166 files changed, 3362 insertions, 3051 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ac22bb7719f7..1cbec0269d39 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -19,6 +19,8 @@ config X86_64
 config X86
        def_bool y
        select HAVE_AOUT if X86_32
+        select HAVE_READQ
+        select HAVE_WRITEQ
        select HAVE_UNSTABLE_SCHED_CLOCK
        select HAVE_IDE
        select HAVE_OPROFILE
@@ -87,6 +89,10 @@ config GENERIC_IOMAP
 config GENERIC_BUG
        def_bool y
        depends on BUG
+        select GENERIC_BUG_RELATIVE_POINTERS if X86_64
+config GENERIC_BUG_RELATIVE_POINTERS
+        bool
 config GENERIC_HWEIGHT
        def_bool y
@@ -242,21 +248,13 @@ config X86_FIND_SMP_CONFIG
        def_bool y
        depends on X86_MPPARSE || X86_VOYAGER
-if ACPI
 config X86_MPPARSE
-        def_bool y
+        bool "Enable MPS table" if ACPI
-        bool "Enable MPS table"
+        default y
        depends on X86_LOCAL_APIC
        help
          For old smp systems that do not have proper acpi support. Newer systems
          (esp with 64bit cpus) with acpi support, MADT and DSDT will override it
-endif
-if !ACPI
-config X86_MPPARSE
-        def_bool y
-        depends on X86_LOCAL_APIC
-endif
 choice
        prompt "Subarchitecture Type"
@@ -465,10 +463,6 @@ config X86_CYCLONE_TIMER
        def_bool y
        depends on X86_GENERICARCH
-config ES7000_CLUSTERED_APIC
-        def_bool y
-        depends on SMP && X86_ES7000 && MPENTIUMIII
 source "arch/x86/Kconfig.cpu"
 config HPET_TIMER
@@ -660,6 +654,30 @@ config X86_VISWS_APIC
        def_bool y
        depends on X86_32 && X86_VISWS
+config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
+        bool "Reroute for broken boot IRQs"
+        default n
+        depends on X86_IO_APIC
+        help
+          This option enables a workaround that fixes a source of
+          spurious interrupts. This is recommended when threaded
+          interrupt handling is used on systems where the generation of
+          superfluous "boot interrupts" cannot be disabled.
+          Some chipsets generate a legacy INTx "boot IRQ" when the IRQ
+          entry in the chipset's IO-APIC is masked (as, e.g. the RT
+          kernel does during interrupt handling). On chipsets where this
+          boot IRQ generation cannot be disabled, this workaround keeps
+          the original IRQ line masked so that only the equivalent "boot
+          IRQ" is delivered to the CPUs. The workaround also tells the
+          kernel to set up the IRQ handler on the boot IRQ line. In this
+          way only one interrupt is delivered to the kernel. Otherwise
+          the spurious second interrupt may cause the kernel to bring
+          down (vital) interrupt lines.
+          Only affects "broken" chipsets. Interrupt sharing may be
+          increased on these systems.
 config X86_MCE
        bool "Machine Check Exception"
        depends on !X86_VOYAGER
@@ -956,24 +974,37 @@ config X86_PAE
 config ARCH_PHYS_ADDR_T_64BIT
       def_bool X86_64 || X86_PAE
+config DIRECT_GBPAGES
+        bool "Enable 1GB pages for kernel pagetables" if EMBEDDED
+        default y
+        depends on X86_64
+        help
+          Allow the kernel linear mapping to use 1GB pages on CPUs that
+          support it. This can improve the kernel's performance a tiny bit by
+          reducing TLB pressure. If in doubt, say "Y".
 # Common NUMA Features
 config NUMA
-        bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)"
+        bool "Numa Memory Allocation and Scheduler Support"
        depends on SMP
        depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && EXPERIMENTAL)
        default n if X86_PC
        default y if (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP)
        help
          Enable NUMA (Non Uniform Memory Access) support.
          The kernel will try to allocate memory used by a CPU on the
          local memory controller of the CPU and add some more
          NUMA awareness to the kernel.
-          For 32-bit this is currently highly experimental and should be only
+          For 64-bit this is recommended if the system is Intel Core i7
-          used for kernel development. It might also cause boot failures.
+          (or later), AMD Opteron, or EM64T NUMA.
-          For 64-bit this is recommended on all multiprocessor Opteron systems.
-          If the system is EM64T, you should say N unless your system is
+          For 32-bit this is only needed on (rare) 32-bit-only platforms
-          EM64T NUMA.
+          that support NUMA topologies, such as NUMAQ / Summit, or if you
+          boot a 32-bit kernel on a 64-bit NUMA platform.
+          Otherwise, you should say N.
 comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
        depends on X86_32 && X86_SUMMIT && (!HIGHMEM64G || !ACPI)
@@ -1493,6 +1524,10 @@ config ARCH_ENABLE_MEMORY_HOTPLUG
        def_bool y
        depends on X86_64 || (X86_32 && HIGHMEM)
+config ARCH_ENABLE_MEMORY_HOTREMOVE
+        def_bool y
+        depends on MEMORY_HOTPLUG
 config HAVE_ARCH_EARLY_PFN_TO_NID
        def_bool X86_64
        depends on NUMA
@@ -1632,13 +1667,6 @@ config APM_ALLOW_INTS
          many of the newer IBM Thinkpads.  If you experience hangs when you
          suspend, try setting this to Y.  Otherwise, say N.
-config APM_REAL_MODE_POWER_OFF
-        bool "Use real mode APM BIOS call to power off"
-        help
-          Use real mode APM BIOS calls to switch off the computer. This is
-          a work-around for a number of buggy BIOSes. Switch this option on if
-          your computer crashes instead of powering off properly.
 endif # APM
 source "arch/x86/kernel/cpu/cpufreq/Kconfig"
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 2a3dfbd5e677..4ee768660f75 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -114,18 +114,6 @@ config DEBUG_RODATA
          data. This is recommended so that we can catch kernel bugs sooner.
          If in doubt, say "Y".
-config DIRECT_GBPAGES
-        bool "Enable gbpages-mapped kernel pagetables"
-        depends on DEBUG_KERNEL && EXPERIMENTAL && X86_64
-        help
-          Enable gigabyte pages support (if the CPU supports it). This can
-          improve the kernel's performance a tiny bit by reducing TLB
-          pressure.
-          This is experimental code.
-          If in doubt, say "N".
 config DEBUG_RODATA_TEST
        bool "Testcase for the DEBUG_RODATA feature"
        depends on DEBUG_RODATA
@@ -307,10 +295,10 @@ config OPTIMIZE_INLINING
          developers have marked 'inline'. Doing so takes away freedom from gcc to
          do what it thinks is best, which is desirable for the gcc 3.x series of
          compilers. The gcc 4.x series have a rewritten inlining algorithm and
-          disabling this option will generate a smaller kernel there. Hopefully
+          enabling this option will generate a smaller kernel there. Hopefully
-          this algorithm is so good that allowing gcc4 to make the decision can
+          this algorithm is so good that allowing gcc 4.x and above to make the
-          become the default in the future, until then this option is there to
+          decision will become the default in the future. Until then this option
-          test gcc for this.
+          is there to test gcc for this.
          If unsure, say N.
diff --git a/arch/x86/boot/tty.c b/arch/x86/boot/tty.c
index 0be77b39328a..7e8e8b25f5f6 100644
--- a/arch/x86/boot/tty.c
+++ b/arch/x86/boot/tty.c
@@ -74,7 +74,7 @@ static int kbd_pending(void)
 {
        u8 pending;
        asm volatile("int $0x16; setnz %0"
-                     : "=rm" (pending)
+                     : "=qm" (pending)
                     : "a" (0x0100));
        return pending;
 }
diff --git a/arch/x86/boot/video-vga.c b/arch/x86/boot/video-vga.c
index b939cb476dec..5d4742ed4aa2 100644
--- a/arch/x86/boot/video-vga.c
+++ b/arch/x86/boot/video-vga.c
@@ -34,7 +34,7 @@ static struct mode_info cga_modes[] = {
        { VIDEO_80x25,  80, 25, 0 },
 };
-__videocard video_vga;
+static __videocard video_vga;
 /* Set basic 80x25 mode */
 static u8 vga_set_basic_mode(void)
@@ -259,7 +259,7 @@ static int vga_probe(void)
        return mode_count[adapter];
 }
-__videocard video_vga = {
+static __videocard video_vga = {
        .card_name      = "VGA",
        .probe          = vga_probe,
        .set_mode       = vga_set_mode,
diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c
index 83598b23093a..3bef2c1febe9 100644
--- a/arch/x86/boot/video.c
+++ b/arch/x86/boot/video.c
@@ -226,7 +226,7 @@ static unsigned int mode_menu(void)
 #ifdef CONFIG_VIDEO_RETAIN
 /* Save screen content to the heap */
-struct saved_screen {
+static struct saved_screen {
        int x, y;
        int curx, cury;
        u16 *data;
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 13b8c86ae985..b30a08ed8eb4 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -77,7 +77,7 @@ CONFIG_AUDIT=y
 CONFIG_AUDITSYSCALL=y
 CONFIG_AUDIT_TREE=y
 # CONFIG_IKCONFIG is not set
-CONFIG_LOG_BUF_SHIFT=17
+CONFIG_LOG_BUF_SHIFT=18
 CONFIG_CGROUPS=y
 # CONFIG_CGROUP_DEBUG is not set
 CONFIG_CGROUP_NS=y
@@ -298,7 +298,7 @@ CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
 # CONFIG_KEXEC_JUMP is not set
 CONFIG_PHYSICAL_START=0x1000000
-CONFIG_RELOCATABLE=y
+# CONFIG_RELOCATABLE is not set
 CONFIG_PHYSICAL_ALIGN=0x200000
 CONFIG_HOTPLUG_CPU=y
 # CONFIG_COMPAT_VDSO is not set
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index f0a03d7a7d63..0e7dbc0a3e46 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -77,7 +77,7 @@ CONFIG_AUDIT=y
 CONFIG_AUDITSYSCALL=y
 CONFIG_AUDIT_TREE=y
 # CONFIG_IKCONFIG is not set
-CONFIG_LOG_BUF_SHIFT=17
+CONFIG_LOG_BUF_SHIFT=18
 CONFIG_CGROUPS=y
 # CONFIG_CGROUP_DEBUG is not set
 CONFIG_CGROUP_NS=y
@@ -298,7 +298,7 @@ CONFIG_SCHED_HRTICK=y
 CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
 CONFIG_PHYSICAL_START=0x1000000
-CONFIG_RELOCATABLE=y
+# CONFIG_RELOCATABLE is not set
 CONFIG_PHYSICAL_ALIGN=0x200000
 CONFIG_HOTPLUG_CPU=y
 # CONFIG_COMPAT_VDSO is not set
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 4bc02b23674b..b195f85526e3 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -32,6 +32,8 @@
 #include <asm/proto.h>
 #include <asm/vdso.h>
+#include <asm/sigframe.h>
 #define DEBUG_SIG 0
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
@@ -41,7 +43,6 @@
                         X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
                         X86_EFLAGS_CF)
-asmlinkage int do_signal(struct pt_regs *regs, sigset_t *oldset);
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
@@ -173,47 +174,28 @@ asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr,
 /*
 * Do a signal return; undo the signal stack.
 */
+#define COPY(x)                 {               \
+        err |= __get_user(regs->x, &sc->x);     \
+}
-struct sigframe
+#define COPY_SEG_CPL3(seg)      {                       \
-{
+                unsigned short tmp;                     \
-        u32 pretcode;
+                err |= __get_user(tmp, &sc->seg);       \
-        int sig;
+                regs->seg = tmp | 3;                    \
-        struct sigcontext_ia32 sc;
-        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
-{
-        u32 pretcode;
-        int sig;
-        u32 pinfo;
-        u32 puc;
-        compat_siginfo_t info;
-        struct ucontext_ia32 uc;
-        char retcode[8];
-        /* fp state follows here */
-};
-#define COPY(x)         {               \
-        unsigned int reg;               \
-        err |= __get_user(reg, &sc->x); \
-        regs->x = reg;                  \
 }
-#define RELOAD_SEG(seg,mask)                                            \
+#define RELOAD_SEG(seg)         {               \
-        { unsigned int cur;                                             \
+        unsigned int cur, pre;                  \
-          unsigned short pre;                                           \
+        err |= __get_user(pre, &sc->seg);       \
-          err |= __get_user(pre, &sc->seg);                             \
+        savesegment(seg, cur);                  \
-          savesegment(seg, cur);                                        \
+        pre |= 3;                               \
-          pre |= mask;                                                  \
+        if (pre != cur)                         \
-          if (pre != cur) loadsegment(seg, pre); }
+                loadsegment(seg, pre);          \
+}
 static int ia32_restore_sigcontext(struct pt_regs *regs,
                                   struct sigcontext_ia32 __user *sc,
-                                   unsigned int *peax)
+                                   unsigned int *pax)
 {
        unsigned int tmpflags, gs, oldgs, err = 0;
        void __user *buf;
@@ -240,18 +222,16 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
        if (gs != oldgs)
                load_gs_index(gs);
-        RELOAD_SEG(fs, 3);
+        RELOAD_SEG(fs);
-        RELOAD_SEG(ds, 3);
+        RELOAD_SEG(ds);
-        RELOAD_SEG(es, 3);
+        RELOAD_SEG(es);
        COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
        COPY(dx); COPY(cx); COPY(ip);
        /* Don't touch extended registers */
-        err |= __get_user(regs->cs, &sc->cs);
+        COPY_SEG_CPL3(cs);
-        regs->cs |= 3;
+        COPY_SEG_CPL3(ss);
-        err |= __get_user(regs->ss, &sc->ss);
-        regs->ss |= 3;
        err |= __get_user(tmpflags, &sc->flags);
        regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
@@ -262,15 +242,13 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
        buf = compat_ptr(tmp);
        err |= restore_i387_xstate_ia32(buf);
-        err |= __get_user(tmp, &sc->ax);
+        err |= __get_user(*pax, &sc->ax);
-        *peax = tmp;
        return err;
 }
 asmlinkage long sys32_sigreturn(struct pt_regs *regs)
 {
-        struct sigframe __user *frame = (struct sigframe __user *)(regs->sp-8);
+        struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8);
        sigset_t set;
        unsigned int ax;
@@ -300,12 +278,12 @@ badframe:
 asmlinkage long sys32_rt_sigreturn(struct pt_regs *regs)
 {
-        struct rt_sigframe __user *frame;
+        struct rt_sigframe_ia32 __user *frame;
        sigset_t set;
        unsigned int ax;
        struct pt_regs tregs;
-        frame = (struct rt_sigframe __user *)(regs->sp - 4);
+        frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4);
        if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
                goto badframe;
@@ -359,20 +337,15 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
        err |= __put_user(regs->dx, &sc->dx);
        err |= __put_user(regs->cx, &sc->cx);
        err |= __put_user(regs->ax, &sc->ax);
-        err |= __put_user(regs->cs, &sc->cs);
-        err |= __put_user(regs->ss, &sc->ss);
        err |= __put_user(current->thread.trap_no, &sc->trapno);
        err |= __put_user(current->thread.error_code, &sc->err);
        err |= __put_user(regs->ip, &sc->ip);
+        err |= __put_user(regs->cs, (unsigned int __user *)&sc->cs);
        err |= __put_user(regs->flags, &sc->flags);
        err |= __put_user(regs->sp, &sc->sp_at_signal);
+        err |= __put_user(regs->ss, (unsigned int __user *)&sc->ss);
-        tmp = save_i387_xstate_ia32(fpstate);
+        err |= __put_user(ptr_to_compat(fpstate), &sc->fpstate);
-        if (tmp < 0)
-                err = -EFAULT;
-        else
-                err |= __put_user(ptr_to_compat(tmp ? fpstate : NULL),
-                                        &sc->fpstate);
        /* non-iBCS2 extensions.. */
        err |= __put_user(mask, &sc->oldmask);
@@ -400,7 +373,7 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
        }
        /* This is the legacy signal stack switching. */
-        else if ((regs->ss & 0xffff) != __USER_DS &&
+        else if ((regs->ss & 0xffff) != __USER32_DS &&
                !(ka->sa.sa_flags & SA_RESTORER) &&
                 ka->sa.sa_restorer)
                sp = (unsigned long) ka->sa.sa_restorer;
@@ -408,6 +381,8 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
        if (used_math()) {
                sp = sp - sig_xstate_ia32_size;
                *fpstate = (struct _fpstate_ia32 *) sp;
+                if (save_i387_xstate_ia32(*fpstate) < 0)
+                        return (void __user *) -1L;
        }
        sp -= frame_size;
@@ -420,7 +395,7 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
 int ia32_setup_frame(int sig, struct k_sigaction *ka,
                     compat_sigset_t *set, struct pt_regs *regs)
 {
-        struct sigframe __user *frame;
+        struct sigframe_ia32 __user *frame;
        void __user *restorer;
        int err = 0;
        void __user *fpstate = NULL;
@@ -430,12 +405,10 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
                u16 poplmovl;
                u32 val;
                u16 int80;
-                u16 pad;
        } __attribute__((packed)) code = {
                0xb858,          /* popl %eax ; movl $...,%eax */
                __NR_ia32_sigreturn,
                0x80cd,         /* int $0x80 */
-                0,
        };
        frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
@@ -471,7 +444,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
         * These are actually not used anymore, but left because some
         * gdb versions depend on them as a marker.
