC_ESR);
        local_irq_restore(flags);
        return 0;
 }
+/*
+ * This device has no shutdown method - fully functioning local APICs
+ * are needed on every CPU up until machine_halt/restart/poweroff.
+ */
 static struct sysdev_class lapic_sysclass = {
        .name           = "lapic",
        .resume         = lapic_resume,
@@ -1307,31 +1743,19 @@ __cpuinit int apic_is_clustered_box(void)
        return (clusters > 2);
 }
-/*
+static __init int setup_nox2apic(char *str)
- * APIC command line parameters
- */
-static int __init apic_set_verbosity(char *str)
 {
-        if (str == NULL)  {
+        disable_x2apic = 1;
-                skip_ioapic_setup = 0;
+        clear_cpu_cap(&boot_cpu_data, X86_FEATURE_X2APIC);
-                ioapic_force = 1;
-                return 0;
-        }
-        if (strcmp("debug", str) == 0)
-                apic_verbosity = APIC_DEBUG;
-        else if (strcmp("verbose", str) == 0)
-                apic_verbosity = APIC_VERBOSE;
-        else {
-                printk(KERN_WARNING "APIC Verbosity level %s not recognised"
-                                " use apic=verbose or apic=debug\n", str);
-                return -EINVAL;
-        }
        return 0;
 }
-early_param("apic", apic_set_verbosity);
+early_param("nox2apic", setup_nox2apic);
-static __init int setup_disableapic(char *str)
+/*
+ * APIC command line parameters
+ */
+static int __init setup_disableapic(char *arg)
 {
        disable_apic = 1;
        setup_clear_cpu_cap(X86_FEATURE_APIC);
@@ -1340,9 +1764,9 @@ static __init int setup_disableapic(char *str)
 early_param("disableapic", setup_disableapic);
 /* same as disableapic, for compatibility */
-static __init int setup_nolapic(char *str)
+static int __init setup_nolapic(char *arg)
 {
-        return setup_disableapic(str);
+        return setup_disableapic(arg);
 }
 early_param("nolapic", setup_nolapic);
@@ -1353,14 +1777,19 @@ static int __init parse_lapic_timer_c2_ok(char *arg)
 }
 early_param("lapic_timer_c2_ok", parse_lapic_timer_c2_ok);
-static __init int setup_noapictimer(char *str)
+static int __init parse_disable_apic_timer(char *arg)
 {
-        if (str[0] != ' ' && str[0] != 0)
-                return 0;
        disable_apic_timer = 1;
-        return 1;
+        return 0;
 }
-__setup("noapictimer", setup_noapictimer);
+early_param("noapictimer", parse_disable_apic_timer);
+static int __init parse_nolapic_timer(char *arg)
+{
+        disable_apic_timer = 1;
+        return 0;
+}
+early_param("nolapic_timer", parse_nolapic_timer);
 static __init int setup_apicpmtimer(char *s)
 {
@@ -1370,6 +1799,31 @@ static __init int setup_apicpmtimer(char *s)
 }
 __setup("apicpmtimer", setup_apicpmtimer);
+static int __init apic_set_verbosity(char *arg)
+{
+        if (!arg)  {
+#ifdef CONFIG_X86_64
+                skip_ioapic_setup = 0;
+                ioapic_force = 1;
+                return 0;
+#endif
+                return -EINVAL;
+        }
+        if (strcmp("debug", arg) == 0)
+                apic_verbosity = APIC_DEBUG;
+        else if (strcmp("verbose", arg) == 0)
+                apic_verbosity = APIC_VERBOSE;
+        else {
+                printk(KERN_WARNING "APIC Verbosity level %s not recognised"
+                        " use apic=verbose or apic=debug\n", arg);
+                return -EINVAL;
+        }
+        return 0;
+}
+early_param("apic", apic_set_verbosity);
 static int __init lapic_insert_resource(void)
 {
        if (!apic_phys)
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index ee76eaad3001..7f0b45a5d788 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -3,22 +3,30 @@
 #
 obj-y                   := intel_cacheinfo.o addon_cpuid_features.o
-obj-y                   += proc.o feature_names.o
+obj-y                   += proc.o capflags.o powerflags.o common.o
-obj-$(CONFIG_X86_32)    += common.o bugs.o
+obj-$(CONFIG_X86_32)    += bugs.o cmpxchg.o
-obj-$(CONFIG_X86_64)    += common_64.o bugs_64.o
+obj-$(CONFIG_X86_64)    += bugs_64.o
-obj-$(CONFIG_X86_32)    += amd.o
-obj-$(CONFIG_X86_64)    += amd_64.o
+obj-$(CONFIG_CPU_SUP_INTEL)             += intel.o
-obj-$(CONFIG_X86_32)    += cyrix.o
+obj-$(CONFIG_CPU_SUP_AMD)               += amd.o
-obj-$(CONFIG_X86_32)    += centaur.o
+obj-$(CONFIG_CPU_SUP_CYRIX_32)          += cyrix.o
-obj-$(CONFIG_X86_64)    += centaur_64.o
+obj-$(CONFIG_CPU_SUP_CENTAUR_32)        += centaur.o
-obj-$(CONFIG_X86_32)    += transmeta.o
+obj-$(CONFIG_CPU_SUP_CENTAUR_64)        += centaur_64.o
-obj-$(CONFIG_X86_32)    += intel.o
+obj-$(CONFIG_CPU_SUP_TRANSMETA_32)      += transmeta.o
-obj-$(CONFIG_X86_64)    += intel_64.o
+obj-$(CONFIG_CPU_SUP_UMC_32)            += umc.o
-obj-$(CONFIG_X86_32)    += umc.o
 obj-$(CONFIG_X86_MCE)   += mcheck/
 obj-$(CONFIG_MTRR)      += mtrr/
 obj-$(CONFIG_CPU_FREQ)  += cpufreq/
 obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o
+quiet_cmd_mkcapflags = MKCAP   $@
+      cmd_mkcapflags = $(PERL) $(srctree)/$(src)/mkcapflags.pl $< $@
+cpufeature = $(src)/../../../../include/asm-x86/cpufeature.h
+targets += capflags.c
+$(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.pl FORCE
+        $(call if_changed,mkcapflags)
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index a6ef672adbba..0d9c993aa93e 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -7,6 +7,8 @@
 #include <asm/pat.h>
 #include <asm/processor.h>
+#include <mach_apic.h>
 struct cpuid_bit {
        u16 feature;
        u8 reg;
@@ -48,6 +50,92 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
        }
 }
+/* leaf 0xb SMT level */
+#define SMT_LEVEL       0
+/* leaf 0xb sub-leaf types */
+#define INVALID_TYPE    0
+#define SMT_TYPE        1
+#define CORE_TYPE       2
+#define LEAFB_SUBTYPE(ecx)              (((ecx) >> 8) & 0xff)
+#define BITS_SHIFT_NEXT_LEVEL(eax)      ((eax) & 0x1f)
+#define LEVEL_MAX_SIBLINGS(ebx)         ((ebx) & 0xffff)
+/*
+ * Check for extended topology enumeration cpuid leaf 0xb and if it
+ * exists, use it for populating initial_apicid and cpu topology
+ * detection.
+ */
+void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+        unsigned int eax, ebx, ecx, edx, sub_index;
+        unsigned int ht_mask_width, core_plus_mask_width;
+        unsigned int core_select_mask, core_level_siblings;
+        if (c->cpuid_level < 0xb)
+                return;
+        cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+        /*
+         * check if the cpuid leaf 0xb is actually implemented.
+         */
+        if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
+                return;
+        set_cpu_cap(c, X86_FEATURE_XTOPOLOGY);
+        /*
+         * initial apic id, which also represents 32-bit extended x2apic id.
+         */
+        c->initial_apicid = edx;
+        /*
+         * Populate HT related information from sub-leaf level 0.
+         */
+        core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
+        core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+        sub_index = 1;
+        do {
+                cpuid_count(0xb, sub_index, &eax, &ebx, &ecx, &edx);
+                /*
+                 * Check for the Core type in the implemented sub leaves.
+                 */
+                if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
+                        core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+                        core_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+                        break;
+                }
+                sub_index++;
+        } while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
+        core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width;
+#ifdef CONFIG_X86_32
+        c->cpu_core_id = phys_pkg_id(c->initial_apicid, ht_mask_width)
+                                                 & core_select_mask;
+        c->phys_proc_id = phys_pkg_id(c->initial_apicid, core_plus_mask_width);
+#else
+        c->cpu_core_id = phys_pkg_id(ht_mask_width) & core_select_mask;
+        c->phys_proc_id = phys_pkg_id(core_plus_mask_width);
+#endif
+        c->x86_max_cores = (core_level_siblings / smp_num_siblings);
+        printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
+               c->phys_proc_id);
+        if (c->x86_max_cores > 1)
+                printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
+                       c->cpu_core_id);
+        return;
+#endif
+}
 #ifdef CONFIG_X86_PAT
 void __cpuinit validate_pat_support(struct cpuinfo_x86 *c)
 {
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 18514ed26104..32e73520adf7 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1,13 +1,22 @@
 #include <linux/init.h>
 #include <linux/bitops.h>
 #include <linux/mm.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
+#ifdef CONFIG_X86_64
+# include <asm/numa_64.h>
+# include <asm/mmconfig.h>
+# include <asm/cacheflush.h>
+#endif
 #include <mach_apic.h>
 #include "cpu.h"
+#ifdef CONFIG_X86_32
 /*
 *      B step AMD K6 before B 9730xxxx have hardware bugs that can cause
 *      misexecution of code under Linux. Owners of such processors should
@@ -24,26 +33,273 @@
 extern void vide(void);
 __asm__(".align 4\nvide: ret");
-static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
+static void __cpuinit init_amd_k5(struct cpuinfo_x86 *c)
 {
-        if (cpuid_eax(0x80000000) >= 0x80000007) {
+/*
-                c->x86_power = cpuid_edx(0x80000007);
+ * General Systems BIOSen alias the cpu frequency registers
-                if (c->x86_power & (1<<8))
+ * of the Elan at 0x000df000. Unfortuantly, one of the Linux
-                        set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+ * drivers subsequently pokes it, and changes the CPU speed.
+ * Workaround : Remove the unneeded alias.
+ */
+#define CBAR            (0xfffc) /* Configuration Base Address  (32-bit) */
+#define CBAR_ENB        (0x80000000)
+#define CBAR_KEY        (0X000000CB)
+        if (c->x86_model == 9 || c->x86_model == 10) {
+                if (inl (CBAR) & CBAR_ENB)
+                        outl (0 | CBAR_KEY, CBAR);
        }
-        /*  Set MTRR capability flag if appropriate */
-        if (c->x86_model == 13 || c->x86_model == 9 ||
-           (c->x86_model == 8 && c->x86_mask >= 8))
-                set_cpu_cap(c, X86_FEATURE_K6_MTRR);
 }
-static void __cpuinit init_amd(struct cpuinfo_x86 *c)
+static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c)
 {
        u32 l, h;
        int mbytes = num_physpages >> (20-PAGE_SHIFT);
-        int r;
+        if (c->x86_model < 6) {
+                /* Based on AMD doc 20734R - June 2000 */
+                if (c->x86_model == 0) {
+                        clear_cpu_cap(c, X86_FEATURE_APIC);
+                        set_cpu_cap(c, X86_FEATURE_PGE);
+                }
+                return;
+        }
+        if (c->x86_model == 6 && c->x86_mask == 1) {
+                const int K6_BUG_LOOP = 1000000;
+                int n;
+                void (*f_vide)(void);
+                unsigned long d, d2;
+                printk(KERN_INFO "AMD K6 stepping B detected - ");
+                /*
+                 * It looks like AMD fixed the 2.6.2 bug and improved indirect
+                 * calls at the same time.
+                 */
+                n = K6_BUG_LOOP;
+                f_vide = vide;
+                rdtscl(d);
+                while (n--)
+                        f_vide();
+                rdtscl(d2);
+                d = d2-d;
+                if (d > 20*K6_BUG_LOOP)
+                        printk("system stability may be impaired when more than 32 MB are used.\n");
+                else
+                        printk("probably OK (after B9730xxxx).\n");
+                printk(KERN_INFO "Please see http://membres.lycos.fr/poulot/k6bug.html\n");
+        }
+        /* K6 with old style WHCR */
+        if (c->x86_model < 8 ||
+           (c->x86_model == 8 && c->x86_mask < 8)) {
+                /* We can only write allocate on the low 508Mb */
+                if (mbytes > 508)
+                        mbytes = 508;
+                rdmsr(MSR_K6_WHCR, l, h);
+                if ((l&0x0000FFFF) == 0) {
+                        unsigned long flags;
+                        l = (1<<0)|((mbytes/4)<<1);
+                        local_irq_save(flags);
+                        wbinvd();
+                        wrmsr(MSR_K6_WHCR, l, h);
+                        local_irq_restore(flags);
+                        printk(KERN_INFO "Enabling old style K6 write allocation for %d Mb\n",
+                                mbytes);
+                }
+                return;
+        }
+        if ((c->x86_model == 8 && c->x86_mask > 7) ||
+             c->x86_model == 9 || c->x86_model == 13) {
+                /* The more serious chips .. */
+                if (mbytes > 4092)
+                        mbytes = 4092;
+                rdmsr(MSR_K6_WHCR, l, h);
+                if ((l&0xFFFF0000) == 0) {
+                        unsigned long flags;
+                        l = ((mbytes>>2)<<22)|(1<<16);
+                        local_irq_save(flags);
+                        wbinvd();
+                        wrmsr(MSR_K6_WHCR, l, h);
+                        local_irq_restore(flags);
+                        printk(KERN_INFO "Enabling new style K6 write allocation for %d Mb\n",
+                                mbytes);
+                }
+                return;
+        }
+        if (c->x86_model == 10) {
+                /* AMD Geode LX is model 10 */
+                /* placeholder for any needed mods */
+                return;
+        }
+}
+static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c)
+{
+        u32 l, h;
+        /*
+         * Bit 15 of Athlon specific MSR 15, needs to be 0
+         * to enable SSE on Palomino/Morgan/Barton CPU's.
+         * If the BIOS didn't enable it already, enable it here.
+         */
+        if (c->x86_model >= 6 && c->x86_model <= 10) {
+                if (!cpu_has(c, X86_FEATURE_XMM)) {
+                        printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
+                        rdmsr(MSR_K7_HWCR, l, h);
+                        l &= ~0x00008000;
+                        wrmsr(MSR_K7_HWCR, l, h);
+                        set_cpu_cap(c, X86_FEATURE_XMM);
+                }
+        }
+        /*
+         * It's been determined by AMD that Athlons since model 8 stepping 1
+         * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx
+         * As per AMD technical note 27212 0.2
+         */
+        if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) {
+                rdmsr(MSR_K7_CLK_CTL, l, h);
+                if ((l & 0xfff00000) != 0x20000000) {
+                        printk ("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", l,
+                                ((l & 0x000fffff)|0x20000000));
+                        wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h);
+                }
+        }
+        set_cpu_cap(c, X86_FEATURE_K7);
+}
+#endif
+#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+static int __cpuinit nearby_node(int apicid)
+{
+        int i, node;
+        for (i = apicid - 1; i >= 0; i--) {
+                node = apicid_to_node[i];
+                if (node != NUMA_NO_NODE && node_online(node))
+                        return node;
+        }
+        for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
+                node = apicid_to_node[i];
+                if (node != NUMA_NO_NODE && node_online(node))
+                        return node;
+        }
+        return first_node(node_online_map); /* Shouldn't happen */
+}
+#endif
+/*
+ * On a AMD dual core setup the lower bits of the APIC id distingush the cores.
+ * Assumes number of cores is a power of two.
+ */
+static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_HT
+        unsigned bits;
+        bits = c->x86_coreid_bits;
+        /* Low order bits define the core id (index of core in socket) */
+        c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
+        /* Convert the initial APIC ID into the socket ID */
+        c->phys_proc_id = c->initial_apicid >> bits;
+#endif
+}
+static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
+{
+#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+        int cpu = smp_processor_id();
+        int node;
+        unsigned apicid = hard_smp_processor_id();
+        node = c->phys_proc_id;
+        if (apicid_to_node[apicid] != NUMA_NO_NODE)
+                node = apicid_to_node[apicid];
+        if (!node_online(node)) {
+                /* Two possibilities here:
+                   - The CPU is missing memory and no node was created.
+                   In that case try picking one from a nearby CPU
+                   - The APIC IDs differ from the HyperTransport node IDs
+                   which the K8 northbridge parsing fills in.
+                   Assume they are all increased by a constant offset,
+                   but in the same order as the HT nodeids.
+                   If that doesn't result in a usable node fall back to the
+                   path for the previous case.  */
+                int ht_nodeid = c->initial_apicid;
+                if (ht_nodeid >= 0 &&
+                    apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+                        node = apicid_to_node[ht_nodeid];
+                /* Pick a nearby node */
+                if (!node_online(node))
+                        node = nearby_node(apicid);
+        }
+        numa_set_node(cpu, node);
+        printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
+#endif
+}
+static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_HT
+        unsigned bits, ecx;
+        /* Multi core CPU? */
+        if (c->extended_cpuid_level < 0x80000008)
+                return;
+        ecx = cpuid_ecx(0x80000008);
+        c->x86_max_cores = (ecx & 0xff) + 1;
+        /* CPU telling us the core id bits shift? */
+        bits = (ecx >> 12) & 0xF;
+        /* Otherwise recompute */
+        if (bits == 0) {
+                while ((1 << bits) < c->x86_max_cores)
+                        bits++;
+        }
+        c->x86_coreid_bits = bits;
+#endif
+}
+static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
+{
+        early_init_amd_mc(c);
+        /* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */
+        if (c->x86_power & (1<<8))
+                set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+#ifdef CONFIG_X86_64
+        set_cpu_cap(c, X86_FEATURE_SYSCALL32);
+#else
+        /*  Set MTRR capability flag if appropriate */
+        if (c->x86 == 5)
+                if (c->x86_model == 13 || c->x86_model == 9 ||
+                    (c->x86_model == 8 && c->x86_mask >= 8))
+                        set_cpu_cap(c, X86_FEATURE_K6_MTRR);
+#endif
+}
+static void __cpuinit init_amd(struct cpuinfo_x86 *c)
+{
 #ifdef CONFIG_SMP
        unsigned long long value;
@@ -54,7 +310,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
         * Errata 63 for SH-B3 steppings
         * Errata 122 for all steppings (F+ have it disabled by default)
         */
-        if (c->x86 == 15) {
+        if (c->x86 == 0xf) {
                rdmsrl(MSR_K7_HWCR, value);
                value |= 1 << 6;
                wrmsrl(MSR_K7_HWCR, value);
@@ -64,209 +320,119 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
        early_init_amd(c);
        /*
-         *      FIXME: We should handle the K5 here. Set up the write
-         *      range and also turn on MSR 83 bits 4 and 31 (write alloc,
-         *      no bus pipeline)
-         */
-        /*
         * Bit 31 in normal CPUID used for nonstandard 3DNow ID;
         * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway
         */
        clear_cpu_cap(c, 0*32+31);
-        r = get_model_name(c);
+#ifdef CONFIG_X86_64
+        /* On C+ stepping K8 rep microcode works well for copy/memset */
+        if (c->x86 == 0xf) {
+                u32 level;
-        switch (c->x86) {
+                level = cpuid_eax(1);
-        case 4:
+                if((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)
-                /*
+                        set_cpu_cap(c, X86_FEATURE_REP_GOOD);
-                 * General Systems BIOSen alias the cpu frequency registers
-                 * of the Elan at 0x000df000. Unfortuantly, one of the Linux
-                 * drivers subsequently pokes it, and changes the CPU speed.
-                 * Workaround : Remove the unneeded alias.
-                 */
-#define CBAR            (0xfffc) /* Configuration Base Address  (32-bit) */
-#define CBAR_ENB        (0x80000000)
-#define CBAR_KEY        (0X000000CB)
-                        if (c->x86_model == 9 || c->x86_model == 10) {
-                                if (inl (CBAR) & CBAR_ENB)
-                                        outl (0 | CBAR_KEY, CBAR);
-                        }
-                        break;
-        case 5:
-                        if (c->x86_model < 6) {
-                                /* Based on AMD doc 20734R - June 2000 */
-                                if (c->x86_model == 0) {
-                                        clear_cpu_cap(c, X86_FEATURE_APIC);
-                                        set_cpu_cap(c, X86_FEATURE_PGE);
-                                }
-                                break;
-                        }
-                        if (c->x86_model == 6 && c->x86_mask == 1) {
-                                const int K6_BUG_LOOP = 1000000;
-                                int n;
-                                void (*f_vide)(void);
-                                unsigned long d, d2;
-                                printk(KERN_INFO "AMD K6 stepping B detected - ");
-                                /*
-                                 * It looks like AMD fixed the 2.6.2 bug and improved indirect
-                                 * calls at the same time.
-                                 */
-                                n = K6_BUG_LOOP;
-                                f_vide = vide;
-                                rdtscl(d);
-                                while (n--)
-                                        f_vide();
-                                rdtscl(d2);
-                                d = d2-d;
-                                if (d > 20*K6_BUG_LOOP)
-                                        printk("system stability may be impaired when more than 32 MB are used.\n");
-                                else
-                                        printk("probably OK (after B9730xxxx).\n");
-                                printk(KERN_INFO "Please see http://membres.lycos.fr/poulot/k6bug.html\n");
-                        }
-                        /* K6 with old style WHCR */
-                        if (c->x86_model < 8 ||
-                           (c->x86_model == 8 && c->x86_mask < 8)) {
-                                /* We can only write allocate on the low 508Mb */
-                                if (mbytes > 508)
-                                        mbytes = 508;
-                                rdmsr(MSR_K6_WHCR, l, h);
-                                if ((l&0x0000FFFF) == 0) {
-                                        unsigned long flags;
-                                        l = (1<<0)|((mbytes/4)<<1);
-                                        local_irq_save(flags);
-                                        wbinvd();
-                                        wrmsr(MSR_K6_WHCR, l, h);
-                                        local_irq_restore(flags);
-                                        printk(KERN_INFO "Enabling old style K6 write allocation for %d Mb\n",
-                                                mbytes);
-                                }
-                                break;
-                        }
-                        if ((c->x86_model == 8 && c->x86_mask > 7) ||
-                             c->x86_model == 9 || c->x86_model == 13) {
-                                /* The more serious chips .. */
-                                if (mbytes > 4092)
-                                        mbytes = 4092;
-                                rdmsr(MSR_K6_WHCR, l, h);
-                                if ((l&0xFFFF0000) == 0) {
-                                        unsigned long flags;
-                                        l = ((mbytes>>2)<<22)|(1<<16);
-                                        local_irq_save(flags);
-                                        wbinvd();
-                                        wrmsr(MSR_K6_WHCR, l, h);
-                                        local_irq_restore(flags);
-                                        printk(KERN_INFO "Enabling new style K6 write allocation for %d Mb\n",
-                                                mbytes);
-                                }
-                                break;
-                        }
-                        if (c->x86_model == 10) {
-                                /* AMD Geode LX is model 10 */
-                                /* placeholder for any needed mods */
-                                break;
-                        }
-                        break;
-        case 6: /* An Athlon/Duron */
-                        /*
-                         * Bit 15 of Athlon specific MSR 15, needs to be 0
-                         * to enable SSE on Palomino/Morgan/Barton CPU's.
-                         * If the BIOS didn't enable it already, enable it here.
-                         */
-                        if (c->x86_model >= 6 && c->x86_model <= 10) {
-                                if (!cpu_has(c, X86_FEATURE_XMM)) {
-                                        printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
-                                        rdmsr(MSR_K7_HWCR, l, h);
-                                        l &= ~0x00008000;
-                                        wrmsr(MSR_K7_HWCR, l, h);
-                                        set_cpu_cap(c, X86_FEATURE_XMM);
-                                }
-                        }
-                        /*
-                         * It's been determined by AMD that Athlons since model 8 stepping 1
-                         * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx
-                         * As per AMD technical note 27212 0.2
-                         */
-                        if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) {
-                                rdmsr(MSR_K7_CLK_CTL, l, h);
-                                if ((l & 0xfff00000) != 0x20000000) {
-                                        printk ("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", l,
-                                                ((l & 0x000fffff)|0x20000000));
-                                        wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h);
-                                }
-                        }
-                        break;
        }
+        if (c->x86 == 0x10 || c->x86 == 0x11)
+                set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+#else
+        /*
+         *      FIXME: We should handle the K5 here. Set up the write
+         *      range and also turn on MSR 83 bits 4 and 31 (write alloc,
+         *      no bus pipeline)
+         */
        switch (c->x86) {
-        case 15:
+        case 4:
-        /* Use K8 tuning for Fam10h and Fam11h */
+                init_amd_k5(c);
-        case 0x10:
-        case 0x11:
-                set_cpu_cap(c, X86_FEATURE_K8);
                break;
-        case 6:
+        case 5:
-                set_cpu_cap(c, X86_FEATURE_K7);
+                init_amd_k6(c);
+                break;
+        case 6: /* An Athlon/Duron */
+                init_amd_k7(c);
                break;
        }
+        /* K6s reports MCEs but don't actually have all the MSRs */
+        if (c->x86 < 6)
+                clear_cpu_cap(c, X86_FEATURE_MCE);
+#endif
+        /* Enable workaround for FXSAVE leak */
        if (c->x86 >= 6)
                set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK);
-        display_cacheinfo(c);
+        if (!c->x86_model_id[0]) {
+                switch (c->x86) {
-        if (cpuid_eax(0x80000000) >= 0x80000008)
+                case 0xf:
-                c->x86_max_cores = (cpuid_ecx(0x80000008) & 0xff) + 1;
+                        /* Should distinguish Models here, but this is only
+                           a fallback anyways. */
+                        strcpy(c->x86_model_id, "Hammer");
+                        break;
+                }
+        }
-#ifdef CONFIG_X86_HT
+        display_cacheinfo(c);
-        /*
-         * On a AMD multi core setup the lower bits of the APIC id
-         * distinguish the cores.
-         */
-        if (c->x86_max_cores > 1) {
-                int cpu = smp_processor_id();
-                unsigned bits = (cpuid_ecx(0x80000008) >> 12) & 0xf;
-                if (bits == 0) {
+        /* Multi core CPU? */
-                        while ((1 << bits) < c->x86_max_cores)
+        if (c->extended_cpuid_level >= 0x80000008) {
-                                bits++;
+                amd_detect_cmp(c);
-                }
+                srat_detect_node(c);
-                c->cpu_core_id = c->phys_proc_id & ((1<<bits)-1);
-                c->phys_proc_id >>= bits;
-                printk(KERN_INFO "CPU %d(%d) -> Core %d\n",
-                       cpu, c->x86_max_cores, c->cpu_core_id);
        }
+#ifdef CONFIG_X86_32
+        detect_ht(c);
 #endif
-        if (cpuid_eax(0x80000000) >= 0x80000006) {
+        if (c->extended_cpuid_level >= 0x80000006) {
-                if ((c->x86 == 0x10) && (cpuid_edx(0x80000006) & 0xf000))
+                if ((c->x86 >= 0x0f) && (cpuid_edx(0x80000006) & 0xf000))
                        num_cache_leaves = 4;
                else
                        num_cache_leaves = 3;
        }
-        /* K6s reports MCEs but don't actually have all the MSRs */
+        if (c->x86 >= 0xf && c->x86 <= 0x11)
-        if (c->x86 < 6)
+                set_cpu_cap(c, X86_FEATURE_K8);
-                clear_cpu_cap(c, X86_FEATURE_MCE);
-        if (cpu_has_xmm2)
+        if (cpu_has_xmm2) {
+                /* MFENCE stops RDTSC speculation */
                set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+        }
+#ifdef CONFIG_X86_64
+        if (c->x86 == 0x10) {
+                /* do this for boot cpu */
+                if (c == &boot_cpu_data)
+                        check_enable_amd_mmconf_dmi();
+                fam10h_check_enable_mmcfg();
+        }
+        if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
+                unsigned long long tseg;
+                /*
+                 * Split up direct mapping around the TSEG SMM area.
+                 * Don't do it for gbpages because there seems very little
+                 * benefit in doing so.
+                 */
+                if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+                    printk(KERN_DEBUG "tseg: %010llx\n", tseg);
+                    if ((tseg>>PMD_SHIFT) <
+                                (max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) ||
+                        ((tseg>>PMD_SHIFT) <
+                                (max_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) &&
+                         (tseg>>PMD_SHIFT) >= (1ULL<<(32 - PMD_SHIFT))))
+                        set_memory_4k((unsigned long)__va(tseg), 1);
+                }
+        }
+#endif
 }
+#ifdef CONFIG_X86_32
 static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 {
        /* AMD errata T13 (order #21922) */
@@ -279,10 +445,12 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, unsigned int
        }
        return size;
 }
+#endif
 static struct cpu_dev amd_cpu_dev __cpuinitdata = {
        .c_vendor       = "AMD",
        .c_ident        = { "AuthenticAMD" },
+#ifdef CONFIG_X86_32
        .c_models = {
                { .vendor = X86_VENDOR_AMD, .family = 4, .model_names =
                  {
@@ -295,9 +463,11 @@ static struct cpu_dev amd_cpu_dev __cpuinitdata = {
                  }
                },
        },
+        .c_size_cache   = amd_size_cache,
+#endif
        .c_early_init   = early_init_amd,
        .c_init         = init_amd,
-        .c_size_cache   = amd_size_cache,
+        .c_x86_vendor   = X86_VENDOR_AMD,
 };
-cpu_vendor_dev_register(X86_VENDOR_AMD, &amd_cpu_dev);
+cpu_dev_register(amd_cpu_dev);
diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
deleted file mode 100644
index d1692b2a41ff..000000000000
--- a/arch/x86/kernel/cpu/amd_64.c
+++ /dev/null
@@ -1,224 +0,0 @@
-#include <linux/init.h>
-#include <linux/mm.h>
-#include <asm/numa_64.h>
-#include <asm/mmconfig.h>
-#include <asm/cacheflush.h>
-#include <mach_apic.h>
-#include "cpu.h"
-int force_mwait __cpuinitdata;
-#ifdef CONFIG_NUMA
-static int __cpuinit nearby_node(int apicid)
-{
-        int i, node;
-        for (i = apicid - 1; i >= 0; i--) {
-                node = apicid_to_node[i];
-                if (node != NUMA_NO_NODE && node_online(node))
-                        return node;
-        }
-        for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
-                node = apicid_to_node[i];
-                if (node != NUMA_NO_NODE && node_online(node))
-                        return node;
-        }
-        return first_node(node_online_map); /* Shouldn't happen */
-}
-#endif
-/*
- * On a AMD dual core setup the lower bits of the APIC id distingush the cores.
- * Assumes number of cores is a power of two.
- */
-static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
-        unsigned bits;
-#ifdef CONFIG_NUMA
-        int cpu = smp_processor_id();
-        int node = 0;
-        unsigned apicid = hard_smp_processor_id();
-#endif
-        bits = c->x86_coreid_bits;
-        /* Low order bits define the core id (index of core in socket) */
-        c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
-        /* Convert the initial APIC ID into the socket ID */
-        c->phys_proc_id = c->initial_apicid >> bits;
-#ifdef CONFIG_NUMA
-        node = c->phys_proc_id;
-        if (apicid_to_node[apicid] != NUMA_NO_NODE)
-                node = apicid_to_node[apicid];
-        if (!node_online(node)) {
-                /* Two possibilities here:
-                   - The CPU is missing memory and no node was created.
-                   In that case try picking one from a nearby CPU
-                   - The APIC IDs differ from the HyperTransport node IDs
-                   which the K8 northbridge parsing fills in.
-                   Assume they are all increased by a constant offset,
-                   but in the same order as the HT nodeids.