         */
-        err |= __copy_to_user(frame->retcode, &code, 8);
+        err |= __put_user(*((u64 *)&code), (u64 *)frame->retcode);
        if (err)
                return -EFAULT;
@@ -501,7 +474,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
 int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
                        compat_sigset_t *set, struct pt_regs *regs)
 {
-        struct rt_sigframe __user *frame;
+        struct rt_sigframe_ia32 __user *frame;
        void __user *restorer;
        int err = 0;
        void __user *fpstate = NULL;
@@ -511,8 +484,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
                u8 movl;
                u32 val;
                u16 int80;
-                u16 pad;
+                u8  pad;
-                u8  pad2;
        } __attribute__((packed)) code = {
                0xb8,
                __NR_ia32_rt_sigreturn,
@@ -559,7 +531,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
         * Not actually used anymore, but left because some gdb
         * versions need it.
         */
-        err |= __copy_to_user(frame->retcode, &code, 8);
+        err |= __put_user(*((u64 *)&code), (u64 *)frame->retcode);
        if (err)
                return -EFAULT;
@@ -572,11 +544,6 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
        regs->dx = (unsigned long) &frame->info;
        regs->cx = (unsigned long) &frame->uc;
-        /* Make -mregparm=3 work */
-        regs->ax = sig;
-        regs->dx = (unsigned long) &frame->info;
-        regs->cx = (unsigned long) &frame->uc;
        loadsegment(ds, __USER32_DS);
        loadsegment(es, __USER32_DS);
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 1a30c0440c6b..ac302a2fa339 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -251,13 +251,6 @@ struct amd_iommu {
        /* Pointer to PCI device of this IOMMU */
        struct pci_dev *dev;
-        /*
-         * Capability pointer. There could be more than one IOMMU per PCI
-         * device function if there are more than one AMD IOMMU capability
-         * pointers.
-         */
-        u16 cap_ptr;
        /* physical address of MMIO space */
        u64 mmio_phys;
        /* virtual address of MMIO space */
@@ -266,6 +259,13 @@ struct amd_iommu {
        /* capabilities of that IOMMU read from ACPI */
        u32 cap;
+        /*
+         * Capability pointer. There could be more than one IOMMU per PCI
+         * device function if there are more than one AMD IOMMU capability
+         * pointers.
+         */
+        u16 cap_ptr;
        /* pci domain of this IOMMU */
        u16 pci_seg;
@@ -284,19 +284,19 @@ struct amd_iommu {
        /* size of command buffer */
        u32 cmd_buf_size;
-        /* event buffer virtual address */
-        u8 *evt_buf;
        /* size of event buffer */
        u32 evt_buf_size;
+        /* event buffer virtual address */
+        u8 *evt_buf;
        /* MSI number for event interrupt */
        u16 evt_msi_num;
-        /* if one, we need to send a completion wait command */
-        int need_sync;
        /* true if interrupts for this IOMMU are already enabled */
        bool int_enabled;
+        /* if one, we need to send a completion wait command */
+        int need_sync;
        /* default dma_ops domain for that IOMMU */
        struct dma_ops_domain *default_dom;
 };
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 3b1510b4fc57..25caa0738af5 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -193,6 +193,7 @@ extern u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask);
 static inline void lapic_shutdown(void) { }
 #define local_apic_timer_c2_ok          1
 static inline void init_apic_mappings(void) { }
+static inline void disable_local_APIC(void) { }
 #endif /* !CONFIG_X86_LOCAL_APIC */
diff --git a/arch/x86/include/asm/bigsmp/apic.h b/arch/x86/include/asm/bigsmp/apic.h
index 1d9543b9d358..ce547f24a1cd 100644
--- a/arch/x86/include/asm/bigsmp/apic.h
+++ b/arch/x86/include/asm/bigsmp/apic.h
@@ -24,8 +24,6 @@ static inline cpumask_t target_cpus(void)
 #define INT_DELIVERY_MODE       (dest_Fixed)
 #define INT_DEST_MODE           (0)    /* phys delivery to target proc */
 #define NO_BALANCE_IRQ          (0)
-#define WAKE_SECONDARY_VIA_INIT
 static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
 {
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 360010322711..9fa9dcdf344b 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -168,7 +168,15 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
 */
 static inline void change_bit(int nr, volatile unsigned long *addr)
 {
-        asm volatile(LOCK_PREFIX "btc %1,%0" : ADDR : "Ir" (nr));
+        if (IS_IMMEDIATE(nr)) {
+                asm volatile(LOCK_PREFIX "xorb %1,%0"
+                        : CONST_MASK_ADDR(nr, addr)
+                        : "iq" ((u8)CONST_MASK(nr)));
+        } else {
+                asm volatile(LOCK_PREFIX "btc %1,%0"
+                        : BITOP_ADDR(addr)
+                        : "Ir" (nr));
+        }
 }
 /**
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 3def2065fcea..d9cf1cd156d2 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -9,7 +9,7 @@
 #ifdef CONFIG_X86_32
 # define __BUG_C0       "2:\t.long 1b, %c0\n"
 #else
-# define __BUG_C0       "2:\t.quad 1b, %c0\n"
+# define __BUG_C0       "2:\t.long 1b - 2b, %c0 - 2b\n"
 #endif
 #define BUG()                                                   \
diff --git a/arch/x86/include/asm/byteorder.h b/arch/x86/include/asm/byteorder.h
index e02ae2d89acf..f110ad417df3 100644
--- a/arch/x86/include/asm/byteorder.h
+++ b/arch/x86/include/asm/byteorder.h
@@ -4,26 +4,33 @@
 #include <asm/types.h>
 #include <linux/compiler.h>
-#ifdef __GNUC__
+#define __LITTLE_ENDIAN
-#ifdef __i386__
+static inline __attribute_const__ __u32 __arch_swab32(__u32 val)
-static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
 {
-#ifdef CONFIG_X86_BSWAP
+#ifdef __i386__
-        asm("bswap %0" : "=r" (x) : "0" (x));
+# ifdef CONFIG_X86_BSWAP
-#else
+        asm("bswap %0" : "=r" (val) : "0" (val));
+# else
        asm("xchgb %b0,%h0\n\t" /* swap lower bytes     */
            "rorl $16,%0\n\t"   /* swap words           */
            "xchgb %b0,%h0"     /* swap higher bytes    */
-            : "=q" (x)
+            : "=q" (val)
-            : "0" (x));
+            : "0" (val));
+# endif
+#else /* __i386__ */
+        asm("bswapl %0"
+            : "=r" (val)
+            : "0" (val));
 #endif
-        return x;
+        return val;
 }
+#define __arch_swab32 __arch_swab32
-static inline __attribute_const__ __u64 ___arch__swab64(__u64 val)
+static inline __attribute_const__ __u64 __arch_swab64(__u64 val)
 {
+#ifdef __i386__
        union {
                struct {
                        __u32 a;
@@ -32,50 +39,27 @@ static inline __attribute_const__ __u64 ___arch__swab64(__u64 val)
                __u64 u;
        } v;
        v.u = val;
-#ifdef CONFIG_X86_BSWAP
+# ifdef CONFIG_X86_BSWAP
        asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1"
            : "=r" (v.s.a), "=r" (v.s.b)
            : "0" (v.s.a), "1" (v.s.b));
-#else
+# else
-        v.s.a = ___arch__swab32(v.s.a);
+        v.s.a = __arch_swab32(v.s.a);
-        v.s.b = ___arch__swab32(v.s.b);
+        v.s.b = __arch_swab32(v.s.b);
        asm("xchgl %0,%1"
            : "=r" (v.s.a), "=r" (v.s.b)
            : "0" (v.s.a), "1" (v.s.b));
-#endif
+# endif
        return v.u;
-}
 #else /* __i386__ */
-static inline __attribute_const__ __u64 ___arch__swab64(__u64 x)
-{
        asm("bswapq %0"
-            : "=r" (x)
+            : "=r" (val)
-            : "0" (x));
+            : "0" (val));
-        return x;
+        return val;
-}
-static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
-{
-        asm("bswapl %0"
-            : "=r" (x)
-            : "0" (x));
-        return x;
-}
 #endif
+}
+#define __arch_swab64 __arch_swab64
-/* Do not define swab16.  Gcc is smart enough to recognize "C" version and
+#include <linux/byteorder.h>
-   convert it into rotation or exhange.  */
-#define __arch__swab64(x) ___arch__swab64(x)
-#define __arch__swab32(x) ___arch__swab32(x)
-#define __BYTEORDER_HAS_U64__
-#endif /* __GNUC__ */
-#include <linux/byteorder/little_endian.h>
 #endif /* _ASM_X86_BYTEORDER_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index cfdf8c2c5c31..ea408dcba513 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -80,7 +80,6 @@
 #define X86_FEATURE_UP          (3*32+ 9) /* smp kernel running on up */
 #define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* "" FXSAVE leaks FOP/FIP/FOP */
 #define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_NOPL        (3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_PEBS        (3*32+12) /* Precise-Event Based Sampling */
 #define X86_FEATURE_BTS         (3*32+13) /* Branch Trace Store */
 #define X86_FEATURE_SYSCALL32   (3*32+14) /* "" syscall in ia32 userspace */
@@ -92,6 +91,8 @@
 #define X86_FEATURE_NOPL        (3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_AMDC1E      (3*32+21) /* AMD C1E detected */
 #define X86_FEATURE_XTOPOLOGY   (3*32+22) /* cpu topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC (3*32+24) /* TSC does not stop in C states */
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3        (4*32+ 0) /* "pni" SSE-3 */
@@ -117,6 +118,7 @@
 #define X86_FEATURE_XSAVE       (4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
 #define X86_FEATURE_OSXSAVE     (4*32+27) /* "" XSAVE enabled in the OS */
 #define X86_FEATURE_AVX         (4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_HYPERVISOR  (4*32+31) /* Running on a hypervisor */
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
 #define X86_FEATURE_XSTORE      (5*32+ 2) /* "rng" RNG present (xstore) */
@@ -237,6 +239,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_xmm4_2          boot_cpu_has(X86_FEATURE_XMM4_2)
 #define cpu_has_x2apic          boot_cpu_has(X86_FEATURE_X2APIC)
 #define cpu_has_xsave           boot_cpu_has(X86_FEATURE_XSAVE)
+#define cpu_has_hypervisor      boot_cpu_has(X86_FEATURE_HYPERVISOR)
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg         1
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 7f225a4b2a26..097794ff6b79 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -71,15 +71,13 @@ static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
 /* Make sure we keep the same behaviour */
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
-#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_64
-        return 0;
-#else
        struct dma_mapping_ops *ops = get_dma_ops(dev);
        if (ops->mapping_error)
                return ops->mapping_error(dev, dma_addr);
-        return (dma_addr == bad_dma_address);
 #endif
+        return (dma_addr == bad_dma_address);
 }
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
diff --git a/arch/x86/include/asm/ds.h b/arch/x86/include/asm/ds.h
index 72c5a190bf48..a95008457ea4 100644
--- a/arch/x86/include/asm/ds.h
+++ b/arch/x86/include/asm/ds.h
@@ -23,12 +23,13 @@
 #ifndef _ASM_X86_DS_H
 #define _ASM_X86_DS_H
-#ifdef CONFIG_X86_DS
 #include <linux/types.h>
 #include <linux/init.h>
+#ifdef CONFIG_X86_DS
 struct task_struct;
 /*
@@ -232,7 +233,8 @@ extern void ds_free(struct ds_context *context);
 #else /* CONFIG_X86_DS */
-#define ds_init_intel(config) do {} while (0)
+struct cpuinfo_x86;
+static inline void __cpuinit ds_init_intel(struct cpuinfo_x86 *ignored) {}
 #endif /* CONFIG_X86_DS */
 #endif /* _ASM_X86_DS_H */
diff --git a/arch/x86/include/asm/emergency-restart.h b/arch/x86/include/asm/emergency-restart.h
index 94826cf87455..cc70c1c78ca4 100644
--- a/arch/x86/include/asm/emergency-restart.h
+++ b/arch/x86/include/asm/emergency-restart.h
@@ -8,7 +8,9 @@ enum reboot_type {
        BOOT_BIOS = 'b',
 #endif
        BOOT_ACPI = 'a',
-        BOOT_EFI = 'e'
+        BOOT_EFI = 'e',
+        BOOT_CF9 = 'p',
+        BOOT_CF9_COND = 'q',
 };
 extern enum reboot_type reboot_type;
diff --git a/arch/x86/include/asm/es7000/apic.h b/arch/x86/include/asm/es7000/apic.h
index 380f0b4f17ed..e24ef876915f 100644
--- a/arch/x86/include/asm/es7000/apic.h
+++ b/arch/x86/include/asm/es7000/apic.h
@@ -9,31 +9,27 @@ static inline int apic_id_registered(void)
                return (1);
 }
-static inline cpumask_t target_cpus(void)
+static inline cpumask_t target_cpus_cluster(void)
 {
-#if defined CONFIG_ES7000_CLUSTERED_APIC
        return CPU_MASK_ALL;
-#else
+}
+static inline cpumask_t target_cpus(void)
+{
        return cpumask_of_cpu(smp_processor_id());
-#endif
 }
-#if defined CONFIG_ES7000_CLUSTERED_APIC
+#define APIC_DFR_VALUE_CLUSTER          (APIC_DFR_CLUSTER)
-#define APIC_DFR_VALUE          (APIC_DFR_CLUSTER)
+#define INT_DELIVERY_MODE_CLUSTER       (dest_LowestPrio)
-#define INT_DELIVERY_MODE       (dest_LowestPrio)
+#define INT_DEST_MODE_CLUSTER           (1) /* logical delivery broadcast to all procs */
-#define INT_DEST_MODE           (1)    /* logical delivery broadcast to all procs */
+#define NO_BALANCE_IRQ_CLUSTER          (1)
-#define NO_BALANCE_IRQ          (1)
-#undef  WAKE_SECONDARY_VIA_INIT
-#define WAKE_SECONDARY_VIA_MIP
-#else
 #define APIC_DFR_VALUE          (APIC_DFR_FLAT)
 #define INT_DELIVERY_MODE       (dest_Fixed)
 #define INT_DEST_MODE           (0)    /* phys delivery to target procs */
 #define NO_BALANCE_IRQ          (0)
 #undef  APIC_DEST_LOGICAL
 #define APIC_DEST_LOGICAL       0x0
-#define WAKE_SECONDARY_VIA_INIT
-#endif
 static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
 {
@@ -60,6 +56,16 @@ static inline unsigned long calculate_ldr(int cpu)
 * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
 * document number 292116).  So here it goes...
 */
+static inline void init_apic_ldr_cluster(void)
+{
+        unsigned long val;
+        int cpu = smp_processor_id();
+        apic_write(APIC_DFR, APIC_DFR_VALUE_CLUSTER);
+        val = calculate_ldr(cpu);
+        apic_write(APIC_LDR, val);
+}
 static inline void init_apic_ldr(void)
 {
        unsigned long val;
@@ -70,10 +76,6 @@ static inline void init_apic_ldr(void)
        apic_write(APIC_LDR, val);
 }
-#ifndef CONFIG_X86_GENERICARCH
-extern void enable_apic_mode(void);
-#endif
 extern int apic_version [MAX_APICS];
 static inline void setup_apic_routing(void)
 {
@@ -144,7 +146,7 @@ static inline int check_phys_apicid_present(int cpu_physical_apicid)
        return (1);
 }
-static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+static inline unsigned int cpu_mask_to_apicid_cluster(cpumask_t cpumask)
 {
        int num_bits_set;
        int cpus_found = 0;
@@ -154,11 +156,7 @@ static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
        num_bits_set = cpus_weight(cpumask);
        /* Return id to all */
        if (num_bits_set == NR_CPUS)
-#if defined CONFIG_ES7000_CLUSTERED_APIC
                return 0xFF;
-#else
-                return cpu_to_logical_apicid(0);
-#endif
        /*
         * The cpus in the mask must all be on the apic cluster.  If are not
         * on the same apicid cluster return default value of TARGET_CPUS.
@@ -171,11 +169,40 @@ static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
                        if (apicid_cluster(apicid) !=
                                        apicid_cluster(new_apicid)){
                                printk ("%s: Not a valid mask!\n", __func__);
-#if defined CONFIG_ES7000_CLUSTERED_APIC
                                return 0xFF;
-#else
+                        }
+                        apicid = new_apicid;
+                        cpus_found++;
+                }
+                cpu++;
+        }
+        return apicid;
+}
+static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+        int num_bits_set;
+        int cpus_found = 0;
+        int cpu;
+        int apicid;
+        num_bits_set = cpus_weight(cpumask);
+        /* Return id to all */
+        if (num_bits_set == NR_CPUS)
+                return cpu_to_logical_apicid(0);
+        /*
+         * The cpus in the mask must all be on the apic cluster.  If are not
+         * on the same apicid cluster return default value of TARGET_CPUS.
+         */
+        cpu = first_cpu(cpumask);
+        apicid = cpu_to_logical_apicid(cpu);
+        while (cpus_found < num_bits_set) {
+                if (cpu_isset(cpu, cpumask)) {
+                        int new_apicid = cpu_to_logical_apicid(cpu);
+                        if (apicid_cluster(apicid) !=
+                                        apicid_cluster(new_apicid)){
+                                printk ("%s: Not a valid mask!\n", __func__);
                                return cpu_to_logical_apicid(0);
-#endif
                        }
                        apicid = new_apicid;
                        cpus_found++;
diff --git a/arch/x86/include/asm/es7000/wakecpu.h b/arch/x86/include/asm/es7000/wakecpu.h
index 398493461913..78f0daaee436 100644
--- a/arch/x86/include/asm/es7000/wakecpu.h
+++ b/arch/x86/include/asm/es7000/wakecpu.h
@@ -1,36 +1,12 @@
 #ifndef __ASM_ES7000_WAKECPU_H
 #define __ASM_ES7000_WAKECPU_H
-/*
+#define TRAMPOLINE_PHYS_LOW     0x467
- * This file copes with machines that wakeup secondary CPUs by the
+#define TRAMPOLINE_PHYS_HIGH    0x469
- * INIT, INIT, STARTUP sequence.
- */
-#ifdef CONFIG_ES7000_CLUSTERED_APIC
-#define WAKE_SECONDARY_VIA_MIP
-#else
-#define WAKE_SECONDARY_VIA_INIT
-#endif
-#ifdef WAKE_SECONDARY_VIA_MIP
-extern int es7000_start_cpu(int cpu, unsigned long eip);
-static inline int
-wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
-{
-        int boot_error = 0;
-        boot_error = es7000_start_cpu(phys_apicid, start_eip);
-        return boot_error;
-}
-#endif
-#define TRAMPOLINE_LOW phys_to_virt(0x467)
-#define TRAMPOLINE_HIGH phys_to_virt(0x469)
-#define boot_cpu_apicid boot_cpu_physical_apicid
 static inline void wait_for_init_deassert(atomic_t *deassert)
 {
-#ifdef WAKE_SECONDARY_VIA_INIT
+#ifndef CONFIG_ES7000_CLUSTERED_APIC
        while (!atomic_read(deassert))
                cpu_relax();
 #endif
@@ -50,9 +26,12 @@ static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
 {
 }
-#define inquire_remote_apic(apicid) do {                \
+extern void __inquire_remote_apic(int apicid);
-                if (apic_verbosity >= APIC_DEBUG)       \
-                        __inquire_remote_apic(apicid);  \
+static inline void inquire_remote_apic(int apicid)
-        } while (0)
+{
+        if (apic_verbosity >= APIC_DEBUG)
+                __inquire_remote_apic(apicid);
+}
 #endif /* __ASM_MACH_WAKECPU_H */
diff --git a/arch/x86/include/asm/genapic_32.h b/arch/x86/include/asm/genapic_32.h
index 5cbd4fcc06fd..0ac17d33a8c7 100644
--- a/arch/x86/include/asm/genapic_32.h
+++ b/arch/x86/include/asm/genapic_32.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_GENAPIC_32_H
 #include <asm/mpspec.h>
+#include <asm/atomic.h>
 /*
 * Generic APIC driver interface.
@@ -65,6 +66,14 @@ struct genapic {
        void (*send_IPI_allbutself)(int vector);
        void (*send_IPI_all)(int vector);
 #endif
+        int (*wakeup_cpu)(int apicid, unsigned long start_eip);
+        int trampoline_phys_low;
+        int trampoline_phys_high;
+        void (*wait_for_init_deassert)(atomic_t *deassert);
+        void (*smp_callin_clear_local_apic)(void);
+        void (*store_NMI_vector)(unsigned short *high, unsigned short *low);
+        void (*restore_NMI_vector)(unsigned short *high, unsigned short *low);
+        void (*inquire_remote_apic)(int apicid);
 };
 #define APICFUNC(x) .x = x,
@@ -105,16 +114,24 @@ struct genapic {
        APICFUNC(get_apic_id)                           \
        .apic_id_mask = APIC_ID_MASK,                   \
        APICFUNC(cpu_mask_to_apicid)                    \
-        APICFUNC(vector_allocation_domain)                      \
+        APICFUNC(vector_allocation_domain)              \
        APICFUNC(acpi_madt_oem_check)                   \
        IPIFUNC(send_IPI_mask)                          \
        IPIFUNC(send_IPI_allbutself)                    \
        IPIFUNC(send_IPI_all)                           \
        APICFUNC(enable_apic_mode)                      \
        APICFUNC(phys_pkg_id)                           \
+        .trampoline_phys_low = TRAMPOLINE_PHYS_LOW,             \
+        .trampoline_phys_high = TRAMPOLINE_PHYS_HIGH,           \
+        APICFUNC(wait_for_init_deassert)                \
+        APICFUNC(smp_callin_clear_local_apic)           \
+        APICFUNC(store_NMI_vector)                      \
+        APICFUNC(restore_NMI_vector)                    \
+        APICFUNC(inquire_remote_apic)                   \
 }
 extern struct genapic *genapic;
+extern void es7000_update_genapic_to_cluster(void);
 enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
 #define get_uv_system_type()            UV_NONE
diff --git a/arch/x86/include/asm/genapic_64.h b/arch/x86/include/asm/genapic_64.h
index 13c4e96199ea..2cae011668b7 100644
--- a/arch/x86/include/asm/genapic_64.h
+++ b/arch/x86/include/asm/genapic_64.h
@@ -32,6 +32,8 @@ struct genapic {
        unsigned int (*get_apic_id)(unsigned long x);
        unsigned long (*set_apic_id)(unsigned int id);
        unsigned long apic_id_mask;
+        /* wakeup_secondary_cpu */
+        int (*wakeup_cpu)(int apicid, unsigned long start_eip);
 };
 extern struct genapic *genapic;
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
new file mode 100644
index 000000000000..369f5c5d09a1
--- /dev/null
+++ b/arch/x86/include/asm/hypervisor.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2008, VMware, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#ifndef ASM_X86__HYPERVISOR_H
+#define ASM_X86__HYPERVISOR_H
+extern unsigned long get_hypervisor_tsc_freq(void);
+extern void init_hypervisor(struct cpuinfo_x86 *c);
+#endif
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index 97989c0e534c..50ca486fd88c 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -129,24 +129,6 @@ typedef struct compat_siginfo {
        } _sifields;
 } compat_siginfo_t;
-struct sigframe32 {
-        u32 pretcode;
-        int sig;
-        struct sigcontext_ia32 sc;
-        struct _fpstate_ia32 fpstate;
-        unsigned int extramask[_COMPAT_NSIG_WORDS-1];
-};
-struct rt_sigframe32 {
-        u32 pretcode;
-        int sig;
-        u32 pinfo;
-        u32 puc;
-        compat_siginfo_t info;
-        struct ucontext_ia32 uc;
-        struct _fpstate_ia32 fpstate;
-};
 struct ustat32 {
        __u32                   f_tfree;
        compat_ino_t            f_tinode;
diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h
index 44c89c3a23e9..38d87379e270 100644
--- a/arch/x86/include/asm/idle.h
+++ b/arch/x86/include/asm/idle.h
@@ -8,8 +8,13 @@ struct notifier_block;
 void idle_notifier_register(struct notifier_block *n);
 void idle_notifier_unregister(struct notifier_block *n);
+#ifdef CONFIG_X86_64
 void enter_idle(void);
 void exit_idle(void);
+#else /* !CONFIG_X86_64 */
+static inline void enter_idle(void) { }
+static inline void exit_idle(void) { }
+#endif /* CONFIG_X86_64 */
 void c1e_remove_cpu(int cpu);
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index ac2abc88cd95..33513b9a67f3 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -4,6 +4,7 @@
 #define ARCH_HAS_IOREMAP_WC
 #include <linux/compiler.h>
+#include <asm-generic/int-ll64.h>
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
@@ -45,20 +46,40 @@ build_mmio_write(__writel, "l", unsigned int, "r", )
 #define mmiowb() barrier()
 #ifdef CONFIG_X86_64
 build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
-build_mmio_read(__readq, "q", unsigned long, "=r", )
 build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
-build_mmio_write(__writeq, "q", unsigned long, "r", )
-#define readq_relaxed(a) __readq(a)
+#else
-#define __raw_readq __readq
-#define __raw_writeq writeq
+static inline __u64 readq(const volatile void __iomem *addr)
+{
+        const volatile u32 __iomem *p = addr;
+        u32 low, high;
+        low = readl(p);
+        high = readl(p + 1);
+        return low + ((u64)high << 32);
+}
+static inline void writeq(__u64 val, volatile void __iomem *addr)
+{
+        writel(val, addr);
+        writel(val >> 32, addr+4);
+}
-/* Let people know we have them */
-#define readq readq
-#define writeq writeq
 #endif
+#define readq_relaxed(a)        readq(a)
+#define __raw_readq(a)          readq(a)
+#define __raw_writeq(val, addr) writeq(val, addr)
+/* Let people know that we have them */
+#define readq                   readq
+#define writeq                  writeq
 extern int iommu_bio_merge;
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 6afd9933a7dd..e475e009ae5d 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -156,11 +156,21 @@ extern int sis_apic_bug;
 /* 1 if "noapic" boot option passed */
 extern int skip_ioapic_setup;
+/* 1 if "noapic" boot option passed */
+extern int noioapicquirk;
+/* -1 if "noapic" boot option passed */
+extern int noioapicreroute;
 /* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
 extern int timer_through_8259;
 static inline void disable_ioapic_setup(void)
 {
+#ifdef CONFIG_PCI
+        noioapicquirk = 1;
+        noioapicreroute = -1;
+#endif
        skip_ioapic_setup = 1;
 }
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index bae0eda95486..28e409fc73f3 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -31,10 +31,6 @@ static inline int irq_canonicalize(int irq)
 # endif
 #endif
-#ifdef CONFIG_IRQBALANCE
-extern int irqbalance_disable(char *str);
-#endif
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern void fixup_irqs(cpumask_t map);
diff --git a/arch/x86/include/asm/irq_regs_32.h b/arch/x86/include/asm/irq_regs_32.h
index af2f02d27fc7..86afd7473457 100644
--- a/arch/x86/include/asm/irq_regs_32.h
+++ b/arch/x86/include/asm/irq_regs_32.h
@@ -9,6 +9,8 @@
 #include <asm/percpu.h>
+#define ARCH_HAS_OWN_IRQ_REGS
 DECLARE_PER_CPU(struct pt_regs *, irq_regs);
 static inline struct pt_regs *get_irq_regs(void)
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index a1f22771a15a..c61d8b2ab8b9 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -5,21 +5,8 @@
 # define PA_CONTROL_PAGE        0
 # define VA_CONTROL_PAGE        1
 # define PA_PGD                 2
-# define VA_PGD                 3
+# define PA_SWAP_PAGE           3
-# define PA_PTE_0               4
+# define PAGES_NR               4
-# define VA_PTE_0               5
-# define PA_PTE_1               6
-# define VA_PTE_1               7
-# define PA_SWAP_PAGE           8
-# ifdef CONFIG_X86_PAE
-#  define PA_PMD_0              9
-#  define VA_PMD_0              10
-#  define PA_PMD_1              11
-#  define VA_PMD_1              12
-#  define PAGES_NR              13
-# else
-#  define PAGES_NR              9
-# endif
 #else
 # define PA_CONTROL_PAGE        0
 # define VA_CONTROL_PAGE        1
@@ -170,6 +157,20 @@ relocate_kernel(unsigned long indirection_page,
                unsigned long start_address) ATTRIB_NORET;
 #endif
+#ifdef CONFIG_X86_32
+#define ARCH_HAS_KIMAGE_ARCH
+struct kimage_arch {
+        pgd_t *pgd;
+#ifdef CONFIG_X86_PAE
+        pmd_t *pmd0;
+        pmd_t *pmd1;
+#endif
+        pte_t *pte0;
+        pte_t *pte1;
+};
+#endif
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_KEXEC_H */
diff --git a/arch/x86/include/asm/mach-default/mach_apic.h b/arch/x86/include/asm/mach-default/mach_apic.h
index ff3a6c236c00..6cb3a467e067 100644
--- a/arch/x86/include/asm/mach-default/mach_apic.h
+++ b/arch/x86/include/asm/mach-default/mach_apic.h
@@ -32,11 +32,13 @@ static inline cpumask_t target_cpus(void)
 #define vector_allocation_domain    (genapic->vector_allocation_domain)
 #define read_apic_id()  (GET_APIC_ID(apic_read(APIC_ID)))
 #define send_IPI_self (genapic->send_IPI_self)
+#define wakeup_secondary_cpu (genapic->wakeup_cpu)
 extern void setup_apic_routing(void);
 #else
 #define INT_DELIVERY_MODE dest_LowestPrio
 #define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
 #define TARGET_CPUS (target_cpus())
+#define wakeup_secondary_cpu wakeup_secondary_cpu_via_init
 /*
 * Set up the logical destination ID.
 *
diff --git a/arch/x86/include/asm/mach-default/mach_wakecpu.h b/arch/x86/include/asm/mach-default/mach_wakecpu.h
index 9d80db91e992..ceb013660146 100644
--- a/arch/x86/include/asm/mach-default/mach_wakecpu.h
+++ b/arch/x86/include/asm/mach-default/mach_wakecpu.h
@@ -1,17 +1,8 @@
 #ifndef _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H
 #define _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H
-/* 
+#define TRAMPOLINE_PHYS_LOW (0x467)
- * This file copes with machines that wakeup secondary CPUs by the
+#define TRAMPOLINE_PHYS_HIGH (0x469)
- * INIT, INIT, STARTUP sequence.