-                   If that doesn't result in a usable node fall back to the
-                   path for the previous case.  */
-                int ht_nodeid = c->initial_apicid;
-                if (ht_nodeid >= 0 &&
-                    apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
-                        node = apicid_to_node[ht_nodeid];
-                /* Pick a nearby node */
-                if (!node_online(node))
-                        node = nearby_node(apicid);
-        }
-        numa_set_node(cpu, node);
-        printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
-#endif
-#endif
-}
-static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
-        unsigned bits, ecx;
-        /* Multi core CPU? */
-        if (c->extended_cpuid_level < 0x80000008)
-                return;
-        ecx = cpuid_ecx(0x80000008);
-        c->x86_max_cores = (ecx & 0xff) + 1;
-        /* CPU telling us the core id bits shift? */
-        bits = (ecx >> 12) & 0xF;
-        /* Otherwise recompute */
-        if (bits == 0) {
-                while ((1 << bits) < c->x86_max_cores)
-                        bits++;
-        }
-        c->x86_coreid_bits = bits;
-#endif
-}
-static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
-{
-        early_init_amd_mc(c);
-        /* c->x86_power is 8000_0007 edx. Bit 8 is constant TSC */
-        if (c->x86_power & (1<<8))
-                set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-        set_cpu_cap(c, X86_FEATURE_SYSCALL32);
-}
-static void __cpuinit init_amd(struct cpuinfo_x86 *c)
-{
-        unsigned level;
-#ifdef CONFIG_SMP
-        unsigned long value;
-        /*
-         * Disable TLB flush filter by setting HWCR.FFDIS on K8
-         * bit 6 of msr C001_0015
-         *
-         * Errata 63 for SH-B3 steppings
-         * Errata 122 for all steppings (F+ have it disabled by default)
-         */
-        if (c->x86 == 0xf) {
-                rdmsrl(MSR_K8_HWCR, value);
-                value |= 1 << 6;
-                wrmsrl(MSR_K8_HWCR, value);
-        }
-#endif
-        /* Bit 31 in normal CPUID used for nonstandard 3DNow ID;
-           3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */
-        clear_cpu_cap(c, 0*32+31);
-        /* On C+ stepping K8 rep microcode works well for copy/memset */
-        if (c->x86 == 0xf) {
-                level = cpuid_eax(1);
-                if((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)
-                        set_cpu_cap(c, X86_FEATURE_REP_GOOD);
-        }
-        if (c->x86 == 0x10 || c->x86 == 0x11)
-                set_cpu_cap(c, X86_FEATURE_REP_GOOD);
-        /* Enable workaround for FXSAVE leak */
-        if (c->x86 >= 6)
-                set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK);
-        level = get_model_name(c);
-        if (!level) {
-                switch (c->x86) {
-                case 0xf:
-                        /* Should distinguish Models here, but this is only
-                           a fallback anyways. */
-                        strcpy(c->x86_model_id, "Hammer");
-                        break;
-                }
-        }
-        display_cacheinfo(c);
-        /* Multi core CPU? */
-        if (c->extended_cpuid_level >= 0x80000008)
-                amd_detect_cmp(c);
-        if (c->extended_cpuid_level >= 0x80000006 &&
-                (cpuid_edx(0x80000006) & 0xf000))
-                num_cache_leaves = 4;
-        else
-                num_cache_leaves = 3;
-        if (c->x86 >= 0xf && c->x86 <= 0x11)
-                set_cpu_cap(c, X86_FEATURE_K8);
-        /* MFENCE stops RDTSC speculation */
-        set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
-        if (c->x86 == 0x10) {
-                /* do this for boot cpu */
-                if (c == &boot_cpu_data)
-                        check_enable_amd_mmconf_dmi();
-                fam10h_check_enable_mmcfg();
-        }
-        if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
-                unsigned long long tseg;
-                /*
-                 * Split up direct mapping around the TSEG SMM area.
-                 * Don't do it for gbpages because there seems very little
-                 * benefit in doing so.
-                 */
-                if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
-                    printk(KERN_DEBUG "tseg: %010llx\n", tseg);
-                    if ((tseg>>PMD_SHIFT) <
-                                (max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) ||
-                        ((tseg>>PMD_SHIFT) <
-                                (max_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) &&
-                         (tseg>>PMD_SHIFT) >= (1ULL<<(32 - PMD_SHIFT))))
-                        set_memory_4k((unsigned long)__va(tseg), 1);
-                }
-        }
-}
-static struct cpu_dev amd_cpu_dev __cpuinitdata = {
-        .c_vendor       = "AMD",
-        .c_ident        = { "AuthenticAMD" },
-        .c_early_init   = early_init_amd,
-        .c_init         = init_amd,
-};
-cpu_vendor_dev_register(X86_VENDOR_AMD, &amd_cpu_dev);
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index a0534c04d38a..89bfdd9cacc6 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -289,7 +289,6 @@ static void __cpuinit init_c3(struct cpuinfo_x86 *c)
        if (c->x86_model >= 6 && c->x86_model < 9)
                set_cpu_cap(c, X86_FEATURE_3DNOW);
-        get_model_name(c);
        display_cacheinfo(c);
 }
@@ -475,6 +474,7 @@ static struct cpu_dev centaur_cpu_dev __cpuinitdata = {
        .c_early_init   = early_init_centaur,
        .c_init         = init_centaur,
        .c_size_cache   = centaur_size_cache,
+        .c_x86_vendor   = X86_VENDOR_CENTAUR,
 };
-cpu_vendor_dev_register(X86_VENDOR_CENTAUR, &centaur_cpu_dev);
+cpu_dev_register(centaur_cpu_dev);
diff --git a/arch/x86/kernel/cpu/centaur_64.c b/arch/x86/kernel/cpu/centaur_64.c
index 1d181c40e2e1..a1625f5a1e78 100644
--- a/arch/x86/kernel/cpu/centaur_64.c
+++ b/arch/x86/kernel/cpu/centaur_64.c
@@ -16,9 +16,10 @@ static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
 static void __cpuinit init_centaur(struct cpuinfo_x86 *c)
 {
+        early_init_centaur(c);
        if (c->x86 == 0x6 && c->x86_model >= 0xf) {
                c->x86_cache_alignment = c->x86_clflush_size * 2;
-                set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
                set_cpu_cap(c, X86_FEATURE_REP_GOOD);
        }
        set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
@@ -29,7 +30,8 @@ static struct cpu_dev centaur_cpu_dev __cpuinitdata = {
        .c_ident        = { "CentaurHauls" },
        .c_early_init   = early_init_centaur,
        .c_init         = init_centaur,
+        .c_x86_vendor   = X86_VENDOR_CENTAUR,
 };
-cpu_vendor_dev_register(X86_VENDOR_CENTAUR, &centaur_cpu_dev);
+cpu_dev_register(centaur_cpu_dev);
diff --git a/arch/x86/kernel/cpu/cmpxchg.c b/arch/x86/kernel/cpu/cmpxchg.c
new file mode 100644
index 000000000000..2056ccf572cc
--- /dev/null
+++ b/arch/x86/kernel/cpu/cmpxchg.c
@@ -0,0 +1,72 @@
+/*
+ * cmpxchg*() fallbacks for CPU not supporting these instructions
+ */
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+#ifndef CONFIG_X86_CMPXCHG
+unsigned long cmpxchg_386_u8(volatile void *ptr, u8 old, u8 new)
+{
+        u8 prev;
+        unsigned long flags;
+        /* Poor man's cmpxchg for 386. Unsuitable for SMP */
+        local_irq_save(flags);
+        prev = *(u8 *)ptr;
+        if (prev == old)
+                *(u8 *)ptr = new;
+        local_irq_restore(flags);
+        return prev;
+}
+EXPORT_SYMBOL(cmpxchg_386_u8);
+unsigned long cmpxchg_386_u16(volatile void *ptr, u16 old, u16 new)
+{
+        u16 prev;
+        unsigned long flags;
+        /* Poor man's cmpxchg for 386. Unsuitable for SMP */
+        local_irq_save(flags);
+        prev = *(u16 *)ptr;
+        if (prev == old)
+                *(u16 *)ptr = new;
+        local_irq_restore(flags);
+        return prev;
+}
+EXPORT_SYMBOL(cmpxchg_386_u16);
+unsigned long cmpxchg_386_u32(volatile void *ptr, u32 old, u32 new)
+{
+        u32 prev;
+        unsigned long flags;
+        /* Poor man's cmpxchg for 386. Unsuitable for SMP */
+        local_irq_save(flags);
+        prev = *(u32 *)ptr;
+        if (prev == old)
+                *(u32 *)ptr = new;
+        local_irq_restore(flags);
+        return prev;
+}
+EXPORT_SYMBOL(cmpxchg_386_u32);
+#endif
+#ifndef CONFIG_X86_CMPXCHG64
+unsigned long long cmpxchg_486_u64(volatile void *ptr, u64 old, u64 new)
+{
+        u64 prev;
+        unsigned long flags;
+        /* Poor man's cmpxchg8b for 386 and 486. Unsuitable for SMP */
+        local_irq_save(flags);
+        prev = *(u64 *)ptr;
+        if (prev == old)
+                *(u64 *)ptr = new;
+        local_irq_restore(flags);
+        return prev;
+}
+EXPORT_SYMBOL(cmpxchg_486_u64);
+#endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4e456bd955bb..7581b62df184 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1,28 +1,62 @@
 #include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
 #include <linux/string.h>
+#include <linux/bootmem.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/kgdb.h>
+#include <linux/topology.h>
 #include <linux/delay.h>
 #include <linux/smp.h>
-#include <linux/module.h>
 #include <linux/percpu.h>
-#include <linux/bootmem.h>
-#include <asm/processor.h>
 #include <asm/i387.h>
 #include <asm/msr.h>
 #include <asm/io.h>
+#include <asm/linkage.h>
 #include <asm/mmu_context.h>
 #include <asm/mtrr.h>
 #include <asm/mce.h>
 #include <asm/pat.h>
 #include <asm/asm.h>
+#include <asm/numa.h>
 #ifdef CONFIG_X86_LOCAL_APIC
 #include <asm/mpspec.h>
 #include <asm/apic.h>
 #include <mach_apic.h>
+#include <asm/genapic.h>
 #endif
+#include <asm/pda.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+#include <asm/desc.h>
+#include <asm/atomic.h>
+#include <asm/proto.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
 #include "cpu.h"
+static struct cpu_dev *this_cpu __cpuinitdata;
+#ifdef CONFIG_X86_64
+/* We need valid kernel segments for data and code in long mode too
+ * IRET will check the segment types  kkeil 2000/10/28
+ * Also sysret mandates a special GDT layout
+ */
+/* The TLS descriptors are currently at a different place compared to i386.
+   Hopefully nobody expects them at a fixed place (Wine?) */
 DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
+        [GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } },
+        [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } },
+        [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } },
+        [GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } },
+        [GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } },
+        [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } },
+} };
+#else
+DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
        [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00cf9a00 } } },
        [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9200 } } },
        [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00cffa00 } } },
@@ -56,17 +90,150 @@ DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
        [GDT_ENTRY_ESPFIX_SS] = { { { 0x00000000, 0x00c09200 } } },
        [GDT_ENTRY_PERCPU] = { { { 0x00000000, 0x00000000 } } },
 } };
+#endif
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
-__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
+#ifdef CONFIG_X86_32
 static int cachesize_override __cpuinitdata = -1;
 static int disable_x86_serial_nr __cpuinitdata = 1;
-struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
+static int __init cachesize_setup(char *str)
+{
+        get_option(&str, &cachesize_override);
+        return 1;
+}
+__setup("cachesize=", cachesize_setup);
+static int __init x86_fxsr_setup(char *s)
+{
+        setup_clear_cpu_cap(X86_FEATURE_FXSR);
+        setup_clear_cpu_cap(X86_FEATURE_XMM);
+        return 1;
+}
+__setup("nofxsr", x86_fxsr_setup);
+static int __init x86_sep_setup(char *s)
+{
+        setup_clear_cpu_cap(X86_FEATURE_SEP);
+        return 1;
+}
+__setup("nosep", x86_sep_setup);
+/* Standard macro to see if a specific flag is changeable */
+static inline int flag_is_changeable_p(u32 flag)
+{
+        u32 f1, f2;
+        asm("pushfl\n\t"
+            "pushfl\n\t"
+            "popl %0\n\t"
+            "movl %0,%1\n\t"
+            "xorl %2,%0\n\t"
+            "pushl %0\n\t"
+            "popfl\n\t"
+            "pushfl\n\t"
+            "popl %0\n\t"
+            "popfl\n\t"
+            : "=&r" (f1), "=&r" (f2)
+            : "ir" (flag));
+        return ((f1^f2) & flag) != 0;
+}
+/* Probe for the CPUID instruction */
+static int __cpuinit have_cpuid_p(void)
+{
+        return flag_is_changeable_p(X86_EFLAGS_ID);
+}
+static void __cpuinit squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
+{
+        if (cpu_has(c, X86_FEATURE_PN) && disable_x86_serial_nr) {
+                /* Disable processor serial number */
+                unsigned long lo, hi;
+                rdmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
+                lo |= 0x200000;
+                wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
+                printk(KERN_NOTICE "CPU serial number disabled.\n");
+                clear_cpu_cap(c, X86_FEATURE_PN);
+                /* Disabling the serial number may affect the cpuid level */
+                c->cpuid_level = cpuid_eax(0);
+        }
+}
+static int __init x86_serial_nr_setup(char *s)
+{
+        disable_x86_serial_nr = 0;
+        return 1;
+}
+__setup("serialnumber", x86_serial_nr_setup);
+#else
+static inline int flag_is_changeable_p(u32 flag)
+{
+        return 1;
+}
+/* Probe for the CPUID instruction */
+static inline int have_cpuid_p(void)
+{
+        return 1;
+}
+static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
+{
+}
+#endif
+/*
+ * Naming convention should be: <Name> [(<Codename>)]
+ * This table only is used unless init_<vendor>() below doesn't set it;
+ * in particular, if CPUID levels 0x80000002..4 are supported, this isn't used
+ *
+ */
+/* Look up CPU names by table lookup. */
+static char __cpuinit *table_lookup_model(struct cpuinfo_x86 *c)
+{
+        struct cpu_model_info *info;
+        if (c->x86_model >= 16)
+                return NULL;    /* Range check */
+        if (!this_cpu)
+                return NULL;
+        info = this_cpu->c_models;
+        while (info && info->family) {
+                if (info->family == c->x86)
+                        return info->model_names[c->x86_model];
+                info++;
+        }
+        return NULL;            /* Not found */
+}
+__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
+/* Current gdt points %fs at the "master" per-cpu area: after this,
+ * it's on the real one. */
+void switch_to_new_gdt(void)
+{
+        struct desc_ptr gdt_descr;
+        gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id());
+        gdt_descr.size = GDT_SIZE - 1;
+        load_gdt(&gdt_descr);
+#ifdef CONFIG_X86_32
+        asm("mov %0, %%fs" : : "r" (__KERNEL_PERCPU) : "memory");
+#endif
+}
+static struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
 static void __cpuinit default_init(struct cpuinfo_x86 *c)
 {
+#ifdef CONFIG_X86_64
+        display_cacheinfo(c);
+#else
        /* Not much we can do here... */
        /* Check if at least it has cpuid */
        if (c->cpuid_level == -1) {
@@ -76,28 +243,22 @@ static void __cpuinit default_init(struct cpuinfo_x86 *c)
                else if (c->x86 == 3)
                        strcpy(c->x86_model_id, "386");
        }
+#endif
 }
 static struct cpu_dev __cpuinitdata default_cpu = {
        .c_init = default_init,
        .c_vendor = "Unknown",
+        .c_x86_vendor = X86_VENDOR_UNKNOWN,
 };
-static struct cpu_dev *this_cpu __cpuinitdata = &default_cpu;
-static int __init cachesize_setup(char *str)
+static void __cpuinit get_model_name(struct cpuinfo_x86 *c)
-{
-        get_option(&str, &cachesize_override);
-        return 1;
-}
-__setup("cachesize=", cachesize_setup);
-int __cpuinit get_model_name(struct cpuinfo_x86 *c)
 {
        unsigned int *v;
        char *p, *q;
-        if (cpuid_eax(0x80000000) < 0x80000004)
+        if (c->extended_cpuid_level < 0x80000004)
-                return 0;
+                return;
        v = (unsigned int *) c->x86_model_id;
        cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
@@ -116,30 +277,34 @@ int __cpuinit get_model_name(struct cpuinfo_x86 *c)
             while (q <= &c->x86_model_id[48])
                  *q++ = '\0';  /* Zero-pad the rest */
        }
-        return 1;
 }
 void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
 {
-        unsigned int n, dummy, ecx, edx, l2size;
+        unsigned int n, dummy, ebx, ecx, edx, l2size;
-        n = cpuid_eax(0x80000000);
+        n = c->extended_cpuid_level;
        if (n >= 0x80000005) {
-                cpuid(0x80000005, &dummy, &dummy, &ecx, &edx);
+                cpuid(0x80000005, &dummy, &ebx, &ecx, &edx);
                printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache %dK (%d bytes/line)\n",
-                        edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
+                                edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
-                c->x86_cache_size = (ecx>>24)+(edx>>24);
+                c->x86_cache_size = (ecx>>24) + (edx>>24);
+#ifdef CONFIG_X86_64
+                /* On K8 L1 TLB is inclusive, so don't count it */
+                c->x86_tlbsize = 0;
+#endif
        }
        if (n < 0x80000006)     /* Some chips just has a large L1. */
                return;
-        ecx = cpuid_ecx(0x80000006);
+        cpuid(0x80000006, &dummy, &ebx, &ecx, &edx);
        l2size = ecx >> 16;
+#ifdef CONFIG_X86_64
+        c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff);
+#else
        /* do processor-specific cache resizing */
        if (this_cpu->c_size_cache)
                l2size = this_cpu->c_size_cache(c, l2size);
@@ -150,116 +315,106 @@ void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
        if (l2size == 0)
                return;         /* Again, no L2 cache is possible */
+#endif
        c->x86_cache_size = l2size;
        printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
-               l2size, ecx & 0xFF);
+                        l2size, ecx & 0xFF);
 }
-/*
+void __cpuinit detect_ht(struct cpuinfo_x86 *c)
- * Naming convention should be: <Name> [(<Codename>)]
- * This table only is used unless init_<vendor>() below doesn't set it;
- * in particular, if CPUID levels 0x80000002..4 are supported, this isn't used
- *
- */
-/* Look up CPU names by table lookup. */
-static char __cpuinit *table_lookup_model(struct cpuinfo_x86 *c)
 {
-        struct cpu_model_info *info;
+#ifdef CONFIG_X86_HT
+        u32 eax, ebx, ecx, edx;
+        int index_msb, core_bits;
-        if (c->x86_model >= 16)
+        if (!cpu_has(c, X86_FEATURE_HT))
-                return NULL;    /* Range check */
+                return;
-        if (!this_cpu)
+        if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
-                return NULL;
+                goto out;
-        info = this_cpu->c_models;
+        if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
+                return;
-        while (info && info->family) {
+        cpuid(1, &eax, &ebx, &ecx, &edx);
-                if (info->family == c->x86)
-                        return info->model_names[c->x86_model];
+        smp_num_siblings = (ebx & 0xff0000) >> 16;
-                info++;
+        if (smp_num_siblings == 1) {
+                printk(KERN_INFO  "CPU: Hyper-Threading is disabled\n");
+        } else if (smp_num_siblings > 1) {
+                if (smp_num_siblings > NR_CPUS) {
+                        printk(KERN_WARNING "CPU: Unsupported number of siblings %d",
+                                        smp_num_siblings);
+                        smp_num_siblings = 1;
+                        return;
+                }
+                index_msb = get_count_order(smp_num_siblings);
+#ifdef CONFIG_X86_64
+                c->phys_proc_id = phys_pkg_id(index_msb);
+#else
+                c->phys_proc_id = phys_pkg_id(c->initial_apicid, index_msb);
+#endif
+                smp_num_siblings = smp_num_siblings / c->x86_max_cores;
+                index_msb = get_count_order(smp_num_siblings);
+                core_bits = get_count_order(c->x86_max_cores);
+#ifdef CONFIG_X86_64
+                c->cpu_core_id = phys_pkg_id(index_msb) &
+                                               ((1 << core_bits) - 1);
+#else
+                c->cpu_core_id = phys_pkg_id(c->initial_apicid, index_msb) &
+                                               ((1 << core_bits) - 1);
+#endif
        }
-        return NULL;            /* Not found */
-}
+out:
+        if ((c->x86_max_cores * smp_num_siblings) > 1) {
+                printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
+                       c->phys_proc_id);
+                printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
+                       c->cpu_core_id);
+        }
+#endif
+}
-static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c, int early)
+static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
 {
        char *v = c->x86_vendor_id;
        int i;
        static int printed;
        for (i = 0; i < X86_VENDOR_NUM; i++) {
-                if (cpu_devs[i]) {
+                if (!cpu_devs[i])
-                        if (!strcmp(v, cpu_devs[i]->c_ident[0]) ||
+                        break;
-                            (cpu_devs[i]->c_ident[1] &&
-                             !strcmp(v, cpu_devs[i]->c_ident[1]))) {
+                if (!strcmp(v, cpu_devs[i]->c_ident[0]) ||
-                                c->x86_vendor = i;
+                    (cpu_devs[i]->c_ident[1] &&
-                                if (!early)
+                     !strcmp(v, cpu_devs[i]->c_ident[1]))) {
-                                        this_cpu = cpu_devs[i];
+                        this_cpu = cpu_devs[i];
-                                return;
+                        c->x86_vendor = this_cpu->c_x86_vendor;
-                        }
+                        return;
                }
        }
        if (!printed) {
                printed++;
-                printk(KERN_ERR "CPU: Vendor unknown, using generic init.\n");
+                printk(KERN_ERR "CPU: vendor_id '%s' unknown, using generic init.\n", v);
                printk(KERN_ERR "CPU: Your system may be unstable.\n");
        }
        c->x86_vendor = X86_VENDOR_UNKNOWN;
        this_cpu = &default_cpu;
 }
+void __cpuinit cpu_detect(struct cpuinfo_x86 *c)
-static int __init x86_fxsr_setup(char *s)
-{
-        setup_clear_cpu_cap(X86_FEATURE_FXSR);
-        setup_clear_cpu_cap(X86_FEATURE_XMM);
-        return 1;
-}
-__setup("nofxsr", x86_fxsr_setup);
-static int __init x86_sep_setup(char *s)
-{
-        setup_clear_cpu_cap(X86_FEATURE_SEP);
-        return 1;
-}
-__setup("nosep", x86_sep_setup);
-/* Standard macro to see if a specific flag is changeable */
-static inline int flag_is_changeable_p(u32 flag)
-{
-        u32 f1, f2;
-        asm("pushfl\n\t"
-            "pushfl\n\t"
-            "popl %0\n\t"
-            "movl %0,%1\n\t"
-            "xorl %2,%0\n\t"
-            "pushl %0\n\t"
-            "popfl\n\t"
-            "pushfl\n\t"
-            "popl %0\n\t"
-            "popfl\n\t"
-            : "=&r" (f1), "=&r" (f2)
-            : "ir" (flag));
-        return ((f1^f2) & flag) != 0;
-}
-/* Probe for the CPUID instruction */
-static int __cpuinit have_cpuid_p(void)
-{
-        return flag_is_changeable_p(X86_EFLAGS_ID);
-}
-void __init cpu_detect(struct cpuinfo_x86 *c)
 {
        /* Get vendor name */
        cpuid(0x00000000, (unsigned int *)&c->cpuid_level,
@@ -268,50 +423,87 @@ void __init cpu_detect(struct cpuinfo_x86 *c)
              (unsigned int *)&c->x86_vendor_id[4]);
        c->x86 = 4;
+        /* Intel-defined flags: level 0x00000001 */
        if (c->cpuid_level >= 0x00000001) {
                u32 junk, tfms, cap0, misc;
                cpuid(0x00000001, &tfms, &misc, &junk, &cap0);
-                c->x86 = (tfms >> 8) & 15;
+                c->x86 = (tfms >> 8) & 0xf;
-                c->x86_model = (tfms >> 4) & 15;
+                c->x86_model = (tfms >> 4) & 0xf;
+                c->x86_mask = tfms & 0xf;
                if (c->x86 == 0xf)
                        c->x86 += (tfms >> 20) & 0xff;
                if (c->x86 >= 0x6)
-                        c->x86_model += ((tfms >> 16) & 0xF) << 4;
+                        c->x86_model += ((tfms >> 16) & 0xf) << 4;
-                c->x86_mask = tfms & 15;
                if (cap0 & (1<<19)) {
-                        c->x86_cache_alignment = ((misc >> 8) & 0xff) * 8;
                        c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
+                        c->x86_cache_alignment = c->x86_clflush_size;
                }
        }
 }
-static void __cpuinit early_get_cap(struct cpuinfo_x86 *c)
+static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c)
 {
        u32 tfms, xlvl;
-        unsigned int ebx;
+        u32 ebx;
-        memset(&c->x86_capability, 0, sizeof c->x86_capability);
+        /* Intel-defined flags: level 0x00000001 */
-        if (have_cpuid_p()) {
+        if (c->cpuid_level >= 0x00000001) {
-                /* Intel-defined flags: level 0x00000001 */
+                u32 capability, excap;
-                if (c->cpuid_level >= 0x00000001) {
+                cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
-                        u32 capability, excap;
+                c->x86_capability[0] = capability;
-                        cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
+                c->x86_capability[4] = excap;
-                        c->x86_capability[0] = capability;
+        }
-                        c->x86_capability[4] = excap;
-                }
-                /* AMD-defined flags: level 0x80000001 */
+        /* AMD-defined flags: level 0x80000001 */
-                xlvl = cpuid_eax(0x80000000);
+        xlvl = cpuid_eax(0x80000000);
-                if ((xlvl & 0xffff0000) == 0x80000000) {
+        c->extended_cpuid_level = xlvl;
-                        if (xlvl >= 0x80000001) {
+        if ((xlvl & 0xffff0000) == 0x80000000) {
-                                c->x86_capability[1] = cpuid_edx(0x80000001);
+                if (xlvl >= 0x80000001) {
-                                c->x86_capability[6] = cpuid_ecx(0x80000001);
+                        c->x86_capability[1] = cpuid_edx(0x80000001);
-                        }
+                        c->x86_capability[6] = cpuid_ecx(0x80000001);
                }
+        }
+#ifdef CONFIG_X86_64
+        if (c->extended_cpuid_level >= 0x80000008) {
+                u32 eax = cpuid_eax(0x80000008);
+                c->x86_virt_bits = (eax >> 8) & 0xff;
+                c->x86_phys_bits = eax & 0xff;
        }
+#endif
+        if (c->extended_cpuid_level >= 0x80000007)
+                c->x86_power = cpuid_edx(0x80000007);
 }
+static void __cpuinit identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_32
+        int i;
+        /*
+         * First of all, decide if this is a 486 or higher
+         * It's a 486 if we can modify the AC flag
+         */
+        if (flag_is_changeable_p(X86_EFLAGS_AC))
+                c->x86 = 4;
+        else
+                c->x86 = 3;
+        for (i = 0; i < X86_VENDOR_NUM; i++)
+                if (cpu_devs[i] && cpu_devs[i]->c_identify) {
+                        c->x86_vendor_id[0] = 0;
+                        cpu_devs[i]->c_identify(c);
+                        if (c->x86_vendor_id[0]) {
+                                get_cpu_vendor(c);
+                                break;
+                        }
+                }
+#endif
+}
 /*
 * Do minimum CPU detection early.
 * Fields really needed: vendor, cpuid_level, family, model, mask,
@@ -321,25 +513,61 @@ static void __cpuinit early_get_cap(struct cpuinfo_x86 *c)
 * WARNING: this function is only called on the BP.  Don't add code here
 * that is supposed to run on all CPUs.
 */
-static void __init early_cpu_detect(void)
+static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 {
-        struct cpuinfo_x86 *c = &boot_cpu_data;
+#ifdef CONFIG_X86_64
+        c->x86_clflush_size = 64;
-        c->x86_cache_alignment = 32;
+#else
        c->x86_clflush_size = 32;
+#endif
+        c->x86_cache_alignment = c->x86_clflush_size;
+        memset(&c->x86_capability, 0, sizeof c->x86_capability);
+        c->extended_cpuid_level = 0;
        if (!have_cpuid_p())
+                identify_cpu_without_cpuid(c);
+        /* cyrix could have cpuid enabled via c_identify()*/
+        if (!have_cpuid_p())
                return;
        cpu_detect(c);
-        get_cpu_vendor(c, 1);
+        get_cpu_vendor(c);
-        early_get_cap(c);
+        get_cpu_cap(c);
-        if (c->x86_vendor != X86_VENDOR_UNKNOWN &&
+        if (this_cpu->c_early_init)
-            cpu_devs[c->x86_vendor]->c_early_init)
+                this_cpu->c_early_init(c);
-                cpu_devs[c->x86_vendor]->c_early_init(c);
+        validate_pat_support(c);
+}
+void __init early_cpu_init(void)
+{
+        struct cpu_dev **cdev;
+        int count = 0;
+        printk("KERNEL supported cpus:\n");
+        for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) {
+                struct cpu_dev *cpudev = *cdev;
+                unsigned int j;
+                if (count >= X86_VENDOR_NUM)
+                        break;
+                cpu_devs[count] = cpudev;
+                count++;
+                for (j = 0; j < 2; j++) {
+                        if (!cpudev->c_ident[j])
+                                continue;
+                        printk("  %s %s\n", cpudev->c_vendor,
+                                cpudev->c_ident[j]);
+                }
+        }
+        early_identify_cpu(&boot_cpu_data);
 }
 /*
@@ -357,86 +585,41 @@ static void __cpuinit detect_nopl(struct cpuinfo_x86 *c)
 static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
 {
-        u32 tfms, xlvl;
+        c->extended_cpuid_level = 0;
-        unsigned int ebx;
-        if (have_cpuid_p()) {
-                /* Get vendor name */
-                cpuid(0x00000000, (unsigned int *)&c->cpuid_level,
-                      (unsigned int *)&c->x86_vendor_id[0],
-                      (unsigned int *)&c->x86_vendor_id[8],
-                      (unsigned int *)&c->x86_vendor_id[4]);
-                get_cpu_vendor(c, 0);
-                /* Initialize the standard set of capabilities */
-                /* Note that the vendor-specific code below might override */
-                /* Intel-defined flags: level 0x00000001 */
-                if (c->cpuid_level >= 0x00000001) {
-                        u32 capability, excap;
-                        cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
-                        c->x86_capability[0] = capability;
-                        c->x86_capability[4] = excap;
-                        c->x86 = (tfms >> 8) & 15;
-                        c->x86_model = (tfms >> 4) & 15;
-                        if (c->x86 == 0xf)
-                                c->x86 += (tfms >> 20) & 0xff;
-                        if (c->x86 >= 0x6)
-                                c->x86_model += ((tfms >> 16) & 0xF) << 4;
-                        c->x86_mask = tfms & 15;
-                        c->initial_apicid = (ebx >> 24) & 0xFF;
-#ifdef CONFIG_X86_HT
-                        c->apicid = phys_pkg_id(c->initial_apicid, 0);
-                        c->phys_proc_id = c->initial_apicid;
-#else
-                        c->apicid = c->initial_apicid;
-#endif
-                        if (test_cpu_cap(c, X86_FEATURE_CLFLSH))
-                                c->x86_clflush_size = ((ebx >> 8) & 0xff) * 8;
-                } else {
-                        /* Have CPUID level 0 only - unheard of */
-                        c->x86 = 4;
-                }
-                /* AMD-defined flags: level 0x80000001 */
+        if (!have_cpuid_p())
-                xlvl = cpuid_eax(0x80000000);
+                identify_cpu_without_cpuid(c);
-                if ((xlvl & 0xffff0000) == 0x80000000) {
-                        if (xlvl >= 0x80000001) {
-                                c->x86_capability[1] = cpuid_edx(0x80000001);
-                                c->x86_capability[6] = cpuid_ecx(0x80000001);
-                        }
-                        if (xlvl >= 0x80000004)
-                                get_model_name(c); /* Default name */
-                }
-                init_scattered_cpuid_features(c);
+        /* cyrix could have cpuid enabled via c_identify()*/
-                detect_nopl(c);
+        if (!have_cpuid_p())
-        }
+                return;
-}
-static void __cpuinit squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
+        cpu_detect(c);
-{
-        if (cpu_has(c, X86_FEATURE_PN) && disable_x86_serial_nr) {
-                /* Disable processor serial number */
-                unsigned long lo, hi;
-                rdmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
-                lo |= 0x200000;
-                wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
-                printk(KERN_NOTICE "CPU serial number disabled.\n");
-                clear_cpu_cap(c, X86_FEATURE_PN);
-                /* Disabling the serial number may affect the cpuid level */
+        get_cpu_vendor(c);
-                c->cpuid_level = cpuid_eax(0);
-        }
-}
-static int __init x86_serial_nr_setup(char *s)
+        get_cpu_cap(c);
-{
-        disable_x86_serial_nr = 0;
-        return 1;
-}
-__setup("serialnumber", x86_serial_nr_setup);
+        if (c->cpuid_level >= 0x00000001) {
+                c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
+#ifdef CONFIG_X86_32
+# ifdef CONFIG_X86_HT
+                c->apicid = phys_pkg_id(c->initial_apicid, 0);
+# else
+                c->apicid = c->initial_apicid;
+# endif
+#endif
+#ifdef CONFIG_X86_HT
+                c->phys_proc_id = c->initial_apicid;
+#endif
+        }
+        get_model_name(c); /* Default name */
+        init_scattered_cpuid_features(c);
+        detect_nopl(c);
+}
 /*
 * This does the hard work of actually picking apart the CPU stuff...
@@ -448,30 +631,29 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
        c->loops_per_jiffy = loops_per_jiffy;
        c->x86_cache_size = -1;
        c->x86_vendor = X86_VENDOR_UNKNOWN;
-        c->cpuid_level = -1;    /* CPUID not detected */
        c->x86_model = c->x86_mask = 0; /* So far unknown... */
        c->x86_vendor_id[0] = '\0'; /* Unset */
        c->x86_model_id[0] = '\0';  /* Unset */
        c->x86_max_cores = 1;
+        c->x86_coreid_bits = 0;
+#ifdef CONFIG_X86_64
+        c->x86_clflush_size = 64;
+#else
+        c->cpuid_level = -1;    /* CPUID not detected */
        c->x86_clflush_size = 32;
+#endif
+        c->x86_cache_alignment = c->x86_clflush_size;
        memset(&c->x86_capability, 0, sizeof c->x86_capability);
-        if (!have_cpuid_p()) {
-                /*
-                 * First of all, decide if this is a 486 or higher
-                 * It's a 486 if we can modify the AC flag
-                 */
-                if (flag_is_changeable_p(X86_EFLAGS_AC))
-                        c->x86 = 4;
-                else
-                        c->x86 = 3;
-        }
        generic_identify(c);
        if (this_cpu->c_identify)
                this_cpu->c_identify(c);
+#ifdef CONFIG_X86_64
+        c->apicid = phys_pkg_id(0);
+#endif
        /*
         * Vendor-specific initialization.  In this section we
         * canonicalize the feature flags, meaning if there are
@@ -505,6 +687,10 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
                                c->x86, c->x86_model);
        }
+#ifdef CONFIG_X86_64
+        detect_ht(c);
+#endif
        /*
         * On SMP, boot_cpu_data holds the common feature set between
         * all CPUs; so make sure that we indicate which features are
@@ -513,7 +699,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
         */
        if (c != &boot_cpu_data) {
                /* AND the already accumulated flags with these */
-                for (i = 0 ; i < NCAPINTS ; i++)
+                for (i = 0; i < NCAPINTS; i++)
                        boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
        }
@@ -521,72 +707,79 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
        for (i = 0; i < NCAPINTS; i++)
                c->x86_capability[i] &= ~cleared_cpu_caps[i];
+#ifdef CONFIG_X86_MCE
        /* Init Machine Check Exception if available. */
        mcheck_init(c);
+#endif
        select_idle_routine(c);
+#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+        numa_add_cpu(smp_processor_id());
+#endif
 }
 void __init identify_boot_cpu(void)
 {
        identify_cpu(&boot_cpu_data);
+#ifdef CONFIG_X86_32
        sysenter_setup();
        enable_sep_cpu();
+#endif
 }
 void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
 {
        BUG_ON(c == &boot_cpu_data);
        identify_cpu(c);
+#ifdef CONFIG_X86_32
        enable_sep_cpu();
+#endif
        mtrr_ap_init();
 }
-#ifdef CONFIG_X86_HT
+struct msr_range {
-void __cpuinit detect_ht(struct cpuinfo_x86 *c)
+        unsigned min;
-{
+        unsigned max;
-        u32     eax, ebx, ecx, edx;
+};
-        int     index_msb, core_bits;
-        cpuid(1, &eax, &ebx, &ecx, &edx);
-        if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY))
-                return;
-        smp_num_siblings = (ebx & 0xff0000) >> 16;
-        if (smp_num_siblings == 1) {
+static struct msr_range msr_range_array[] __cpuinitdata = {
-                printk(KERN_INFO  "CPU: Hyper-Threading is disabled\n");
+        { 0x00000000, 0x00000418},
-        } else if (smp_num_siblings > 1) {
+        { 0xc0000000, 0xc000040b},
+        { 0xc0010000, 0xc0010142},
+        { 0xc0011000, 0xc001103b},
+};
-                if (smp_num_siblings > NR_CPUS) {
+static void __cpuinit print_cpu_msr(void)
-                        printk(KERN_WARNING "CPU: Unsupported number of the "
+{
-                                        "siblings %d", smp_num_siblings);
+        unsigned index;
-                        smp_num_siblings = 1;
+        u64 val;
-                        return;
+        int i;
+        unsigned index_min, index_max;
+        for (i = 0; i < ARRAY_SIZE(msr_range_array); i++) {
+                index_min = msr_range_array[i].min;
+                index_max = msr_range_array[i].max;
+                for (index = index_min; index < index_max; index++) {
+                        if (rdmsrl_amd_safe(index, &val))
+                                continue;
+                        printk(KERN_INFO " MSR%08x: %016llx\n", index, val);
                }
+        }
+}
-                index_msb = get_count_order(smp_num_siblings);
+static int show_msr __cpuinitdata;
-                c->phys_proc_id = phys_pkg_id(c->initial_apicid, index_msb);
+static __init int setup_show_msr(char *arg)
+{
-                printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
+        int num;
-                       c->phys_proc_id);
-                smp_num_siblings = smp_num_siblings / c->x86_max_cores;
-                index_msb = get_count_order(smp_num_siblings) ;
-                core_bits = get_count_order(c->x86_max_cores);
+        get_option(&arg, &num);
-                c->cpu_core_id = phys_pkg_id(c->initial_apicid, index_msb) &
+        if (num > 0)
-                                               ((1 << core_bits) - 1);
+                show_msr = num;
+        return 1;
-                if (c->x86_max_cores > 1)
-                        printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
-                               c->cpu_core_id);
-        }
 }
-#endif
+__setup("show_msr=", setup_show_msr);
 static __init int setup_noclflush(char *arg)
 {
@@ -605,17 +798,25 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
                vendor = c->x86_vendor_id;
        if (vendor && strncmp(c->x86_model_id, vendor, strlen(vendor)))
-                printk("%s ", vendor);
+                printk(KERN_CONT "%s ", vendor);
-        if (!c->x86_model_id[0])
+        if (c->x86_model_id[0])
-                printk("%d86", c->x86);
+                printk(KERN_CONT "%s", c->x86_model_id);
        else
-                printk("%s", c->x86_model_id);
+                printk(KERN_CONT "%d86", c->x86);
        if (c->x86_mask || c->cpuid_level >= 0)
-                printk(" stepping %02x\n", c->x86_mask);
+                printk(KERN_CONT " stepping %02x\n", c->x86_mask);
        else
-                printk("\n");
+                printk(KERN_CONT "\n");
+#ifdef CONFIG_SMP
+        if (c->cpu_index < show_msr)
+                print_cpu_msr();
+#else
+        if (show_msr)
+                print_cpu_msr();
+#endif
 }
 static __init int setup_disablecpuid(char *arg)
@@ -631,19 +832,89 @@ __setup("clearcpuid=", setup_disablecpuid);
 cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
-void __init early_cpu_init(void)
+#ifdef CONFIG_X86_64
+struct x8664_pda **_cpu_pda __read_mostly;
+EXPORT_SYMBOL(_cpu_pda);
+struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
+char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
+void __cpuinit pda_init(int cpu)
+{
+        struct x8664_pda *pda = cpu_pda(cpu);
+        /* Setup up data that may be needed in __get_free_pages early */
+        loadsegment(fs, 0);
+        loadsegment(gs, 0);
+        /* Memory clobbers used to order PDA accessed */
+        mb();
+        wrmsrl(MSR_GS_BASE, pda);
+        mb();
+        pda->cpunumber = cpu;
+        pda->irqcount = -1;
+        pda->kernelstack = (unsigned long)stack_thread_info() -
+                                 PDA_STACKOFFSET + THREAD_SIZE;
+        pda->active_mm = &init_mm;
+        pda->mmu_state = 0;
+        if (cpu == 0) {
+                /* others are initialized in smpboot.c */
+                pda->pcurrent = &init_task;
+                pda->irqstackptr = boot_cpu_stack;
+                pda->irqstackptr += IRQSTACKSIZE - 64;
+        } else {
+                if (!pda->irqstackptr) {
+                        pda->irqstackptr = (char *)
+                                __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
+                        if (!pda->irqstackptr)
+                                panic("cannot allocate irqstack for cpu %d",
+                                      cpu);
+                        pda->irqstackptr += IRQSTACKSIZE - 64;
+                }
+                if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE)
+                        pda->nodenumber = cpu_to_node(cpu);
+        }
+}
+char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
+                           DEBUG_STKSZ] __page_aligned_bss;
+extern asmlinkage void ignore_sysret(void);
+/* May not be marked __init: used by software suspend */
+void syscall_init(void)
 {
-        struct cpu_vendor_dev *cvdev;
+        /*
+         * LSTAR and STAR live in a bit strange symbiosis.
+         * They both write to the same internal register. STAR allows to
+         * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
+         */
+        wrmsrl(MSR_STAR,  ((u64)__USER32_CS)<<48  | ((u64)__KERNEL_CS)<<32);
+        wrmsrl(MSR_LSTAR, system_call);
+        wrmsrl(MSR_CSTAR, ignore_sysret);
-        for (cvdev = __x86cpuvendor_start ;
+#ifdef CONFIG_IA32_EMULATION
-             cvdev < __x86cpuvendor_end   ;
+        syscall32_cpu_init();
-             cvdev++)
+#endif
-                cpu_devs[cvdev->vendor] = cvdev->cpu_dev;
-        early_cpu_detect();
+        /* Flags to clear on syscall */
-        validate_pat_support(&boot_cpu_data);
+        wrmsrl(MSR_SYSCALL_MASK,
+               X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|X86_EFLAGS_IOPL);
 }
+unsigned long kernel_eflags;
+/*
+ * Copies of the original ist values from the tss are only accessed during
+ * debugging, no special alignment required.
+ */
+DEFINE_PER_CPU(struct orig_ist, orig_ist);
+#else
 /* Make sure %fs is initialized properly in idle threads */
 struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs)
 {
@@ -651,25 +922,136 @@ struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs)
        regs->fs = __KERNEL_PERCPU;
        return regs;
 }
+#endif
-/* Current gdt points %fs at the "master" per-cpu area: after this,
- * it's on the real one. */
-void switch_to_new_gdt(void)
-{
-        struct desc_ptr gdt_descr;
-        gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id());
-        gdt_descr.size = GDT_SIZE - 1;
-        load_gdt(&gdt_descr);
-        asm("mov %0, %%fs" : : "r" (__KERNEL_PERCPU) : "memory");
-}
 /*
 * cpu_init() initializes state that is per-CPU. Some data is already
 * initialized (naturally) in the bootstrap process, such as the GDT
 * and IDT. We reload them nevertheless, this function acts as a
 * 'CPU state barrier', nothing should get across.
+ * A lot of state is already set up in PDA init for 64 bit
 */
+#ifdef CONFIG_X86_64
+void __cpuinit cpu_init(void)
+{
+        int cpu = stack_smp_processor_id();
+        struct tss_struct *t = &per_cpu(init_tss, cpu);
+        struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu);
+        unsigned long v;
+        char *estacks = NULL;
+        struct task_struct *me;
+        int i;
+        /* CPU 0 is initialised in head64.c */
+        if (cpu != 0)
+                pda_init(cpu);
+        else
+                estacks = boot_exception_stacks;
+        me = current;
+        if (cpu_test_and_set(cpu, cpu_initialized))
+                panic("CPU#%d already initialized!\n", cpu);
+        printk(KERN_INFO "Initializing CPU#%d\n", cpu);
+        clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
+        /*
+         * Initialize the per-CPU GDT with the boot GDT,
+         * and set up the GDT descriptor:
+         */
+        switch_to_new_gdt();
+        load_idt((const struct desc_ptr *)&idt_descr);
+        memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
+        syscall_init();
+        wrmsrl(MSR_FS_BASE, 0);
+        wrmsrl(MSR_KERNEL_GS_BASE, 0);
+        barrier();
+        check_efer();
+        if (cpu != 0 && x2apic)
+                enable_x2apic();
+        /*
+         * set up and load the per-CPU TSS
+         */
+        if (!orig_ist->ist[0]) {
+                static const unsigned int order[N_EXCEPTION_STACKS] = {
+                  [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER,
+                  [DEBUG_STACK - 1] = DEBUG_STACK_ORDER
+                };
+                for (v = 0; v < N_EXCEPTION_STACKS; v++) {
+                        if (cpu) {
+                                estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]);
+                                if (!estacks)
+                                        panic("Cannot allocate exception "
+                                              "stack %ld %d\n", v, cpu);
+                        }
+                        estacks += PAGE_SIZE << order[v];
+                        orig_ist->ist[v] = t->x86_tss.ist[v] =
+                                        (unsigned long)estacks;
+                }
+        }
+        t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+        /*
+         * <= is required because the CPU will access up to
+         * 8 bits beyond the end of the IO permission bitmap.
+         */
+        for (i = 0; i <= IO_BITMAP_LONGS; i++)
+                t->io_bitmap[i] = ~0UL;
+        atomic_inc(&init_mm.mm_count);
+        me->active_mm = &init_mm;
+        if (me->mm)
+                BUG();
+        enter_lazy_tlb(&init_mm, me);
+        load_sp0(t, &current->thread);
+        set_tss_desc(cpu, t);
+        load_TR_desc();
+        load_LDT(&init_mm.context);
+#ifdef CONFIG_KGDB
+        /*
+         * If the kgdb is connected no debug regs should be altered.  This
+         * is only applicable when KGDB and a KGDB I/O module are built
+         * into the kernel and you are using early debugging with
+         * kgdbwait. KGDB will control the kernel HW breakpoint registers.
+         */
+        if (kgdb_connected && arch_kgdb_ops.correct_hw_break)
+                arch_kgdb_ops.correct_hw_break();
+        else {
+#endif
+        /*
+         * Clear all 6 debug registers:
+         */
+        set_debugreg(0UL, 0);
+        set_debugreg(0UL, 1);
+        set_debugreg(0UL, 2);
+        set_debugreg(0UL, 3);
+        set_debugreg(0UL, 6);
+        set_debugreg(0UL, 7);
+#ifdef CONFIG_KGDB
+        /* If the kgdb is connected no debug regs should be altered. */
+        }
+#endif
+        fpu_init();
+        raw_local_save_flags(kernel_eflags);
+        if (is_uv_system())
+                uv_cpu_init();
+}
+#else
 void __cpuinit cpu_init(void)
 {
        int cpu = smp_processor_id();
@@ -723,9 +1105,20 @@ void __cpuinit cpu_init(void)
        /*
         * Force FPU initialization:
         */
-        current_thread_info()->status = 0;
+        if (cpu_has_xsave)
+                current_thread_info()->status = TS_XSAVE;
+        else
+                current_thread_info()->status = 0;
        clear_used_math();
        mxcsr_feature_mask_init();
+        /*
+         * Boot processor to setup the FP and extended state context info.
+         */
+        if (!smp_processor_id())
+                init_thread_xstate();
+        xsave_init();
 }
 #ifdef CONFIG_HOTPLUG_CPU
@@ -739,3 +1132,5 @@ void __cpuinit cpu_uninit(void)
        per_cpu(cpu_tlbstate, cpu).active_mm = &init_mm;
 }
 #endif
+#endif
diff --git a/arch/x86/kernel/cpu/common_64.c b/arch/x86/kernel/cpu/common_64.c
deleted file mode 100644
index 305b465889b0..000000000000
--- a/arch/x86/kernel/cpu/common_64.c
+++ /dev/null
@@ -1,763 +0,0 @@
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/string.h>
-#include <linux/bootmem.h>
-#include <linux/bitops.h>
-#include <linux/module.h>
-#include <linux/kgdb.h>
-#include <linux/topology.h>
-#include <linux/delay.h>
-#include <linux/smp.h>
-#include <linux/percpu.h>
-#include <asm/i387.h>
-#include <asm/msr.h>
-#include <asm/io.h>
-#include <asm/linkage.h>
-#include <asm/mmu_context.h>
-#include <asm/mtrr.h>
-#include <asm/mce.h>
-#include <asm/pat.h>
-#include <asm/asm.h>
-#include <asm/numa.h>
-#ifdef CONFIG_X86_LOCAL_APIC
-#include <asm/mpspec.h>
-#include <asm/apic.h>
-#include <mach_apic.h>
-#endif
-#include <asm/pda.h>
-#include <asm/pgtable.h>
-#include <asm/processor.h>
-#include <asm/desc.h>
-#include <asm/atomic.h>
-#include <asm/proto.h>
-#include <asm/sections.h>
-#include <asm/setup.h>
-#include <asm/genapic.h>
-#include "cpu.h"
-/* We need valid kernel segments for data and code in long mode too
- * IRET will check the segment types  kkeil 2000/10/28
- * Also sysret mandates a special GDT layout
- */
-/* The TLS descriptors are currently at a different place compared to i386.
-   Hopefully nobody expects them at a fixed place (Wine?) */
-DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = {
-        [GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } },
-        [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } },
-        [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } },
-        [GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } },
-        [GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } },
-        [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } },
-} };
-EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
-__u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
-/* Current gdt points %fs at the "master" per-cpu area: after this,
- * it's on the real one. */
-void switch_to_new_gdt(void)
-{
-        struct desc_ptr gdt_descr;
-        gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id());
-        gdt_descr.size = GDT_SIZE - 1;
-        load_gdt(&gdt_descr);
-}
-struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
-static void __cpuinit default_init(struct cpuinfo_x86 *c)
-{
-        display_cacheinfo(c);
-}
-static struct cpu_dev __cpuinitdata default_cpu = {
-        .c_init = default_init,
-        .c_vendor = "Unknown",
-};
-static struct cpu_dev *this_cpu __cpuinitdata = &default_cpu;
-int __cpuinit get_model_name(struct cpuinfo_x86 *c)
-{
-        unsigned int *v;
-        if (c->extended_cpuid_level < 0x80000004)
-                return 0;
-        v = (unsigned int *) c->x86_model_id;
-        cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]);
-        cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]);
-        cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
-        c->x86_model_id[48] = 0;
-        return 1;
-}
-void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
-{
-        unsigned int n, dummy, ebx, ecx, edx;
-        n = c->extended_cpuid_level;
-        if (n >= 0x80000005) {
-                cpuid(0x80000005, &dummy, &ebx, &ecx, &edx);
-                printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), "
-                       "D cache %dK (%d bytes/line)\n",
-                       edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
-                c->x86_cache_size = (ecx>>24) + (edx>>24);
-                /* On K8 L1 TLB is inclusive, so don't count it */
-                c->x86_tlbsize = 0;
-        }
-        if (n >= 0x80000006) {
-                cpuid(0x80000006, &dummy, &ebx, &ecx, &edx);
-                ecx = cpuid_ecx(0x80000006);
-                c->x86_cache_size = ecx >> 16;
-                c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff);
-                printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
-                c->x86_cache_size, ecx & 0xFF);
-        }
-}
-void __cpuinit detect_ht(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
-        u32 eax, ebx, ecx, edx;
-        int index_msb, core_bits;
-        cpuid(1, &eax, &ebx, &ecx, &edx);
-        if (!cpu_has(c, X86_FEATURE_HT))
-                return;
-        if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
-                goto out;
-        smp_num_siblings = (ebx & 0xff0000) >> 16;
-        if (smp_num_siblings == 1) {
-                printk(KERN_INFO  "CPU: Hyper-Threading is disabled\n");
-        } else if (smp_num_siblings > 1) {
-                if (smp_num_siblings > NR_CPUS) {
-                        printk(KERN_WARNING "CPU: Unsupported number of "
-                               "siblings %d", smp_num_siblings);
-                        smp_num_siblings = 1;
-                        return;
-                }
-                index_msb = get_count_order(smp_num_siblings);
-                c->phys_proc_id = phys_pkg_id(index_msb);
-                smp_num_siblings = smp_num_siblings / c->x86_max_cores;
-                index_msb = get_count_order(smp_num_siblings);
-                core_bits = get_count_order(c->x86_max_cores);
-                c->cpu_core_id = phys_pkg_id(index_msb) &
-                                               ((1 << core_bits) - 1);
-        }
-out:
-        if ((c->x86_max_cores * smp_num_siblings) > 1) {
-                printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
-                       c->phys_proc_id);
-                printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
-                       c->cpu_core_id);
-        }
-#endif
-}
-static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c)
-{
-        char *v = c->x86_vendor_id;
-        int i;
-        static int printed;
-        for (i = 0; i < X86_VENDOR_NUM; i++) {
-                if (cpu_devs[i]) {
-                        if (!strcmp(v, cpu_devs[i]->c_ident[0]) ||
-                            (cpu_devs[i]->c_ident[1] &&
-                            !strcmp(v, cpu_devs[i]->c_ident[1]))) {
-                                c->x86_vendor = i;
-                                this_cpu = cpu_devs[i];
-                                return;
-                        }
-                }
-        }
-        if (!printed) {
-                printed++;
-                printk(KERN_ERR "CPU: Vendor unknown, using generic init.\n");
-                printk(KERN_ERR "CPU: Your system may be unstable.\n");
-        }
-        c->x86_vendor = X86_VENDOR_UNKNOWN;
-}
-static void __init early_cpu_support_print(void)
-{
-        int i,j;
-        struct cpu_dev *cpu_devx;
-        printk("KERNEL supported cpus:\n");
-        for (i = 0; i < X86_VENDOR_NUM; i++) {
-                cpu_devx = cpu_devs[i];
-                if (!cpu_devx)
-                        continue;
-                for (j = 0; j < 2; j++) {
-                        if (!cpu_devx->c_ident[j])
-                                continue;
-                        printk("  %s %s\n", cpu_devx->c_vendor,
-                                cpu_devx->c_ident[j]);
-                }
-        }
-}
-/*
- * The NOPL instruction is supposed to exist on all CPUs with
- * family >= 6, unfortunately, that's not true in practice because
- * of early VIA chips and (more importantly) broken virtualizers that
- * are not easy to detect.  Hence, probe for it based on first
- * principles.
- *
- * Note: no 64-bit chip is known to lack these, but put the code here
- * for consistency with 32 bits, and to make it utterly trivial to
- * diagnose the problem should it ever surface.
- */
-static void __cpuinit detect_nopl(struct cpuinfo_x86 *c)
-{
-        const u32 nopl_signature = 0x888c53b1; /* Random number */
-        u32 has_nopl = nopl_signature;
-        clear_cpu_cap(c, X86_FEATURE_NOPL);
-        if (c->x86 >= 6) {
-                asm volatile("\n"
-                             "1:      .byte 0x0f,0x1f,0xc0\n" /* nopl %eax */
-                             "2:\n"
-                             "        .section .fixup,\"ax\"\n"
-                             "3:      xor %0,%0\n"
-                             "        jmp 2b\n"
-                             "        .previous\n"
-                             _ASM_EXTABLE(1b,3b)
-                             : "+a" (has_nopl));
-                if (has_nopl == nopl_signature)
-                        set_cpu_cap(c, X86_FEATURE_NOPL);
-        }
-}
-static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c);
-void __init early_cpu_init(void)
-{
-        struct cpu_vendor_dev *cvdev;
-        for (cvdev = __x86cpuvendor_start ;
-             cvdev < __x86cpuvendor_end   ;
-             cvdev++)
-                cpu_devs[cvdev->vendor] = cvdev->cpu_dev;
-        early_cpu_support_print();
-        early_identify_cpu(&boot_cpu_data);
-}
-/* Do some early cpuid on the boot CPU to get some parameter that are
-   needed before check_bugs. Everything advanced is in identify_cpu
-   below. */
-static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c)
-{
-        u32 tfms, xlvl;
-        c->loops_per_jiffy = loops_per_jiffy;
-        c->x86_cache_size = -1;
-        c->x86_vendor = X86_VENDOR_UNKNOWN;
-        c->x86_model = c->x86_mask = 0; /* So far unknown... */
-        c->x86_vendor_id[0] = '\0'; /* Unset */
-        c->x86_model_id[0] = '\0';  /* Unset */
-        c->x86_clflush_size = 64;
-        c->x86_cache_alignment = c->x86_clflush_size;
-        c->x86_max_cores = 1;
-        c->x86_coreid_bits = 0;
-        c->extended_cpuid_level = 0;
-        memset(&c->x86_capability, 0, sizeof c->x86_capability);
-        /* Get vendor name */
-        cpuid(0x00000000, (unsigned int *)&c->cpuid_level,
-              (unsigned int *)&c->x86_vendor_id[0],
-              (unsigned int *)&c->x86_vendor_id[8],
-              (unsigned int *)&c->x86_vendor_id[4]);
-        get_cpu_vendor(c);
-        /* Initialize the standard set of capabilities */
-        /* Note that the vendor-specific code below might override */
-        /* Intel-defined flags: level 0x00000001 */
-        if (c->cpuid_level >= 0x00000001) {
-                __u32 misc;
-                cpuid(0x00000001, &tfms, &misc, &c->x86_capability[4],
-                      &c->x86_capability[0]);
-                c->x86 = (tfms >> 8) & 0xf;
-                c->x86_model = (tfms >> 4) & 0xf;
-                c->x86_mask = tfms & 0xf;
-                if (c->x86 == 0xf)
-                        c->x86 += (tfms >> 20) & 0xff;
-                if (c->x86 >= 0x6)
-                        c->x86_model += ((tfms >> 16) & 0xF) << 4;
-                if (test_cpu_cap(c, X86_FEATURE_CLFLSH))
-                        c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
-        } else {
-                /* Have CPUID level 0 only - unheard of */
-                c->x86 = 4;
-        }
-        c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xff;
-#ifdef CONFIG_SMP
-        c->phys_proc_id = c->initial_apicid;
-#endif
-        /* AMD-defined flags: level 0x80000001 */
-        xlvl = cpuid_eax(0x80000000);
-        c->extended_cpuid_level = xlvl;
-        if ((xlvl & 0xffff0000) == 0x80000000) {
-                if (xlvl >= 0x80000001) {
-                        c->x86_capability[1] = cpuid_edx(0x80000001);
-                        c->x86_capability[6] = cpuid_ecx(0x80000001);
-                }
-                if (xlvl >= 0x80000004)
-                        get_model_name(c); /* Default name */
-        }
-        /* Transmeta-defined flags: level 0x80860001 */
-        xlvl = cpuid_eax(0x80860000);
-        if ((xlvl & 0xffff0000) == 0x80860000) {
-                /* Don't set x86_cpuid_level here for now to not confuse. */
-                if (xlvl >= 0x80860001)
-                        c->x86_capability[2] = cpuid_edx(0x80860001);
-        }
-        if (c->extended_cpuid_level >= 0x80000007)
-                c->x86_power = cpuid_edx(0x80000007);
-        if (c->extended_cpuid_level >= 0x80000008) {
-                u32 eax = cpuid_eax(0x80000008);
-                c->x86_virt_bits = (eax >> 8) & 0xff;
-                c->x86_phys_bits = eax & 0xff;
-        }
-        detect_nopl(c);
-        if (c->x86_vendor != X86_VENDOR_UNKNOWN &&
-            cpu_devs[c->x86_vendor]->c_early_init)
-                cpu_devs[c->x86_vendor]->c_early_init(c);
-        validate_pat_support(c);
-}
-/*
- * This does the hard work of actually picking apart the CPU stuff...
- */
-static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
-{
-        int i;
-        early_identify_cpu(c);
-        init_scattered_cpuid_features(c);
-        c->apicid = phys_pkg_id(0);
-        /*
-         * Vendor-specific initialization.  In this section we
-         * canonicalize the feature flags, meaning if there are
-         * features a certain CPU supports which CPUID doesn't
-         * tell us, CPUID claiming incorrect flags, or other bugs,
-         * we handle them here.
-         *
-         * At the end of this section, c->x86_capability better
-         * indicate the features this CPU genuinely supports!
-         */
-        if (this_cpu->c_init)
-                this_cpu->c_init(c);
-        detect_ht(c);
-        /*
-         * On SMP, boot_cpu_data holds the common feature set between
-         * all CPUs; so make sure that we indicate which features are
-         * common between the CPUs.  The first time this routine gets
-         * executed, c == &boot_cpu_data.
-         */
-        if (c != &boot_cpu_data) {
-                /* AND the already accumulated flags with these */
-                for (i = 0; i < NCAPINTS; i++)
-                        boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
-        }
-        /* Clear all flags overriden by options */
-        for (i = 0; i < NCAPINTS; i++)
-                c->x86_capability[i] &= ~cleared_cpu_caps[i];
-#ifdef CONFIG_X86_MCE
-        mcheck_init(c);
-#endif
-        select_idle_routine(c);
-#ifdef CONFIG_NUMA
-        numa_add_cpu(smp_processor_id());
-#endif
-}
-void __cpuinit identify_boot_cpu(void)
-{
-        identify_cpu(&boot_cpu_data);
-}
-void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
-{
-        BUG_ON(c == &boot_cpu_data);
-        identify_cpu(c);
-        mtrr_ap_init();
-}
-static __init int setup_noclflush(char *arg)
-{
-        setup_clear_cpu_cap(X86_FEATURE_CLFLSH);
-        return 1;
-}
-__setup("noclflush", setup_noclflush);
-struct msr_range {
-        unsigned min;
-        unsigned max;
-};
-static struct msr_range msr_range_array[] __cpuinitdata = {
-        { 0x00000000, 0x00000418},
-        { 0xc0000000, 0xc000040b},
-        { 0xc0010000, 0xc0010142},
-        { 0xc0011000, 0xc001103b},
-};
-static void __cpuinit print_cpu_msr(void)
-{
-        unsigned index;
-        u64 val;
-        int i;
-        unsigned index_min, index_max;
-        for (i = 0; i < ARRAY_SIZE(msr_range_array); i++) {
-                index_min = msr_range_array[i].min;
-                index_max = msr_range_array[i].max;
-                for (index = index_min; index < index_max; index++) {
-                        if (rdmsrl_amd_safe(index, &val))
-                                continue;
-                        printk(KERN_INFO " MSR%08x: %016llx\n", index, val);
-                }
-        }
-}
-static int show_msr __cpuinitdata;
-static __init int setup_show_msr(char *arg)
-{
-        int num;
-        get_option(&arg, &num);
-        if (num > 0)
-                show_msr = num;
-        return 1;
-}
-__setup("show_msr=", setup_show_msr);
-void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
-{
-        if (c->x86_model_id[0])
-                printk(KERN_CONT "%s", c->x86_model_id);
-        if (c->x86_mask || c->cpuid_level >= 0)
-                printk(KERN_CONT " stepping %02x\n", c->x86_mask);
-        else
-                printk(KERN_CONT "\n");
-#ifdef CONFIG_SMP
-        if (c->cpu_index < show_msr)
-                print_cpu_msr();
-#else
-        if (show_msr)
-                print_cpu_msr();
-#endif
-}
-static __init int setup_disablecpuid(char *arg)
-{
-        int bit;
-        if (get_option(&arg, &bit) && bit < NCAPINTS*32)
-                setup_clear_cpu_cap(bit);
-        else
-                return 0;
-        return 1;
-}
-__setup("clearcpuid=", setup_disablecpuid);
-cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
-struct x8664_pda **_cpu_pda __read_mostly;
-EXPORT_SYMBOL(_cpu_pda);
-struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
-char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
-unsigned long __supported_pte_mask __read_mostly = ~0UL;
-EXPORT_SYMBOL_GPL(__supported_pte_mask);
-static int do_not_nx __cpuinitdata;
-/* noexec=on|off
-Control non executable mappings for 64bit processes.
-on      Enable(default)
-off     Disable
-*/
-static int __init nonx_setup(char *str)
-{
-        if (!str)
-                return -EINVAL;
-        if (!strncmp(str, "on", 2)) {
-                __supported_pte_mask |= _PAGE_NX;
-                do_not_nx = 0;
-        } else if (!strncmp(str, "off", 3)) {
-                do_not_nx = 1;
-                __supported_pte_mask &= ~_PAGE_NX;
-        }
-        return 0;
-}
-early_param("noexec", nonx_setup);
-int force_personality32;
-/* noexec32=on|off
-Control non executable heap for 32bit processes.
-To control the stack too use noexec=off
-on      PROT_READ does not imply PROT_EXEC for 32bit processes (default)
-off     PROT_READ implies PROT_EXEC
-*/
-static int __init nonx32_setup(char *str)
-{
-        if (!strcmp(str, "on"))
-                force_personality32 &= ~READ_IMPLIES_EXEC;
-        else if (!strcmp(str, "off"))
-                force_personality32 |= READ_IMPLIES_EXEC;
-        return 1;
-}
-__setup("noexec32=", nonx32_setup);
-void pda_init(int cpu)
-{
-        struct x8664_pda *pda = cpu_pda(cpu);
-        /* Setup up data that may be needed in __get_free_pages early */
-        loadsegment(fs, 0);
-        loadsegment(gs, 0);
-        /* Memory clobbers used to order PDA accessed */
-        mb();
-        wrmsrl(MSR_GS_BASE, pda);
-        mb();
-        pda->cpunumber = cpu;
-        pda->irqcount = -1;
-        pda->kernelstack = (unsigned long)stack_thread_info() -
-                                 PDA_STACKOFFSET + THREAD_SIZE;
-        pda->active_mm = &init_mm;
-        pda->mmu_state = 0;
-        if (cpu == 0) {
-                /* others are initialized in smpboot.c */
-                pda->pcurrent = &init_task;
-                pda->irqstackptr = boot_cpu_stack;
-                pda->irqstackptr += IRQSTACKSIZE - 64;
-        } else {
-                if (!pda->irqstackptr) {
-                        pda->irqstackptr = (char *)
-                                __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
-                        if (!pda->irqstackptr)
-                                panic("cannot allocate irqstack for cpu %d",
-                                      cpu);
-                        pda->irqstackptr += IRQSTACKSIZE - 64;
-                }
-                if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE)
-                        pda->nodenumber = cpu_to_node(cpu);
-        }
-}
-char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
-                           DEBUG_STKSZ] __page_aligned_bss;
-extern asmlinkage void ignore_sysret(void);
-/* May not be marked __init: used by software suspend */
-void syscall_init(void)
-{
-        /*
-         * LSTAR and STAR live in a bit strange symbiosis.
-         * They both write to the same internal register. STAR allows to
-         * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
-         */
-        wrmsrl(MSR_STAR,  ((u64)__USER32_CS)<<48  | ((u64)__KERNEL_CS)<<32);
-        wrmsrl(MSR_LSTAR, system_call);
-        wrmsrl(MSR_CSTAR, ignore_sysret);
-#ifdef CONFIG_IA32_EMULATION
-        syscall32_cpu_init();
-#endif
-        /* Flags to clear on syscall */
-        wrmsrl(MSR_SYSCALL_MASK,
-               X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|X86_EFLAGS_IOPL);
-}
-void __cpuinit check_efer(void)
-{
-        unsigned long efer;
-        rdmsrl(MSR_EFER, efer);
-        if (!(efer & EFER_NX) || do_not_nx)
-                __supported_pte_mask &= ~_PAGE_NX;
-}
-unsigned long kernel_eflags;
-/*
- * Copies of the original ist values from the tss are only accessed during
- * debugging, no special alignment required.