- */
-#define WAKE_SECONDARY_VIA_INIT
-#define TRAMPOLINE_LOW phys_to_virt(0x467)
-#define TRAMPOLINE_HIGH phys_to_virt(0x469)
-#define boot_cpu_apicid boot_cpu_physical_apicid
 static inline void wait_for_init_deassert(atomic_t *deassert)
 {
@@ -33,9 +24,12 @@ static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
 {
 }
-#define inquire_remote_apic(apicid) do {                \
+extern void __inquire_remote_apic(int apicid);
-                if (apic_verbosity >= APIC_DEBUG)       \
-                        __inquire_remote_apic(apicid);  \
+static inline void inquire_remote_apic(int apicid)
-        } while (0)
+{
+        if (apic_verbosity >= APIC_DEBUG)
+                __inquire_remote_apic(apicid);
+}
 #endif /* _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H */
diff --git a/arch/x86/include/asm/mach-default/smpboot_hooks.h b/arch/x86/include/asm/mach-default/smpboot_hooks.h
index dbab36d64d48..23bf52103b89 100644
--- a/arch/x86/include/asm/mach-default/smpboot_hooks.h
+++ b/arch/x86/include/asm/mach-default/smpboot_hooks.h
@@ -13,9 +13,11 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
        CMOS_WRITE(0xa, 0xf);
        local_flush_tlb();
        pr_debug("1.\n");
-        *((volatile unsigned short *) TRAMPOLINE_HIGH) = start_eip >> 4;
+        *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
+                                                                 start_eip >> 4;
        pr_debug("2.\n");
-        *((volatile unsigned short *) TRAMPOLINE_LOW) = start_eip & 0xf;
+        *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
+                                                         start_eip & 0xf;
        pr_debug("3.\n");
 }
@@ -32,7 +34,7 @@ static inline void smpboot_restore_warm_reset_vector(void)
         */
        CMOS_WRITE(0, 0xf);
-        *((volatile long *) phys_to_virt(0x467)) = 0;
+        *((volatile long *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
 }
 static inline void __init smpboot_setup_io_apic(void)
diff --git a/arch/x86/include/asm/mach-generic/mach_apic.h b/arch/x86/include/asm/mach-generic/mach_apic.h
index 5180bd7478fb..e430f47df667 100644
--- a/arch/x86/include/asm/mach-generic/mach_apic.h
+++ b/arch/x86/include/asm/mach-generic/mach_apic.h
@@ -27,6 +27,7 @@
 #define vector_allocation_domain (genapic->vector_allocation_domain)
 #define enable_apic_mode (genapic->enable_apic_mode)
 #define phys_pkg_id (genapic->phys_pkg_id)
+#define wakeup_secondary_cpu (genapic->wakeup_cpu)
 extern void generic_bigsmp_probe(void);
diff --git a/arch/x86/include/asm/mach-generic/mach_wakecpu.h b/arch/x86/include/asm/mach-generic/mach_wakecpu.h
new file mode 100644
index 000000000000..1ab16b168c8a
--- /dev/null
+++ b/arch/x86/include/asm/mach-generic/mach_wakecpu.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_X86_MACH_GENERIC_MACH_WAKECPU_H
+#define _ASM_X86_MACH_GENERIC_MACH_WAKECPU_H
+#define TRAMPOLINE_PHYS_LOW (genapic->trampoline_phys_low)
+#define TRAMPOLINE_PHYS_HIGH (genapic->trampoline_phys_high)
+#define wait_for_init_deassert (genapic->wait_for_init_deassert)
+#define smp_callin_clear_local_apic (genapic->smp_callin_clear_local_apic)
+#define store_NMI_vector (genapic->store_NMI_vector)
+#define restore_NMI_vector (genapic->restore_NMI_vector)
+#define inquire_remote_apic (genapic->inquire_remote_apic)
+#endif /* _ASM_X86_MACH_GENERIC_MACH_APIC_H */
diff --git a/arch/x86/include/asm/mmu_context_32.h b/arch/x86/include/asm/mmu_context_32.h
index 8e10015781fb..7e98ce1d2c0e 100644
--- a/arch/x86/include/asm/mmu_context_32.h
+++ b/arch/x86/include/asm/mmu_context_32.h
@@ -4,9 +4,8 @@
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
 #ifdef CONFIG_SMP
-        unsigned cpu = smp_processor_id();
+        if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK)
-        if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK)
+                x86_write_percpu(cpu_tlbstate.state, TLBSTATE_LAZY);
-                per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_LAZY;
 #endif
 }
@@ -20,8 +19,8 @@ static inline void switch_mm(struct mm_struct *prev,
                /* stop flush ipis for the previous mm */
                cpu_clear(cpu, prev->cpu_vm_mask);
 #ifdef CONFIG_SMP
-                per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK;
+                x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
-                per_cpu(cpu_tlbstate, cpu).active_mm = next;
+                x86_write_percpu(cpu_tlbstate.active_mm, next);
 #endif
                cpu_set(cpu, next->cpu_vm_mask);
@@ -36,8 +35,8 @@ static inline void switch_mm(struct mm_struct *prev,
        }
 #ifdef CONFIG_SMP
        else {
-                per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK;
+                x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
-                BUG_ON(per_cpu(cpu_tlbstate, cpu).active_mm != next);
+                BUG_ON(x86_read_percpu(cpu_tlbstate.active_mm) != next);
                if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
                        /* We were in lazy tlb mode and leave_mm disabled
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e38859d577a1..cb58643947b9 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -85,7 +85,9 @@
 /* AMD64 MSRs. Not complete. See the architecture manual for a more
   complete list. */
+#define MSR_AMD64_PATCH_LEVEL           0x0000008b
 #define MSR_AMD64_NB_CFG                0xc001001f
+#define MSR_AMD64_PATCH_LOADER          0xc0010020
 #define MSR_AMD64_IBSFETCHCTL           0xc0011030
 #define MSR_AMD64_IBSFETCHLINAD         0xc0011031
 #define MSR_AMD64_IBSFETCHPHYSAD        0xc0011032
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index c2a812ebde89..4640ddd58fb9 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -22,10 +22,10 @@ static inline unsigned long long native_read_tscp(unsigned int *aux)
 }
 /*
- * i386 calling convention returns 64-bit value in edx:eax, while
+ * both i386 and x86_64 returns 64-bit value in edx:eax, but gcc's "A"
- * x86_64 returns at rax. Also, the "A" constraint does not really
+ * constraint has different meanings. For i386, "A" means exactly
- * mean rdx:rax in x86_64, so we need specialized behaviour for each
+ * edx:eax, while for x86_64 it doesn't mean rdx:rax or edx:eax. Instead,
- * architecture
+ * it means rax *or* rdx.
 */
 #ifdef CONFIG_X86_64
 #define DECLARE_ARGS(val, low, high)    unsigned low, high
@@ -181,10 +181,10 @@ static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 }
 #define rdtscl(low)                                             \
-        ((low) = (u32)native_read_tsc())
+        ((low) = (u32)__native_read_tsc())
 #define rdtscll(val)                                            \
-        ((val) = native_read_tsc())
+        ((val) = __native_read_tsc())
 #define rdpmc(counter, low, high)                       \
 do {                                                    \
diff --git a/arch/x86/include/asm/numaq/wakecpu.h b/arch/x86/include/asm/numaq/wakecpu.h
index c577bda5b1c5..6f499df8eddb 100644
--- a/arch/x86/include/asm/numaq/wakecpu.h
+++ b/arch/x86/include/asm/numaq/wakecpu.h
@@ -3,12 +3,8 @@
 /* This file copes with machines that wakeup secondary CPUs by NMIs */
-#define WAKE_SECONDARY_VIA_NMI
+#define TRAMPOLINE_PHYS_LOW (0x8)
+#define TRAMPOLINE_PHYS_HIGH (0xa)
-#define TRAMPOLINE_LOW phys_to_virt(0x8)
-#define TRAMPOLINE_HIGH phys_to_virt(0xa)
-#define boot_cpu_apicid boot_cpu_logical_apicid
 /* We don't do anything here because we use NMI's to boot instead */
 static inline void wait_for_init_deassert(atomic_t *deassert)
@@ -27,17 +23,23 @@ static inline void smp_callin_clear_local_apic(void)
 static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
 {
        printk("Storing NMI vector\n");
-        *high = *((volatile unsigned short *) TRAMPOLINE_HIGH);
+        *high =
-        *low = *((volatile unsigned short *) TRAMPOLINE_LOW);
+          *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH));
+        *low =
+          *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW));
 }
 static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
 {
        printk("Restoring NMI vector\n");
-        *((volatile unsigned short *) TRAMPOLINE_HIGH) = *high;
+        *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
-        *((volatile unsigned short *) TRAMPOLINE_LOW) = *low;
+                                                                 *high;
+        *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
+                                                                 *low;
 }
-#define inquire_remote_apic(apicid) {}
+static inline void inquire_remote_apic(int apicid)
+{
+}
 #endif /* __ASM_NUMAQ_WAKECPU_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 875b38edf193..647781298e7e 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -19,6 +19,8 @@ struct pci_sysdata {
 };
 extern int pci_routeirq;
+extern int noioapicquirk;
+extern int noioapicreroute;
 /* scan a bus after allocating a pci_sysdata for it */
 extern struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops,
diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h
index 5b28995d664e..d02d936840a3 100644
--- a/arch/x86/include/asm/pci_64.h
+++ b/arch/x86/include/asm/pci_64.h
@@ -34,8 +34,6 @@ extern void pci_iommu_alloc(void);
 */
 #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
-#if defined(CONFIG_GART_IOMMU) || defined(CONFIG_CALGARY_IOMMU)
 #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       \
        dma_addr_t ADDR_NAME;
 #define DECLARE_PCI_UNMAP_LEN(LEN_NAME)         \
@@ -49,18 +47,6 @@ extern void pci_iommu_alloc(void);
 #define pci_unmap_len_set(PTR, LEN_NAME, VAL)           \
        (((PTR)->LEN_NAME) = (VAL))
-#else
-/* No IOMMU */
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)
-#define pci_unmap_addr(PTR, ADDR_NAME)          (0)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0)
-#define pci_unmap_len(PTR, LEN_NAME)            (0)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL)   do { } while (0)
-#endif
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_PCI_64_H */
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index b17edfd23628..e0d199fe1d83 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -56,23 +56,55 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
 #define pte_none(x)             (!(x).pte_low)
 /*
- * Bits 0, 6 and 7 are taken, split up the 29 bits of offset
+ * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken,
- * into this range:
+ * split up the 29 bits of offset into this range:
 */
 #define PTE_FILE_MAX_BITS       29
+#define PTE_FILE_SHIFT1         (_PAGE_BIT_PRESENT + 1)
+#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
+#define PTE_FILE_SHIFT2         (_PAGE_BIT_FILE + 1)
+#define PTE_FILE_SHIFT3         (_PAGE_BIT_PROTNONE + 1)
+#else
+#define PTE_FILE_SHIFT2         (_PAGE_BIT_PROTNONE + 1)
+#define PTE_FILE_SHIFT3         (_PAGE_BIT_FILE + 1)
+#endif
+#define PTE_FILE_BITS1          (PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1)
+#define PTE_FILE_BITS2          (PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1)
 #define pte_to_pgoff(pte)                                               \
-        ((((pte).pte_low >> 1) & 0x1f) + (((pte).pte_low >> 8) << 5))
+        ((((pte).pte_low >> PTE_FILE_SHIFT1)                            \
+          & ((1U << PTE_FILE_BITS1) - 1))                               \
+         + ((((pte).pte_low >> PTE_FILE_SHIFT2)                         \
+             & ((1U << PTE_FILE_BITS2) - 1)) << PTE_FILE_BITS1)         \
+         + (((pte).pte_low >> PTE_FILE_SHIFT3)                          \
+            << (PTE_FILE_BITS1 + PTE_FILE_BITS2)))
 #define pgoff_to_pte(off)                                               \
-        ((pte_t) { .pte_low = (((off) & 0x1f) << 1) +                   \
+        ((pte_t) { .pte_low =                                           \
-                        (((off) >> 5) << 8) + _PAGE_FILE })
+         (((off) & ((1U << PTE_FILE_BITS1) - 1)) << PTE_FILE_SHIFT1)    \
+         + ((((off) >> PTE_FILE_BITS1) & ((1U << PTE_FILE_BITS2) - 1))  \
+            << PTE_FILE_SHIFT2)                                         \
+         + (((off) >> (PTE_FILE_BITS1 + PTE_FILE_BITS2))                \
+            << PTE_FILE_SHIFT3)                                         \
+         + _PAGE_FILE })
 /* Encode and de-code a swap entry */
-#define __swp_type(x)                   (((x).val >> 1) & 0x1f)
+#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
-#define __swp_offset(x)                 ((x).val >> 8)
+#define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
-#define __swp_entry(type, offset)                               \
+#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
-        ((swp_entry_t) { ((type) << 1) | ((offset) << 8) })
+#else
+#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1)
+#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1)
+#endif
+#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
+#define __swp_type(x)                   (((x).val >> (_PAGE_BIT_PRESENT + 1)) \
+                                         & ((1U << SWP_TYPE_BITS) - 1))
+#define __swp_offset(x)                 ((x).val >> SWP_OFFSET_SHIFT)
+#define __swp_entry(type, offset)       ((swp_entry_t) { \
+                                         ((type) << (_PAGE_BIT_PRESENT + 1)) \
+                                         | ((offset) << SWP_OFFSET_SHIFT) })
 #define __pte_to_swp_entry(pte)         ((swp_entry_t) { (pte).pte_low })
 #define __swp_entry_to_pte(x)           ((pte_t) { .pte = (x).val })
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 52597aeadfff..447da43cddb3 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -166,6 +166,7 @@ static inline int pte_none(pte_t pte)
 #define PTE_FILE_MAX_BITS       32
 /* Encode and de-code a swap entry */
+#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5)
 #define __swp_type(x)                   (((x).val) & 0x1f)
 #define __swp_offset(x)                 ((x).val >> 5)
 #define __swp_entry(type, offset)       ((swp_entry_t){(type) | (offset) << 5})
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index c012f3b11671..83e69f4a37f0 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -10,7 +10,6 @@
 #define _PAGE_BIT_PCD           4       /* page cache disabled */
 #define _PAGE_BIT_ACCESSED      5       /* was accessed (raised by CPU) */
 #define _PAGE_BIT_DIRTY         6       /* was written to (raised by CPU) */
-#define _PAGE_BIT_FILE          6
 #define _PAGE_BIT_PSE           7       /* 4 MB (or 2MB) page */
 #define _PAGE_BIT_PAT           7       /* on 4KB pages */
 #define _PAGE_BIT_GLOBAL        8       /* Global TLB entry PPro+ */
@@ -22,6 +21,12 @@
 #define _PAGE_BIT_CPA_TEST      _PAGE_BIT_UNUSED1
 #define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
+/* If _PAGE_BIT_PRESENT is clear, we use these: */
+/* - if the user mapped it with PROT_NONE; pte_present gives true */
+#define _PAGE_BIT_PROTNONE      _PAGE_BIT_GLOBAL
+/* - set: nonlinear file mapping, saved PTE; unset:swap */
+#define _PAGE_BIT_FILE          _PAGE_BIT_DIRTY
 #define _PAGE_PRESENT   (_AT(pteval_t, 1) << _PAGE_BIT_PRESENT)
 #define _PAGE_RW        (_AT(pteval_t, 1) << _PAGE_BIT_RW)
 #define _PAGE_USER      (_AT(pteval_t, 1) << _PAGE_BIT_USER)
@@ -46,11 +51,8 @@
 #define _PAGE_NX        (_AT(pteval_t, 0))
 #endif
-/* If _PAGE_PRESENT is clear, we use these: */
+#define _PAGE_FILE      (_AT(pteval_t, 1) << _PAGE_BIT_FILE)
-#define _PAGE_FILE      _PAGE_DIRTY     /* nonlinear file mapping,
+#define _PAGE_PROTNONE  (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
-                                         * saved PTE; unset:swap */
-#define _PAGE_PROTNONE  _PAGE_PSE       /* if the user mapped it with PROT_NONE;
-                                           pte_present gives true */
 #define _PAGE_TABLE     (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |        \
                         _PAGE_ACCESSED | _PAGE_DIRTY)
@@ -158,8 +160,19 @@
 #define PGD_IDENT_ATTR   0x001          /* PRESENT (no other attributes) */
 #endif
+/*
+ * Macro to mark a page protection value as UC-
+ */
+#define pgprot_noncached(prot)                                  \
+        ((boot_cpu_data.x86 > 3)                                \
+         ? (__pgprot(pgprot_val(prot) | _PAGE_CACHE_UC_MINUS))  \
+         : (prot))
 #ifndef __ASSEMBLY__
+#define pgprot_writecombine     pgprot_writecombine
+extern pgprot_t pgprot_writecombine(pgprot_t prot);
 /*
 * ZERO_PAGE is a global shared page that is always zero: used
 * for zero-mapped memory areas etc..
@@ -329,6 +342,9 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 #define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
 #ifndef __ASSEMBLY__
+/* Indicate that x86 has its own track and untrack pfn vma functions */
+#define __HAVE_PFNMAP_TRACKING
 #define __HAVE_PHYS_MEM_ACCESS_PROT
 struct file;
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index f9d5889b336b..72b020deb46b 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -101,15 +101,6 @@ extern unsigned long pg0[];
 #endif
 /*
- * Macro to mark a page protection value as "uncacheable".
- * On processors which do not support it, this is a no-op.
- */
-#define pgprot_noncached(prot)                                  \
-        ((boot_cpu_data.x86 > 3)                                \
-         ? (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT)) \
-         : (prot))
-/*
 * Conversion functions: convert a page and protection to a page entry,
 * and a page entry and page directory to the page they refer to.
 */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 545a0e042bb2..ba09289accaa 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -146,7 +146,7 @@ static inline void native_pgd_clear(pgd_t *pgd)
 #define PGDIR_MASK      (~(PGDIR_SIZE - 1))
-#define MAXMEM           _AC(0x00003fffffffffff, UL)
+#define MAXMEM           _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
 #define VMALLOC_START    _AC(0xffffc20000000000, UL)
 #define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
 #define VMEMMAP_START    _AC(0xffffe20000000000, UL)
@@ -177,12 +177,6 @@ static inline int pmd_bad(pmd_t pmd)
 #define pages_to_mb(x)  ((x) >> (20 - PAGE_SHIFT))   /* FIXME: is this right? */
 /*
- * Macro to mark a page protection value as "uncacheable".
- */
-#define pgprot_noncached(prot)                                  \
-        (__pgprot(pgprot_val((prot)) | _PAGE_PCD | _PAGE_PWT))
-/*
 * Conversion functions: convert a page and protection to a page entry,
 * and a page entry and page directory to the page they refer to.
 */
@@ -250,10 +244,22 @@ static inline int pud_large(pud_t pte)
 extern int direct_gbpages;
 /* Encode and de-code a swap entry */
-#define __swp_type(x)                   (((x).val >> 1) & 0x3f)
+#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
-#define __swp_offset(x)                 ((x).val >> 8)
+#define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
-#define __swp_entry(type, offset)       ((swp_entry_t) { ((type) << 1) | \
+#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
-                                                         ((offset) << 8) })
+#else
+#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1)
+#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1)
+#endif
+#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
+#define __swp_type(x)                   (((x).val >> (_PAGE_BIT_PRESENT + 1)) \
+                                         & ((1U << SWP_TYPE_BITS) - 1))
+#define __swp_offset(x)                 ((x).val >> SWP_OFFSET_SHIFT)
+#define __swp_entry(type, offset)       ((swp_entry_t) { \
+                                         ((type) << (_PAGE_BIT_PRESENT + 1)) \
+                                         | ((offset) << SWP_OFFSET_SHIFT) })
 #define __pte_to_swp_entry(pte)         ((swp_entry_t) { pte_val((pte)) })
 #define __swp_entry_to_pte(x)           ((pte_t) { .pte = (x).val })
diff --git a/arch/x86/include/asm/prctl.h b/arch/x86/include/asm/prctl.h
index fe681147a4f7..a8894647dd9a 100644
--- a/arch/x86/include/asm/prctl.h
+++ b/arch/x86/include/asm/prctl.h
@@ -6,5 +6,8 @@
 #define ARCH_GET_FS 0x1003
 #define ARCH_GET_GS 0x1004
+#ifdef CONFIG_X86_64
+extern long sys_arch_prctl(int, unsigned long);
+#endif /* CONFIG_X86_64 */
 #endif /* _ASM_X86_PRCTL_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 5ca01e383269..a570eafa4755 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -110,6 +110,7 @@ struct cpuinfo_x86 {
        /* Index into per_cpu list: */
        u16                     cpu_index;
 #endif
+        unsigned int            x86_hyper_vendor;
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 #define X86_VENDOR_INTEL        0
@@ -123,6 +124,9 @@ struct cpuinfo_x86 {
 #define X86_VENDOR_UNKNOWN      0xff
+#define X86_HYPER_VENDOR_NONE  0
+#define X86_HYPER_VENDOR_VMWARE 1
 /*
 * capabilities of CPUs
 */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index d1531c8480b7..eefb0594b058 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -271,8 +271,6 @@ extern int do_get_thread_area(struct task_struct *p, int idx,
 extern int do_set_thread_area(struct task_struct *p, int idx,
                              struct user_desc __user *info, int can_allocate);
-#define __ARCH_WANT_COMPAT_SYS_PTRACE
 #endif /* __KERNEL__ */
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index df7710354f85..562d4fd31ba8 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_REBOOT_H
 #define _ASM_X86_REBOOT_H
+#include <linux/kdebug.h>
 struct pt_regs;
 struct machine_ops {
@@ -18,4 +20,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs);
 void native_machine_shutdown(void);
 void machine_real_restart(const unsigned char *code, int length);
+typedef void (*nmi_shootdown_cb)(int, struct die_args*);
+void nmi_shootdown_cpus(nmi_shootdown_cb callback);
 #endif /* _ASM_X86_REBOOT_H */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 1ed8b2e80727..4fcd53fd5f43 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -20,6 +20,8 @@ static inline void visws_early_detect(void) { }
 static inline int is_visws_box(void) { return 0; }
 #endif
+extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
+extern int wakeup_secondary_cpu_via_init(int apicid, unsigned long start_eip);
 /*
 * Any setup quirks to be performed?
 */
@@ -43,6 +45,7 @@ struct x86_quirks {
        void (*smp_read_mpc_oem)(struct mp_config_oemtable *oemtable,
                                    unsigned short oemsize);
        int (*setup_ioapic_ids)(void);
+        int (*update_genapic)(void);
 };
 extern struct x86_quirks *x86_quirks;
diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h
new file mode 100644
index 000000000000..4e0fe26d27d3
--- /dev/null
+++ b/arch/x86/include/asm/sigframe.h
@@ -0,0 +1,70 @@
+#ifndef _ASM_X86_SIGFRAME_H
+#define _ASM_X86_SIGFRAME_H
+#include <asm/sigcontext.h>
+#include <asm/siginfo.h>
+#include <asm/ucontext.h>
+#ifdef CONFIG_X86_32
+#define sigframe_ia32           sigframe
+#define rt_sigframe_ia32        rt_sigframe
+#define sigcontext_ia32         sigcontext
+#define _fpstate_ia32           _fpstate
+#define ucontext_ia32           ucontext
+#else /* !CONFIG_X86_32 */
+#ifdef CONFIG_IA32_EMULATION
+#include <asm/ia32.h>
+#endif /* CONFIG_IA32_EMULATION */
+#endif /* CONFIG_X86_32 */
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+struct sigframe_ia32 {
+        u32 pretcode;
+        int sig;
+        struct sigcontext_ia32 sc;
+        /*
+         * 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_ia32 fpstate_unused;
+#ifdef CONFIG_IA32_EMULATION
+        unsigned int extramask[_COMPAT_NSIG_WORDS-1];
+#else /* !CONFIG_IA32_EMULATION */
+        unsigned long extramask[_NSIG_WORDS-1];
+#endif /* CONFIG_IA32_EMULATION */
+        char retcode[8];
+        /* fp state follows here */
+};
+struct rt_sigframe_ia32 {
+        u32 pretcode;
+        int sig;
+        u32 pinfo;
+        u32 puc;
+#ifdef CONFIG_IA32_EMULATION
+        compat_siginfo_t info;
+#else /* !CONFIG_IA32_EMULATION */
+        struct siginfo info;
+#endif /* CONFIG_IA32_EMULATION */
+        struct ucontext_ia32 uc;
+        char retcode[8];
+        /* fp state follows here */
+};
+#endif /* defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) */
+#ifdef CONFIG_X86_64
+struct rt_sigframe {
+        char __user *pretcode;
+        struct ucontext uc;
+        struct siginfo info;
+        /* fp state follows here */
+};
+#endif /* CONFIG_X86_64 */
+#endif /* _ASM_X86_SIGFRAME_H */
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 96ac44f275da..7761a5d554bb 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -121,6 +121,10 @@ typedef unsigned long sigset_t;
 #ifndef __ASSEMBLY__
+# ifdef __KERNEL__
+extern void do_notify_resume(struct pt_regs *, void *, __u32);
+# endif /* __KERNEL__ */
 #ifdef __i386__
 # ifdef __KERNEL__
 struct old_sigaction {
@@ -141,8 +145,6 @@ struct k_sigaction {
        struct sigaction sa;
 };
-extern void do_notify_resume(struct pt_regs *, void *, __u32);
 # else /* __KERNEL__ */
 /* Here we must cater to libcs that poke about in kernel headers.  */
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index be44f7dab395..e3cc3c063ec5 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -27,7 +27,7 @@
 #else /* CONFIG_X86_32 */
 # define SECTION_SIZE_BITS      27 /* matt - 128 is convenient right now */
 # define MAX_PHYSADDR_BITS      44
-# define MAX_PHYSMEM_BITS       44
+# define MAX_PHYSMEM_BITS       44 /* Can be max 45 bits */
 #endif
 #endif /* CONFIG_SPARSEMEM */
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 87803da44010..9c6797c3e56c 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -19,6 +19,13 @@
 /* kernel/ioport.c */
 asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
+/* kernel/ldt.c */
+asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
+/* kernel/tls.c */
+asmlinkage int sys_set_thread_area(struct user_desc __user *);
+asmlinkage int sys_get_thread_area(struct user_desc __user *);
 /* X86_32 only */
 #ifdef CONFIG_X86_32
 /* kernel/process_32.c */
@@ -33,14 +40,11 @@ asmlinkage int sys_sigaction(int, const struct old_sigaction __user *,
                             struct old_sigaction __user *);
 asmlinkage int sys_sigaltstack(unsigned long);
 asmlinkage unsigned long sys_sigreturn(unsigned long);
-asmlinkage int sys_rt_sigreturn(unsigned long);
+asmlinkage int sys_rt_sigreturn(struct pt_regs);
 /* kernel/ioport.c */
 asmlinkage long sys_iopl(unsigned long);
-/* kernel/ldt.c */
-asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
 /* kernel/sys_i386_32.c */
 asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long,
                          unsigned long, unsigned long, unsigned long);
@@ -54,10 +58,6 @@ asmlinkage int sys_uname(struct old_utsname __user *);
 struct oldold_utsname;
 asmlinkage int sys_olduname(struct oldold_utsname __user *);
-/* kernel/tls.c */
-asmlinkage int sys_set_thread_area(struct user_desc __user *);
-asmlinkage int sys_get_thread_area(struct user_desc __user *);
 /* kernel/vm86_32.c */
 asmlinkage int sys_vm86old(struct pt_regs);
 asmlinkage int sys_vm86(struct pt_regs);
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 2ed3f0f44ff7..8e626ea33a1a 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -17,12 +17,12 @@
 # define AT_VECTOR_SIZE_ARCH 1
 #endif
-#ifdef CONFIG_X86_32
 struct task_struct; /* one of the stranger aspects of C forward declarations */
 struct task_struct *__switch_to(struct task_struct *prev,
                                struct task_struct *next);
+#ifdef CONFIG_X86_32
 /*
 * Saving eflags is important. It switches not only IOPL between tasks,
 * it also protects other tasks from NT leaking through sysenter etc.
@@ -314,6 +314,8 @@ extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
 void default_idle(void);
+void stop_this_cpu(void *dummy);
 /*
 * Force strict CPU ordering.
 * And yes, this is required on UP too when we're talking
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index e44d379faad2..8dbc57390d25 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -24,7 +24,7 @@ struct exec_domain;
 struct thread_info {
        struct task_struct      *task;          /* main task structure */
        struct exec_domain      *exec_domain;   /* execution domain */
-        unsigned long           flags;          /* low level flags */
+        __u32                   flags;          /* low level flags */
        __u32                   status;         /* thread synchronous flags */
        __u32                   cpu;            /* current CPU */
        int                     preempt_count;  /* 0 => preemptable,
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 4850e4b02b61..ff386ff50ed7 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -239,7 +239,7 @@ struct pci_bus;
 void set_pci_bus_resources_arch_default(struct pci_bus *b);
 #ifdef CONFIG_SMP
-#define mc_capable()                    (boot_cpu_data.x86_max_cores > 1)
+#define mc_capable()    (cpus_weight(per_cpu(cpu_core_map, 0)) != nr_cpu_ids)
 #define smt_capable()                   (smp_num_siblings > 1)
 #endif
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
index fa0d79facdbc..780ba0ab94f9 100644
--- a/arch/x86/include/asm/trampoline.h
+++ b/arch/x86/include/asm/trampoline.h
@@ -3,6 +3,7 @@
 #ifndef __ASSEMBLY__
+#ifdef CONFIG_X86_TRAMPOLINE
 /*
 * Trampoline 80x86 program as an array.
 */
@@ -13,8 +14,14 @@ extern unsigned char *trampoline_base;
 extern unsigned long init_rsp;
 extern unsigned long initial_code;
+#define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE)
 #define TRAMPOLINE_BASE 0x6000
 extern unsigned long setup_trampoline(void);
+extern void __init reserve_trampoline_memory(void);
+#else
+static inline void reserve_trampoline_memory(void) {};
+#endif /* CONFIG_X86_TRAMPOLINE */
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 45dee286e45c..2ee0a3bceedf 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -46,6 +46,10 @@ dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *, long);
 dotraplinkage void do_invalid_TSS(struct pt_regs *, long);
 dotraplinkage void do_segment_not_present(struct pt_regs *, long);
 dotraplinkage void do_stack_segment(struct pt_regs *, long);
+#ifdef CONFIG_X86_64
+dotraplinkage void do_double_fault(struct pt_regs *, long);
+asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *);
+#endif
 dotraplinkage void do_general_protection(struct pt_regs *, long);
 dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
 dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long);
@@ -72,10 +76,13 @@ static inline int get_si_code(unsigned long condition)
 extern int panic_on_unrecovered_nmi;
 extern int kstack_depth_to_print;
-#ifdef CONFIG_X86_32
 void math_error(void __user *);
-unsigned long patch_espfix_desc(unsigned long, unsigned long);
 asmlinkage void math_emulate(long);
+#ifdef CONFIG_X86_32
+unsigned long patch_espfix_desc(unsigned long, unsigned long);
+#else
+asmlinkage void smp_thermal_interrupt(void);
+asmlinkage void mce_threshold_interrupt(void);
 #endif
 #endif /* _ASM_X86_TRAPS_H */
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 9cd83a8e40d5..38ae163cc91b 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -34,8 +34,6 @@ static inline cycles_t get_cycles(void)
 static __always_inline cycles_t vget_cycles(void)
 {
-        cycles_t cycles;
        /*
         * We only do VDSOs on TSC capable CPUs, so this shouldnt
         * access boot_cpu_data (which is not VDSO-safe):
@@ -44,11 +42,7 @@ static __always_inline cycles_t vget_cycles(void)
        if (!cpu_has_tsc)
                return 0;
 #endif
-        rdtsc_barrier();
+        return (cycles_t)__native_read_tsc();
-        cycles = (cycles_t)__native_read_tsc();
-        rdtsc_barrier();
-        return cycles;
 }
 extern void tsc_init(void);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 35c54921b2e4..580c3ee6c58c 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -350,14 +350,14 @@ do {									\
 #define __put_user_nocheck(x, ptr, size)                        \
 ({                                                              \
-        long __pu_err;                                          \
+        int __pu_err;                                           \
        __put_user_size((x), (ptr), (size), __pu_err, -EFAULT); \
        __pu_err;                                               \
 })
 #define __get_user_nocheck(x, ptr, size)                                \
 ({                                                                      \
-        long __gu_err;                                                  \
+        int __gu_err;                                                   \
        unsigned long __gu_val;                                         \
        __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);    \
        (x) = (__force __typeof__(*(ptr)))__gu_val;                     \
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 664f15280f14..f8cfd00db450 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -46,7 +46,7 @@ int __copy_from_user(void *dst, const void __user *src, unsigned size)
                return ret;
        case 10:
                __get_user_asm(*(u64 *)dst, (u64 __user *)src,
-                               ret, "q", "", "=r", 16);
+                               ret, "q", "", "=r", 10);
                if (unlikely(ret))
                        return ret;
                __get_user_asm(*(u16 *)(8 + (char *)dst),
diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h
index d931d3b7e6f7..7ed17ff502b9 100644
--- a/arch/x86/include/asm/uv/bios.h
+++ b/arch/x86/include/asm/uv/bios.h
@@ -32,13 +32,18 @@
 enum uv_bios_cmd {
        UV_BIOS_COMMON,
        UV_BIOS_GET_SN_INFO,
-        UV_BIOS_FREQ_BASE
+        UV_BIOS_FREQ_BASE,
+        UV_BIOS_WATCHLIST_ALLOC,
+        UV_BIOS_WATCHLIST_FREE,
+        UV_BIOS_MEMPROTECT,
+        UV_BIOS_GET_PARTITION_ADDR
 };
 /*
 * Status values returned from a BIOS call.