- */
-DEFINE_PER_CPU(struct orig_ist, orig_ist);
-/*
- * cpu_init() initializes state that is per-CPU. Some data is already
- * initialized (naturally) in the bootstrap process, such as the GDT
- * and IDT. We reload them nevertheless, this function acts as a
- * 'CPU state barrier', nothing should get across.
- * A lot of state is already set up in PDA init.
- */
-void __cpuinit cpu_init(void)
-{
-        int cpu = stack_smp_processor_id();
-        struct tss_struct *t = &per_cpu(init_tss, cpu);
-        struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu);
-        unsigned long v;
-        char *estacks = NULL;
-        struct task_struct *me;
-        int i;
-        /* CPU 0 is initialised in head64.c */
-        if (cpu != 0)
-                pda_init(cpu);
-        else
-                estacks = boot_exception_stacks;
-        me = current;
-        if (cpu_test_and_set(cpu, cpu_initialized))
-                panic("CPU#%d already initialized!\n", cpu);
-        printk(KERN_INFO "Initializing CPU#%d\n", cpu);
-        clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
-        /*
-         * Initialize the per-CPU GDT with the boot GDT,
-         * and set up the GDT descriptor:
-         */
-        switch_to_new_gdt();
-        load_idt((const struct desc_ptr *)&idt_descr);
-        memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
-        syscall_init();
-        wrmsrl(MSR_FS_BASE, 0);
-        wrmsrl(MSR_KERNEL_GS_BASE, 0);
-        barrier();
-        check_efer();
-        /*
-         * set up and load the per-CPU TSS
-         */
-        if (!orig_ist->ist[0]) {
-                static const unsigned int order[N_EXCEPTION_STACKS] = {
-                  [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER,
-                  [DEBUG_STACK - 1] = DEBUG_STACK_ORDER
-                };
-                for (v = 0; v < N_EXCEPTION_STACKS; v++) {
-                        if (cpu) {
-                                estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]);
-                                if (!estacks)
-                                        panic("Cannot allocate exception "
-                                              "stack %ld %d\n", v, cpu);
-                        }
-                        estacks += PAGE_SIZE << order[v];
-                        orig_ist->ist[v] = t->x86_tss.ist[v] =
-                                        (unsigned long)estacks;
-                }
-        }
-        t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
-        /*
-         * <= is required because the CPU will access up to
-         * 8 bits beyond the end of the IO permission bitmap.
-         */
-        for (i = 0; i <= IO_BITMAP_LONGS; i++)
-                t->io_bitmap[i] = ~0UL;
-        atomic_inc(&init_mm.mm_count);
-        me->active_mm = &init_mm;
-        if (me->mm)
-                BUG();
-        enter_lazy_tlb(&init_mm, me);
-        load_sp0(t, &current->thread);
-        set_tss_desc(cpu, t);
-        load_TR_desc();
-        load_LDT(&init_mm.context);
-#ifdef CONFIG_KGDB
-        /*
-         * If the kgdb is connected no debug regs should be altered.  This
-         * is only applicable when KGDB and a KGDB I/O module are built
-         * into the kernel and you are using early debugging with
-         * kgdbwait. KGDB will control the kernel HW breakpoint registers.
-         */
-        if (kgdb_connected && arch_kgdb_ops.correct_hw_break)
-                arch_kgdb_ops.correct_hw_break();
-        else {
-#endif
-        /*
-         * Clear all 6 debug registers:
-         */
-        set_debugreg(0UL, 0);
-        set_debugreg(0UL, 1);
-        set_debugreg(0UL, 2);
-        set_debugreg(0UL, 3);
-        set_debugreg(0UL, 6);
-        set_debugreg(0UL, 7);
-#ifdef CONFIG_KGDB
-        /* If the kgdb is connected no debug regs should be altered. */
-        }
-#endif
-        fpu_init();
-        raw_local_save_flags(kernel_eflags);
-        if (is_uv_system())
-                uv_cpu_init();
-}
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 4d894e8565fe..de4094a39210 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -21,23 +21,16 @@ struct cpu_dev {
        void            (*c_init)(struct cpuinfo_x86 * c);
        void            (*c_identify)(struct cpuinfo_x86 * c);
        unsigned int    (*c_size_cache)(struct cpuinfo_x86 * c, unsigned int size);
+        int     c_x86_vendor;
 };
-extern struct cpu_dev * cpu_devs [X86_VENDOR_NUM];
+#define cpu_dev_register(cpu_devX) \
+        static struct cpu_dev *__cpu_dev_##cpu_devX __used \
+        __attribute__((__section__(".x86_cpu_dev.init"))) = \
+        &cpu_devX;
-struct cpu_vendor_dev {
+extern struct cpu_dev *__x86_cpu_dev_start[], *__x86_cpu_dev_end[];
-        int vendor;
-        struct cpu_dev *cpu_dev;
-};
-#define cpu_vendor_dev_register(cpu_vendor_id, cpu_dev) \
-        static struct cpu_vendor_dev __cpu_vendor_dev_##cpu_vendor_id __used \
-        __attribute__((__section__(".x86cpuvendor.init"))) = \
-        { cpu_vendor_id, cpu_dev }
-extern struct cpu_vendor_dev __x86cpuvendor_start[], __x86cpuvendor_end[];
-extern int get_model_name(struct cpuinfo_x86 *c);
 extern void display_cacheinfo(struct cpuinfo_x86 *c);
 #endif
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 898a5a2002ed..ffd0f5ed071a 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -121,7 +121,7 @@ static void __cpuinit set_cx86_reorder(void)
        setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */
        /* Load/Store Serialize to mem access disable (=reorder it) */
-        setCx86(CX86_PCR0, getCx86(CX86_PCR0) & ~0x80);
+        setCx86_old(CX86_PCR0, getCx86_old(CX86_PCR0) & ~0x80);
        /* set load/store serialize from 1GB to 4GB */
        ccr3 |= 0xe0;
        setCx86(CX86_CCR3, ccr3);
@@ -132,11 +132,11 @@ static void __cpuinit set_cx86_memwb(void)
        printk(KERN_INFO "Enable Memory-Write-back mode on Cyrix/NSC processor.\n");
        /* CCR2 bit 2: unlock NW bit */
-        setCx86(CX86_CCR2, getCx86(CX86_CCR2) & ~0x04);
+        setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) & ~0x04);
        /* set 'Not Write-through' */
        write_cr0(read_cr0() | X86_CR0_NW);
        /* CCR2 bit 2: lock NW bit and set WT1 */
-        setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14);
+        setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x14);
 }
 /*
@@ -150,14 +150,14 @@ static void __cpuinit geode_configure(void)
        local_irq_save(flags);
        /* Suspend on halt power saving and enable #SUSP pin */
-        setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
+        setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x88);
        ccr3 = getCx86(CX86_CCR3);
        setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);       /* enable MAPEN */
        /* FPU fast, DTE cache, Mem bypass */
-        setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x38);
+        setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x38);
        setCx86(CX86_CCR3, ccr3);                       /* disable MAPEN */
        set_cx86_memwb();
@@ -291,7 +291,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c)
                /* GXm supports extended cpuid levels 'ala' AMD */
                if (c->cpuid_level == 2) {
                        /* Enable cxMMX extensions (GX1 Datasheet 54) */
-                        setCx86(CX86_CCR7, getCx86(CX86_CCR7) | 1);
+                        setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7) | 1);
                        /*
                         * GXm : 0x30 ... 0x5f GXm  datasheet 51
@@ -301,7 +301,6 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c)
                         */
                        if ((0x30 <= dir1 && dir1 <= 0x6f) || (0x80 <= dir1 && dir1 <= 0x8f))
                                geode_configure();
-                        get_model_name(c);  /* get CPU marketing name */
                        return;
                } else { /* MediaGX */
                        Cx86_cb[2] = (dir0_lsn & 1) ? '3' : '4';
@@ -314,7 +313,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c)
                if (dir1 > 7) {
                        dir0_msn++;  /* M II */
                        /* Enable MMX extensions (App note 108) */
-                        setCx86(CX86_CCR7, getCx86(CX86_CCR7)|1);
+                        setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7)|1);
                } else {
                        c->coma_bug = 1;      /* 6x86MX, it has the bug. */
                }
@@ -429,7 +428,7 @@ static void __cpuinit cyrix_identify(struct cpuinfo_x86 *c)
                        local_irq_save(flags);
                        ccr3 = getCx86(CX86_CCR3);
                        setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);       /* enable MAPEN  */
-                        setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x80);  /* enable cpuid  */
+                        setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x80);  /* enable cpuid  */
                        setCx86(CX86_CCR3, ccr3);                       /* disable MAPEN */
                        local_irq_restore(flags);
                }
@@ -442,14 +441,16 @@ static struct cpu_dev cyrix_cpu_dev __cpuinitdata = {
        .c_early_init   = early_init_cyrix,
        .c_init         = init_cyrix,
        .c_identify     = cyrix_identify,
+        .c_x86_vendor   = X86_VENDOR_CYRIX,
 };
-cpu_vendor_dev_register(X86_VENDOR_CYRIX, &cyrix_cpu_dev);
+cpu_dev_register(cyrix_cpu_dev);
 static struct cpu_dev nsc_cpu_dev __cpuinitdata = {
        .c_vendor       = "NSC",
        .c_ident        = { "Geode by NSC" },
        .c_init         = init_nsc,
+        .c_x86_vendor   = X86_VENDOR_NSC,
 };
-cpu_vendor_dev_register(X86_VENDOR_NSC, &nsc_cpu_dev);
+cpu_dev_register(nsc_cpu_dev);
diff --git a/arch/x86/kernel/cpu/feature_names.c b/arch/x86/kernel/cpu/feature_names.c
deleted file mode 100644
index c9017799497c..000000000000
--- a/arch/x86/kernel/cpu/feature_names.c
+++ /dev/null
@@ -1,84 +0,0 @@
-/*
- * Strings for the various x86 capability flags.
- *
- * This file must not contain any executable code.
- */
-#include <asm/cpufeature.h>
-/*
- * These flag bits must match the definitions in <asm/cpufeature.h>.
- * NULL means this bit is undefined or reserved; either way it doesn't
- * have meaning as far as Linux is concerned.  Note that it's important
- * to realize there is a difference between this table and CPUID -- if
- * applications want to get the raw CPUID data, they should access
- * /dev/cpu/<cpu_nr>/cpuid instead.
- */
-const char * const x86_cap_flags[NCAPINTS*32] = {
-        /* Intel-defined */
-        "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
-        "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov",
-        "pat", "pse36", "pn", "clflush", NULL, "dts", "acpi", "mmx",
-        "fxsr", "sse", "sse2", "ss", "ht", "tm", "ia64", "pbe",
-        /* AMD-defined */
-        NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-        NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL,
-        NULL, NULL, NULL, "mp", "nx", NULL, "mmxext", NULL,
-        NULL, "fxsr_opt", "pdpe1gb", "rdtscp", NULL, "lm",
-        "3dnowext", "3dnow",
-        /* Transmeta-defined */
-        "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL,
-        NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-        NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-        NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-        /* Other (Linux-defined) */
-        "cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr",
-        NULL, NULL, NULL, NULL,
-        "constant_tsc", "up", NULL, "arch_perfmon",
-        "pebs", "bts", NULL, NULL,
-        "rep_good", NULL, NULL, NULL,
-        "nopl", NULL, NULL, NULL,
-        NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-        /* Intel-defined (#2) */
-        "pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est",
-        "tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL,
-        NULL, NULL, "dca", "sse4_1", "sse4_2", NULL, NULL, "popcnt",
-        NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-        /* VIA/Cyrix/Centaur-defined */
-        NULL, NULL, "rng", "rng_en", NULL, NULL, "ace", "ace_en",
-        "ace2", "ace2_en", "phe", "phe_en", "pmm", "pmm_en", NULL, NULL,
-        NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-        NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-        /* AMD-defined (#2) */
-        "lahf_lm", "cmp_legacy", "svm", "extapic",
-        "cr8_legacy", "abm", "sse4a", "misalignsse",
-        "3dnowprefetch", "osvw", "ibs", "sse5",
-        "skinit", "wdt", NULL, NULL,
-        NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-        NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-        /* Auxiliary (Linux-defined) */
-        "ida", NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-        NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-        NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-        NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-};
-const char *const x86_power_flags[32] = {
-        "ts",   /* temperature sensor */
-        "fid",  /* frequency id control */
-        "vid",  /* voltage id control */
-        "ttp",  /* thermal trip */
-        "tm",
-        "stc",
-        "100mhzsteps",
-        "hwpstate",
-        "",     /* tsc invariant mapped to constant_tsc */
-                /* nothing */
-};
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index f113ef4595f6..99468dbd08da 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -15,6 +15,11 @@
 #include <asm/ds.h>
 #include <asm/bugs.h>
+#ifdef CONFIG_X86_64
+#include <asm/topology.h>
+#include <asm/numa_64.h>
+#endif
 #include "cpu.h"
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -23,23 +28,22 @@
 #include <mach_apic.h>
 #endif
-#ifdef CONFIG_X86_INTEL_USERCOPY
-/*
- * Alignment at which movsl is preferred for bulk memory copies.
- */
-struct movsl_mask movsl_mask __read_mostly;
-#endif
 static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 {
-        /* Netburst reports 64 bytes clflush size, but does IO in 128 bytes */
-        if (c->x86 == 15 && c->x86_cache_alignment == 64)
-                c->x86_cache_alignment = 128;
        if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
                (c->x86 == 0x6 && c->x86_model >= 0x0e))
                set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+#ifdef CONFIG_X86_64
+        set_cpu_cap(c, X86_FEATURE_SYSENTER32);
+#else
+        /* Netburst reports 64 bytes clflush size, but does IO in 128 bytes */
+        if (c->x86 == 15 && c->x86_cache_alignment == 64)
+                c->x86_cache_alignment = 128;
+#endif
 }
+#ifdef CONFIG_X86_32
 /*
 *      Early probe support logic for ppro memory erratum #50
 *
@@ -59,15 +63,54 @@ int __cpuinit ppro_with_ram_bug(void)
        return 0;
 }
+#ifdef CONFIG_X86_F00F_BUG
+static void __cpuinit trap_init_f00f_bug(void)
+{
+        __set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO);
-/*
+        /*
- * P4 Xeon errata 037 workaround.
+         * Update the IDT descriptor and reload the IDT so that
- * Hardware prefetcher may cause stale data to be loaded into the cache.
+         * it uses the read-only mapped virtual address.
- */
+         */
-static void __cpuinit Intel_errata_workarounds(struct cpuinfo_x86 *c)
+        idt_descr.address = fix_to_virt(FIX_F00F_IDT);
+        load_idt(&idt_descr);
+}
+#endif
+static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c)
 {
        unsigned long lo, hi;
+#ifdef CONFIG_X86_F00F_BUG
+        /*
+         * All current models of Pentium and Pentium with MMX technology CPUs
+         * have the F0 0F bug, which lets nonprivileged users lock up the system.
+         * Note that the workaround only should be initialized once...
+         */
+        c->f00f_bug = 0;
+        if (!paravirt_enabled() && c->x86 == 5) {
+                static int f00f_workaround_enabled;
+                c->f00f_bug = 1;
+                if (!f00f_workaround_enabled) {
+                        trap_init_f00f_bug();
+                        printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n");
+                        f00f_workaround_enabled = 1;
+                }
+        }
+#endif
+        /*
+         * SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until
+         * model 3 mask 3
+         */
+        if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633)
+                clear_cpu_cap(c, X86_FEATURE_SEP);
+        /*
+         * P4 Xeon errata 037 workaround.
+         * Hardware prefetcher may cause stale data to be loaded into the cache.
+         */
        if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) {
                rdmsr(MSR_IA32_MISC_ENABLE, lo, hi);
                if ((lo & (1<<9)) == 0) {
@@ -77,13 +120,68 @@ static void __cpuinit Intel_errata_workarounds(struct cpuinfo_x86 *c)
                        wrmsr (MSR_IA32_MISC_ENABLE, lo, hi);
                }
        }
+        /*
+         * See if we have a good local APIC by checking for buggy Pentia,
+         * i.e. all B steppings and the C2 stepping of P54C when using their
+         * integrated APIC (see 11AP erratum in "Pentium Processor
+         * Specification Update").
+         */
+        if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
+            (c->x86_mask < 0x6 || c->x86_mask == 0xb))
+                set_cpu_cap(c, X86_FEATURE_11AP);
+#ifdef CONFIG_X86_INTEL_USERCOPY
+        /*
+         * Set up the preferred alignment for movsl bulk memory moves
+         */
+        switch (c->x86) {
+        case 4:         /* 486: untested */
+                break;
+        case 5:         /* Old Pentia: untested */
+                break;
+        case 6:         /* PII/PIII only like movsl with 8-byte alignment */
+                movsl_mask.mask = 7;
+                break;
+        case 15:        /* P4 is OK down to 8-byte alignment */
+                movsl_mask.mask = 7;
+                break;
+        }
+#endif
+#ifdef CONFIG_X86_NUMAQ
+        numaq_tsc_disable();
+#endif
 }
+#else
+static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c)
+{
+}
+#endif
+static void __cpuinit srat_detect_node(void)
+{
+#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+        unsigned node;
+        int cpu = smp_processor_id();
+        int apicid = hard_smp_processor_id();
+        /* Don't do the funky fallback heuristics the AMD version employs
+           for now. */
+        node = apicid_to_node[apicid];
+        if (node == NUMA_NO_NODE || !node_online(node))
+                node = first_node(node_online_map);
+        numa_set_node(cpu, node);
+        printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
+#endif
+}
 /*
 * find out the number of processor cores on the die
 */
-static int __cpuinit num_cpu_cores(struct cpuinfo_x86 *c)
+static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c)
 {
        unsigned int eax, ebx, ecx, edx;
@@ -98,45 +196,51 @@ static int __cpuinit num_cpu_cores(struct cpuinfo_x86 *c)
                return 1;
 }
-#ifdef CONFIG_X86_F00F_BUG
+static void __cpuinit detect_vmx_virtcap(struct cpuinfo_x86 *c)
-static void __cpuinit trap_init_f00f_bug(void)
 {
-        __set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO);
+        /* Intel VMX MSR indicated features */
+#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW    0x00200000
-        /*
+#define X86_VMX_FEATURE_PROC_CTLS_VNMI          0x00400000
-         * Update the IDT descriptor and reload the IDT so that
+#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS      0x80000000
-         * it uses the read-only mapped virtual address.
+#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC    0x00000001
-         */
+#define X86_VMX_FEATURE_PROC_CTLS2_EPT          0x00000002
-        idt_descr.address = fix_to_virt(FIX_F00F_IDT);
+#define X86_VMX_FEATURE_PROC_CTLS2_VPID         0x00000020
-        load_idt(&idt_descr);
+        u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+        clear_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
+        clear_cpu_cap(c, X86_FEATURE_VNMI);
+        clear_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
+        clear_cpu_cap(c, X86_FEATURE_EPT);
+        clear_cpu_cap(c, X86_FEATURE_VPID);
+        rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
+        msr_ctl = vmx_msr_high | vmx_msr_low;
+        if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)
+                set_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
+        if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI)
+                set_cpu_cap(c, X86_FEATURE_VNMI);
+        if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) {
+                rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
+                      vmx_msr_low, vmx_msr_high);
+                msr_ctl2 = vmx_msr_high | vmx_msr_low;
+                if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
+                    (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
+                        set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
+                if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+                        set_cpu_cap(c, X86_FEATURE_EPT);
+                if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
+                        set_cpu_cap(c, X86_FEATURE_VPID);
+        }
 }
-#endif
 static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 {
        unsigned int l2 = 0;
-        char *p = NULL;
        early_init_intel(c);
-#ifdef CONFIG_X86_F00F_BUG
+        intel_workarounds(c);
-        /*
-         * All current models of Pentium and Pentium with MMX technology CPUs
-         * have the F0 0F bug, which lets nonprivileged users lock up the system.
-         * Note that the workaround only should be initialized once...
-         */
-        c->f00f_bug = 0;
-        if (!paravirt_enabled() && c->x86 == 5) {
-                static int f00f_workaround_enabled;
-                c->f00f_bug = 1;
-                if (!f00f_workaround_enabled) {
-                        trap_init_f00f_bug();
-                        printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n");
-                        f00f_workaround_enabled = 1;
-                }
-        }
-#endif
        l2 = init_intel_cacheinfo(c);
        if (c->cpuid_level > 9) {
@@ -146,16 +250,32 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
                        set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
        }
-        /* SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until model 3 mask 3 */
+        if (cpu_has_xmm2)
-        if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633)
+                set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
-                clear_cpu_cap(c, X86_FEATURE_SEP);
+        if (cpu_has_ds) {
+                unsigned int l1;
+                rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
+                if (!(l1 & (1<<11)))
+                        set_cpu_cap(c, X86_FEATURE_BTS);
+                if (!(l1 & (1<<12)))
+                        set_cpu_cap(c, X86_FEATURE_PEBS);
+                ds_init_intel(c);
+        }
+#ifdef CONFIG_X86_64
+        if (c->x86 == 15)
+                c->x86_cache_alignment = c->x86_clflush_size * 2;
+        if (c->x86 == 6)
+                set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+#else
        /*
         * Names for the Pentium II/Celeron processors
         * detectable only by also checking the cache size.
         * Dixon is NOT a Celeron.
         */
        if (c->x86 == 6) {
+                char *p = NULL;
                switch (c->x86_model) {
                case 5:
                        if (c->x86_mask == 0) {
@@ -178,71 +298,41 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
                                p = "Celeron (Coppermine)";
                        break;
                }
-        }
-        if (p)
-                strcpy(c->x86_model_id, p);
-        c->x86_max_cores = num_cpu_cores(c);
-        detect_ht(c);
-        /* Work around errata */
+                if (p)
-        Intel_errata_workarounds(c);
+                        strcpy(c->x86_model_id, p);
-#ifdef CONFIG_X86_INTEL_USERCOPY
-        /*
-         * Set up the preferred alignment for movsl bulk memory moves
-         */
-        switch (c->x86) {
-        case 4:         /* 486: untested */
-                break;
-        case 5:         /* Old Pentia: untested */
-                break;
-        case 6:         /* PII/PIII only like movsl with 8-byte alignment */
-                movsl_mask.mask = 7;
-                break;
-        case 15:        /* P4 is OK down to 8-byte alignment */
-                movsl_mask.mask = 7;
-                break;
        }
-#endif
-        if (cpu_has_xmm2)
+        if (c->x86 == 15)
-                set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
-        if (c->x86 == 15) {
                set_cpu_cap(c, X86_FEATURE_P4);
-        }
        if (c->x86 == 6)
                set_cpu_cap(c, X86_FEATURE_P3);
-        if (cpu_has_ds) {
-                unsigned int l1;
-                rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
-                if (!(l1 & (1<<11)))
-                        set_cpu_cap(c, X86_FEATURE_BTS);
-                if (!(l1 & (1<<12)))
-                        set_cpu_cap(c, X86_FEATURE_PEBS);
-                ds_init_intel(c);
-        }
        if (cpu_has_bts)
                ptrace_bts_init_intel(c);
-        /*
+#endif
-         * See if we have a good local APIC by checking for buggy Pentia,
-         * i.e. all B steppings and the C2 stepping of P54C when using their
-         * integrated APIC (see 11AP erratum in "Pentium Processor
-         * Specification Update").
-         */
-        if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
-            (c->x86_mask < 0x6 || c->x86_mask == 0xb))
-                set_cpu_cap(c, X86_FEATURE_11AP);
-#ifdef CONFIG_X86_NUMAQ
+        detect_extended_topology(c);
-        numaq_tsc_disable();
+        if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
+                /*
+                 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
+                 * detection.
+                 */
+                c->x86_max_cores = intel_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+                detect_ht(c);
 #endif
+        }
+        /* Work around errata */
+        srat_detect_node();
+        if (cpu_has(c, X86_FEATURE_VMX))
+                detect_vmx_virtcap(c);
 }
+#ifdef CONFIG_X86_32
 static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 {
        /*
@@ -255,10 +345,12 @@ static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned i
                size = 256;
        return size;
 }
+#endif
 static struct cpu_dev intel_cpu_dev __cpuinitdata = {
        .c_vendor       = "Intel",
        .c_ident        = { "GenuineIntel" },
+#ifdef CONFIG_X86_32
        .c_models = {
                { .vendor = X86_VENDOR_INTEL, .family = 4, .model_names =
                  {
@@ -308,76 +400,12 @@ static struct cpu_dev intel_cpu_dev __cpuinitdata = {
                  }
                },
        },
+        .c_size_cache   = intel_size_cache,
+#endif
        .c_early_init   = early_init_intel,
        .c_init         = init_intel,
-        .c_size_cache   = intel_size_cache,
+        .c_x86_vendor   = X86_VENDOR_INTEL,
 };
-cpu_vendor_dev_register(X86_VENDOR_INTEL, &intel_cpu_dev);
+cpu_dev_register(intel_cpu_dev);
-#ifndef CONFIG_X86_CMPXCHG
-unsigned long cmpxchg_386_u8(volatile void *ptr, u8 old, u8 new)
-{
-        u8 prev;
-        unsigned long flags;
-        /* Poor man's cmpxchg for 386. Unsuitable for SMP */
-        local_irq_save(flags);
-        prev = *(u8 *)ptr;
-        if (prev == old)
-                *(u8 *)ptr = new;
-        local_irq_restore(flags);
-        return prev;
-}
-EXPORT_SYMBOL(cmpxchg_386_u8);
-unsigned long cmpxchg_386_u16(volatile void *ptr, u16 old, u16 new)
-{
-        u16 prev;
-        unsigned long flags;
-        /* Poor man's cmpxchg for 386. Unsuitable for SMP */
-        local_irq_save(flags);
-        prev = *(u16 *)ptr;
-        if (prev == old)
-                *(u16 *)ptr = new;
-        local_irq_restore(flags);
-        return prev;
-}
-EXPORT_SYMBOL(cmpxchg_386_u16);
-unsigned long cmpxchg_386_u32(volatile void *ptr, u32 old, u32 new)
-{
-        u32 prev;
-        unsigned long flags;
-        /* Poor man's cmpxchg for 386. Unsuitable for SMP */
-        local_irq_save(flags);
-        prev = *(u32 *)ptr;
-        if (prev == old)
-                *(u32 *)ptr = new;
-        local_irq_restore(flags);
-        return prev;
-}
-EXPORT_SYMBOL(cmpxchg_386_u32);
-#endif
-#ifndef CONFIG_X86_CMPXCHG64
-unsigned long long cmpxchg_486_u64(volatile void *ptr, u64 old, u64 new)
-{
-        u64 prev;
-        unsigned long flags;
-        /* Poor man's cmpxchg8b for 386 and 486. Unsuitable for SMP */
-        local_irq_save(flags);
-        prev = *(u64 *)ptr;
-        if (prev == old)
-                *(u64 *)ptr = new;
-        local_irq_restore(flags);
-        return prev;
-}
-EXPORT_SYMBOL(cmpxchg_486_u64);
-#endif
-/* arch_initcall(intel_cpu_init); */
diff --git a/arch/x86/kernel/cpu/intel_64.c b/arch/x86/kernel/cpu/intel_64.c
deleted file mode 100644
index 1019c58d39f0..000000000000
--- a/arch/x86/kernel/cpu/intel_64.c
+++ /dev/null
@@ -1,95 +0,0 @@
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <asm/processor.h>
-#include <asm/ptrace.h>
-#include <asm/topology.h>
-#include <asm/numa_64.h>
-#include "cpu.h"
-static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
-{
-        if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
-            (c->x86 == 0x6 && c->x86_model >= 0x0e))
-                set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-        set_cpu_cap(c, X86_FEATURE_SYSENTER32);
-}
-/*
- * find out the number of processor cores on the die
- */
-static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c)
-{
-        unsigned int eax, t;
-        if (c->cpuid_level < 4)
-                return 1;
-        cpuid_count(4, 0, &eax, &t, &t, &t);
-        if (eax & 0x1f)
-                return ((eax >> 26) + 1);
-        else
-                return 1;
-}
-static void __cpuinit srat_detect_node(void)
-{
-#ifdef CONFIG_NUMA
-        unsigned node;
-        int cpu = smp_processor_id();
-        int apicid = hard_smp_processor_id();
-        /* Don't do the funky fallback heuristics the AMD version employs
-           for now. */
-        node = apicid_to_node[apicid];
-        if (node == NUMA_NO_NODE || !node_online(node))
-                node = first_node(node_online_map);
-        numa_set_node(cpu, node);
-        printk(KERN_INFO "CPU %d/%x -> Node %d\n", cpu, apicid, node);
-#endif
-}
-static void __cpuinit init_intel(struct cpuinfo_x86 *c)
-{
-        init_intel_cacheinfo(c);
-        if (c->cpuid_level > 9) {
-                unsigned eax = cpuid_eax(10);
-                /* Check for version and the number of counters */
-                if ((eax & 0xff) && (((eax>>8) & 0xff) > 1))
-                        set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
-        }
-        if (cpu_has_ds) {
-                unsigned int l1, l2;
-                rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
-                if (!(l1 & (1<<11)))
-                        set_cpu_cap(c, X86_FEATURE_BTS);
-                if (!(l1 & (1<<12)))
-                        set_cpu_cap(c, X86_FEATURE_PEBS);
-        }
-        if (cpu_has_bts)
-                ds_init_intel(c);
-        if (c->x86 == 15)
-                c->x86_cache_alignment = c->x86_clflush_size * 2;
-        if (c->x86 == 6)
-                set_cpu_cap(c, X86_FEATURE_REP_GOOD);
-        set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
-        c->x86_max_cores = intel_num_cpu_cores(c);
-        srat_detect_node();
-}
-static struct cpu_dev intel_cpu_dev __cpuinitdata = {
-        .c_vendor       = "Intel",
-        .c_ident        = { "GenuineIntel" },
-        .c_early_init   = early_init_intel,
-        .c_init         = init_intel,
-};
-cpu_vendor_dev_register(X86_VENDOR_INTEL, &intel_cpu_dev);
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 6b0a10b002f1..3f46afbb1cf1 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -1,8 +1,8 @@
 /*
- *      Routines to indentify caches on Intel CPU.
+ *      Routines to indentify caches on Intel CPU.
 *
- *      Changes:
+ *      Changes:
- *      Venkatesh Pallipadi     : Adding cache identification through cpuid(4)
+ *      Venkatesh Pallipadi     : Adding cache identification through cpuid(4)
 *              Ashok Raj <ashok.raj@intel.com>: Work with CPU hotplug infrastructure.
 *      Andi Kleen / Andreas Herrmann   : CPUID4 emulation on AMD.
 */
@@ -13,6 +13,7 @@
 #include <linux/compiler.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
+#include <linux/pci.h>
 #include <asm/processor.h>
 #include <asm/smp.h>
@@ -130,9 +131,18 @@ struct _cpuid4_info {
        union _cpuid4_leaf_ebx ebx;
        union _cpuid4_leaf_ecx ecx;
        unsigned long size;
+        unsigned long can_disable;
        cpumask_t shared_cpu_map;       /* future?: only cpus/node is needed */
 };
+#ifdef CONFIG_PCI
+static struct pci_device_id k8_nb_id[] = {
+        { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1103) },
+        { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1203) },
+        {}
+};
+#endif
 unsigned short                  num_cache_leaves;
 /* AMD doesn't have CPUID4. Emulate it here to report the same
@@ -182,9 +192,10 @@ static unsigned short assocs[] __cpuinitdata = {
 static unsigned char levels[] __cpuinitdata = { 1, 1, 2, 3 };
 static unsigned char types[] __cpuinitdata = { 1, 2, 3, 3 };
-static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
+static void __cpuinit
-                       union _cpuid4_leaf_ebx *ebx,
+amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
-                       union _cpuid4_leaf_ecx *ecx)
+                     union _cpuid4_leaf_ebx *ebx,
+                     union _cpuid4_leaf_ecx *ecx)
 {
        unsigned dummy;
        unsigned line_size, lines_per_tag, assoc, size_in_kb;
@@ -251,27 +262,40 @@ static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
                (ebx->split.ways_of_associativity + 1) - 1;
 }
-static int __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
+static void __cpuinit
+amd_check_l3_disable(int index, struct _cpuid4_info *this_leaf)
+{
+        if (index < 3)
+                return;
+        this_leaf->can_disable = 1;
+}
+static int
+__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
 {
        union _cpuid4_leaf_eax  eax;
        union _cpuid4_leaf_ebx  ebx;
        union _cpuid4_leaf_ecx  ecx;
        unsigned                edx;
-        if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+        if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
                amd_cpuid4(index, &eax, &ebx, &ecx);
-        else
+                if (boot_cpu_data.x86 >= 0x10)
-                cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full,  &edx);
+                        amd_check_l3_disable(index, this_leaf);
+        } else {
+                cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
+        }
        if (eax.split.type == CACHE_TYPE_NULL)
                return -EIO; /* better error ? */
        this_leaf->eax = eax;
        this_leaf->ebx = ebx;
        this_leaf->ecx = ecx;
-        this_leaf->size = (ecx.split.number_of_sets + 1) *
+        this_leaf->size = (ecx.split.number_of_sets          + 1) *
-                (ebx.split.coherency_line_size + 1) *
+                          (ebx.split.coherency_line_size     + 1) *
-                (ebx.split.physical_line_partition + 1) *
+                          (ebx.split.physical_line_partition + 1) *
-                (ebx.split.ways_of_associativity + 1);
+                          (ebx.split.ways_of_associativity   + 1);
        return 0;
 }
@@ -453,7 +477,7 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
 /* pointer to _cpuid4_info array (for each cache leaf) */
 static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info);
-#define CPUID4_INFO_IDX(x, y)    (&((per_cpu(cpuid4_info, x))[y]))
+#define CPUID4_INFO_IDX(x, y)   (&((per_cpu(cpuid4_info, x))[y]))
 #ifdef CONFIG_SMP
 static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
@@ -490,7 +514,7 @@ static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
        this_leaf = CPUID4_INFO_IDX(cpu, index);
        for_each_cpu_mask_nr(sibling, this_leaf->shared_cpu_map) {
-                sibling_leaf = CPUID4_INFO_IDX(sibling, index); 
+                sibling_leaf = CPUID4_INFO_IDX(sibling, index);
                cpu_clear(cpu, sibling_leaf->shared_cpu_map);
        }
 }
@@ -572,7 +596,7 @@ struct _index_kobject {
 /* pointer to array of kobjects for cpuX/cache/indexY */
 static DEFINE_PER_CPU(struct _index_kobject *, index_kobject);
-#define INDEX_KOBJECT_PTR(x, y)    (&((per_cpu(index_kobject, x))[y]))
+#define INDEX_KOBJECT_PTR(x, y)         (&((per_cpu(index_kobject, x))[y]))
 #define show_one_plus(file_name, object, val)                           \
 static ssize_t show_##file_name                                         \
@@ -637,6 +661,99 @@ static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf) {
        }
 }
+#define to_object(k)    container_of(k, struct _index_kobject, kobj)
+#define to_attr(a)      container_of(a, struct _cache_attr, attr)
+#ifdef CONFIG_PCI
+static struct pci_dev *get_k8_northbridge(int node)
+{
+        struct pci_dev *dev = NULL;
+        int i;
+        for (i = 0; i <= node; i++) {
+                do {
+                        dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
+                        if (!dev)
+                                break;
+                } while (!pci_match_id(&k8_nb_id[0], dev));
+                if (!dev)
+                        break;
+        }
+        return dev;
+}
+#else
+static struct pci_dev *get_k8_northbridge(int node)
+{
+        return NULL;
+}
+#endif
+static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf)
+{
+        int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map));
+        struct pci_dev *dev = NULL;
+        ssize_t ret = 0;
+        int i;
+        if (!this_leaf->can_disable)
+                return sprintf(buf, "Feature not enabled\n");
+        dev = get_k8_northbridge(node);
+        if (!dev) {
+                printk(KERN_ERR "Attempting AMD northbridge operation on a system with no northbridge\n");
+                return -EINVAL;
+        }
+        for (i = 0; i < 2; i++) {
+                unsigned int reg;
+                pci_read_config_dword(dev, 0x1BC + i * 4, &reg);
+                ret += sprintf(buf, "%sEntry: %d\n", buf, i);
+                ret += sprintf(buf, "%sReads:  %s\tNew Entries: %s\n",  
+                        buf,
+                        reg & 0x80000000 ? "Disabled" : "Allowed",
+                        reg & 0x40000000 ? "Disabled" : "Allowed");
+                ret += sprintf(buf, "%sSubCache: %x\tIndex: %x\n",
+                        buf, (reg & 0x30000) >> 16, reg & 0xfff);
+        }
+        return ret;
+}
+static ssize_t
+store_cache_disable(struct _cpuid4_info *this_leaf, const char *buf,
+                    size_t count)
+{
+        int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map));
+        struct pci_dev *dev = NULL;
+        unsigned int ret, index, val;
+        if (!this_leaf->can_disable)
+                return 0;
+        if (strlen(buf) > 15)
+                return -EINVAL;
+        ret = sscanf(buf, "%x %x", &index, &val);
+        if (ret != 2)
+                return -EINVAL;
+        if (index > 1)
+                return -EINVAL;
+        val |= 0xc0000000;
+        dev = get_k8_northbridge(node);
+        if (!dev) {
+                printk(KERN_ERR "Attempting AMD northbridge operation on a system with no northbridge\n");
+                return -EINVAL;
+        }
+        pci_write_config_dword(dev, 0x1BC + index * 4, val & ~0x40000000);
+        wbinvd();
+        pci_write_config_dword(dev, 0x1BC + index * 4, val);
+        return 1;
+}
 struct _cache_attr {
        struct attribute attr;
        ssize_t (*show)(struct _cpuid4_info *, char *);
@@ -657,6 +774,8 @@ define_one_ro(size);
 define_one_ro(shared_cpu_map);
 define_one_ro(shared_cpu_list);
+static struct _cache_attr cache_disable = __ATTR(cache_disable, 0644, show_cache_disable, store_cache_disable);
 static struct attribute * default_attrs[] = {
        &type.attr,
        &level.attr,
@@ -667,12 +786,10 @@ static struct attribute * default_attrs[] = {
        &size.attr,
        &shared_cpu_map.attr,
        &shared_cpu_list.attr,
+        &cache_disable.attr,
        NULL
 };
-#define to_object(k) container_of(k, struct _index_kobject, kobj)
-#define to_attr(a) container_of(a, struct _cache_attr, attr)
 static ssize_t show(struct kobject * kobj, struct attribute * attr, char * buf)
 {
        struct _cache_attr *fattr = to_attr(attr);
@@ -682,14 +799,22 @@ static ssize_t show(struct kobject * kobj, struct attribute * attr, char * buf)
        ret = fattr->show ?
                fattr->show(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index),
                        buf) :
-                0;
+                0;
        return ret;
 }
 static ssize_t store(struct kobject * kobj, struct attribute * attr,
                     const char * buf, size_t count)
 {
-        return 0;
+        struct _cache_attr *fattr = to_attr(attr);
+        struct _index_kobject *this_leaf = to_object(kobj);
+        ssize_t ret;
+        ret = fattr->store ?
+                fattr->store(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index),
+                        buf, count) :
+                0;
+        return ret;
 }
 static struct sysfs_ops sysfs_ops = {
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 726a5fcdf341..4b031a4ac856 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -860,7 +860,7 @@ error:
        return err;
 }
-static void mce_remove_device(unsigned int cpu)
+static __cpuinit void mce_remove_device(unsigned int cpu)
 {
        int i;
diff --git a/arch/x86/kernel/cpu/mkcapflags.pl b/arch/x86/kernel/cpu/mkcapflags.pl
new file mode 100644
index 000000000000..dfea390e1608
--- /dev/null
+++ b/arch/x86/kernel/cpu/mkcapflags.pl
@@ -0,0 +1,32 @@
+#!/usr/bin/perl
+#
+# Generate the x86_cap_flags[] array from include/asm-x86/cpufeature.h
+#
+($in, $out) = @ARGV;
+open(IN, "< $in\0")   or die "$0: cannot open: $in: $!\n";
+open(OUT, "> $out\0") or die "$0: cannot create: $out: $!\n";
+print OUT "#include <asm/cpufeature.h>\n\n";
+print OUT "const char * const x86_cap_flags[NCAPINTS*32] = {\n";
+while (defined($line = <IN>)) {
+        if ($line =~ /^\s*\#\s*define\s+(X86_FEATURE_(\S+))\s+(.*)$/) {
+                $macro = $1;
+                $feature = $2;
+                $tail = $3;
+                if ($tail =~ /\/\*\s*\"([^"]*)\".*\*\//) {
+                        $feature = $1;
+                }
+                if ($feature ne '') {
+                        printf OUT "\t%-32s = \"%s\",\n",
+                                "[$macro]", "\L$feature";
+                }
+        }
+}
+print OUT "};\n";
+close(IN);
+close(OUT);
diff --git a/arch/x86/kernel/cpu/powerflags.c b/arch/x86/kernel/cpu/powerflags.c
new file mode 100644
index 000000000000..5abbea297e0c
--- /dev/null
+++ b/arch/x86/kernel/cpu/powerflags.c
@@ -0,0 +1,20 @@
+/*
+ * Strings for the various x86 power flags
+ *
+ * This file must not contain any executable code.
+ */
+#include <asm/cpufeature.h>
+const char *const x86_power_flags[32] = {
+        "ts",   /* temperature sensor */
+        "fid",  /* frequency id control */
+        "vid",  /* voltage id control */
+        "ttp",  /* thermal trip */
+        "tm",
+        "stc",
+        "100mhzsteps",
+        "hwpstate",
+        "",     /* tsc invariant mapped to constant_tsc */
+                /* nothing */
+};
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index b911a2c61b8f..52b3fefbd5af 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -5,6 +5,18 @@
 #include <asm/msr.h>
 #include "cpu.h"
+static void __cpuinit early_init_transmeta(struct cpuinfo_x86 *c)
+{
+        u32 xlvl;
+        /* Transmeta-defined flags: level 0x80860001 */
+        xlvl = cpuid_eax(0x80860000);
+        if ((xlvl & 0xffff0000) == 0x80860000) {
+                if (xlvl >= 0x80860001)
+                        c->x86_capability[2] = cpuid_edx(0x80860001);
+        }
+}
 static void __cpuinit init_transmeta(struct cpuinfo_x86 *c)
 {
        unsigned int cap_mask, uk, max, dummy;
@@ -12,7 +24,8 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c)
        unsigned int cpu_rev, cpu_freq = 0, cpu_flags, new_cpu_rev;
        char cpu_info[65];
-        get_model_name(c);      /* Same as AMD/Cyrix */
+        early_init_transmeta(c);
        display_cacheinfo(c);
        /* Print CMS and CPU revision */
@@ -85,23 +98,12 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c)
 #endif
 }
-static void __cpuinit transmeta_identify(struct cpuinfo_x86 *c)
-{
-        u32 xlvl;
-        /* Transmeta-defined flags: level 0x80860001 */
-        xlvl = cpuid_eax(0x80860000);
-        if ((xlvl & 0xffff0000) == 0x80860000) {
-                if (xlvl >= 0x80860001)
-                        c->x86_capability[2] = cpuid_edx(0x80860001);
-        }
-}
 static struct cpu_dev transmeta_cpu_dev __cpuinitdata = {
        .c_vendor       = "Transmeta",
        .c_ident        = { "GenuineTMx86", "TransmetaCPU" },
+        .c_early_init   = early_init_transmeta,
        .c_init         = init_transmeta,
-        .c_identify     = transmeta_identify,
+        .c_x86_vendor   = X86_VENDOR_TRANSMETA,
 };
-cpu_vendor_dev_register(X86_VENDOR_TRANSMETA, &transmeta_cpu_dev);
+cpu_dev_register(transmeta_cpu_dev);
diff --git a/arch/x86/kernel/cpu/umc.c b/arch/x86/kernel/cpu/umc.c
index b1fc90989d75..e777f79e0960 100644
--- a/arch/x86/kernel/cpu/umc.c
+++ b/arch/x86/kernel/cpu/umc.c
@@ -19,7 +19,8 @@ static struct cpu_dev umc_cpu_dev __cpuinitdata = {
                  }
                },
        },
+        .c_x86_vendor   = X86_VENDOR_UMC,
 };
-cpu_vendor_dev_register(X86_VENDOR_UMC, &umc_cpu_dev);
+cpu_dev_register(umc_cpu_dev);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 66e48aa2dd1b..78e642feac30 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -148,6 +148,9 @@ void __init e820_print_map(char *who)
                case E820_NVS:
                        printk(KERN_CONT "(ACPI NVS)\n");
                        break;
+                case E820_UNUSABLE:
+                        printk("(unusable)\n");
+                        break;
                default:
                        printk(KERN_CONT "type %u\n", e820.map[i].type);
                        break;
@@ -1260,6 +1263,7 @@ static inline const char *e820_type_to_string(int e820_type)
        case E820_RAM:  return "System RAM";
        case E820_ACPI: return "ACPI Tables";
        case E820_NVS:  return "ACPI Non-volatile Storage";
+        case E820_UNUSABLE:     return "Unusable memory";
        default:        return "reserved";
        }
 }
@@ -1267,6 +1271,7 @@ static inline const char *e820_type_to_string(int e820_type)
 /*
 * Mark e820 reserved areas as busy for the resource manager.
 */
+static struct resource __initdata *e820_res;
 void __init e820_reserve_resources(void)
 {
        int i;
@@ -1274,6 +1279,7 @@ void __init e820_reserve_resources(void)
        u64 end;
        res = alloc_bootmem_low(sizeof(struct resource) * e820.nr_map);
+        e820_res = res;
        for (i = 0; i < e820.nr_map; i++) {
                end = e820.map[i].addr + e820.map[i].size - 1;
 #ifndef CONFIG_RESOURCES_64BIT
@@ -1287,7 +1293,14 @@ void __init e820_reserve_resources(void)
                res->end = end;
                res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
-                insert_resource(&iomem_resource, res);
+                /*
+                 * don't register the region that could be conflicted with
+                 * pci device BAR resource and insert them later in
+                 * pcibios_resource_survey()
+                 */
+                if (e820.map[i].type != E820_RESERVED || res->start < (1ULL<<20))
+                        insert_resource(&iomem_resource, res);
                res++;
        }
@@ -1299,6 +1312,19 @@ void __init e820_reserve_resources(void)
        }
 }
+void __init e820_reserve_resources_late(void)
+{
+        int i;
+        struct resource *res;
+        res = e820_res;
+        for (i = 0; i < e820.nr_map; i++) {
+                if (!res->parent && res->end)
+                        reserve_region_with_split(&iomem_resource, res->start, res->end, res->name);
+                res++;
+        }
+}
 char *__init default_machine_specific_memory_setup(void)
 {
        char *who = "BIOS-e820";
diff --git a/arch/x86/mach-es7000/es7000plat.c b/arch/x86/kernel/es7000_32.c
index 50189af14b85..849e5cd485b8 100644
--- a/arch/x86/mach-es7000/es7000plat.c
+++ b/arch/x86/kernel/es7000_32.c
@@ -39,10 +39,93 @@
 #include <asm/nmi.h>
 #include <asm/smp.h>
 #include <asm/apicdef.h>
-#include "es7000.h"
 #include <mach_mpparse.h>
 /*
+ * ES7000 chipsets
+ */
+#define NON_UNISYS              0
+#define ES7000_CLASSIC          1
+#define ES7000_ZORRO            2
+#define MIP_REG                 1
+#define MIP_PSAI_REG            4
+#define MIP_BUSY                1
+#define MIP_SPIN                0xf0000
+#define MIP_VALID               0x0100000000000000ULL
+#define MIP_PORT(VALUE) ((VALUE >> 32) & 0xffff)
+#define MIP_RD_LO(VALUE)        (VALUE & 0xffffffff)
+struct mip_reg_info {
+        unsigned long long mip_info;
+        unsigned long long delivery_info;
+        unsigned long long host_reg;
+        unsigned long long mip_reg;
+};
+struct part_info {
+        unsigned char type;
+        unsigned char length;
+        unsigned char part_id;
+        unsigned char apic_mode;
+        unsigned long snum;
+        char ptype[16];
+        char sname[64];
+        char pname[64];
+};
+struct psai {
+        unsigned long long entry_type;
+        unsigned long long addr;
+        unsigned long long bep_addr;
+};
+struct es7000_mem_info {
+        unsigned char type;
+        unsigned char length;
+        unsigned char resv[6];
+        unsigned long long  start;
+        unsigned long long  size;
+};
+struct es7000_oem_table {
+        unsigned long long hdr;
+        struct mip_reg_info mip;
+        struct part_info pif;
+        struct es7000_mem_info shm;
+        struct psai psai;
+};
+#ifdef CONFIG_ACPI
+struct oem_table {
+        struct acpi_table_header Header;
+        u32 OEMTableAddr;
+        u32 OEMTableSize;
+};
+extern int find_unisys_acpi_oem_table(unsigned long *oem_addr);
+#endif
+struct mip_reg {
+        unsigned long long off_0;
+        unsigned long long off_8;
+        unsigned long long off_10;
+        unsigned long long off_18;
+        unsigned long long off_20;
+        unsigned long long off_28;
+        unsigned long long off_30;
+        unsigned long long off_38;
+};
+#define MIP_SW_APIC             0x1020b
+#define MIP_FUNC(VALUE)         (VALUE & 0xff)
+/*
 * ES7000 Globals
 */
@@ -72,7 +155,7 @@ es7000_rename_gsi(int ioapic, int gsi)
                        base += nr_ioapic_registers[i];
        }
-        if (!ioapic && (gsi < 16)) 
+        if (!ioapic && (gsi < 16))
                gsi += base;
        return gsi;
 }
diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c
index eaff0bbb1444..6c9bfc9e1e95 100644
--- a/arch/x86/kernel/genapic_64.c
+++ b/arch/x86/kernel/genapic_64.c
@@ -16,87 +16,63 @@
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/hardirq.h>
+#include <linux/dmar.h>
 #include <asm/smp.h>
 #include <asm/ipi.h>
 #include <asm/genapic.h>
-#ifdef CONFIG_ACPI
+extern struct genapic apic_flat;
-#include <acpi/acpi_bus.h>
+extern struct genapic apic_physflat;
-#endif
+extern struct genapic apic_x2xpic_uv_x;
+extern struct genapic apic_x2apic_phys;
-DEFINE_PER_CPU(int, x2apic_extra_bits);
+extern struct genapic apic_x2apic_cluster;
 struct genapic __read_mostly *genapic = &apic_flat;
-static enum uv_system_type uv_system_type;
+static struct genapic *apic_probe[] __initdata = {
+        &apic_x2apic_uv_x,
+        &apic_x2apic_phys,
+        &apic_x2apic_cluster,
+        &apic_physflat,
+        NULL,
+};
 /*
 * Check the APIC IDs in bios_cpu_apicid and choose the APIC mode.
 */
 void __init setup_apic_routing(void)
 {
-        if (uv_system_type == UV_NON_UNIQUE_APIC)
+        if (genapic == &apic_x2apic_phys || genapic == &apic_x2apic_cluster) {
-                genapic = &apic_x2apic_uv_x;
+                if (!intr_remapping_enabled)
-        else
+                        genapic = &apic_flat;
-#ifdef CONFIG_ACPI
+        }
-        /*
-         * Quirk: some x86_64 machines can only use physical APIC mode
-         * regardless of how many processors are present (x86_64 ES7000
-         * is an example).
-         */
-        if (acpi_gbl_FADT.header.revision > FADT2_REVISION_ID &&
-                        (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL))
-                genapic = &apic_physflat;
-        else
-#endif
-        if (max_physical_apicid < 8)
-                genapic = &apic_flat;
-        else
-                genapic = &apic_physflat;
-        printk(KERN_INFO "Setting APIC routing to %s\n", genapic->name);
+        if (genapic == &apic_flat) {
+                if (max_physical_apicid >= 8)
+                        genapic = &apic_physflat;
+                printk(KERN_INFO "Setting APIC routing to %s\n", genapic->name);
+        }
 }
 /* Same for both flat and physical. */
-void send_IPI_self(int vector)
+void apic_send_IPI_self(int vector)
 {
        __send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL);
 }
 int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
-        if (!strcmp(oem_id, "SGI")) {
+        int i;
-                if (!strcmp(oem_table_id, "UVL"))
-                        uv_system_type = UV_LEGACY_APIC;
+        for (i = 0; apic_probe[i]; ++i) {
-                else if (!strcmp(oem_table_id, "UVX"))
+                if (apic_probe[i]->acpi_madt_oem_check(oem_id, oem_table_id)) {
-                        uv_system_type = UV_X2APIC;
+                        genapic = apic_probe[i];
-                else if (!strcmp(oem_table_id, "UVH"))
+                        printk(KERN_INFO "Setting APIC routing to %s.\n",
-                        uv_system_type = UV_NON_UNIQUE_APIC;
+                                genapic->name);
+                        return 1;
+                }
        }
        return 0;
 }
-unsigned int read_apic_id(void)
-{
-        unsigned int id;
-        WARN_ON(preemptible() && num_online_cpus() > 1);
-        id = apic_read(APIC_ID);
-        if (uv_system_type >= UV_X2APIC)
-                id  |= __get_cpu_var(x2apic_extra_bits);
-        return id;
-}
-enum uv_system_type get_uv_system_type(void)
-{
-        return uv_system_type;
-}
-int is_uv_system(void)
-{
-        return uv_system_type != UV_NONE;
-}
-EXPORT_SYMBOL_GPL(is_uv_system);
diff --git a/arch/x86/kernel/genapic_flat_64.c b/arch/x86/kernel/genapic_flat_64.c
index 786548a62d38..9eca5ba7a6b1 100644
--- a/arch/x86/kernel/genapic_flat_64.c
+++ b/arch/x86/kernel/genapic_flat_64.c
@@ -15,9 +15,20 @@
 #include <linux/kernel.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
+#include <linux/hardirq.h>
 #include <asm/smp.h>
 #include <asm/ipi.h>
 #include <asm/genapic.h>
+#include <mach_apicdef.h>
+#ifdef CONFIG_ACPI
+#include <acpi/acpi_bus.h>
+#endif
+static int __init flat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+        return 1;
+}
 static cpumask_t flat_target_cpus(void)
 {
@@ -95,9 +106,33 @@ static void flat_send_IPI_all(int vector)
                __send_IPI_shortcut(APIC_DEST_ALLINC, vector, APIC_DEST_LOGICAL);
 }
+static unsigned int get_apic_id(unsigned long x)
+{
+        unsigned int id;
+        id = (((x)>>24) & 0xFFu);
+        return id;
+}
+static unsigned long set_apic_id(unsigned int id)
+{
+        unsigned long x;
+        x = ((id & 0xFFu)<<24);
+        return x;
+}
+static unsigned int read_xapic_id(void)
+{
+        unsigned int id;
+        id = get_apic_id(apic_read(APIC_ID));
+        return id;
+}
 static int flat_apic_id_registered(void)
 {
-        return physid_isset(GET_APIC_ID(read_apic_id()), phys_cpu_present_map);
+        return physid_isset(read_xapic_id(), phys_cpu_present_map);
 }
 static unsigned int flat_cpu_mask_to_apicid(cpumask_t cpumask)
@@ -112,6 +147,7 @@ static unsigned int phys_pkg_id(int index_msb)
 struct genapic apic_flat =  {
        .name = "flat",
+        .acpi_madt_oem_check = flat_acpi_madt_oem_check,
        .int_delivery_mode = dest_LowestPrio,
        .int_dest_mode = (APIC_DEST_LOGICAL != 0),
        .target_cpus = flat_target_cpus,
@@ -121,8 +157,12 @@ struct genapic apic_flat =  {
        .send_IPI_all = flat_send_IPI_all,
        .send_IPI_allbutself = flat_send_IPI_allbutself,
        .send_IPI_mask = flat_send_IPI_mask,
+        .send_IPI_self = apic_send_IPI_self,
        .cpu_mask_to_apicid = flat_cpu_mask_to_apicid,
        .phys_pkg_id = phys_pkg_id,
+        .get_apic_id = get_apic_id,
+        .set_apic_id = set_apic_id,
+        .apic_id_mask = (0xFFu<<24),
 };
 /*
@@ -130,6 +170,21 @@ struct genapic apic_flat =  {
 * We cannot use logical delivery in this case because the mask
 * overflows, so use physical mode.
 */
+static int __init physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+#ifdef CONFIG_ACPI
+        /*
+         * Quirk: some x86_64 machines can only use physical APIC mode
+         * regardless of how many processors are present (x86_64 ES7000
+         * is an example).
+         */
+        if (acpi_gbl_FADT.header.revision > FADT2_REVISION_ID &&
+                (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL))
+                return 1;
+#endif
+        return 0;
+}
 static cpumask_t physflat_target_cpus(void)
 {
@@ -176,6 +231,7 @@ static unsigned int physflat_cpu_mask_to_apicid(cpumask_t cpumask)
 struct genapic apic_physflat =  {
        .name = "physical flat",
+        .acpi_madt_oem_check = physflat_acpi_madt_oem_check,
        .int_delivery_mode = dest_Fixed,
        .int_dest_mode = (APIC_DEST_PHYSICAL != 0),
        .target_cpus = physflat_target_cpus,
@@ -185,6 +241,10 @@ struct genapic apic_physflat =  {
        .send_IPI_all = physflat_send_IPI_all,
        .send_IPI_allbutself = physflat_send_IPI_allbutself,
        .send_IPI_mask = physflat_send_IPI_mask,
+        .send_IPI_self = apic_send_IPI_self,
        .cpu_mask_to_apicid = physflat_cpu_mask_to_apicid,
        .phys_pkg_id = phys_pkg_id,
+        .get_apic_id = get_apic_id,
+        .set_apic_id = set_apic_id,
+        .apic_id_mask = (0xFFu<<24),
 };
diff --git a/arch/x86/kernel/genx2apic_cluster.c b/arch/x86/kernel/genx2apic_cluster.c
new file mode 100644
index 000000000000..e4bf2cc0d743
--- /dev/null
+++ b/arch/x86/kernel/genx2apic_cluster.c
@@ -0,0 +1,159 @@
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/dmar.h>
+#include <asm/smp.h>
+#include <asm/ipi.h>
+#include <asm/genapic.h>
+DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
+static int __init x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+        if (cpu_has_x2apic)
+                return 1;
+        return 0;
+}
+/* Start with all IRQs pointing to boot CPU.  IRQ balancing will shift them. */
+static cpumask_t x2apic_target_cpus(void)
+{
+        return cpumask_of_cpu(0);
+}
+/*
+ * for now each logical cpu is in its own vector allocation domain.
+ */
+static cpumask_t x2apic_vector_allocation_domain(int cpu)
+{
+        cpumask_t domain = CPU_MASK_NONE;
+        cpu_set(cpu, domain);
+        return domain;
+}
+static void __x2apic_send_IPI_dest(unsigned int apicid, int vector,
+                                   unsigned int dest)
+{
+        unsigned long cfg;
+        cfg = __prepare_ICR(0, vector, dest);
+        /*
+         * send the IPI.
+         */
+        x2apic_icr_write(cfg, apicid);
+}
+/*
+ * for now, we send the IPI's one by one in the cpumask.
+ * TBD: Based on the cpu mask, we can send the IPI's to the cluster group
+ * at once. We have 16 cpu's in a cluster. This will minimize IPI register
+ * writes.
+ */
+static void x2apic_send_IPI_mask(cpumask_t mask, int vector)
+{
+        unsigned long flags;
+        unsigned long query_cpu;
+        local_irq_save(flags);
+        for_each_cpu_mask(query_cpu, mask) {
+                __x2apic_send_IPI_dest(per_cpu(x86_cpu_to_logical_apicid, query_cpu),
+                                       vector, APIC_DEST_LOGICAL);
+        }
+        local_irq_restore(flags);
+}
+static void x2apic_send_IPI_allbutself(int vector)
+{
+        cpumask_t mask = cpu_online_map;
+        cpu_clear(smp_processor_id(), mask);
+        if (!cpus_empty(mask))
+                x2apic_send_IPI_mask(mask, vector);
+}
+static void x2apic_send_IPI_all(int vector)
+{
+        x2apic_send_IPI_mask(cpu_online_map, vector);
+}
+static int x2apic_apic_id_registered(void)
+{
+        return 1;
+}
+static unsigned int x2apic_cpu_mask_to_apicid(cpumask_t cpumask)
+{
+        int cpu;
+        /*
+         * We're using fixed IRQ delivery, can only return one phys APIC ID.
+         * May as well be the first.
+         */
+        cpu = first_cpu(cpumask);
+        if ((unsigned)cpu < NR_CPUS)
+                return per_cpu(x86_cpu_to_logical_apicid, cpu);
+        else
+                return BAD_APICID;
+}
+static unsigned int get_apic_id(unsigned long x)
+{
+        unsigned int id;
+        id = x;
+        return id;
+}
+static unsigned long set_apic_id(unsigned int id)
+{
+        unsigned long x;
+        x = id;
+        return x;
+}
+static unsigned int phys_pkg_id(int index_msb)
+{
+        return current_cpu_data.initial_apicid >> index_msb;
+}
+static void x2apic_send_IPI_self(int vector)
+{
+        apic_write(APIC_SELF_IPI, vector);
+}
+static void init_x2apic_ldr(void)
+{
+        int cpu = smp_processor_id();
+        per_cpu(x86_cpu_to_logical_apicid, cpu) = apic_read(APIC_LDR);
+        return;
+}
+struct genapic apic_x2apic_cluster = {
+        .name = "cluster x2apic",
+        .acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
+        .int_delivery_mode = dest_LowestPrio,
+        .int_dest_mode = (APIC_DEST_LOGICAL != 0),
+        .target_cpus = x2apic_target_cpus,
+        .vector_allocation_domain = x2apic_vector_allocation_domain,
+        .apic_id_registered = x2apic_apic_id_registered,
+        .init_apic_ldr = init_x2apic_ldr,
+        .send_IPI_all = x2apic_send_IPI_all,
+        .send_IPI_allbutself = x2apic_send_IPI_allbutself,
+        .send_IPI_mask = x2apic_send_IPI_mask,
+        .send_IPI_self = x2apic_send_IPI_self,
+        .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid,
+        .phys_pkg_id = phys_pkg_id,
+        .get_apic_id = get_apic_id,
+        .set_apic_id = set_apic_id,
+        .apic_id_mask = (0xFFFFFFFFu),
+};
diff --git a/arch/x86/kernel/genx2apic_phys.c b/arch/x86/kernel/genx2apic_phys.c
new file mode 100644
index 000000000000..8f1343df2627
--- /dev/null
+++ b/arch/x86/kernel/genx2apic_phys.c
@@ -0,0 +1,154 @@
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/dmar.h>
+#include <asm/smp.h>
+#include <asm/ipi.h>
+#include <asm/genapic.h>
+static int x2apic_phys;
+static int set_x2apic_phys_mode(char *arg)
+{
+        x2apic_phys = 1;
+        return 0;
+}
+early_param("x2apic_phys", set_x2apic_phys_mode);
+static int __init x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+        if (cpu_has_x2apic && x2apic_phys)
+                return 1;
+        return 0;
+}
+/* Start with all IRQs pointing to boot CPU.  IRQ balancing will shift them. */
+static cpumask_t x2apic_target_cpus(void)
+{
+        return cpumask_of_cpu(0);
+}
+static cpumask_t x2apic_vector_allocation_domain(int cpu)
+{
+        cpumask_t domain = CPU_MASK_NONE;
+        cpu_set(cpu, domain);
+        return domain;
+}
+static void __x2apic_send_IPI_dest(unsigned int apicid, int vector,
+                                   unsigned int dest)
+{
+        unsigned long cfg;
+        cfg = __prepare_ICR(0, vector, dest);
+        /*
+         * send the IPI.
+         */
+        x2apic_icr_write(cfg, apicid);
+}
+static void x2apic_send_IPI_mask(cpumask_t mask, int vector)
+{
+        unsigned long flags;
+        unsigned long query_cpu;
+        local_irq_save(flags);
+        for_each_cpu_mask(query_cpu, mask) {
+                __x2apic_send_IPI_dest(per_cpu(x86_cpu_to_apicid, query_cpu),
+                                       vector, APIC_DEST_PHYSICAL);
+        }
+        local_irq_restore(flags);
+}
+static void x2apic_send_IPI_allbutself(int vector)
+{
+        cpumask_t mask = cpu_online_map;
+        cpu_clear(smp_processor_id(), mask);
+        if (!cpus_empty(mask))
+                x2apic_send_IPI_mask(mask, vector);
+}
+static void x2apic_send_IPI_all(int vector)
+{
+        x2apic_send_IPI_mask(cpu_online_map, vector);
+}
+static int x2apic_apic_id_registered(void)
+{
+        return 1;
+}
+static unsigned int x2apic_cpu_mask_to_apicid(cpumask_t cpumask)
+{
+        int cpu;
+        /*
+         * We're using fixed IRQ delivery, can only return one phys APIC ID.
+         * May as well be the first.