 */
 enum {
+        BIOS_STATUS_MORE_PASSES         =  1,
        BIOS_STATUS_SUCCESS             =  0,
        BIOS_STATUS_UNIMPLEMENTED       = -ENOSYS,
        BIOS_STATUS_EINVAL              = -EINVAL,
@@ -71,6 +76,21 @@ union partition_info_u {
        };
 };
+union uv_watchlist_u {
+        u64     val;
+        struct {
+                u64     blade   : 16,
+                        size    : 32,
+                        filler  : 16;
+        };
+};
+enum uv_memprotect {
+        UV_MEMPROT_RESTRICT_ACCESS,
+        UV_MEMPROT_ALLOW_AMO,
+        UV_MEMPROT_ALLOW_RW
+};
 /*
 * bios calls have 6 parameters
 */
@@ -80,14 +100,20 @@ extern s64 uv_bios_call_reentrant(enum uv_bios_cmd, u64, u64, u64, u64, u64);
 extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *);
 extern s64 uv_bios_freq_base(u64, u64 *);
+extern int uv_bios_mq_watchlist_alloc(int, unsigned long, unsigned int,
+                                        unsigned long *);
+extern int uv_bios_mq_watchlist_free(int, int);
+extern s64 uv_bios_change_memprotect(u64, u64, enum uv_memprotect);
+extern s64 uv_bios_reserved_page_pa(u64, u64 *, u64 *, u64 *);
 extern void uv_bios_init(void);
+extern unsigned long sn_rtc_cycles_per_second;
 extern int uv_type;
 extern long sn_partition_id;
-extern long uv_coherency_id;
+extern long sn_coherency_id;
-extern long uv_region_size;
+extern long sn_region_size;
-#define partition_coherence_id()        (uv_coherency_id)
+#define partition_coherence_id()        (sn_coherency_id)
 extern struct kobject *sgi_uv_kobj;     /* /sys/firmware/sgi_uv */
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 7a5782610b2b..777327ef05c1 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -113,25 +113,37 @@
 */
 #define UV_MAX_NASID_VALUE      (UV_MAX_NUMALINK_NODES * 2)
+struct uv_scir_s {
+        struct timer_list timer;
+        unsigned long   offset;
+        unsigned long   last;
+        unsigned long   idle_on;
+        unsigned long   idle_off;
+        unsigned char   state;
+        unsigned char   enabled;
+};
 /*
 * The following defines attributes of the HUB chip. These attributes are
 * frequently referenced and are kept in the per-cpu data areas of each cpu.
 * They are kept together in a struct to minimize cache misses.
 */
 struct uv_hub_info_s {
-        unsigned long   global_mmr_base;
+        unsigned long           global_mmr_base;
-        unsigned long   gpa_mask;
+        unsigned long           gpa_mask;
-        unsigned long   gnode_upper;
+        unsigned long           gnode_upper;
-        unsigned long   lowmem_remap_top;
+        unsigned long           lowmem_remap_top;
-        unsigned long   lowmem_remap_base;
+        unsigned long           lowmem_remap_base;
-        unsigned short  pnode;
+        unsigned short          pnode;
-        unsigned short  pnode_mask;
+        unsigned short          pnode_mask;
-        unsigned short  coherency_domain_number;
+        unsigned short          coherency_domain_number;
-        unsigned short  numa_blade_id;
+        unsigned short          numa_blade_id;
-        unsigned char   blade_processor_id;
+        unsigned char           blade_processor_id;
-        unsigned char   m_val;
+        unsigned char           m_val;
-        unsigned char   n_val;
+        unsigned char           n_val;
+        struct uv_scir_s        scir;
 };
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define uv_hub_info             (&__get_cpu_var(__uv_hub_info))
 #define uv_cpu_hub_info(cpu)    (&per_cpu(__uv_hub_info, cpu))
@@ -163,6 +175,30 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define UV_APIC_PNODE_SHIFT     6
+/* Local Bus from cpu's perspective */
+#define LOCAL_BUS_BASE          0x1c00000
+#define LOCAL_BUS_SIZE          (4 * 1024 * 1024)
+/*
+ * System Controller Interface Reg
+ *
+ * Note there are NO leds on a UV system.  This register is only
+ * used by the system controller to monitor system-wide operation.
+ * There are 64 regs per node.  With Nahelem cpus (2 cores per node,
+ * 8 cpus per core, 2 threads per cpu) there are 32 cpu threads on
+ * a node.
+ *
+ * The window is located at top of ACPI MMR space
+ */
+#define SCIR_WINDOW_COUNT       64
+#define SCIR_LOCAL_MMR_BASE     (LOCAL_BUS_BASE + \
+                                 LOCAL_BUS_SIZE - \
+                                 SCIR_WINDOW_COUNT)
+#define SCIR_CPU_HEARTBEAT      0x01    /* timer interrupt */
+#define SCIR_CPU_ACTIVITY       0x02    /* not idle */
+#define SCIR_CPU_HB_INTERVAL    (HZ)    /* once per second */
 /*
 * Macros for converting between kernel virtual addresses, socket local physical
 * addresses, and UV global physical addresses.
@@ -174,7 +210,7 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
 {
        if (paddr < uv_hub_info->lowmem_remap_top)
-                paddr += uv_hub_info->lowmem_remap_base;
+                paddr |= uv_hub_info->lowmem_remap_base;
        return paddr | uv_hub_info->gnode_upper;
 }
@@ -182,19 +218,7 @@ static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
 /* socket virtual --> UV global physical address */
 static inline unsigned long uv_gpa(void *v)
 {
-        return __pa(v) | uv_hub_info->gnode_upper;
+        return uv_soc_phys_ram_to_gpa(__pa(v));
-}
-/* socket virtual --> UV global physical address */
-static inline void *uv_vgpa(void *v)
-{
-        return (void *)uv_gpa(v);
-}
-/* UV global physical address --> socket virtual */
-static inline void *uv_va(unsigned long gpa)
-{
-        return __va(gpa & uv_hub_info->gpa_mask);
 }
 /* pnode, offset --> socket virtual */
@@ -277,6 +301,16 @@ static inline void uv_write_local_mmr(unsigned long offset, unsigned long val)
        *uv_local_mmr_address(offset) = val;
 }
+static inline unsigned char uv_read_local_mmr8(unsigned long offset)
+{
+        return *((unsigned char *)uv_local_mmr_address(offset));
+}
+static inline void uv_write_local_mmr8(unsigned long offset, unsigned char val)
+{
+        *((unsigned char *)uv_local_mmr_address(offset)) = val;
+}
 /*
 * Structures and definitions for converting between cpu, node, pnode, and blade
 * numbers.
@@ -351,5 +385,20 @@ static inline int uv_num_possible_blades(void)
        return uv_possible_blades;
 }
-#endif /* _ASM_X86_UV_UV_HUB_H */
+/* Update SCIR state */
+static inline void uv_set_scir_bits(unsigned char value)
+{
+        if (uv_hub_info->scir.state != value) {
+                uv_hub_info->scir.state = value;
+                uv_write_local_mmr8(uv_hub_info->scir.offset, value);
+        }
+}
+static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
+{
+        if (uv_cpu_hub_info(cpu)->scir.state != value) {
+                uv_cpu_hub_info(cpu)->scir.state = value;
+                uv_write_local_mmr8(uv_cpu_hub_info(cpu)->scir.offset, value);
+        }
+}
+#endif /* _ASM_X86_UV_UV_HUB_H */
diff --git a/arch/x86/include/asm/vmi.h b/arch/x86/include/asm/vmi.h
index b7c0dea119fe..61e08c0a2907 100644
--- a/arch/x86/include/asm/vmi.h
+++ b/arch/x86/include/asm/vmi.h
@@ -223,9 +223,15 @@ struct pci_header {
 } __attribute__((packed));
 /* Function prototypes for bootstrapping */
+#ifdef CONFIG_VMI
 extern void vmi_init(void);
+extern void vmi_activate(void);
 extern void vmi_bringup(void);
-extern void vmi_apply_boot_page_allocations(void);
+#else
+static inline void vmi_init(void) {}
+static inline void vmi_activate(void) {}
+static inline void vmi_bringup(void) {}
+#endif
 /* State needed to start an application processor in an SMP system. */
 struct vmi_ap_state {
diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
new file mode 100644
index 000000000000..c11b7e100d83
--- /dev/null
+++ b/arch/x86/include/asm/vmware.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2008, VMware, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#ifndef ASM_X86__VMWARE_H
+#define ASM_X86__VMWARE_H
+extern unsigned long vmware_get_tsc_khz(void);
+extern int vmware_platform(void);
+extern void vmware_set_feature_bits(struct cpuinfo_x86 *c);
+#endif
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 3f6000d95fe2..5e79ca694326 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -33,8 +33,14 @@
 #ifndef _ASM_X86_XEN_HYPERCALL_H
 #define _ASM_X86_XEN_HYPERCALL_H
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/types.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index a38d25ac87d2..81fbd735aec4 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -33,39 +33,10 @@
 #ifndef _ASM_X86_XEN_HYPERVISOR_H
 #define _ASM_X86_XEN_HYPERVISOR_H
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <xen/interface/xen.h>
-#include <xen/interface/version.h>
-#include <asm/ptrace.h>
-#include <asm/page.h>
-#include <asm/desc.h>
-#if defined(__i386__)
-#  ifdef CONFIG_X86_PAE
-#   include <asm-generic/pgtable-nopud.h>
-#  else
-#   include <asm-generic/pgtable-nopmd.h>
-#  endif
-#endif
-#include <asm/xen/hypercall.h>
 /* arch/i386/kernel/setup.c */
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
-/* arch/i386/mach-xen/evtchn.c */
-/* Force a proper event-channel callback from Xen. */
-extern void force_evtchn_callback(void);
-/* Turn jiffies into Xen system time. */
-u64 jiffies_to_st(unsigned long jiffies);
-#define MULTI_UVMFLAGS_INDEX 3
-#define MULTI_UVMDOMID_INDEX 4
 enum xen_domain_type {
        XEN_NATIVE,
        XEN_PV_DOMAIN,
@@ -74,9 +45,15 @@ enum xen_domain_type {
 extern enum xen_domain_type xen_domain_type;
+#ifdef CONFIG_XEN
 #define xen_domain()            (xen_domain_type != XEN_NATIVE)
-#define xen_pv_domain()         (xen_domain_type == XEN_PV_DOMAIN)
+#else
+#define xen_domain()            (0)
+#endif
+#define xen_pv_domain()         (xen_domain() && xen_domain_type == XEN_PV_DOMAIN)
+#define xen_hvm_domain()        (xen_domain() && xen_domain_type == XEN_HVM_DOMAIN)
 #define xen_initial_domain()    (xen_pv_domain() && xen_start_info->flags & SIF_INITDOMAIN)
-#define xen_hvm_domain()        (xen_domain_type == XEN_HVM_DOMAIN)
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index bc628998a1b9..7ef617ef1df3 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -1,11 +1,16 @@
 #ifndef _ASM_X86_XEN_PAGE_H
 #define _ASM_X86_XEN_PAGE_H
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
 #include <linux/pfn.h>
 #include <asm/uaccess.h>
+#include <asm/page.h>
 #include <asm/pgtable.h>
+#include <xen/interface/xen.h>
 #include <xen/features.h>
 /* Xen machine address */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index b2077d3fe977..1f208aaee780 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -12,6 +12,7 @@ CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_early_printk.o = -pg
 endif
 #
@@ -23,9 +24,9 @@ CFLAGS_vsyscall_64.o	:= $(PROFILING) -g0 $(nostackp)
 CFLAGS_hpet.o           := $(nostackp)
 CFLAGS_tsc.o            := $(nostackp)
-obj-y                   := process_$(BITS).o signal_$(BITS).o entry_$(BITS).o
+obj-y                   := process_$(BITS).o signal.o entry_$(BITS).o
 obj-y                   += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
-obj-y                   += time_$(BITS).o ioport.o ldt.o
+obj-y                   += time_$(BITS).o ioport.o ldt.o dumpstack.o
 obj-y                   += setup.o i8259.o irqinit_$(BITS).o setup_percpu.o
 obj-$(CONFIG_X86_VISWS) += visws_quirks.o
 obj-$(CONFIG_X86_32)    += probe_roms_32.o
@@ -41,7 +42,7 @@ obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-y                           += process.o
 obj-y                           += i387.o xsave.o
 obj-y                           += ptrace.o
-obj-y                           += ds.o
+obj-$(CONFIG_X86_DS)            += ds.o
 obj-$(CONFIG_X86_32)            += tls.o
 obj-$(CONFIG_IA32_EMULATION)    += tls.o
 obj-y                           += step.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 4c51a2f8fd31..65d0b72777ea 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1360,6 +1360,17 @@ static void __init acpi_process_madt(void)
                        disable_acpi();
                }
        }
+        /*
+         * ACPI supports both logical (e.g. Hyper-Threading) and physical
+         * processors, where MPS only supports physical.