+         */
+        cpu = first_cpu(cpumask);
+        if ((unsigned)cpu < NR_CPUS)
+                return per_cpu(x86_cpu_to_apicid, cpu);
+        else
+                return BAD_APICID;
+}
+static unsigned int get_apic_id(unsigned long x)
+{
+        unsigned int id;
+        id = x;
+        return id;
+}
+static unsigned long set_apic_id(unsigned int id)
+{
+        unsigned long x;
+        x = id;
+        return x;
+}
+static unsigned int phys_pkg_id(int index_msb)
+{
+        return current_cpu_data.initial_apicid >> index_msb;
+}
+void x2apic_send_IPI_self(int vector)
+{
+        apic_write(APIC_SELF_IPI, vector);
+}
+void init_x2apic_ldr(void)
+{
+        return;
+}
+struct genapic apic_x2apic_phys = {
+        .name = "physical x2apic",
+        .acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
+        .int_delivery_mode = dest_Fixed,
+        .int_dest_mode = (APIC_DEST_PHYSICAL != 0),
+        .target_cpus = x2apic_target_cpus,
+        .vector_allocation_domain = x2apic_vector_allocation_domain,
+        .apic_id_registered = x2apic_apic_id_registered,
+        .init_apic_ldr = init_x2apic_ldr,
+        .send_IPI_all = x2apic_send_IPI_all,
+        .send_IPI_allbutself = x2apic_send_IPI_allbutself,
+        .send_IPI_mask = x2apic_send_IPI_mask,
+        .send_IPI_self = x2apic_send_IPI_self,
+        .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid,
+        .phys_pkg_id = phys_pkg_id,
+        .get_apic_id = get_apic_id,
+        .set_apic_id = set_apic_id,
+        .apic_id_mask = (0xFFFFFFFFu),
+};
diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c
index bfa837cb16be..ae2ffc8a400c 100644
--- a/arch/x86/kernel/genx2apic_uv_x.c
+++ b/arch/x86/kernel/genx2apic_uv_x.c
@@ -12,12 +12,12 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/string.h>
-#include <linux/kernel.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/bootmem.h>
 #include <linux/module.h>
+#include <linux/hardirq.h>
 #include <asm/smp.h>
 #include <asm/ipi.h>
 #include <asm/genapic.h>
@@ -26,6 +26,36 @@
 #include <asm/uv/uv_hub.h>
 #include <asm/uv/bios.h>
+DEFINE_PER_CPU(int, x2apic_extra_bits);
+static enum uv_system_type uv_system_type;
+static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+        if (!strcmp(oem_id, "SGI")) {
+                if (!strcmp(oem_table_id, "UVL"))
+                        uv_system_type = UV_LEGACY_APIC;
+                else if (!strcmp(oem_table_id, "UVX"))
+                        uv_system_type = UV_X2APIC;
+                else if (!strcmp(oem_table_id, "UVH")) {
+                        uv_system_type = UV_NON_UNIQUE_APIC;
+                        return 1;
+                }
+        }
+        return 0;
+}
+enum uv_system_type get_uv_system_type(void)
+{
+        return uv_system_type;
+}
+int is_uv_system(void)
+{
+        return uv_system_type != UV_NONE;
+}
+EXPORT_SYMBOL_GPL(is_uv_system);
 DEFINE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 EXPORT_PER_CPU_SYMBOL_GPL(__uv_hub_info);
@@ -123,6 +153,10 @@ static int uv_apic_id_registered(void)
        return 1;
 }
+static void uv_init_apic_ldr(void)
+{
+}
 static unsigned int uv_cpu_mask_to_apicid(cpumask_t cpumask)
 {
        int cpu;
@@ -138,9 +172,34 @@ static unsigned int uv_cpu_mask_to_apicid(cpumask_t cpumask)
                return BAD_APICID;
 }
+static unsigned int get_apic_id(unsigned long x)
+{
+        unsigned int id;
+        WARN_ON(preemptible() && num_online_cpus() > 1);
+        id = x | __get_cpu_var(x2apic_extra_bits);
+        return id;
+}
+static unsigned long set_apic_id(unsigned int id)
+{
+        unsigned long x;
+        /* maskout x2apic_extra_bits ? */
+        x = id;
+        return x;
+}
+static unsigned int uv_read_apic_id(void)
+{
+        return get_apic_id(apic_read(APIC_ID));
+}
 static unsigned int phys_pkg_id(int index_msb)
 {
-        return GET_APIC_ID(read_apic_id()) >> index_msb;
+        return uv_read_apic_id() >> index_msb;
 }
 #ifdef ZZZ              /* Needs x2apic patch */
@@ -152,17 +211,22 @@ static void uv_send_IPI_self(int vector)
 struct genapic apic_x2apic_uv_x = {
        .name = "UV large system",
+        .acpi_madt_oem_check = uv_acpi_madt_oem_check,
        .int_delivery_mode = dest_Fixed,
        .int_dest_mode = (APIC_DEST_PHYSICAL != 0),
        .target_cpus = uv_target_cpus,
        .vector_allocation_domain = uv_vector_allocation_domain,/* Fixme ZZZ */
        .apic_id_registered = uv_apic_id_registered,
+        .init_apic_ldr = uv_init_apic_ldr,
        .send_IPI_all = uv_send_IPI_all,
        .send_IPI_allbutself = uv_send_IPI_allbutself,
        .send_IPI_mask = uv_send_IPI_mask,
        /* ZZZ.send_IPI_self = uv_send_IPI_self, */
        .cpu_mask_to_apicid = uv_cpu_mask_to_apicid,
        .phys_pkg_id = phys_pkg_id,     /* Fixme ZZZ */
+        .get_apic_id = get_apic_id,
+        .set_apic_id = set_apic_id,
+        .apic_id_mask = (0xFFFFFFFFu),
 };
 static __cpuinit void set_x2apic_extra_bits(int pnode)
@@ -401,3 +465,5 @@ void __cpuinit uv_cpu_init(void)
        if (get_uv_system_type() == UV_NON_UNIQUE_APIC)
                set_x2apic_extra_bits(uv_hub_info->pnode);
 }
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index eb9ddd8efb82..45723f1fe198 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -21,9 +21,12 @@
 # include <asm/sigcontext32.h>
 # include <asm/user32.h>
 #else
-# define save_i387_ia32         save_i387
+# define save_i387_xstate_ia32          save_i387_xstate
-# define restore_i387_ia32      restore_i387
+# define restore_i387_xstate_ia32       restore_i387_xstate
 # define _fpstate_ia32          _fpstate
+# define _xstate_ia32           _xstate
+# define sig_xstate_ia32_size   sig_xstate_size
+# define fx_sw_reserved_ia32    fx_sw_reserved
 # define user_i387_ia32_struct  user_i387_struct
 # define user32_fxsr_struct     user_fxsr_struct
 #endif
@@ -36,6 +39,7 @@
 static unsigned int             mxcsr_feature_mask __read_mostly = 0xffffffffu;
 unsigned int xstate_size;
+unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32);
 static struct i387_fxsave_struct fx_scratch __cpuinitdata;
 void __cpuinit mxcsr_feature_mask_init(void)
@@ -61,6 +65,11 @@ void __init init_thread_xstate(void)
                return;
        }
+        if (cpu_has_xsave) {
+                xsave_cntxt_init();
+                return;
+        }
        if (cpu_has_fxsr)
                xstate_size = sizeof(struct i387_fxsave_struct);
 #ifdef CONFIG_X86_32
@@ -83,9 +92,19 @@ void __cpuinit fpu_init(void)
        write_cr0(oldcr0 & ~(X86_CR0_TS|X86_CR0_EM)); /* clear TS and EM */
+        /*
+         * Boot processor to setup the FP and extended state context info.
+         */
+        if (!smp_processor_id())
+                init_thread_xstate();
+        xsave_init();
        mxcsr_feature_mask_init();
        /* clean state in init */
-        current_thread_info()->status = 0;
+        if (cpu_has_xsave)
+                current_thread_info()->status = TS_XSAVE;
+        else
+                current_thread_info()->status = 0;
        clear_used_math();
 }
 #endif  /* CONFIG_X86_64 */
@@ -195,6 +214,13 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
         */
        target->thread.xstate->fxsave.mxcsr &= mxcsr_feature_mask;
+        /*
+         * update the header bits in the xsave header, indicating the
+         * presence of FP and SSE state.
+         */
+        if (cpu_has_xsave)
+                target->thread.xstate->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
        return ret;
 }
@@ -395,6 +421,12 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
        if (!ret)
                convert_to_fxsr(target, &env);
+        /*
+         * update the header bit in the xsave header, indicating the
+         * presence of FP.
+         */
+        if (cpu_has_xsave)
+                target->thread.xstate->xsave.xsave_hdr.xstate_bv |= XSTATE_FP;
        return ret;
 }
@@ -407,7 +439,6 @@ static inline int save_i387_fsave(struct _fpstate_ia32 __user *buf)
        struct task_struct *tsk = current;
        struct i387_fsave_struct *fp = &tsk->thread.xstate->fsave;
-        unlazy_fpu(tsk);
        fp->status = fp->swd;
        if (__copy_to_user(buf, fp, sizeof(struct i387_fsave_struct)))
                return -1;
@@ -421,8 +452,6 @@ static int save_i387_fxsave(struct _fpstate_ia32 __user *buf)
        struct user_i387_ia32_struct env;
        int err = 0;
-        unlazy_fpu(tsk);
        convert_from_fxsr(&env, tsk);
        if (__copy_to_user(buf, &env, sizeof(env)))
                return -1;
@@ -432,16 +461,40 @@ static int save_i387_fxsave(struct _fpstate_ia32 __user *buf)
        if (err)
                return -1;
-        if (__copy_to_user(&buf->_fxsr_env[0], fx,
+        if (__copy_to_user(&buf->_fxsr_env[0], fx, xstate_size))
-                           sizeof(struct i387_fxsave_struct)))
                return -1;
        return 1;
 }
-int save_i387_ia32(struct _fpstate_ia32 __user *buf)
+static int save_i387_xsave(void __user *buf)
+{
+        struct _fpstate_ia32 __user *fx = buf;
+        int err = 0;
+        if (save_i387_fxsave(fx) < 0)
+                return -1;
+        err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved_ia32,
+                             sizeof(struct _fpx_sw_bytes));
+        err |= __put_user(FP_XSTATE_MAGIC2,
+                          (__u32 __user *) (buf + sig_xstate_ia32_size
+                                            - FP_XSTATE_MAGIC2_SIZE));
+        if (err)
+                return -1;
+        return 1;
+}
+int save_i387_xstate_ia32(void __user *buf)
 {
+        struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf;
+        struct task_struct *tsk = current;
        if (!used_math())
                return 0;
+        if (!access_ok(VERIFY_WRITE, buf, sig_xstate_ia32_size))
+                return -EACCES;
        /*
         * This will cause a "finit" to be triggered by the next
         * attempted FPU operation by the 'current' process.
@@ -451,13 +504,17 @@ int save_i387_ia32(struct _fpstate_ia32 __user *buf)
        if (!HAVE_HWFP) {
                return fpregs_soft_get(current, NULL,
                                       0, sizeof(struct user_i387_ia32_struct),
-                                       NULL, buf) ? -1 : 1;
+                                       NULL, fp) ? -1 : 1;
        }
+        unlazy_fpu(tsk);
+        if (cpu_has_xsave)
+                return save_i387_xsave(fp);
        if (cpu_has_fxsr)
-                return save_i387_fxsave(buf);
+                return save_i387_fxsave(fp);
        else
-                return save_i387_fsave(buf);
+                return save_i387_fsave(fp);
 }
 static inline int restore_i387_fsave(struct _fpstate_ia32 __user *buf)
@@ -468,14 +525,15 @@ static inline int restore_i387_fsave(struct _fpstate_ia32 __user *buf)
                                sizeof(struct i387_fsave_struct));
 }
-static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf)
+static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf,
+                               unsigned int size)
 {
        struct task_struct *tsk = current;
        struct user_i387_ia32_struct env;
        int err;
        err = __copy_from_user(&tsk->thread.xstate->fxsave, &buf->_fxsr_env[0],
-                               sizeof(struct i387_fxsave_struct));
+                               size);
        /* mxcsr reserved bits must be masked to zero for security reasons */
        tsk->thread.xstate->fxsave.mxcsr &= mxcsr_feature_mask;
        if (err || __copy_from_user(&env, buf, sizeof(env)))
@@ -485,14 +543,69 @@ static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf)
        return 0;
 }
-int restore_i387_ia32(struct _fpstate_ia32 __user *buf)
+static int restore_i387_xsave(void __user *buf)
+{
+        struct _fpx_sw_bytes fx_sw_user;
+        struct _fpstate_ia32 __user *fx_user =
+                        ((struct _fpstate_ia32 __user *) buf);
+        struct i387_fxsave_struct __user *fx =
+                (struct i387_fxsave_struct __user *) &fx_user->_fxsr_env[0];
+        struct xsave_hdr_struct *xsave_hdr =
+                                &current->thread.xstate->xsave.xsave_hdr;
+        u64 mask;
+        int err;
+        if (check_for_xstate(fx, buf, &fx_sw_user))
+                goto fx_only;
+        mask = fx_sw_user.xstate_bv;
+        err = restore_i387_fxsave(buf, fx_sw_user.xstate_size);
+        xsave_hdr->xstate_bv &= pcntxt_mask;
+        /*
+         * These bits must be zero.
+         */
+        xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
+        /*
+         * Init the state that is not present in the memory layout
+         * and enabled by the OS.
+         */
+        mask = ~(pcntxt_mask & ~mask);
+        xsave_hdr->xstate_bv &= mask;
+        return err;
+fx_only:
+        /*
+         * Couldn't find the extended state information in the memory
+         * layout. Restore the FP/SSE and init the other extended state
+         * enabled by the OS.
+         */
+        xsave_hdr->xstate_bv = XSTATE_FPSSE;
+        return restore_i387_fxsave(buf, sizeof(struct i387_fxsave_struct));
+}
+int restore_i387_xstate_ia32(void __user *buf)
 {
        int err;
        struct task_struct *tsk = current;
+        struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf;
        if (HAVE_HWFP)
                clear_fpu(tsk);
+        if (!buf) {
+                if (used_math()) {
+                        clear_fpu(tsk);
+                        clear_used_math();
+                }
+                return 0;
+        } else
+                if (!access_ok(VERIFY_READ, buf, sig_xstate_ia32_size))
+                        return -EACCES;
        if (!used_math()) {
                err = init_fpu(tsk);
                if (err)
@@ -500,14 +613,17 @@ int restore_i387_ia32(struct _fpstate_ia32 __user *buf)
        }
        if (HAVE_HWFP) {
-                if (cpu_has_fxsr)
+                if (cpu_has_xsave)
-                        err = restore_i387_fxsave(buf);
+                        err = restore_i387_xsave(buf);
+                else if (cpu_has_fxsr)
+                        err = restore_i387_fxsave(fp, sizeof(struct
+                                                           i387_fxsave_struct));
                else
-                        err = restore_i387_fsave(buf);
+                        err = restore_i387_fsave(fp);
        } else {
                err = fpregs_soft_set(current, NULL,
                                      0, sizeof(struct user_i387_ia32_struct),
-                                      NULL, buf) != 0;
+                                      NULL, fp) != 0;
        }
        set_used_math();
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index dc92b49d9204..4b8a53d841f7 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -282,6 +282,30 @@ static int __init i8259A_init_sysfs(void)
 device_initcall(i8259A_init_sysfs);
+void mask_8259A(void)
+{
+        unsigned long flags;
+        spin_lock_irqsave(&i8259A_lock, flags);
+        outb(0xff, PIC_MASTER_IMR);     /* mask all of 8259A-1 */
+        outb(0xff, PIC_SLAVE_IMR);      /* mask all of 8259A-2 */
+        spin_unlock_irqrestore(&i8259A_lock, flags);
+}
+void unmask_8259A(void)
+{
+        unsigned long flags;
+        spin_lock_irqsave(&i8259A_lock, flags);
+        outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */
+        outb(cached_slave_mask, PIC_SLAVE_IMR);   /* restore slave IRQ mask */
+        spin_unlock_irqrestore(&i8259A_lock, flags);
+}
 void init_8259A(int auto_eoi)
 {
        unsigned long flags;
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 09cddb57bec4..e710289f673e 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -46,10 +46,13 @@
 #include <asm/nmi.h>
 #include <asm/msidef.h>
 #include <asm/hypertransport.h>
+#include <asm/setup.h>
 #include <mach_apic.h>
 #include <mach_apicdef.h>
+#define __apicdebuginit(type) static type __init
 int (*ioapic_renumber_irq)(int ioapic, int irq);
 atomic_t irq_mis_count;
@@ -1341,7 +1344,8 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
        ioapic_write_entry(apic, pin, entry);
 }
-void __init print_IO_APIC(void)
+__apicdebuginit(void) print_IO_APIC(void)
 {
        int apic, i;
        union IO_APIC_reg_00 reg_00;
@@ -1456,9 +1460,7 @@ void __init print_IO_APIC(void)
        return;
 }
-#if 0
+__apicdebuginit(void) print_APIC_bitfield(int base)
-static void print_APIC_bitfield(int base)
 {
        unsigned int v;
        int i, j;
@@ -1479,9 +1481,10 @@ static void print_APIC_bitfield(int base)
        }
 }
-void /*__init*/ print_local_APIC(void *dummy)
+__apicdebuginit(void) print_local_APIC(void *dummy)
 {
        unsigned int v, ver, maxlvt;
+        u64 icr;
        if (apic_verbosity == APIC_QUIET)
                return;
@@ -1490,7 +1493,7 @@ void /*__init*/ print_local_APIC(void *dummy)
                smp_processor_id(), hard_smp_processor_id());
        v = apic_read(APIC_ID);
        printk(KERN_INFO "... APIC ID:      %08x (%01x)\n", v,
-                        GET_APIC_ID(read_apic_id()));
+                        GET_APIC_ID(v));
        v = apic_read(APIC_LVR);
        printk(KERN_INFO "... APIC VERSION: %08x\n", v);
        ver = GET_APIC_VERSION(v);
@@ -1532,10 +1535,9 @@ void /*__init*/ print_local_APIC(void *dummy)
                printk(KERN_DEBUG "... APIC ESR: %08x\n", v);
        }
-        v = apic_read(APIC_ICR);
+        icr = apic_icr_read();
-        printk(KERN_DEBUG "... APIC ICR: %08x\n", v);
+        printk(KERN_DEBUG "... APIC ICR: %08x\n", icr);
-        v = apic_read(APIC_ICR2);
+        printk(KERN_DEBUG "... APIC ICR2: %08x\n", icr >> 32);
-        printk(KERN_DEBUG "... APIC ICR2: %08x\n", v);
        v = apic_read(APIC_LVTT);
        printk(KERN_DEBUG "... APIC LVTT: %08x\n", v);
@@ -1563,12 +1565,12 @@ void /*__init*/ print_local_APIC(void *dummy)
        printk("\n");
 }
-void print_all_local_APICs(void)
+__apicdebuginit(void) print_all_local_APICs(void)
 {
        on_each_cpu(print_local_APIC, NULL, 1);
 }
-void /*__init*/ print_PIC(void)
+__apicdebuginit(void) print_PIC(void)
 {
        unsigned int v;
        unsigned long flags;
@@ -1600,7 +1602,17 @@ void /*__init*/ print_PIC(void)
        printk(KERN_DEBUG "... PIC ELCR: %04x\n", v);
 }
-#endif  /*  0  */
+__apicdebuginit(int) print_all_ICs(void)
+{
+        print_PIC();
+        print_all_local_APICs();
+        print_IO_APIC();
+        return 0;
+}
+fs_initcall(print_all_ICs);
 static void __init enable_IO_APIC(void)
 {
@@ -1698,8 +1710,7 @@ void disable_IO_APIC(void)
                entry.dest_mode       = 0; /* Physical */
                entry.delivery_mode   = dest_ExtINT; /* ExtInt */
                entry.vector          = 0;
-                entry.dest.physical.physical_dest =
+                entry.dest.physical.physical_dest = read_apic_id();
-                                        GET_APIC_ID(read_apic_id());
                /*
                 * Add it to the IO-APIC irq-routing table:
@@ -1725,10 +1736,8 @@ static void __init setup_ioapic_ids_from_mpc(void)
        unsigned char old_id;
        unsigned long flags;
-#ifdef CONFIG_X86_NUMAQ
+        if (x86_quirks->setup_ioapic_ids && x86_quirks->setup_ioapic_ids())
-        if (found_numaq)
                return;
-#endif
        /*
         * Don't check I/O APIC IDs for xAPIC systems.  They have
@@ -2329,8 +2338,6 @@ void __init setup_IO_APIC(void)
        setup_IO_APIC_irqs();
        init_IO_APIC_traps();
        check_timer();
-        if (!acpi_ioapic)
-                print_IO_APIC();
 }
 /*
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 61a83b70c18f..a1bec2969c6a 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -37,6 +37,7 @@
 #include <acpi/acpi_bus.h>
 #endif
 #include <linux/bootmem.h>
+#include <linux/dmar.h>
 #include <asm/idle.h>
 #include <asm/io.h>
@@ -49,10 +50,13 @@
 #include <asm/nmi.h>
 #include <asm/msidef.h>
 #include <asm/hypertransport.h>
+#include <asm/irq_remapping.h>
 #include <mach_ipi.h>
 #include <mach_apic.h>
+#define __apicdebuginit(type) static type __init
 struct irq_cfg {
        cpumask_t domain;
        cpumask_t old_domain;
@@ -87,8 +91,6 @@ int first_system_vector = 0xfe;
 char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE};
-#define __apicdebuginit  __init
 int sis_apic_bug; /* not actually supported, dummy for compile */
 static int no_timer_check;
@@ -108,6 +110,9 @@ static DEFINE_SPINLOCK(vector_lock);
 */
 int nr_ioapic_registers[MAX_IO_APICS];
+/* I/O APIC RTE contents at the OS boot up */
+struct IO_APIC_route_entry *early_ioapic_entries[MAX_IO_APICS];
 /* I/O APIC entries */
 struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
 int nr_ioapics;
@@ -303,7 +308,12 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
                pin = entry->pin;
                if (pin == -1)
                        break;
-                io_apic_write(apic, 0x11 + pin*2, dest);
+                /*
+                 * With interrupt-remapping, destination information comes
+                 * from interrupt-remapping table entry.
+                 */
+                if (!irq_remapped(irq))
+                        io_apic_write(apic, 0x11 + pin*2, dest);
                reg = io_apic_read(apic, 0x10 + pin*2);
                reg &= ~IO_APIC_REDIR_VECTOR_MASK;
                reg |= vector;
@@ -440,6 +450,69 @@ static void clear_IO_APIC (void)
                        clear_IO_APIC_pin(apic, pin);
 }
+/*
+ * Saves and masks all the unmasked IO-APIC RTE's
+ */
+int save_mask_IO_APIC_setup(void)
+{
+        union IO_APIC_reg_01 reg_01;
+        unsigned long flags;
+        int apic, pin;
+        /*
+         * The number of IO-APIC IRQ registers (== #pins):
+         */
+        for (apic = 0; apic < nr_ioapics; apic++) {
+                spin_lock_irqsave(&ioapic_lock, flags);
+                reg_01.raw = io_apic_read(apic, 1);
+                spin_unlock_irqrestore(&ioapic_lock, flags);
+                nr_ioapic_registers[apic] = reg_01.bits.entries+1;
+        }
+        for (apic = 0; apic < nr_ioapics; apic++) {
+                early_ioapic_entries[apic] =
+                        kzalloc(sizeof(struct IO_APIC_route_entry) *
+                                nr_ioapic_registers[apic], GFP_KERNEL);
+                if (!early_ioapic_entries[apic])
+                        return -ENOMEM;
+        }
+        for (apic = 0; apic < nr_ioapics; apic++)
+                for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+                        struct IO_APIC_route_entry entry;
+                        entry = early_ioapic_entries[apic][pin] =
+                                ioapic_read_entry(apic, pin);
+                        if (!entry.mask) {
+                                entry.mask = 1;
+                                ioapic_write_entry(apic, pin, entry);
+                        }
+                }
+        return 0;
+}
+void restore_IO_APIC_setup(void)
+{
+        int apic, pin;
+        for (apic = 0; apic < nr_ioapics; apic++)
+                for (pin = 0; pin < nr_ioapic_registers[apic]; pin++)
+                        ioapic_write_entry(apic, pin,
+                                           early_ioapic_entries[apic][pin]);
+}
+void reinit_intr_remapped_IO_APIC(int intr_remapping)
+{
+        /*
+         * for now plain restore of previous settings.
+         * TBD: In the case of OS enabling interrupt-remapping,
+         * IO-APIC RTE's need to be setup to point to interrupt-remapping
+         * table entries. for now, do a plain restore, and wait for
+         * the setup_IO_APIC_irqs() to do proper initialization.
+         */
+        restore_IO_APIC_setup();
+}
 int skip_ioapic_setup;
 int ioapic_force;
@@ -839,18 +912,98 @@ void __setup_vector_irq(int cpu)
 }
 static struct irq_chip ioapic_chip;
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip ir_ioapic_chip;
+#endif
 static void ioapic_register_intr(int irq, unsigned long trigger)
 {
-        if (trigger) {
+        if (trigger)
                irq_desc[irq].status |= IRQ_LEVEL;
-                set_irq_chip_and_handler_name(irq, &ioapic_chip,
+        else
-                                              handle_fasteoi_irq, "fasteoi");
-        } else {
                irq_desc[irq].status &= ~IRQ_LEVEL;
+#ifdef CONFIG_INTR_REMAP
+        if (irq_remapped(irq)) {
+                irq_desc[irq].status |= IRQ_MOVE_PCNTXT;
+                if (trigger)
+                        set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
+                                                      handle_fasteoi_irq,
+                                                     "fasteoi");
+                else
+                        set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
+                                                      handle_edge_irq, "edge");
+                return;
+        }
+#endif
+        if (trigger)
+                set_irq_chip_and_handler_name(irq, &ioapic_chip,
+                                              handle_fasteoi_irq,
+                                              "fasteoi");
+        else
                set_irq_chip_and_handler_name(irq, &ioapic_chip,
                                              handle_edge_irq, "edge");
+}
+static int setup_ioapic_entry(int apic, int irq,
+                              struct IO_APIC_route_entry *entry,
+                              unsigned int destination, int trigger,
+                              int polarity, int vector)
+{
+        /*
+         * add it to the IO-APIC irq-routing table:
+         */
+        memset(entry,0,sizeof(*entry));
+#ifdef CONFIG_INTR_REMAP
+        if (intr_remapping_enabled) {
+                struct intel_iommu *iommu = map_ioapic_to_ir(apic);
+                struct irte irte;
+                struct IR_IO_APIC_route_entry *ir_entry =
+                        (struct IR_IO_APIC_route_entry *) entry;
+                int index;
+                if (!iommu)
+                        panic("No mapping iommu for ioapic %d\n", apic);
+                index = alloc_irte(iommu, irq, 1);
+                if (index < 0)
+                        panic("Failed to allocate IRTE for ioapic %d\n", apic);
+                memset(&irte, 0, sizeof(irte));
+                irte.present = 1;
+                irte.dst_mode = INT_DEST_MODE;
+                irte.trigger_mode = trigger;
+                irte.dlvry_mode = INT_DELIVERY_MODE;
+                irte.vector = vector;
+                irte.dest_id = IRTE_DEST(destination);
+                modify_irte(irq, &irte);
+                ir_entry->index2 = (index >> 15) & 0x1;
+                ir_entry->zero = 0;
+                ir_entry->format = 1;
+                ir_entry->index = (index & 0x7fff);
+        } else
+#endif
+        {
+                entry->delivery_mode = INT_DELIVERY_MODE;
+                entry->dest_mode = INT_DEST_MODE;
+                entry->dest = destination;
        }
+        entry->mask = 0;                                /* enable IRQ */
+        entry->trigger = trigger;
+        entry->polarity = polarity;
+        entry->vector = vector;
+        /* Mask level triggered irqs.
+         * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
+         */
+        if (trigger)
+                entry->mask = 1;
+        return 0;
 }
 static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq,
@@ -875,24 +1028,15 @@ static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq,
                    apic, mp_ioapics[apic].mp_apicid, pin, cfg->vector,
                    irq, trigger, polarity);
-        /*
-         * add it to the IO-APIC irq-routing table:
-         */
-        memset(&entry,0,sizeof(entry));
-        entry.delivery_mode = INT_DELIVERY_MODE;
-        entry.dest_mode = INT_DEST_MODE;
-        entry.dest = cpu_mask_to_apicid(mask);
-        entry.mask = 0;                         /* enable IRQ */
-        entry.trigger = trigger;
-        entry.polarity = polarity;
-        entry.vector = cfg->vector;
-        /* Mask level triggered irqs.
+        if (setup_ioapic_entry(mp_ioapics[apic].mp_apicid, irq, &entry,
-         * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
+                               cpu_mask_to_apicid(mask), trigger, polarity,
-         */
+                               cfg->vector)) {
-        if (trigger)
+                printk("Failed to setup ioapic entry for ioapic  %d, pin %d\n",
-                entry.mask = 1;
+                       mp_ioapics[apic].mp_apicid, pin);
+                __clear_irq_vector(irq);
+                return;
+        }
        ioapic_register_intr(irq, trigger);
        if (irq < 16)
@@ -944,6 +1088,9 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
 {
        struct IO_APIC_route_entry entry;
+        if (intr_remapping_enabled)
+                return;
        memset(&entry, 0, sizeof(entry));
        /*
@@ -970,7 +1117,8 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
        ioapic_write_entry(apic, pin, entry);
 }
-void __apicdebuginit print_IO_APIC(void)
+__apicdebuginit(void) print_IO_APIC(void)
 {
        int apic, i;
        union IO_APIC_reg_00 reg_00;
@@ -1064,9 +1212,7 @@ void __apicdebuginit print_IO_APIC(void)
        return;
 }
-#if 0
+__apicdebuginit(void) print_APIC_bitfield(int base)
-static __apicdebuginit void print_APIC_bitfield (int base)
 {
        unsigned int v;
        int i, j;
@@ -1087,9 +1233,10 @@ static __apicdebuginit void print_APIC_bitfield (int base)
        }
 }
-void __apicdebuginit print_local_APIC(void * dummy)
+__apicdebuginit(void) print_local_APIC(void *dummy)
 {
        unsigned int v, ver, maxlvt;
+        unsigned long icr;
        if (apic_verbosity == APIC_QUIET)
                return;
@@ -1097,7 +1244,7 @@ void __apicdebuginit print_local_APIC(void * dummy)
        printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
                smp_processor_id(), hard_smp_processor_id());
        v = apic_read(APIC_ID);
-        printk(KERN_INFO "... APIC ID:      %08x (%01x)\n", v, GET_APIC_ID(read_apic_id()));
+        printk(KERN_INFO "... APIC ID:      %08x (%01x)\n", v, read_apic_id());
        v = apic_read(APIC_LVR);
        printk(KERN_INFO "... APIC VERSION: %08x\n", v);
        ver = GET_APIC_VERSION(v);
@@ -1133,10 +1280,9 @@ void __apicdebuginit print_local_APIC(void * dummy)
        v = apic_read(APIC_ESR);
        printk(KERN_DEBUG "... APIC ESR: %08x\n", v);
-        v = apic_read(APIC_ICR);
+        icr = apic_icr_read();
-        printk(KERN_DEBUG "... APIC ICR: %08x\n", v);
+        printk(KERN_DEBUG "... APIC ICR: %08x\n", icr);
-        v = apic_read(APIC_ICR2);
+        printk(KERN_DEBUG "... APIC ICR2: %08x\n", icr >> 32);
-        printk(KERN_DEBUG "... APIC ICR2: %08x\n", v);
        v = apic_read(APIC_LVTT);
        printk(KERN_DEBUG "... APIC LVTT: %08x\n", v);
@@ -1164,12 +1310,12 @@ void __apicdebuginit print_local_APIC(void * dummy)
        printk("\n");
 }
-void print_all_local_APICs (void)
+__apicdebuginit(void) print_all_local_APICs(void)
 {
        on_each_cpu(print_local_APIC, NULL, 1);
 }
-void __apicdebuginit print_PIC(void)
+__apicdebuginit(void) print_PIC(void)
 {
        unsigned int v;
        unsigned long flags;
@@ -1201,7 +1347,17 @@ void __apicdebuginit print_PIC(void)
        printk(KERN_DEBUG "... PIC ELCR: %04x\n", v);
 }
-#endif  /*  0  */
+__apicdebuginit(int) print_all_ICs(void)
+{
+        print_PIC();
+        print_all_local_APICs();
+        print_IO_APIC();
+        return 0;
+}
+fs_initcall(print_all_ICs);
 void __init enable_IO_APIC(void)
 {
@@ -1291,7 +1447,7 @@ void disable_IO_APIC(void)
                entry.dest_mode       = 0; /* Physical */
                entry.delivery_mode   = dest_ExtINT; /* ExtInt */
                entry.vector          = 0;
-                entry.dest          = GET_APIC_ID(read_apic_id());
+                entry.dest            = read_apic_id();
                /*
                 * Add it to the IO-APIC irq-routing table:
@@ -1397,6 +1553,147 @@ static int ioapic_retrigger_irq(unsigned int irq)
 */
 #ifdef CONFIG_SMP
+#ifdef CONFIG_INTR_REMAP
+static void ir_irq_migration(struct work_struct *work);
+static DECLARE_DELAYED_WORK(ir_migration_work, ir_irq_migration);
+/*
+ * Migrate the IO-APIC irq in the presence of intr-remapping.
+ *
+ * For edge triggered, irq migration is a simple atomic update(of vector
+ * and cpu destination) of IRTE and flush the hardware cache.
+ *
+ * For level triggered, we need to modify the io-apic RTE aswell with the update
+ * vector information, along with modifying IRTE with vector and destination.
+ * So irq migration for level triggered is little  bit more complex compared to
+ * edge triggered migration. But the good news is, we use the same algorithm
+ * for level triggered migration as we have today, only difference being,
+ * we now initiate the irq migration from process context instead of the
+ * interrupt context.
+ *
+ * In future, when we do a directed EOI (combined with cpu EOI broadcast
+ * suppression) to the IO-APIC, level triggered irq migration will also be
+ * as simple as edge triggered migration and we can do the irq migration
+ * with a simple atomic update to IO-APIC RTE.
+ */
+static void migrate_ioapic_irq(int irq, cpumask_t mask)
+{
+        struct irq_cfg *cfg = irq_cfg + irq;
+        struct irq_desc *desc = irq_desc + irq;
+        cpumask_t tmp, cleanup_mask;
+        struct irte irte;
+        int modify_ioapic_rte = desc->status & IRQ_LEVEL;
+        unsigned int dest;
+        unsigned long flags;
+        cpus_and(tmp, mask, cpu_online_map);
+        if (cpus_empty(tmp))
+                return;
+        if (get_irte(irq, &irte))
+                return;
+        if (assign_irq_vector(irq, mask))
+                return;
+        cpus_and(tmp, cfg->domain, mask);
+        dest = cpu_mask_to_apicid(tmp);
+        if (modify_ioapic_rte) {
+                spin_lock_irqsave(&ioapic_lock, flags);
+                __target_IO_APIC_irq(irq, dest, cfg->vector);
+                spin_unlock_irqrestore(&ioapic_lock, flags);
+        }
+        irte.vector = cfg->vector;
+        irte.dest_id = IRTE_DEST(dest);
+        /*
+         * Modified the IRTE and flushes the Interrupt entry cache.
+         */
+        modify_irte(irq, &irte);
+        if (cfg->move_in_progress) {
+                cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
+                cfg->move_cleanup_count = cpus_weight(cleanup_mask);
+                send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+                cfg->move_in_progress = 0;
+        }
+        irq_desc[irq].affinity = mask;
+}
+static int migrate_irq_remapped_level(int irq)
+{
+        int ret = -1;
+        mask_IO_APIC_irq(irq);
+        if (io_apic_level_ack_pending(irq)) {
+                /*
+                 * Interrupt in progress. Migrating irq now will change the
+                 * vector information in the IO-APIC RTE and that will confuse
+                 * the EOI broadcast performed by cpu.
+                 * So, delay the irq migration to the next instance.
+                 */
+                schedule_delayed_work(&ir_migration_work, 1);
+                goto unmask;
+        }
+        /* everthing is clear. we have right of way */
+        migrate_ioapic_irq(irq, irq_desc[irq].pending_mask);
+        ret = 0;
+        irq_desc[irq].status &= ~IRQ_MOVE_PENDING;
+        cpus_clear(irq_desc[irq].pending_mask);
+unmask:
+        unmask_IO_APIC_irq(irq);
+        return ret;
+}
+static void ir_irq_migration(struct work_struct *work)
+{
+        int irq;
+        for (irq = 0; irq < NR_IRQS; irq++) {
+                struct irq_desc *desc = irq_desc + irq;
+                if (desc->status & IRQ_MOVE_PENDING) {
+                        unsigned long flags;
+                        spin_lock_irqsave(&desc->lock, flags);
+                        if (!desc->chip->set_affinity ||
+                            !(desc->status & IRQ_MOVE_PENDING)) {
+                                desc->status &= ~IRQ_MOVE_PENDING;
+                                spin_unlock_irqrestore(&desc->lock, flags);
+                                continue;
+                        }
+                        desc->chip->set_affinity(irq,
+                                                 irq_desc[irq].pending_mask);
+                        spin_unlock_irqrestore(&desc->lock, flags);
+                }
+        }
+}
+/*
+ * Migrates the IRQ destination in the process context.
+ */
+static void set_ir_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
+{
+        if (irq_desc[irq].status & IRQ_LEVEL) {
+                irq_desc[irq].status |= IRQ_MOVE_PENDING;
+                irq_desc[irq].pending_mask = mask;
+                migrate_irq_remapped_level(irq);
+                return;
+        }
+        migrate_ioapic_irq(irq, mask);
+}
+#endif
 asmlinkage void smp_irq_move_cleanup_interrupt(void)
 {
        unsigned vector, me;
@@ -1453,6 +1750,17 @@ static void irq_complete_move(unsigned int irq)
 #else
 static inline void irq_complete_move(unsigned int irq) {}
 #endif
+#ifdef CONFIG_INTR_REMAP
+static void ack_x2apic_level(unsigned int irq)
+{
+        ack_x2APIC_irq();
+}
+static void ack_x2apic_edge(unsigned int irq)
+{
+        ack_x2APIC_irq();
+}
+#endif
 static void ack_apic_edge(unsigned int irq)
 {
@@ -1527,6 +1835,21 @@ static struct irq_chip ioapic_chip __read_mostly = {
        .retrigger      = ioapic_retrigger_irq,
 };
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip ir_ioapic_chip __read_mostly = {
+        .name           = "IR-IO-APIC",
+        .startup        = startup_ioapic_irq,
+        .mask           = mask_IO_APIC_irq,
+        .unmask         = unmask_IO_APIC_irq,
+        .ack            = ack_x2apic_edge,
+        .eoi            = ack_x2apic_level,
+#ifdef CONFIG_SMP
+        .set_affinity   = set_ir_ioapic_affinity_irq,
+#endif
+        .retrigger      = ioapic_retrigger_irq,
+};
+#endif
 static inline void init_IO_APIC_traps(void)
 {
        int irq;
@@ -1712,6 +2035,8 @@ static inline void __init check_timer(void)
         * 8259A.
         */
        if (pin1 == -1) {
+                if (intr_remapping_enabled)
+                        panic("BIOS bug: timer not connected to IO-APIC");
                pin1 = pin2;
                apic1 = apic2;
                no_pin1 = 1;
@@ -1738,6 +2063,8 @@ static inline void __init check_timer(void)
                                clear_IO_APIC_pin(0, pin1);
                        goto out;
                }
+                if (intr_remapping_enabled)
+                        panic("timer doesn't work through Interrupt-remapped IO-APIC");
                clear_IO_APIC_pin(apic1, pin1);
                if (!no_pin1)
                        apic_printk(APIC_QUIET, KERN_ERR "..MP-BIOS bug: "
@@ -1854,8 +2181,6 @@ void __init setup_IO_APIC(void)
        setup_IO_APIC_irqs();
        init_IO_APIC_traps();
        check_timer();
-        if (!acpi_ioapic)
-                print_IO_APIC();
 }
 struct sysfs_ioapic_data {
@@ -1977,6 +2302,9 @@ void destroy_irq(unsigned int irq)
        dynamic_irq_cleanup(irq);
+#ifdef CONFIG_INTR_REMAP
+        free_irte(irq);
+#endif
        spin_lock_irqsave(&vector_lock, flags);
        __clear_irq_vector(irq);
        spin_unlock_irqrestore(&vector_lock, flags);
@@ -1995,11 +2323,42 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
        tmp = TARGET_CPUS;
        err = assign_irq_vector(irq, tmp);
-        if (!err) {
+        if (err)
-                cpus_and(tmp, cfg->domain, tmp);
+                return err;
-                dest = cpu_mask_to_apicid(tmp);
+        cpus_and(tmp, cfg->domain, tmp);
+        dest = cpu_mask_to_apicid(tmp);
+#ifdef CONFIG_INTR_REMAP
+        if (irq_remapped(irq)) {
+                struct irte irte;
+                int ir_index;
+                u16 sub_handle;
+                ir_index = map_irq_to_irte_handle(irq, &sub_handle);
+                BUG_ON(ir_index == -1);
+                memset (&irte, 0, sizeof(irte));
+                irte.present = 1;
+                irte.dst_mode = INT_DEST_MODE;
+                irte.trigger_mode = 0; /* edge */
+                irte.dlvry_mode = INT_DELIVERY_MODE;
+                irte.vector = cfg->vector;
+                irte.dest_id = IRTE_DEST(dest);
+                modify_irte(irq, &irte);
                msg->address_hi = MSI_ADDR_BASE_HI;
+                msg->data = sub_handle;
+                msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
+                                  MSI_ADDR_IR_SHV |
+                                  MSI_ADDR_IR_INDEX1(ir_index) |
+                                  MSI_ADDR_IR_INDEX2(ir_index);
+        } else
+#endif
+        {
+                msg->address_hi = MSI_ADDR_BASE_HI;
                msg->address_lo =
                        MSI_ADDR_BASE_LO |
                        ((INT_DEST_MODE == 0) ?
@@ -2049,6 +2408,55 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
        write_msi_msg(irq, &msg);
        irq_desc[irq].affinity = mask;
 }
+#ifdef CONFIG_INTR_REMAP
+/*
+ * Migrate the MSI irq to another cpumask. This migration is
+ * done in the process context using interrupt-remapping hardware.
+ */
+static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
+{
+        struct irq_cfg *cfg = irq_cfg + irq;
+        unsigned int dest;
+        cpumask_t tmp, cleanup_mask;
+        struct irte irte;
+        cpus_and(tmp, mask, cpu_online_map);
+        if (cpus_empty(tmp))
+                return;
+        if (get_irte(irq, &irte))
+                return;
+        if (assign_irq_vector(irq, mask))
+                return;
+        cpus_and(tmp, cfg->domain, mask);
+        dest = cpu_mask_to_apicid(tmp);
+        irte.vector = cfg->vector;
+        irte.dest_id = IRTE_DEST(dest);
+        /*
+         * atomically update the IRTE with the new destination and vector.
+         */
+        modify_irte(irq, &irte);
+        /*
+         * After this point, all the interrupts will start arriving
+         * at the new destination. So, time to cleanup the previous
+         * vector allocation.
+         */
+        if (cfg->move_in_progress) {
+                cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
+                cfg->move_cleanup_count = cpus_weight(cleanup_mask);
+                send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+                cfg->move_in_progress = 0;
+        }
+        irq_desc[irq].affinity = mask;
+}
+#endif
 #endif /* CONFIG_SMP */
 /*
@@ -2066,26 +2474,157 @@ static struct irq_chip msi_chip = {
        .retrigger      = ioapic_retrigger_irq,
 };
-int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip msi_ir_chip = {
+        .name           = "IR-PCI-MSI",
+        .unmask         = unmask_msi_irq,
+        .mask           = mask_msi_irq,
+        .ack            = ack_x2apic_edge,
+#ifdef CONFIG_SMP
+        .set_affinity   = ir_set_msi_irq_affinity,
+#endif
+        .retrigger      = ioapic_retrigger_irq,
+};
+/*
+ * Map the PCI dev to the corresponding remapping hardware unit
+ * and allocate 'nvec' consecutive interrupt-remapping table entries
+ * in it.
+ */
+static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec)
 {
+        struct intel_iommu *iommu;
+        int index;
+        iommu = map_dev_to_ir(dev);
+        if (!iommu) {
+                printk(KERN_ERR
+                       "Unable to map PCI %s to iommu\n", pci_name(dev));
+                return -ENOENT;
+        }
+        index = alloc_irte(iommu, irq, nvec);
+        if (index < 0) {
+                printk(KERN_ERR
+                       "Unable to allocate %d IRTE for PCI %s\n", nvec,
+                        pci_name(dev));
+                return -ENOSPC;
+        }
+        return index;
+}
+#endif
+static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc, int irq)
+{
+        int ret;
        struct msi_msg msg;
+        ret = msi_compose_msg(dev, irq, &msg);
+        if (ret < 0)
+                return ret;
+        set_irq_msi(irq, desc);
+        write_msi_msg(irq, &msg);
+#ifdef CONFIG_INTR_REMAP
+        if (irq_remapped(irq)) {
+                struct irq_desc *desc = irq_desc + irq;
+                /*
+                 * irq migration in process context
+                 */
+                desc->status |= IRQ_MOVE_PCNTXT;
+                set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge");
+        } else
+#endif
+                set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
+        return 0;
+}
+int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
+{
        int irq, ret;
        irq = create_irq();
        if (irq < 0)
                return irq;
-        ret = msi_compose_msg(dev, irq, &msg);
+#ifdef CONFIG_INTR_REMAP
+        if (!intr_remapping_enabled)
+                goto no_ir;
+        ret = msi_alloc_irte(dev, irq, 1);
+        if (ret < 0)
+                goto error;
+no_ir:
+#endif
+        ret = setup_msi_irq(dev, desc, irq);
        if (ret < 0) {
                destroy_irq(irq);
                return ret;
        }
+        return 0;
-        set_irq_msi(irq, desc);
+#ifdef CONFIG_INTR_REMAP
-        write_msi_msg(irq, &msg);
+error:
+        destroy_irq(irq);
+        return ret;
+#endif
+}
-        set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
+int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+        int irq, ret, sub_handle;
+        struct msi_desc *desc;
+#ifdef CONFIG_INTR_REMAP
+        struct intel_iommu *iommu = 0;
+        int index = 0;
+#endif
+        sub_handle = 0;
+        list_for_each_entry(desc, &dev->msi_list, list) {
+                irq = create_irq();
+                if (irq < 0)
+                        return irq;
+#ifdef CONFIG_INTR_REMAP
+                if (!intr_remapping_enabled)
+                        goto no_ir;
+                if (!sub_handle) {
+                        /*
+                         * allocate the consecutive block of IRTE's
+                         * for 'nvec'
+                         */
+                        index = msi_alloc_irte(dev, irq, nvec);
+                        if (index < 0) {
+                                ret = index;
+                                goto error;
+                        }
+                } else {
+                        iommu = map_dev_to_ir(dev);
+                        if (!iommu) {
+                                ret = -ENOENT;
+                                goto error;
+                        }
+                        /*
+                         * setup the mapping between the irq and the IRTE
+                         * base index, the sub_handle pointing to the
+                         * appropriate interrupt remap table entry.
+                         */
+                        set_irte_irq(irq, iommu, index, sub_handle);
+                }
+no_ir:
+#endif
+                ret = setup_msi_irq(dev, desc, irq);
+                if (ret < 0)
+                        goto error;
+                sub_handle++;
+        }
        return 0;
+error:
+        destroy_irq(irq);
+        return ret;
 }
 void arch_teardown_msi_irq(unsigned int irq)
@@ -2333,6 +2872,10 @@ void __init setup_ioapic_dest(void)
                                setup_IO_APIC_irq(ioapic, pin, irq,
                                                  irq_trigger(irq_entry),
                                                  irq_polarity(irq_entry));
+#ifdef CONFIG_INTR_REMAP
+                        else if (intr_remapping_enabled)
+                                set_ir_ioapic_affinity_irq(irq, TARGET_CPUS);
+#endif
                        else
                                set_ioapic_affinity_irq(irq, TARGET_CPUS);
                }
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index d66914287ee1..9200a1e2752d 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -74,6 +74,15 @@ void __init init_ISA_irqs (void)
        }
 }
+/*
+ * IRQ2 is cascade interrupt to second interrupt controller
+ */
+static struct irqaction irq2 = {
+        .handler = no_action,
+        .mask = CPU_MASK_NONE,
+        .name = "cascade",
+};
 /* Overridden in paravirt.c */
 void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
@@ -98,6 +107,46 @@ void __init native_init_IRQ(void)
                        set_intr_gate(vector, interrupt[i]);
        }
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_SMP)
+        /*
+         * IRQ0 must be given a fixed assignment and initialized,
+         * because it's used before the IO-APIC is set up.
+         */
+        set_intr_gate(FIRST_DEVICE_VECTOR, interrupt[0]);
+        /*
+         * The reschedule interrupt is a CPU-to-CPU reschedule-helper
+         * IPI, driven by wakeup.
+         */
+        alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
+        /* IPI for invalidation */
+        alloc_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt);
+        /* IPI for generic function call */
+        alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
+        /* IPI for single call function */
+        set_intr_gate(CALL_FUNCTION_SINGLE_VECTOR, call_function_single_interrupt);
+#endif
+#ifdef CONFIG_X86_LOCAL_APIC
+        /* self generated IPI for local APIC timer */
+        alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
+        /* IPI vectors for APIC spurious and error interrupts */
+        alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
+        alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+#endif
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_MCE_P4THERMAL)
+        /* thermal monitor LVT interrupt */
+        alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+#endif
+        if (!acpi_ioapic)
+                setup_irq(2, &irq2);
        /* setup after call gates are initialised (usually add in
         * the architecture specific gates)
         */
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index b3fb430725cb..f98f4e1dba09 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -397,7 +397,9 @@ static int __init smp_read_mpc(struct mp_config_table *mpc, unsigned early)
       generic_bigsmp_probe();
 #endif
+#ifdef CONFIG_X86_32
        setup_apic_routing();
+#endif
        if (!num_processors)
                printk(KERN_ERR "MPTABLE: no processors registered!\n");
        return num_processors;
diff --git a/arch/x86/kernel/numaq_32.c b/arch/x86/kernel/numaq_32.c
index eecc8c18f010..4caff39078e0 100644
--- a/arch/x86/kernel/numaq_32.c
+++ b/arch/x86/kernel/numaq_32.c
@@ -229,6 +229,12 @@ static void __init smp_read_mpc_oem(struct mp_config_oemtable *oemtable,
        }
 }
+static int __init numaq_setup_ioapic_ids(void)
+{
+        /* so can skip it */
+        return 1;
+}
 static struct x86_quirks numaq_x86_quirks __initdata = {
        .arch_pre_time_init     = numaq_pre_time_init,
        .arch_time_init         = NULL,
@@ -243,6 +249,7 @@ static struct x86_quirks numaq_x86_quirks __initdata = {
        .mpc_oem_bus_info       = mpc_oem_bus_info,
        .mpc_oem_pci_bus        = mpc_oem_pci_bus,
        .smp_read_mpc_oem       = smp_read_mpc_oem,
+        .setup_ioapic_ids       = numaq_setup_ioapic_ids,
 };
 void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index e2f43768723a..6b0bb73998dd 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -374,8 +374,6 @@ struct pv_cpu_ops pv_cpu_ops = {
 struct pv_apic_ops pv_apic_ops = {
 #ifdef CONFIG_X86_LOCAL_APIC
-        .apic_write = native_apic_write,
-        .apic_read = native_apic_read,
        .setup_boot_clock = setup_boot_APIC_clock,
        .setup_secondary_clock = setup_secondary_APIC_clock,
        .startup_ipi_hook = paravirt_nop,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ec7a2ba9bce8..c622772744d8 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -15,7 +15,6 @@ unsigned long idle_nomwait;
 EXPORT_SYMBOL(idle_nomwait);
 struct kmem_cache *task_xstate_cachep;
-static int force_mwait __cpuinitdata;
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 141efab52400..46c98efbbf8d 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -758,6 +758,8 @@ void __init setup_arch(char **cmdline_p)
 #else
        num_physpages = max_pfn;
+        if (cpu_has_x2apic)
+                check_x2apic();
        /* How many end-of-memory variables you have, grandma! */
        /* need this before calling reserve_initrd */
diff --git a/arch/x86/kernel/sigframe.h b/arch/x86/kernel/sigframe.h
index 8b4956e800ac..cc673aa55ce4 100644
--- a/arch/x86/kernel/sigframe.h
+++ b/arch/x86/kernel/sigframe.h
@@ -3,9 +3,18 @@ struct sigframe {
        char __user *pretcode;
        int sig;
        struct sigcontext sc;
-        struct _fpstate fpstate;
+        /*
+         * fpstate is unused. fpstate is moved/allocated after
+         * retcode[] below. This movement allows to have the FP state and the
+         * future state extensions (xsave) stay together.
+         * And at the same time retaining the unused fpstate, prevents changing
+         * the offset of extramask[] in the sigframe and thus prevent any
+         * legacy application accessing/modifying it.
+         */
+        struct _fpstate fpstate_unused;
        unsigned long extramask[_NSIG_WORDS-1];
        char retcode[8];
+        /* fp state follows here */
 };
 struct rt_sigframe {
@@ -15,14 +24,15 @@ struct rt_sigframe {
        void __user *puc;
        struct siginfo info;
        struct ucontext uc;
-        struct _fpstate fpstate;
        char retcode[8];
+        /* fp state follows here */
 };
 #else
 struct rt_sigframe {
        char __user *pretcode;
        struct ucontext uc;
        struct siginfo info;
+        /* fp state follows here */
 };
 int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index 2a2435d3037d..b21070ea33a4 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -161,28 +161,14 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
        }
        {
-                struct _fpstate __user *buf;
+                void __user *buf;
                err |= __get_user(buf, &sc->fpstate);
-                if (buf) {
+                err |= restore_i387_xstate(buf);
-                        if (!access_ok(VERIFY_READ, buf, sizeof(*buf)))
-                                goto badframe;
-                        err |= restore_i387(buf);
-                } else {
-                        struct task_struct *me = current;
-                        if (used_math()) {
-                                clear_fpu(me);
-                                clear_used_math();
-                        }
-                }
        }
        err |= __get_user(*pax, &sc->ax);
        return err;
-badframe:
-        return 1;
 }
 asmlinkage unsigned long sys_sigreturn(unsigned long __unused)
@@ -264,7 +250,7 @@ badframe:
 * Set up a signal frame.
 */
 static int
-setup_sigcontext(struct sigcontext __user *sc, struct _fpstate __user *fpstate,
+setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
                 struct pt_regs *regs, unsigned long mask)
 {
        int tmp, err = 0;
@@ -291,7 +277,7 @@ setup_sigcontext(struct sigcontext __user *sc, struct _fpstate __user *fpstate,
        err |= __put_user(regs->sp, &sc->sp_at_signal);
        err |= __put_user(regs->ss, (unsigned int __user *)&sc->ss);
-        tmp = save_i387(fpstate);
+        tmp = save_i387_xstate(fpstate);
        if (tmp < 0)
                err = 1;
        else
@@ -308,7 +294,8 @@ setup_sigcontext(struct sigcontext __user *sc, struct _fpstate __user *fpstate,
 * Determine which stack to use..
 */
 static inline void __user *
-get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size)
+get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
+             void **fpstate)
 {
        unsigned long sp;
@@ -334,6 +321,11 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size)
                        sp = (unsigned long) ka->sa.sa_restorer;
        }
+        if (used_math()) {
+                sp = sp - sig_xstate_size;
+                *fpstate = (struct _fpstate *) sp;
+        }
        sp -= frame_size;
        /*
         * Align the stack pointer according to the i386 ABI,
@@ -352,8 +344,9 @@ setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
        void __user *restorer;
        int err = 0;
        int usig;
+        void __user *fpstate = NULL;
-        frame = get_sigframe(ka, regs, sizeof(*frame));
+        frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
        if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
                goto give_sigsegv;
@@ -368,7 +361,7 @@ setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
        if (err)
                goto give_sigsegv;
-        err = setup_sigcontext(&frame->sc, &frame->fpstate, regs, set->sig[0]);
+        err = setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0]);
        if (err)
                goto give_sigsegv;
@@ -429,8 +422,9 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
        void __user *restorer;
        int err = 0;
        int usig;
+        void __user *fpstate = NULL;
-        frame = get_sigframe(ka, regs, sizeof(*frame));
+        frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
        if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
                goto give_sigsegv;
@@ -449,13 +443,16 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
                goto give_sigsegv;
        /* Create the ucontext.  */
-        err |= __put_user(0, &frame->uc.uc_flags);
+        if (cpu_has_xsave)
+                err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags);
+        else
+                err |= __put_user(0, &frame->uc.uc_flags);
        err |= __put_user(0, &frame->uc.uc_link);
        err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
        err |= __put_user(sas_ss_flags(regs->sp),
                          &frame->uc.uc_stack.ss_flags);
        err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
-        err |= setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
+        err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
                                regs, set->sig[0]);
        err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
        if (err)
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index 694aa888bb19..823a55bf8c39 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -53,69 +53,6 @@ sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
 }
 /*
- * Signal frame handlers.
- */
-static inline int save_i387(struct _fpstate __user *buf)
-{
-        struct task_struct *tsk = current;
-        int err = 0;
-        BUILD_BUG_ON(sizeof(struct user_i387_struct) !=
-                        sizeof(tsk->thread.xstate->fxsave));
-        if ((unsigned long)buf % 16)
-                printk("save_i387: bad fpstate %p\n", buf);
-        if (!used_math())
-                return 0;
-        clear_used_math(); /* trigger finit */
-        if (task_thread_info(tsk)->status & TS_USEDFPU) {
-                err = save_i387_checking((struct i387_fxsave_struct __user *)
-                                         buf);
-                if (err)
-                        return err;
-                task_thread_info(tsk)->status &= ~TS_USEDFPU;
-                stts();
-        } else {
-                if (__copy_to_user(buf, &tsk->thread.xstate->fxsave,
-                                   sizeof(struct i387_fxsave_struct)))
-                        return -1;
-        }
-        return 1;
-}
-/*
- * This restores directly out of user space. Exceptions are handled.
- */
-static inline int restore_i387(struct _fpstate __user *buf)
-{
-        struct task_struct *tsk = current;
-        int err;
-        if (!used_math()) {
-                err = init_fpu(tsk);
-                if (err)
-                        return err;
-        }
-        if (!(task_thread_info(current)->status & TS_USEDFPU)) {
-                clts();
-                task_thread_info(current)->status |= TS_USEDFPU;
-        }
-        err = restore_fpu_checking((__force struct i387_fxsave_struct *)buf);
-        if (unlikely(err)) {
-                /*
-                 * Encountered an error while doing the restore from the
-                 * user buffer, clear the fpu state.
-                 */
-                clear_fpu(tsk);
-                clear_used_math();
-        }
-        return err;
-}
-/*
 * Do a signal return; undo the signal stack.
 */
 static int
@@ -159,25 +96,11 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
        {
                struct _fpstate __user *buf;
                err |= __get_user(buf, &sc->fpstate);
+                err |= restore_i387_xstate(buf);
-                if (buf) {
-                        if (!access_ok(VERIFY_READ, buf, sizeof(*buf)))
-                                goto badframe;
-                        err |= restore_i387(buf);
-                } else {
-                        struct task_struct *me = current;
-                        if (used_math()) {
-                                clear_fpu(me);
-                                clear_used_math();
-                        }
-                }
        }
        err |= __get_user(*pax, &sc->ax);
        return err;
-badframe:
-        return 1;
 }
 asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
@@ -269,26 +192,23 @@ get_stack(struct k_sigaction *ka, struct pt_regs *regs, unsigned long size)
                        sp = current->sas_ss_sp + current->sas_ss_size;
        }
-        return (void __user *)round_down(sp - size, 16);
+        return (void __user *)round_down(sp - size, 64);
 }
 static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
                           sigset_t *set, struct pt_regs *regs)
 {
        struct rt_sigframe __user *frame;
-        struct _fpstate __user *fp = NULL;
+        void __user *fp = NULL;
        int err = 0;
        struct task_struct *me = current;
        if (used_math()) {
-                fp = get_stack(ka, regs, sizeof(struct _fpstate));
+                fp = get_stack(ka, regs, sig_xstate_size);
                frame = (void __user *)round_down(
                        (unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8;
-                if (!access_ok(VERIFY_WRITE, fp, sizeof(struct _fpstate)))
+                if (save_i387_xstate(fp) < 0)
-                        goto give_sigsegv;
-                if (save_i387(fp) < 0)
                        err |= -1;
        } else
                frame = get_stack(ka, regs, sizeof(struct rt_sigframe)) - 8;
@@ -303,7 +223,10 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
        }
        /* Create the ucontext.  */
-        err |= __put_user(0, &frame->uc.uc_flags);
+        if (cpu_has_xsave)
+                err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags);
+        else
+                err |= __put_user(0, &frame->uc.uc_flags);
        err |= __put_user(0, &frame->uc.uc_link);
        err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
        err |= __put_user(sas_ss_flags(regs->sp),
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 4e7ccb0e2a9b..9056f7e272c0 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -123,7 +123,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
 static atomic_t init_deasserted;
-static int boot_cpu_logical_apicid;
 /* representing cpus for which sibling maps can be computed */
 static cpumask_t cpu_sibling_setup_map;
@@ -165,6 +164,8 @@ static void unmap_cpu_to_node(int cpu)
 #endif
 #ifdef CONFIG_X86_32
+static int boot_cpu_logical_apicid;
 u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly =
                                        { [0 ... NR_CPUS-1] = BAD_APICID };
@@ -210,7 +211,7 @@ static void __cpuinit smp_callin(void)
        /*
         * (This works even if the APIC is not enabled.)
         */
-        phys_id = GET_APIC_ID(read_apic_id());
+        phys_id = read_apic_id();
        cpuid = smp_processor_id();
        if (cpu_isset(cpuid, cpu_callin_map)) {
                panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
@@ -551,8 +552,7 @@ static inline void __inquire_remote_apic(int apicid)
                        printk(KERN_CONT
                               "a previous APIC delivery may have failed\n");
-                apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(apicid));
+                apic_icr_write(APIC_DM_REMRD | regs[i], apicid);
-                apic_write(APIC_ICR, APIC_DM_REMRD | regs[i]);
                timeout = 0;
                do {
@@ -584,11 +584,9 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
        int maxlvt;
        /* Target chip */
-        apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(logical_apicid));
        /* Boot on the stack */
        /* Kick the second */
-        apic_write(APIC_ICR, APIC_DM_NMI | APIC_DEST_LOGICAL);
+        apic_icr_write(APIC_DM_NMI | APIC_DEST_LOGICAL, logical_apicid);
        pr_debug("Waiting for send to finish...\n");
        send_status = safe_apic_wait_icr_idle();
@@ -641,13 +639,11 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
        /*
         * Turn INIT on target chip
         */
-        apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
        /*
         * Send IPI
         */
-        apic_write(APIC_ICR,
+        apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT,
-                   APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT);
+                       phys_apicid);
        pr_debug("Waiting for send to finish...\n");
        send_status = safe_apic_wait_icr_idle();
@@ -657,10 +653,8 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
        pr_debug("Deasserting INIT.\n");
        /* Target chip */
-        apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
        /* Send IPI */
-        apic_write(APIC_ICR, APIC_INT_LEVELTRIG | APIC_DM_INIT);
+        apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid);
        pr_debug("Waiting for send to finish...\n");
        send_status = safe_apic_wait_icr_idle();
@@ -703,11 +697,10 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
                 */
                /* Target chip */
-                apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
                /* Boot on the stack */
                /* Kick the second */
-                apic_write(APIC_ICR, APIC_DM_STARTUP | (start_eip >> 12));
+                apic_icr_write(APIC_DM_STARTUP | (start_eip >> 12),
+                               phys_apicid);
                /*
                 * Give the other CPU some time to accept the IPI.
@@ -1176,10 +1169,17 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
         * Setup boot CPU information
         */
        smp_store_cpu_info(0); /* Final full version of the data */
+#ifdef CONFIG_X86_32
        boot_cpu_logical_apicid = logical_smp_processor_id();
+#endif
        current_thread_info()->cpu = 0;  /* needed? */
        set_cpu_sibling_map(0);
+#ifdef CONFIG_X86_64
+        enable_IR_x2apic();
+        setup_apic_routing();
+#endif
        if (smp_sanity_check(max_cpus) < 0) {
                printk(KERN_INFO "SMP disabled\n");
                disable_smp();
@@ -1187,9 +1187,9 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
        }
        preempt_disable();
-        if (GET_APIC_ID(read_apic_id()) != boot_cpu_physical_apicid) {
+        if (read_apic_id() != boot_cpu_physical_apicid) {
                panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
-                     GET_APIC_ID(read_apic_id()), boot_cpu_physical_apicid);
+                     read_apic_id(), boot_cpu_physical_apicid);
                /* Or can we switch back to PIC here? */
        }
        preempt_enable();
diff --git a/arch/x86/kernel/summit_32.c b/arch/x86/kernel/summit_32.c
index d67ce5f044ba..7b987852e876 100644
--- a/arch/x86/kernel/summit_32.c
+++ b/arch/x86/kernel/summit_32.c
@@ -30,7 +30,7 @@
 #include <linux/init.h>
 #include <asm/io.h>
 #include <asm/bios_ebda.h>
-#include <asm/mach-summit/mach_mpparse.h>
+#include <asm/summit/mpparse.h>
 static struct rio_table_hdr *rio_table_hdr __initdata;
 static struct scal_detail   *scal_devs[MAX_NUMNODES] __initdata;
diff --git a/arch/x86/kernel/traps_32.c b/arch/x86/kernel/traps_32.c
index 03df8e45e5a1..da5a5964fccb 100644
--- a/arch/x86/kernel/traps_32.c
+++ b/arch/x86/kernel/traps_32.c
@@ -1228,7 +1228,6 @@ void __init trap_init(void)
        set_bit(SYSCALL_VECTOR, used_vectors);
-        init_thread_xstate();
        /*
         * Should be a barrier for any external CPU state:
         */
diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c
index 7a31f104bef9..2887a789e38f 100644
--- a/arch/x86/kernel/traps_64.c
+++ b/arch/x86/kernel/traps_64.c
@@ -1138,7 +1138,7 @@ asmlinkage void math_state_restore(void)
        /*
         * Paranoid restore. send a SIGSEGV if we fail to restore the state.