+         */
+        if (acpi_lapic && acpi_ioapic)
+                printk(KERN_INFO "Using ACPI (MADT) for SMP configuration "
+                       "information\n");
+        else if (acpi_lapic)
+                printk(KERN_INFO "Using ACPI for processor (LAPIC) "
+                       "configuration information\n");
 #endif
        return;
 }
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index e4899e0e8787..0a60d60ed036 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -187,6 +187,8 @@ static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
        spin_lock_irqsave(&iommu->lock, flags);
        ret = __iommu_queue_command(iommu, cmd);
+        if (!ret)
+                iommu->need_sync = 1;
        spin_unlock_irqrestore(&iommu->lock, flags);
        return ret;
@@ -210,10 +212,13 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
        cmd.data[0] = CMD_COMPL_WAIT_INT_MASK;
        CMD_SET_TYPE(&cmd, CMD_COMPL_WAIT);
-        iommu->need_sync = 0;
        spin_lock_irqsave(&iommu->lock, flags);
+        if (!iommu->need_sync)
+                goto out;
+        iommu->need_sync = 0;
        ret = __iommu_queue_command(iommu, &cmd);
        if (ret)
@@ -230,8 +235,9 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
        status &= ~MMIO_STATUS_COM_WAIT_INT_MASK;
        writel(status, iommu->mmio_base + MMIO_STATUS_OFFSET);
-        if (unlikely((i == EXIT_LOOP_COUNT) && printk_ratelimit()))
+        if (unlikely(i == EXIT_LOOP_COUNT))
-                printk(KERN_WARNING "AMD IOMMU: Completion wait loop failed\n");
+                panic("AMD IOMMU: Completion wait loop failed\n");
 out:
        spin_unlock_irqrestore(&iommu->lock, flags);
@@ -254,8 +260,6 @@ static int iommu_queue_inv_dev_entry(struct amd_iommu *iommu, u16 devid)
        ret = iommu_queue_command(iommu, &cmd);
-        iommu->need_sync = 1;
        return ret;
 }
@@ -281,8 +285,6 @@ static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu,
        ret = iommu_queue_command(iommu, &cmd);
-        iommu->need_sync = 1;
        return ret;
 }
@@ -343,7 +345,7 @@ static int iommu_map(struct protection_domain *dom,
        u64 __pte, *pte, *page;
        bus_addr  = PAGE_ALIGN(bus_addr);
-        phys_addr = PAGE_ALIGN(bus_addr);
+        phys_addr = PAGE_ALIGN(phys_addr);
        /* only support 512GB address spaces for now */
        if (bus_addr > IOMMU_MAP_SIZE_L3 || !(prot & IOMMU_PROT_MASK))
@@ -599,7 +601,7 @@ static void dma_ops_free_pagetable(struct dma_ops_domain *dma_dom)
                        continue;
                p2 = IOMMU_PTE_PAGE(p1[i]);
-                for (j = 0; j < 512; ++i) {
+                for (j = 0; j < 512; ++j) {
                        if (!IOMMU_PTE_PRESENT(p2[j]))
                                continue;
                        p3 = IOMMU_PTE_PAGE(p2[j]);
@@ -762,8 +764,6 @@ static void set_device_domain(struct amd_iommu *iommu,
        write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
        iommu_queue_inv_dev_entry(iommu, devid);
-        iommu->need_sync = 1;
 }
 /*****************************************************************************
@@ -858,6 +858,9 @@ static int get_device_resources(struct device *dev,
                print_devid(_bdf, 1);
        }
+        if (domain_for_device(_bdf) == NULL)
+                set_device_domain(*iommu, *domain, _bdf);
        return 1;
 }
@@ -908,7 +911,7 @@ static void dma_ops_domain_unmap(struct amd_iommu *iommu,
        if (address >= dom->aperture_size)
                return;
-        WARN_ON(address & 0xfffULL || address > dom->aperture_size);
+        WARN_ON(address & ~PAGE_MASK || address >= dom->aperture_size);
        pte  = dom->pte_pages[IOMMU_PTE_L1_INDEX(address)];
        pte += IOMMU_PTE_L0_INDEX(address);
@@ -920,8 +923,8 @@ static void dma_ops_domain_unmap(struct amd_iommu *iommu,
 /*
 * This function contains common code for mapping of a physically
- * contiguous memory region into DMA address space. It is uses by all
+ * contiguous memory region into DMA address space. It is used by all
- * mapping functions provided by this IOMMU driver.
+ * mapping functions provided with this IOMMU driver.
 * Must be called with the domain lock held.
 */
 static dma_addr_t __map_single(struct device *dev,
@@ -981,7 +984,8 @@ static void __unmap_single(struct amd_iommu *iommu,
        dma_addr_t i, start;
        unsigned int pages;
-        if ((dma_addr == 0) || (dma_addr + size > dma_dom->aperture_size))
+        if ((dma_addr == bad_dma_address) ||
+            (dma_addr + size > dma_dom->aperture_size))
                return;
        pages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
@@ -1031,8 +1035,7 @@ static dma_addr_t map_single(struct device *dev, phys_addr_t paddr,
        if (addr == bad_dma_address)
                goto out;
-        if (unlikely(iommu->need_sync))
+        iommu_completion_wait(iommu);
-                iommu_completion_wait(iommu);
 out:
        spin_unlock_irqrestore(&domain->lock, flags);
@@ -1060,8 +1063,7 @@ static void unmap_single(struct device *dev, dma_addr_t dma_addr,
        __unmap_single(iommu, domain->priv, dma_addr, size, dir);
-        if (unlikely(iommu->need_sync))
+        iommu_completion_wait(iommu);
-                iommu_completion_wait(iommu);
        spin_unlock_irqrestore(&domain->lock, flags);
 }
@@ -1127,8 +1129,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
                        goto unmap;
        }
-        if (unlikely(iommu->need_sync))
+        iommu_completion_wait(iommu);
-                iommu_completion_wait(iommu);
 out:
        spin_unlock_irqrestore(&domain->lock, flags);
@@ -1173,8 +1174,7 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist,
                s->dma_address = s->dma_length = 0;
        }
-        if (unlikely(iommu->need_sync))
+        iommu_completion_wait(iommu);
-                iommu_completion_wait(iommu);
        spin_unlock_irqrestore(&domain->lock, flags);
 }
@@ -1225,8 +1225,7 @@ static void *alloc_coherent(struct device *dev, size_t size,
                goto out;
        }
-        if (unlikely(iommu->need_sync))
+        iommu_completion_wait(iommu);
-                iommu_completion_wait(iommu);
 out:
        spin_unlock_irqrestore(&domain->lock, flags);
@@ -1257,8 +1256,7 @@ static void free_coherent(struct device *dev, size_t size,
        __unmap_single(iommu, domain->priv, dma_addr, size, DMA_BIDIRECTIONAL);
-        if (unlikely(iommu->need_sync))
+        iommu_completion_wait(iommu);
-                iommu_completion_wait(iommu);
        spin_unlock_irqrestore(&domain->lock, flags);
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 30ae2701b3df..c6cc22815d35 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -427,6 +427,10 @@ static u8 * __init alloc_command_buffer(struct amd_iommu *iommu)
        memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
                        &entry, sizeof(entry));
+        /* set head and tail to zero manually */
+        writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
+        writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
        iommu_feature_enable(iommu, CONTROL_CMDBUF_EN);
        return cmd_buf;
@@ -1074,7 +1078,8 @@ int __init amd_iommu_init(void)
                goto free;
        /* IOMMU rlookup table - find the IOMMU for a specific device */
-        amd_iommu_rlookup_table = (void *)__get_free_pages(GFP_KERNEL,
+        amd_iommu_rlookup_table = (void *)__get_free_pages(
+                        GFP_KERNEL | __GFP_ZERO,
                        get_order(rlookup_table_size));
        if (amd_iommu_rlookup_table == NULL)
                goto free;
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index 04a7f960bbc0..20c6e12c0475 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -441,6 +441,7 @@ static void lapic_timer_setup(enum clock_event_mode mode,
                v = apic_read(APIC_LVTT);
                v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
                apic_write(APIC_LVTT, v);
+                apic_write(APIC_TMICT, 0xffffffff);
                break;
        case CLOCK_EVT_MODE_RESUME:
                /* Nothing to do here */
@@ -559,13 +560,13 @@ static int __init calibrate_by_pmtimer(long deltapm, long *delta)
        } else {
                res = (((u64)deltapm) *  mult) >> 22;
                do_div(res, 1000000);
-                printk(KERN_WARNING "APIC calibration not consistent "
+                pr_warning("APIC calibration not consistent "
                        "with PM Timer: %ldms instead of 100ms\n",
                        (long)res);
                /* Correct the lapic counter value */
                res = (((u64)(*delta)) * pm_100ms);
                do_div(res, deltapm);
-                printk(KERN_INFO "APIC delta adjusted to PM-Timer: "
+                pr_info("APIC delta adjusted to PM-Timer: "
                        "%lu (%ld)\n", (unsigned long)res, *delta);
                *delta = (long)res;
        }
@@ -645,8 +646,7 @@ static int __init calibrate_APIC_clock(void)
         */
        if (calibration_result < (1000000 / HZ)) {
                local_irq_enable();
-                printk(KERN_WARNING
+                pr_warning("APIC frequency too slow, disabling apic timer\n");
-                       "APIC frequency too slow, disabling apic timer\n");
                return -1;
        }
@@ -672,13 +672,9 @@ static int __init calibrate_APIC_clock(void)
                while (lapic_cal_loops <= LAPIC_CAL_LOOPS)
                        cpu_relax();
-                local_irq_disable();
                /* Stop the lapic timer */
                lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, levt);
-                local_irq_enable();
                /* Jiffies delta */
                deltaj = lapic_cal_j2 - lapic_cal_j1;
                apic_printk(APIC_VERBOSE, "... jiffies delta = %lu\n", deltaj);
@@ -692,8 +688,7 @@ static int __init calibrate_APIC_clock(void)
                local_irq_enable();
        if (levt->features & CLOCK_EVT_FEAT_DUMMY) {
-                printk(KERN_WARNING
+                pr_warning("APIC timer disabled due to verification failure.\n");
-                       "APIC timer disabled due to verification failure.\n");
                        return -1;
        }
@@ -714,7 +709,7 @@ void __init setup_boot_APIC_clock(void)
         * broadcast mechanism is used. On UP systems simply ignore it.
         */
        if (disable_apic_timer) {
-                printk(KERN_INFO "Disabling APIC timer\n");
+                pr_info("Disabling APIC timer\n");
                /* No broadcast on UP ! */
                if (num_possible_cpus() > 1) {
                        lapic_clockevent.mult = 1;
@@ -741,7 +736,7 @@ void __init setup_boot_APIC_clock(void)
        if (nmi_watchdog != NMI_IO_APIC)
                lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
        else
-                printk(KERN_WARNING "APIC timer registered as dummy,"
+                pr_warning("APIC timer registered as dummy,"
                        " due to nmi_watchdog=%d!\n", nmi_watchdog);
        /* Setup the lapic or request the broadcast */
@@ -773,8 +768,7 @@ static void local_apic_timer_interrupt(void)
         * spurious.
         */
        if (!evt->event_handler) {
-                printk(KERN_WARNING
+                pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", cpu);
-                       "Spurious LAPIC timer interrupt on cpu %d\n", cpu);
                /* Switch it off */
                lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
                return;
@@ -814,9 +808,7 @@ void smp_apic_timer_interrupt(struct pt_regs *regs)
         * Besides, if we don't timer interrupts ignore the global
         * interrupt lock, which is the WrongThing (tm) to do.
         */
-#ifdef CONFIG_X86_64
        exit_idle();
-#endif
        irq_enter();
        local_apic_timer_interrupt();
        irq_exit();
@@ -1093,7 +1085,7 @@ static void __cpuinit lapic_setup_esr(void)
        unsigned int oldvalue, value, maxlvt;
        if (!lapic_is_integrated()) {
-                printk(KERN_INFO "No ESR for 82489DX.\n");
+                pr_info("No ESR for 82489DX.\n");
                return;
        }
@@ -1104,7 +1096,7 @@ static void __cpuinit lapic_setup_esr(void)
                 * ESR disabled - we can't do anything useful with the
                 * errors anyway - mbligh
                 */
-                printk(KERN_INFO "Leaving ESR disabled.\n");
+                pr_info("Leaving ESR disabled.\n");
                return;
        }
@@ -1298,7 +1290,7 @@ void check_x2apic(void)
        rdmsr(MSR_IA32_APICBASE, msr, msr2);
        if (msr & X2APIC_ENABLE) {
-                printk("x2apic enabled by BIOS, switching to x2apic ops\n");
+                pr_info("x2apic enabled by BIOS, switching to x2apic ops\n");
                x2apic_preenabled = x2apic = 1;
                apic_ops = &x2apic_ops;
        }
@@ -1310,12 +1302,12 @@ void enable_x2apic(void)
        rdmsr(MSR_IA32_APICBASE, msr, msr2);
        if (!(msr & X2APIC_ENABLE)) {
-                printk("Enabling x2apic\n");
+                pr_info("Enabling x2apic\n");
                wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
        }
 }
-void enable_IR_x2apic(void)
+void __init enable_IR_x2apic(void)
 {
 #ifdef CONFIG_INTR_REMAP
        int ret;
@@ -1325,9 +1317,8 @@ void enable_IR_x2apic(void)
                return;
        if (!x2apic_preenabled && disable_x2apic) {
-                printk(KERN_INFO
+                pr_info("Skipped enabling x2apic and Interrupt-remapping "
-                       "Skipped enabling x2apic and Interrupt-remapping "
+                        "because of nox2apic\n");
-                       "because of nox2apic\n");
                return;
        }
@@ -1335,22 +1326,19 @@ void enable_IR_x2apic(void)
                panic("Bios already enabled x2apic, can't enforce nox2apic");
        if (!x2apic_preenabled && skip_ioapic_setup) {
-                printk(KERN_INFO
+                pr_info("Skipped enabling x2apic and Interrupt-remapping "
-                       "Skipped enabling x2apic and Interrupt-remapping "
+                        "because of skipping io-apic setup\n");
-                       "because of skipping io-apic setup\n");
                return;
        }
        ret = dmar_table_init();
        if (ret) {
-                printk(KERN_INFO
+                pr_info("dmar_table_init() failed with %d:\n", ret);
-                       "dmar_table_init() failed with %d:\n", ret);
                if (x2apic_preenabled)
                        panic("x2apic enabled by bios. But IR enabling failed");
                else
-                        printk(KERN_INFO
+                        pr_info("Not enabling x2apic,Intr-remapping\n");
-                               "Not enabling x2apic,Intr-remapping\n");
                return;
        }
@@ -1359,7 +1347,7 @@ void enable_IR_x2apic(void)
        ret = save_mask_IO_APIC_setup();
        if (ret) {
-                printk(KERN_INFO "Saving IO-APIC state failed: %d\n", ret);
+                pr_info("Saving IO-APIC state failed: %d\n", ret);
                goto end;
        }
@@ -1394,14 +1382,11 @@ end:
        if (!ret) {
                if (!x2apic_preenabled)
-                        printk(KERN_INFO
+                        pr_info("Enabled x2apic and interrupt-remapping\n");
-                               "Enabled x2apic and interrupt-remapping\n");
                else
-                        printk(KERN_INFO
+                        pr_info("Enabled Interrupt-remapping\n");
-                               "Enabled Interrupt-remapping\n");
        } else
-                printk(KERN_ERR
+                pr_err("Failed to enable Interrupt-remapping and x2apic\n");
-                       "Failed to enable Interrupt-remapping and x2apic\n");
 #else
        if (!cpu_has_x2apic)
                return;
@@ -1410,8 +1395,8 @@ end:
                panic("x2apic enabled prior OS handover,"
                      " enable CONFIG_INTR_REMAP");
-        printk(KERN_INFO "Enable CONFIG_INTR_REMAP for enabling intr-remapping "
+        pr_info("Enable CONFIG_INTR_REMAP for enabling intr-remapping "
-               " and x2apic\n");
+                " and x2apic\n");
 #endif
        return;
@@ -1428,7 +1413,7 @@ end:
 static int __init detect_init_APIC(void)
 {
        if (!cpu_has_apic) {
-                printk(KERN_INFO "No local APIC present\n");
+                pr_info("No local APIC present\n");
                return -1;
        }
@@ -1469,8 +1454,8 @@ static int __init detect_init_APIC(void)
                 * "lapic" specified.