         */
-        if (unlikely(restore_fpu_checking(&me->thread.xstate->fxsave))) {
+        if (unlikely(restore_fpu_checking(me))) {
                stts();
                force_sig(SIGSEGV, me);
                return;
@@ -1179,10 +1179,6 @@ void __init trap_init(void)
        set_system_gate(IA32_SYSCALL_VECTOR, ia32_syscall);
 #endif
        /*
-         * initialize the per thread extended state:
-         */
-        init_thread_xstate();
-        /*
         * Should be a barrier for any external CPU state:
         */
        cpu_init();
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 8c9ad02af5a2..8b6c393ab9fd 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -905,8 +905,8 @@ static inline int __init activate_vmi(void)
 #endif
 #ifdef CONFIG_X86_LOCAL_APIC
-        para_fill(pv_apic_ops.apic_read, APICRead);
+       para_fill(apic_ops->read, APICRead);
-        para_fill(pv_apic_ops.apic_write, APICWrite);
+       para_fill(apic_ops->write, APICWrite);
 #endif
        /*
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
index af5bdad84604..a9b8560adbc2 100644
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ b/arch/x86/kernel/vmlinux_32.lds.S
@@ -140,10 +140,10 @@ SECTIONS
        *(.con_initcall.init)
        __con_initcall_end = .;
  }
-  .x86cpuvendor.init : AT(ADDR(.x86cpuvendor.init) - LOAD_OFFSET) {
+  .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
-        __x86cpuvendor_start = .;
+        __x86_cpu_dev_start = .;
-        *(.x86cpuvendor.init)
+        *(.x86_cpu_dev.init)
-        __x86cpuvendor_end = .;
+        __x86_cpu_dev_end = .;
  }
  SECURITY_INIT
  . = ALIGN(4);
@@ -180,6 +180,7 @@ SECTIONS
  . = ALIGN(PAGE_SIZE);
  .data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
        __per_cpu_start = .;
+        *(.data.percpu.page_aligned)
        *(.data.percpu)
        *(.data.percpu.shared_aligned)
        __per_cpu_end = .;
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index 63e5c1a22e88..201e81a91a95 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -168,13 +168,12 @@ SECTIONS
        *(.con_initcall.init)
  }
  __con_initcall_end = .;
-  . = ALIGN(16);
+  __x86_cpu_dev_start = .;
-  __x86cpuvendor_start = .;
+  .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
-  .x86cpuvendor.init : AT(ADDR(.x86cpuvendor.init) - LOAD_OFFSET) {
+        *(.x86_cpu_dev.init)
-        *(.x86cpuvendor.init)
  }
-  __x86cpuvendor_end = .;
  SECURITY_INIT
+  __x86_cpu_dev_end = .;
  . = ALIGN(8);
  .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
new file mode 100644
index 000000000000..07713d64debe
--- /dev/null
+++ b/arch/x86/kernel/xsave.c
@@ -0,0 +1,316 @@
+/*
+ * xsave/xrstor support.
+ *
+ * Author: Suresh Siddha <suresh.b.siddha@intel.com>
+ */
+#include <linux/bootmem.h>
+#include <linux/compat.h>
+#include <asm/i387.h>
+#ifdef CONFIG_IA32_EMULATION
+#include <asm/sigcontext32.h>
+#endif
+#include <asm/xcr.h>
+/*
+ * Supported feature mask by the CPU and the kernel.
+ */
+u64 pcntxt_mask;
+struct _fpx_sw_bytes fx_sw_reserved;
+#ifdef CONFIG_IA32_EMULATION
+struct _fpx_sw_bytes fx_sw_reserved_ia32;
+#endif
+/*
+ * Check for the presence of extended state information in the
+ * user fpstate pointer in the sigcontext.
+ */
+int check_for_xstate(struct i387_fxsave_struct __user *buf,
+                     void __user *fpstate,
+                     struct _fpx_sw_bytes *fx_sw_user)
+{
+        int min_xstate_size = sizeof(struct i387_fxsave_struct) +
+                              sizeof(struct xsave_hdr_struct);
+        unsigned int magic2;
+        int err;
+        err = __copy_from_user(fx_sw_user, &buf->sw_reserved[0],
+                               sizeof(struct _fpx_sw_bytes));
+        if (err)
+                return err;
+        /*
+         * First Magic check failed.
+         */
+        if (fx_sw_user->magic1 != FP_XSTATE_MAGIC1)
+                return -1;
+        /*
+         * Check for error scenarios.
+         */
+        if (fx_sw_user->xstate_size < min_xstate_size ||
+            fx_sw_user->xstate_size > xstate_size ||
+            fx_sw_user->xstate_size > fx_sw_user->extended_size)
+                return -1;
+        err = __get_user(magic2, (__u32 *) (((void *)fpstate) +
+                                            fx_sw_user->extended_size -
+                                            FP_XSTATE_MAGIC2_SIZE));
+        /*
+         * Check for the presence of second magic word at the end of memory
+         * layout. This detects the case where the user just copied the legacy
+         * fpstate layout with out copying the extended state information
+         * in the memory layout.
+         */
+        if (err || magic2 != FP_XSTATE_MAGIC2)
+                return -1;
+        return 0;
+}
+#ifdef CONFIG_X86_64
+/*
+ * Signal frame handlers.
+ */
+int save_i387_xstate(void __user *buf)
+{
+        struct task_struct *tsk = current;
+        int err = 0;
+        if (!access_ok(VERIFY_WRITE, buf, sig_xstate_size))
+                return -EACCES;
+        BUG_ON(sig_xstate_size < xstate_size);
+        if ((unsigned long)buf % 64)
+                printk("save_i387_xstate: bad fpstate %p\n", buf);
+        if (!used_math())
+                return 0;
+        clear_used_math(); /* trigger finit */
+        if (task_thread_info(tsk)->status & TS_USEDFPU) {
+                /*
+                 * Start with clearing the user buffer. This will present a
+                 * clean context for the bytes not touched by the fxsave/xsave.
+                 */
+                __clear_user(buf, sig_xstate_size);
+                if (task_thread_info(tsk)->status & TS_XSAVE)
+                        err = xsave_user(buf);
+                else
+                        err = fxsave_user(buf);
+                if (err)
+                        return err;
+                task_thread_info(tsk)->status &= ~TS_USEDFPU;
+                stts();
+        } else {
+                if (__copy_to_user(buf, &tsk->thread.xstate->fxsave,
+                                   xstate_size))
+                        return -1;
+        }
+        if (task_thread_info(tsk)->status & TS_XSAVE) {
+                struct _fpstate __user *fx = buf;
+                err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved,
+                                     sizeof(struct _fpx_sw_bytes));
+                err |= __put_user(FP_XSTATE_MAGIC2,
+                                  (__u32 __user *) (buf + sig_xstate_size
+                                                    - FP_XSTATE_MAGIC2_SIZE));
+        }
+        return 1;
+}
+/*
+ * Restore the extended state if present. Otherwise, restore the FP/SSE
+ * state.
+ */
+int restore_user_xstate(void __user *buf)
+{
+        struct _fpx_sw_bytes fx_sw_user;
+        u64 mask;
+        int err;
+        if (((unsigned long)buf % 64) ||
+             check_for_xstate(buf, buf, &fx_sw_user))
+                goto fx_only;
+        mask = fx_sw_user.xstate_bv;
+        /*
+         * restore the state passed by the user.
+         */
+        err = xrestore_user(buf, mask);
+        if (err)
+                return err;
+        /*
+         * init the state skipped by the user.
+         */
+        mask = pcntxt_mask & ~mask;
+        xrstor_state(init_xstate_buf, mask);
+        return 0;
+fx_only:
+        /*
+         * couldn't find the extended state information in the
+         * memory layout. Restore just the FP/SSE and init all
+         * the other extended state.
+         */
+        xrstor_state(init_xstate_buf, pcntxt_mask & ~XSTATE_FPSSE);
+        return fxrstor_checking((__force struct i387_fxsave_struct *)buf);
+}
+/*
+ * This restores directly out of user space. Exceptions are handled.
+ */
+int restore_i387_xstate(void __user *buf)
+{
+        struct task_struct *tsk = current;
+        int err = 0;
+        if (!buf) {
+                if (used_math())
+                        goto clear;
+                return 0;
+        } else
+                if (!access_ok(VERIFY_READ, buf, sig_xstate_size))
+                        return -EACCES;
+        if (!used_math()) {
+                err = init_fpu(tsk);
+                if (err)
+                        return err;
+        }
+        if (!(task_thread_info(current)->status & TS_USEDFPU)) {
+                clts();
+                task_thread_info(current)->status |= TS_USEDFPU;
+        }
+        if (task_thread_info(tsk)->status & TS_XSAVE)
+                err = restore_user_xstate(buf);
+        else
+                err = fxrstor_checking((__force struct i387_fxsave_struct *)
+                                       buf);
+        if (unlikely(err)) {
+                /*
+                 * Encountered an error while doing the restore from the
+                 * user buffer, clear the fpu state.
+                 */
+clear:
+                clear_fpu(tsk);
+                clear_used_math();
+        }
+        return err;
+}
+#endif
+/*
+ * Prepare the SW reserved portion of the fxsave memory layout, indicating
+ * the presence of the extended state information in the memory layout
+ * pointed by the fpstate pointer in the sigcontext.
+ * This will be saved when ever the FP and extended state context is
+ * saved on the user stack during the signal handler delivery to the user.
+ */
+void prepare_fx_sw_frame(void)
+{
+        int size_extended = (xstate_size - sizeof(struct i387_fxsave_struct)) +
+                             FP_XSTATE_MAGIC2_SIZE;
+        sig_xstate_size = sizeof(struct _fpstate) + size_extended;
+#ifdef CONFIG_IA32_EMULATION
+        sig_xstate_ia32_size = sizeof(struct _fpstate_ia32) + size_extended;
+#endif
+        memset(&fx_sw_reserved, 0, sizeof(fx_sw_reserved));
+        fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
+        fx_sw_reserved.extended_size = sig_xstate_size;
+        fx_sw_reserved.xstate_bv = pcntxt_mask;
+        fx_sw_reserved.xstate_size = xstate_size;
+#ifdef CONFIG_IA32_EMULATION
+        memcpy(&fx_sw_reserved_ia32, &fx_sw_reserved,
+               sizeof(struct _fpx_sw_bytes));
+        fx_sw_reserved_ia32.extended_size = sig_xstate_ia32_size;
+#endif
+}
+/*
+ * Represents init state for the supported extended state.
+ */
+struct xsave_struct *init_xstate_buf;
+#ifdef CONFIG_X86_64
+unsigned int sig_xstate_size = sizeof(struct _fpstate);
+#endif
+/*
+ * Enable the extended processor state save/restore feature
+ */
+void __cpuinit xsave_init(void)
+{
+        if (!cpu_has_xsave)
+                return;
+        set_in_cr4(X86_CR4_OSXSAVE);
+        /*
+         * Enable all the features that the HW is capable of
+         * and the Linux kernel is aware of.
+         */
+        xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
+}
+/*
+ * setup the xstate image representing the init state
+ */
+void setup_xstate_init(void)
+{
+        init_xstate_buf = alloc_bootmem(xstate_size);
+        init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT;
+}
+/*
+ * Enable and initialize the xsave feature.
+ */
+void __init xsave_cntxt_init(void)
+{
+        unsigned int eax, ebx, ecx, edx;
+        cpuid_count(0xd, 0, &eax, &ebx, &ecx, &edx);
+        pcntxt_mask = eax + ((u64)edx << 32);
+        if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) {
+                printk(KERN_ERR "FP/SSE not shown under xsave features 0x%llx\n",
+                       pcntxt_mask);
+                BUG();
+        }
+        /*
+         * for now OS knows only about FP/SSE
+         */
+        pcntxt_mask = pcntxt_mask & XCNTXT_MASK;
+        xsave_init();
+        /*
+         * Recompute the context size for enabled features
+         */
+        cpuid_count(0xd, 0, &eax, &ebx, &ecx, &edx);
+        xstate_size = ebx;
+        prepare_fx_sw_frame();
+        setup_xstate_init();
+        printk(KERN_INFO "xsave/xrstor: enabled xstate_bv 0x%llx, "
+               "cntxt size 0x%x\n",
+               pcntxt_mask, xstate_size);
+}
diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h
index 23e8373507ad..17e25995b65b 100644
--- a/arch/x86/kvm/vmx.h
+++ b/arch/x86/kvm/vmx.h
@@ -331,21 +331,6 @@ enum vmcs_field {
 #define AR_RESERVD_MASK 0xfffe0f00
-#define MSR_IA32_VMX_BASIC                      0x480
-#define MSR_IA32_VMX_PINBASED_CTLS              0x481
-#define MSR_IA32_VMX_PROCBASED_CTLS             0x482
-#define MSR_IA32_VMX_EXIT_CTLS                  0x483
-#define MSR_IA32_VMX_ENTRY_CTLS                 0x484
-#define MSR_IA32_VMX_MISC                       0x485
-#define MSR_IA32_VMX_CR0_FIXED0                 0x486
-#define MSR_IA32_VMX_CR0_FIXED1                 0x487
-#define MSR_IA32_VMX_CR4_FIXED0                 0x488
-#define MSR_IA32_VMX_CR4_FIXED1                 0x489
-#define MSR_IA32_VMX_VMCS_ENUM                  0x48a
-#define MSR_IA32_VMX_PROCBASED_CTLS2            0x48b
-#define MSR_IA32_VMX_EPT_VPID_CAP               0x48c
-#define MSR_IA32_FEATURE_CONTROL                0x3a
 #define MSR_IA32_FEATURE_CONTROL_LOCKED         0x1
 #define MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED  0x4
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index d9249a882aa5..65f0b8a47bed 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -55,6 +55,7 @@
 #include <linux/lguest_launcher.h>
 #include <linux/virtio_console.h>
 #include <linux/pm.h>
+#include <asm/apic.h>
 #include <asm/lguest.h>
 #include <asm/paravirt.h>
 #include <asm/param.h>
@@ -783,14 +784,44 @@ static void lguest_wbinvd(void)
 * code qualifies for Advanced.  It will also never interrupt anything.  It
 * does, however, allow us to get through the Linux boot code. */
 #ifdef CONFIG_X86_LOCAL_APIC
-static void lguest_apic_write(unsigned long reg, u32 v)
+static void lguest_apic_write(u32 reg, u32 v)
 {
 }
-static u32 lguest_apic_read(unsigned long reg)
+static u32 lguest_apic_read(u32 reg)
 {
        return 0;
 }
+static u64 lguest_apic_icr_read(void)
+{
+        return 0;
+}
+static void lguest_apic_icr_write(u32 low, u32 id)
+{
+        /* Warn to see if there's any stray references */
+        WARN_ON(1);
+}
+static void lguest_apic_wait_icr_idle(void)
+{
+        return;
+}
+static u32 lguest_apic_safe_wait_icr_idle(void)
+{
+        return 0;
+}
+static struct apic_ops lguest_basic_apic_ops = {
+        .read = lguest_apic_read,
+        .write = lguest_apic_write,
+        .icr_read = lguest_apic_icr_read,
+        .icr_write = lguest_apic_icr_write,
+        .wait_icr_idle = lguest_apic_wait_icr_idle,
+        .safe_wait_icr_idle = lguest_apic_safe_wait_icr_idle,
+};
 #endif
 /* STOP!  Until an interrupt comes in. */
@@ -990,8 +1021,7 @@ __init void lguest_init(void)
 #ifdef CONFIG_X86_LOCAL_APIC
        /* apic read/write intercepts */
-        pv_apic_ops.apic_write = lguest_apic_write;
+        apic_ops = &lguest_basic_apic_ops;
-        pv_apic_ops.apic_read = lguest_apic_read;
 #endif
        /* time operations */
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index aa3fa4119424..55e11aa6d66c 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -17,9 +17,6 @@ ifeq ($(CONFIG_X86_32),y)
        lib-$(CONFIG_X86_USE_3DNOW) += mmx_32.o
 else
        obj-y += io_64.o iomap_copy_64.o
-        CFLAGS_csum-partial_64.o := -funroll-loops
        lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
        lib-y += thunk_64.o clear_page_64.o copy_page_64.o
        lib-y += memmove_64.o memset_64.o
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 24e60944971a..9e68075544f6 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -14,6 +14,13 @@
 #include <asm/uaccess.h>
 #include <asm/mmx.h>
+#ifdef CONFIG_X86_INTEL_USERCOPY
+/*
+ * Alignment at which movsl is preferred for bulk memory copies.
+ */
+struct movsl_mask movsl_mask __read_mostly;
+#endif
 static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned long n)
 {
 #ifdef CONFIG_X86_INTEL_USERCOPY
diff --git a/arch/x86/mach-default/setup.c b/arch/x86/mach-default/setup.c
index 3f2cf11f201a..37b9ae4d44c5 100644
--- a/arch/x86/mach-default/setup.c
+++ b/arch/x86/mach-default/setup.c
@@ -38,15 +38,6 @@ void __init pre_intr_init_hook(void)
        init_ISA_irqs();
 }
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-static struct irqaction irq2 = {
-        .handler = no_action,
-        .mask = CPU_MASK_NONE,
-        .name = "cascade",
-};
 /**
 * intr_init_hook - post gate setup interrupt initialisation
 *
@@ -62,12 +53,6 @@ void __init intr_init_hook(void)
                if (x86_quirks->arch_intr_init())
                        return;
        }
-#ifdef CONFIG_X86_LOCAL_APIC
-        apic_intr_init();
-#endif
-        if (!acpi_ioapic)
-                setup_irq(2, &irq2);
 }
 /**
diff --git a/arch/x86/mach-es7000/Makefile b/arch/x86/mach-es7000/Makefile
deleted file mode 100644
index 3ef8b43b62fc..000000000000
--- a/arch/x86/mach-es7000/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-#
-# Makefile for the linux kernel.
-#
-obj-$(CONFIG_X86_ES7000)        := es7000plat.o
diff --git a/arch/x86/mach-es7000/es7000.h b/arch/x86/mach-es7000/es7000.h
deleted file mode 100644
index c8d5aa132fa0..000000000000
--- a/arch/x86/mach-es7000/es7000.h
+++ /dev/null
@@ -1,114 +0,0 @@
-/*
- * Written by: Garry Forsgren, Unisys Corporation
- *             Natalie Protasevich, Unisys Corporation
- * This file contains the code to configure and interface 
- * with Unisys ES7000 series hardware system manager.
- *
- * Copyright (c) 2003 Unisys Corporation.  All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * Contact information: Unisys Corporation, Township Line & Union Meeting 
- * Roads-A, Unisys Way, Blue Bell, Pennsylvania, 19424, or:
- *
- * http://www.unisys.com
- */
-/*
- * ES7000 chipsets
- */
-#define NON_UNISYS              0
-#define ES7000_CLASSIC          1
-#define ES7000_ZORRO            2
-#define MIP_REG                 1
-#define MIP_PSAI_REG            4
-#define MIP_BUSY                1
-#define MIP_SPIN                0xf0000
-#define MIP_VALID               0x0100000000000000ULL
-#define MIP_PORT(VALUE) ((VALUE >> 32) & 0xffff)
-#define MIP_RD_LO(VALUE)        (VALUE & 0xffffffff)   
-struct mip_reg_info {
-        unsigned long long mip_info;
-        unsigned long long delivery_info;
-        unsigned long long host_reg;
-        unsigned long long mip_reg;
-};
-struct part_info {
-        unsigned char type;   
-        unsigned char length;
-        unsigned char part_id;
-        unsigned char apic_mode;
-        unsigned long snum;    
-        char ptype[16];
-        char sname[64];
-        char pname[64];
-};
-struct psai {
-        unsigned long long entry_type;
-        unsigned long long addr;
-        unsigned long long bep_addr;
-};
-struct es7000_mem_info {
-        unsigned char type;   
-        unsigned char length;
-        unsigned char resv[6];
-        unsigned long long  start; 
-        unsigned long long  size; 
-};
-struct es7000_oem_table {
-        unsigned long long hdr;
-        struct mip_reg_info mip;
-        struct part_info pif;
-        struct es7000_mem_info shm;
-        struct psai psai;
-};
-#ifdef CONFIG_ACPI
-struct oem_table {
-        struct acpi_table_header Header;
-        u32 OEMTableAddr;
-        u32 OEMTableSize;
-};
-extern int find_unisys_acpi_oem_table(unsigned long *oem_addr);
-#endif
-struct mip_reg {
-        unsigned long long off_0;
-        unsigned long long off_8;
-        unsigned long long off_10;
-        unsigned long long off_18;
-        unsigned long long off_20;
-        unsigned long long off_28;
-        unsigned long long off_30;
-        unsigned long long off_38;
-};
-#define MIP_SW_APIC             0x1020b
-#define MIP_FUNC(VALUE)         (VALUE & 0xff)
-extern int parse_unisys_oem (char *oemptr);
-extern void setup_unisys(void);
-extern int es7000_start_cpu(int cpu, unsigned long eip);
-extern void es7000_sw_apic(void);
diff --git a/arch/x86/mach-generic/Makefile b/arch/x86/mach-generic/Makefile
index 0dbd7803a1d5..6730f4e7c744 100644
--- a/arch/x86/mach-generic/Makefile
+++ b/arch/x86/mach-generic/Makefile
@@ -9,4 +9,3 @@ obj-$(CONFIG_X86_NUMAQ)		+= numaq.o
 obj-$(CONFIG_X86_SUMMIT)        += summit.o
 obj-$(CONFIG_X86_BIGSMP)        += bigsmp.o
 obj-$(CONFIG_X86_ES7000)        += es7000.o
-obj-$(CONFIG_X86_ES7000)        += ../../x86/mach-es7000/
diff --git a/arch/x86/mach-generic/bigsmp.c b/arch/x86/mach-generic/bigsmp.c
index 59d771714559..df37fc9d6a26 100644
--- a/arch/x86/mach-generic/bigsmp.c
+++ b/arch/x86/mach-generic/bigsmp.c
@@ -5,18 +5,17 @@
 #define APIC_DEFINITION 1
 #include <linux/threads.h>
 #include <linux/cpumask.h>
-#include <asm/smp.h>
 #include <asm/mpspec.h>
 #include <asm/genapic.h>
 #include <asm/fixmap.h>
 #include <asm/apicdef.h>
 #include <linux/kernel.h>
-#include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/dmi.h>
-#include <asm/mach-bigsmp/mach_apic.h>
+#include <asm/bigsmp/apicdef.h>
-#include <asm/mach-bigsmp/mach_apicdef.h>
+#include <linux/smp.h>
-#include <asm/mach-bigsmp/mach_ipi.h>
+#include <asm/bigsmp/apic.h>
+#include <asm/bigsmp/ipi.h>
 #include <asm/mach-default/mach_mpparse.h>
 static int dmi_bigsmp; /* can be set by dmi scanners */
diff --git a/arch/x86/mach-generic/es7000.c b/arch/x86/mach-generic/es7000.c
index 4742626f08c4..520cca0ee04e 100644
--- a/arch/x86/mach-generic/es7000.c
+++ b/arch/x86/mach-generic/es7000.c
@@ -4,20 +4,19 @@
 #define APIC_DEFINITION 1
 #include <linux/threads.h>
 #include <linux/cpumask.h>
-#include <asm/smp.h>
 #include <asm/mpspec.h>
 #include <asm/genapic.h>
 #include <asm/fixmap.h>
 #include <asm/apicdef.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/smp.h>
 #include <linux/init.h>
-#include <asm/mach-es7000/mach_apicdef.h>
+#include <asm/es7000/apicdef.h>
-#include <asm/mach-es7000/mach_apic.h>
+#include <linux/smp.h>
-#include <asm/mach-es7000/mach_ipi.h>
+#include <asm/es7000/apic.h>
-#include <asm/mach-es7000/mach_mpparse.h>
+#include <asm/es7000/ipi.h>
-#include <asm/mach-es7000/mach_wakecpu.h>
+#include <asm/es7000/mpparse.h>
+#include <asm/es7000/wakecpu.h>
 static int probe_es7000(void)
 {
diff --git a/arch/x86/mach-generic/numaq.c b/arch/x86/mach-generic/numaq.c
index 8091e68764c4..8cf58394975e 100644
--- a/arch/x86/mach-generic/numaq.c
+++ b/arch/x86/mach-generic/numaq.c
@@ -4,7 +4,6 @@
 #define APIC_DEFINITION 1
 #include <linux/threads.h>
 #include <linux/cpumask.h>
-#include <linux/smp.h>
 #include <asm/mpspec.h>
 #include <asm/genapic.h>
 #include <asm/fixmap.h>
@@ -12,11 +11,12 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <asm/mach-numaq/mach_apic.h>
+#include <asm/numaq/apicdef.h>
-#include <asm/mach-numaq/mach_apicdef.h>
+#include <linux/smp.h>
-#include <asm/mach-numaq/mach_ipi.h>
+#include <asm/numaq/apic.h>
-#include <asm/mach-numaq/mach_mpparse.h>
+#include <asm/numaq/ipi.h>
-#include <asm/mach-numaq/mach_wakecpu.h>
+#include <asm/numaq/mpparse.h>
+#include <asm/numaq/wakecpu.h>
 #include <asm/numaq.h>
 static int mps_oem_check(struct mp_config_table *mpc, char *oem,
diff --git a/arch/x86/mach-generic/summit.c b/arch/x86/mach-generic/summit.c
index a97ea0f35b1e..6ad6b67a723d 100644
--- a/arch/x86/mach-generic/summit.c
+++ b/arch/x86/mach-generic/summit.c
@@ -4,19 +4,18 @@
 #define APIC_DEFINITION 1
 #include <linux/threads.h>
 #include <linux/cpumask.h>
-#include <asm/smp.h>
 #include <asm/mpspec.h>
 #include <asm/genapic.h>
 #include <asm/fixmap.h>
 #include <asm/apicdef.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/smp.h>
 #include <linux/init.h>
-#include <asm/mach-summit/mach_apic.h>
+#include <asm/summit/apicdef.h>
-#include <asm/mach-summit/mach_apicdef.h>
+#include <linux/smp.h>
-#include <asm/mach-summit/mach_ipi.h>
+#include <asm/summit/apic.h>
-#include <asm/mach-summit/mach_mpparse.h>
+#include <asm/summit/ipi.h>
+#include <asm/summit/mpparse.h>
 static int probe_summit(void)
 {
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index fb30486c82f7..83e13f2d53d2 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -88,6 +88,62 @@ early_param("gbpages", parse_direct_gbpages_on);
 int after_bootmem;
+unsigned long __supported_pte_mask __read_mostly = ~0UL;
+EXPORT_SYMBOL_GPL(__supported_pte_mask);
+static int do_not_nx __cpuinitdata;
+/*
+ * noexec=on|off
+ * Control non-executable mappings for 64-bit processes.
+ *
+ * on   Enable (default)
+ * off  Disable
+ */
+static int __init nonx_setup(char *str)
+{
+        if (!str)
+                return -EINVAL;
+        if (!strncmp(str, "on", 2)) {
+                __supported_pte_mask |= _PAGE_NX;
+                do_not_nx = 0;
+        } else if (!strncmp(str, "off", 3)) {
+                do_not_nx = 1;
+                __supported_pte_mask &= ~_PAGE_NX;
+        }
+        return 0;
+}
+early_param("noexec", nonx_setup);
+void __cpuinit check_efer(void)
+{
+        unsigned long efer;
+        rdmsrl(MSR_EFER, efer);
+        if (!(efer & EFER_NX) || do_not_nx)
+                __supported_pte_mask &= ~_PAGE_NX;
+}
+int force_personality32;
+/*
+ * noexec32=on|off
+ * Control non executable heap for 32bit processes.
+ * To control the stack too use noexec=off
+ *
+ * on   PROT_READ does not imply PROT_EXEC for 32-bit processes (default)
+ * off  PROT_READ implies PROT_EXEC
+ */
+static int __init nonx32_setup(char *str)
+{
+        if (!strcmp(str, "on"))
+                force_personality32 &= ~READ_IMPLIES_EXEC;
+        else if (!strcmp(str, "off"))
+                force_personality32 |= READ_IMPLIES_EXEC;
+        return 1;
+}
+__setup("noexec32=", nonx32_setup);
 /*
 * NOTE: This function is marked __ref because it calls __init function
 * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 19af06927fbc..1d88d2b39771 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -250,10 +250,5 @@ int __init pci_acpi_init(void)
                        acpi_pci_irq_enable(dev);
        }
-#ifdef CONFIG_X86_IO_APIC
-        if (acpi_ioapic)
-                print_IO_APIC();
-#endif
        return 0;
 }
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 8791fc55e715..844df0cbbd3e 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -33,6 +33,7 @@
 #include <linux/bootmem.h>
 #include <asm/pat.h>
+#include <asm/e820.h>
 #include "pci.h"
@@ -227,6 +228,8 @@ void __init pcibios_resource_survey(void)
        pcibios_allocate_bus_resources(&pci_root_buses);
        pcibios_allocate_resources(0);
        pcibios_allocate_resources(1);
+        e820_reserve_resources_late();
 }
 /**
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index d9635764ce3d..654a2234f8f3 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -209,7 +209,7 @@ static int __init pci_mmcfg_check_hostbridge(void)
        return name != NULL;
 }
-static void __init pci_mmcfg_insert_resources(unsigned long resource_flags)
+static void __init pci_mmcfg_insert_resources(void)
 {
 #define PCI_MMCFG_RESOURCE_NAME_LEN 19
        int i;
@@ -233,7 +233,7 @@ static void __init pci_mmcfg_insert_resources(unsigned long resource_flags)
                         cfg->pci_segment);
                res->start = cfg->address;
                res->end = res->start + (num_buses << 20) - 1;
-                res->flags = IORESOURCE_MEM | resource_flags;
+                res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
                insert_resource(&iomem_resource, res);
                names += PCI_MMCFG_RESOURCE_NAME_LEN;
        }
@@ -434,11 +434,9 @@ static void __init __pci_mmcfg_init(int early)
            (pci_mmcfg_config[0].address == 0))
                return;
-        if (pci_mmcfg_arch_init()) {
+        if (pci_mmcfg_arch_init())
-                if (known_bridge)
-                        pci_mmcfg_insert_resources(IORESOURCE_BUSY);
                pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;
-        } else {
+        else {
                /*
                 * Signal not to attempt to insert mmcfg resources because
                 * the architecture mmcfg setup could not initialize.
@@ -475,7 +473,7 @@ static int __init pci_mmcfg_late_insert_resources(void)
         * marked so it won't cause request errors when __request_region is
         * called.
         */
-        pci_mmcfg_insert_resources(0);
+        pci_mmcfg_insert_resources();
        return 0;
 }
diff --git a/arch/x86/power/cpu_32.c b/arch/x86/power/cpu_32.c
index d3e083dea720..274d06082f48 100644
--- a/arch/x86/power/cpu_32.c
+++ b/arch/x86/power/cpu_32.c
@@ -11,6 +11,7 @@
 #include <linux/suspend.h>
 #include <asm/mtrr.h>
 #include <asm/mce.h>
+#include <asm/xcr.h>
 static struct saved_context saved_context;
@@ -126,6 +127,12 @@ static void __restore_processor_state(struct saved_context *ctxt)
        if (boot_cpu_has(X86_FEATURE_SEP))
                enable_sep_cpu();
+        /*
+         * restore XCR0 for xsave capable cpu's.
+         */
+        if (cpu_has_xsave)
+                xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
        fix_processor_context();
        do_fpu_end();
        mtrr_ap_init();
diff --git a/arch/x86/power/cpu_64.c b/arch/x86/power/cpu_64.c
index 66bdfb591fd8..e3b6cf70d62c 100644
--- a/arch/x86/power/cpu_64.c
+++ b/arch/x86/power/cpu_64.c
@@ -14,6 +14,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mtrr.h>
+#include <asm/xcr.h>
 static void fix_processor_context(void);
@@ -122,6 +123,12 @@ static void __restore_processor_state(struct saved_context *ctxt)
        wrmsrl(MSR_GS_BASE, ctxt->gs_base);
        wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
+        /*
+         * restore XCR0 for xsave capable cpu's.
+         */
+        if (cpu_has_xsave)
+                xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
        fix_processor_context();
        do_fpu_end();
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 7dcd321a0508..a27d562a9744 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -36,6 +36,7 @@
 #include <xen/hvc-console.h>
 #include <asm/paravirt.h>
+#include <asm/apic.h>
 #include <asm/page.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
@@ -580,16 +581,47 @@ static void xen_io_delay(void)
 }
 #ifdef CONFIG_X86_LOCAL_APIC
-static u32 xen_apic_read(unsigned long reg)
+static u32 xen_apic_read(u32 reg)
 {
        return 0;
 }
-static void xen_apic_write(unsigned long reg, u32 val)
+static void xen_apic_write(u32 reg, u32 val)
 {
        /* Warn to see if there's any stray references */
        WARN_ON(1);
 }
+static u64 xen_apic_icr_read(void)
+{
+        return 0;
+}
+static void xen_apic_icr_write(u32 low, u32 id)
+{
+        /* Warn to see if there's any stray references */
+        WARN_ON(1);
+}
+static void xen_apic_wait_icr_idle(void)
+{
+        return;
+}
+static u32 xen_safe_apic_wait_icr_idle(void)
+{
+        return 0;
+}
+static struct apic_ops xen_basic_apic_ops = {
+        .read = xen_apic_read,
+        .write = xen_apic_write,
+        .icr_read = xen_apic_icr_read,
+        .icr_write = xen_apic_icr_write,
+        .wait_icr_idle = xen_apic_wait_icr_idle,
+        .safe_wait_icr_idle = xen_safe_apic_wait_icr_idle,
+};
 #endif
 static void xen_flush_tlb(void)
@@ -1273,8 +1305,6 @@ static const struct pv_irq_ops xen_irq_ops __initdata = {
 static const struct pv_apic_ops xen_apic_ops __initdata = {
 #ifdef CONFIG_X86_LOCAL_APIC
-        .apic_write = xen_apic_write,
-        .apic_read = xen_apic_read,
        .setup_boot_clock = paravirt_nop,
        .setup_secondary_clock = paravirt_nop,
        .startup_ipi_hook = paravirt_nop,
@@ -1677,6 +1707,13 @@ asmlinkage void __init xen_start_kernel(void)
        pv_apic_ops = xen_apic_ops;
        pv_mmu_ops = xen_mmu_ops;
+#ifdef CONFIG_X86_LOCAL_APIC
+        /*
+         * set up the basic apic ops.
+         */
+        apic_ops = &xen_basic_apic_ops;
+#endif
        if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
                pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
                pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;