                 */
                if (!force_enable_local_apic) {
-                        printk(KERN_INFO "Local APIC disabled by BIOS -- "
+                        pr_info("Local APIC disabled by BIOS -- "
-                               "you can enable it with \"lapic\"\n");
+                                "you can enable it with \"lapic\"\n");
                        return -1;
                }
                /*
@@ -1480,8 +1465,7 @@ static int __init detect_init_APIC(void)
                 */
                rdmsr(MSR_IA32_APICBASE, l, h);
                if (!(l & MSR_IA32_APICBASE_ENABLE)) {
-                        printk(KERN_INFO
+                        pr_info("Local APIC disabled by BIOS -- reenabling.\n");
-                               "Local APIC disabled by BIOS -- reenabling.\n");
                        l &= ~MSR_IA32_APICBASE_BASE;
                        l |= MSR_IA32_APICBASE_ENABLE | APIC_DEFAULT_PHYS_BASE;
                        wrmsr(MSR_IA32_APICBASE, l, h);
@@ -1494,7 +1478,7 @@ static int __init detect_init_APIC(void)
         */
        features = cpuid_edx(1);
        if (!(features & (1 << X86_FEATURE_APIC))) {
-                printk(KERN_WARNING "Could not enable APIC!\n");
+                pr_warning("Could not enable APIC!\n");
                return -1;
        }
        set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
@@ -1505,14 +1489,14 @@ static int __init detect_init_APIC(void)
        if (l & MSR_IA32_APICBASE_ENABLE)
                mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
-        printk(KERN_INFO "Found and enabled local APIC!\n");
+        pr_info("Found and enabled local APIC!\n");
        apic_pm_activate();
        return 0;
 no_apic:
-        printk(KERN_INFO "No local APIC present or hardware disabled\n");
+        pr_info("No local APIC present or hardware disabled\n");
        return -1;
 }
 #endif
@@ -1588,12 +1572,12 @@ int __init APIC_init_uniprocessor(void)
 {
 #ifdef CONFIG_X86_64
        if (disable_apic) {
-                printk(KERN_INFO "Apic disabled\n");
+                pr_info("Apic disabled\n");
                return -1;
        }
        if (!cpu_has_apic) {
                disable_apic = 1;
-                printk(KERN_INFO "Apic disabled by BIOS\n");
+                pr_info("Apic disabled by BIOS\n");
                return -1;
        }
 #else
@@ -1605,8 +1589,8 @@ int __init APIC_init_uniprocessor(void)
         */
        if (!cpu_has_apic &&
            APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
-                printk(KERN_ERR "BIOS bug, local APIC 0x%x not detected!...\n",
+                pr_err("BIOS bug, local APIC 0x%x not detected!...\n",
-                       boot_cpu_physical_apicid);
+                        boot_cpu_physical_apicid);
                clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
                return -1;
        }
@@ -1682,9 +1666,7 @@ void smp_spurious_interrupt(struct pt_regs *regs)
 {
        u32 v;
-#ifdef CONFIG_X86_64
        exit_idle();
-#endif
        irq_enter();
        /*
         * Check if this really is a spurious interrupt and ACK it
@@ -1699,8 +1681,8 @@ void smp_spurious_interrupt(struct pt_regs *regs)
        add_pda(irq_spurious_count, 1);
 #else
        /* see sw-dev-man vol 3, chapter 7.4.13.5 */
-        printk(KERN_INFO "spurious APIC interrupt on CPU#%d, "
+        pr_info("spurious APIC interrupt on CPU#%d, "
-               "should never happen.\n", smp_processor_id());
+                "should never happen.\n", smp_processor_id());
        __get_cpu_var(irq_stat).irq_spurious_count++;
 #endif
        irq_exit();
@@ -1713,9 +1695,7 @@ void smp_error_interrupt(struct pt_regs *regs)
 {
        u32 v, v1;
-#ifdef CONFIG_X86_64
        exit_idle();
-#endif
        irq_enter();
        /* First tickle the hardware, only then report what went on. -- REW */
        v = apic_read(APIC_ESR);
@@ -1724,17 +1704,18 @@ void smp_error_interrupt(struct pt_regs *regs)
        ack_APIC_irq();
        atomic_inc(&irq_err_count);
-        /* Here is what the APIC error bits mean:
+        /*
-           0: Send CS error
+         * Here is what the APIC error bits mean:
-           1: Receive CS error
+         * 0: Send CS error
-           2: Send accept error
+         * 1: Receive CS error
-           3: Receive accept error
+         * 2: Send accept error
-           4: Reserved
+         * 3: Receive accept error
-           5: Send illegal vector
+         * 4: Reserved
-           6: Received illegal vector
+         * 5: Send illegal vector
-           7: Illegal register address
+         * 6: Received illegal vector
-        */
+         * 7: Illegal register address
-        printk(KERN_DEBUG "APIC error on CPU%d: %02x(%02x)\n",
+         */
+        pr_debug("APIC error on CPU%d: %02x(%02x)\n",
                smp_processor_id(), v , v1);
        irq_exit();
 }
@@ -1838,15 +1819,15 @@ void __cpuinit generic_processor_info(int apicid, int version)
         * Validate version
         */
        if (version == 0x0) {
-                printk(KERN_WARNING "BIOS bug, APIC version is 0 for CPU#%d! "
+                pr_warning("BIOS bug, APIC version is 0 for CPU#%d! "
-                                "fixing up to 0x10. (tell your hw vendor)\n",
+                        "fixing up to 0x10. (tell your hw vendor)\n",
-                                version);
+                        version);
                version = 0x10;
        }
        apic_version[apicid] = version;
        if (num_processors >= NR_CPUS) {
-                printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached."
+                pr_warning("WARNING: NR_CPUS limit of %i reached."
                        "  Processor ignored.\n", NR_CPUS);
                return;
        }
@@ -2209,7 +2190,7 @@ static int __init apic_set_verbosity(char *arg)
        else if (strcmp("verbose", arg) == 0)
                apic_verbosity = APIC_VERBOSE;
        else {
-                printk(KERN_WARNING "APIC Verbosity level %s not recognised"
+                pr_warning("APIC Verbosity level %s not recognised"
                        " use apic=verbose or apic=debug\n", arg);
                return -EINVAL;
        }
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 5145a6e72bbb..3a26525a3f31 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -391,11 +391,7 @@ static int power_off;
 #else
 static int power_off = 1;
 #endif
-#ifdef CONFIG_APM_REAL_MODE_POWER_OFF
-static int realmode_power_off = 1;
-#else
 static int realmode_power_off;
-#endif
 #ifdef CONFIG_APM_ALLOW_INTS
 static int allow_ints = 1;
 #else
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 6649d09ad88f..ee4df08feee6 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -11,7 +11,7 @@
 #include <linux/suspend.h>
 #include <linux/kbuild.h>
 #include <asm/ucontext.h>
-#include "sigframe.h"
+#include <asm/sigframe.h>
 #include <asm/pgtable.h>
 #include <asm/fixmap.h>
 #include <asm/processor.h>
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 7fcf63d22f8b..1d41d3f1edbc 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -20,6 +20,8 @@
 #include <xen/interface/xen.h>
+#include <asm/sigframe.h>
 #define __NO_STUBS 1
 #undef __SYSCALL
 #undef _ASM_X86_UNISTD_64_H
@@ -87,7 +89,7 @@ int main(void)
        BLANK();
 #undef ENTRY
        DEFINE(IA32_RT_SIGFRAME_sigcontext,
-               offsetof (struct rt_sigframe32, uc.uc_mcontext));
+               offsetof (struct rt_sigframe_ia32, uc.uc_mcontext));
        BLANK();
 #endif
        DEFINE(pbe_address, offsetof(struct pbe, address));
diff --git a/arch/x86/kernel/bios_uv.c b/arch/x86/kernel/bios_uv.c
index f0dfe6f17e7e..2a0a2a3cac26 100644
--- a/arch/x86/kernel/bios_uv.c
+++ b/arch/x86/kernel/bios_uv.c
@@ -69,10 +69,10 @@ s64 uv_bios_call_reentrant(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
 long sn_partition_id;
 EXPORT_SYMBOL_GPL(sn_partition_id);
-long uv_coherency_id;
+long sn_coherency_id;
-EXPORT_SYMBOL_GPL(uv_coherency_id);
+EXPORT_SYMBOL_GPL(sn_coherency_id);
-long uv_region_size;
+long sn_region_size;
-EXPORT_SYMBOL_GPL(uv_region_size);
+EXPORT_SYMBOL_GPL(sn_region_size);
 int uv_type;
@@ -100,6 +100,56 @@ s64 uv_bios_get_sn_info(int fc, int *uvtype, long *partid, long *coher,
        return ret;
 }
+int
+uv_bios_mq_watchlist_alloc(int blade, unsigned long addr, unsigned int mq_size,
+                           unsigned long *intr_mmr_offset)
+{
+        union uv_watchlist_u size_blade;
+        u64 watchlist;
+        s64 ret;
+        size_blade.size = mq_size;
+        size_blade.blade = blade;
+        /*
+         * bios returns watchlist number or negative error number.
+         */
+        ret = (int)uv_bios_call_irqsave(UV_BIOS_WATCHLIST_ALLOC, addr,
+                        size_blade.val, (u64)intr_mmr_offset,
+                        (u64)&watchlist, 0);
+        if (ret < BIOS_STATUS_SUCCESS)
+                return ret;
+        return watchlist;
+}
+EXPORT_SYMBOL_GPL(uv_bios_mq_watchlist_alloc);
+int
+uv_bios_mq_watchlist_free(int blade, int watchlist_num)
+{
+        return (int)uv_bios_call_irqsave(UV_BIOS_WATCHLIST_FREE,
+                                blade, watchlist_num, 0, 0, 0);
+}
+EXPORT_SYMBOL_GPL(uv_bios_mq_watchlist_free);
+s64
+uv_bios_change_memprotect(u64 paddr, u64 len, enum uv_memprotect perms)
+{
+        return uv_bios_call_irqsave(UV_BIOS_MEMPROTECT, paddr, len,
+                                        perms, 0, 0);
+}
+EXPORT_SYMBOL_GPL(uv_bios_change_memprotect);
+s64
+uv_bios_reserved_page_pa(u64 buf, u64 *cookie, u64 *addr, u64 *len)
+{
+        s64 ret;
+        ret = uv_bios_call_irqsave(UV_BIOS_GET_PARTITION_ADDR, (u64)cookie,
+                                        (u64)addr, buf, (u64)len, 0);
+        return ret;
+}
+EXPORT_SYMBOL_GPL(uv_bios_reserved_page_pa);
 s64 uv_bios_freq_base(u64 clock_type, u64 *ticks_per_second)
 {
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 82ec6075c057..a5c04e88777e 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -4,6 +4,7 @@
 obj-y                   := intel_cacheinfo.o addon_cpuid_features.o
 obj-y                   += proc.o capflags.o powerflags.o common.o
+obj-y                   += vmware.o hypervisor.o
 obj-$(CONFIG_X86_32)    += bugs.o cmpxchg.o
 obj-$(CONFIG_X86_64)    += bugs_64.o
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b9c9ea0217a9..42e0853030cb 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -36,6 +36,7 @@
 #include <asm/proto.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
+#include <asm/hypervisor.h>
 #include "cpu.h"
@@ -703,6 +704,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
        detect_ht(c);
 #endif
+        init_hypervisor(c);
        /*
         * On SMP, boot_cpu_data holds the common feature set between
         * all CPUs; so make sure that we indicate which features are
@@ -862,7 +864,7 @@ EXPORT_SYMBOL(_cpu_pda);
 struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
-char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
+static char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
 void __cpuinit pda_init(int cpu)
 {
@@ -903,8 +905,8 @@ void __cpuinit pda_init(int cpu)
        }
 }
-char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
+static char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
-                           DEBUG_STKSZ] __page_aligned_bss;
+                                  DEBUG_STKSZ] __page_aligned_bss;
 extern asmlinkage void ignore_sysret(void);
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index d3dcd58b87cd..7f05f44b97e9 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -115,9 +115,20 @@ static int query_current_values_with_pending_wait(struct powernow_k8_data *data)
        u32 i = 0;
        if (cpu_family == CPU_HW_PSTATE) {
-                rdmsr(MSR_PSTATE_STATUS, lo, hi);
+                if (data->currpstate == HW_PSTATE_INVALID) {
-                i = lo & HW_PSTATE_MASK;
+                        /* read (initial) hw pstate if not yet set */
-                data->currpstate = i;
+                        rdmsr(MSR_PSTATE_STATUS, lo, hi);
+                        i = lo & HW_PSTATE_MASK;
+                        /*
+                         * a workaround for family 11h erratum 311 might cause
+                         * an "out-of-range Pstate if the core is in Pstate-0
+                         */
+                        if (i >= data->numps)
+                                data->currpstate = HW_PSTATE_0;
+                        else
+                                data->currpstate = i;
+                }
                return 0;
        }
        do {
@@ -1121,6 +1132,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
        }
        data->cpu = pol->cpu;
+        data->currpstate = HW_PSTATE_INVALID;
        if (powernow_k8_cpu_init_acpi(data)) {
                /*
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
index ab48cfed4d96..65cfb5d7f77f 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
@@ -5,6 +5,19 @@
 *  http://www.gnu.org/licenses/gpl.html
 */
+enum pstate {
+        HW_PSTATE_INVALID = 0xff,
+        HW_PSTATE_0 = 0,
+        HW_PSTATE_1 = 1,
+        HW_PSTATE_2 = 2,
+        HW_PSTATE_3 = 3,
+        HW_PSTATE_4 = 4,
+        HW_PSTATE_5 = 5,
+        HW_PSTATE_6 = 6,
+        HW_PSTATE_7 = 7,
+};
 struct powernow_k8_data {
        unsigned int cpu;
@@ -23,7 +36,9 @@ struct powernow_k8_data {
        u32 exttype; /* extended interface = 1 */
        /* keep track of the current fid / vid or pstate */
-        u32 currvid, currfid, currpstate;
+        u32 currvid;
+        u32 currfid;
+        enum pstate currpstate;
        /* the powernow_table includes all frequency and vid/fid pairings:
         * fid are the lower 8 bits of the index, vid are the upper 8 bits.
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
new file mode 100644
index 000000000000..fb5b86af0b01
--- /dev/null
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -0,0 +1,58 @@
+/*
+ * Common hypervisor code
+ *
+ * Copyright (C) 2008, VMware, Inc.
+ * Author : Alok N Kataria <akataria@vmware.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#include <asm/processor.h>
+#include <asm/vmware.h>
+#include <asm/hypervisor.h>
+static inline void __cpuinit
+detect_hypervisor_vendor(struct cpuinfo_x86 *c)
+{
+        if (vmware_platform()) {
+                c->x86_hyper_vendor = X86_HYPER_VENDOR_VMWARE;
+        } else {
+                c->x86_hyper_vendor = X86_HYPER_VENDOR_NONE;
+        }
+}
+unsigned long get_hypervisor_tsc_freq(void)
+{
+        if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE)
+                return vmware_get_tsc_khz();
+        return 0;
+}
+static inline void __cpuinit
+hypervisor_set_feature_bits(struct cpuinfo_x86 *c)
+{
+        if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE) {
+                vmware_set_feature_bits(c);
+                return;
+        }
+}
+void __cpuinit init_hypervisor(struct cpuinfo_x86 *c)
+{
+        detect_hypervisor_vendor(c);
+        hypervisor_set_feature_bits(c);
+}
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index cce0b6118d55..816f27f289b1 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -307,12 +307,11 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
                set_cpu_cap(c, X86_FEATURE_P4);
        if (c->x86 == 6)
                set_cpu_cap(c, X86_FEATURE_P3);
+#endif
        if (cpu_has_bts)
                ptrace_bts_init_intel(c);
-#endif
        detect_extended_topology(c);
        if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
                /*
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 3f46afbb1cf1..68b5d8681cbb 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -644,20 +644,17 @@ static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf)
        return show_shared_cpu_map_func(leaf, 1, buf);
 }
-static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf) {
+static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf)
-        switch(this_leaf->eax.split.type) {
+{
-            case CACHE_TYPE_DATA:
+        switch (this_leaf->eax.split.type) {
+        case CACHE_TYPE_DATA:
                return sprintf(buf, "Data\n");
-                break;
+        case CACHE_TYPE_INST:
-            case CACHE_TYPE_INST:
                return sprintf(buf, "Instruction\n");
-                break;
+        case CACHE_TYPE_UNIFIED:
-            case CACHE_TYPE_UNIFIED:
                return sprintf(buf, "Unified\n");
-                break;
+        default:
-            default:
                return sprintf(buf, "Unknown\n");
-                break;
        }
 }
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 4b031a4ac856..1c838032fd37 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -510,12 +510,9 @@ static void __cpuinit mce_cpu_features(struct cpuinfo_x86 *c)
 */
 void __cpuinit mcheck_init(struct cpuinfo_x86 *c)
 {
-        static cpumask_t mce_cpus = CPU_MASK_NONE;
        mce_cpu_quirks(c);
        if (mce_dont_init ||
-            cpu_test_and_set(smp_processor_id(), mce_cpus) ||
            !mce_available(c))
                return;
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index c78c04821ea1..1159e269e596 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -803,6 +803,7 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
 }
 static struct res_range __initdata range[RANGE_NUM];
+static int __initdata nr_range;
 #ifdef CONFIG_MTRR_SANITIZER
@@ -1206,39 +1207,43 @@ struct mtrr_cleanup_result {
 #define PSHIFT          (PAGE_SHIFT - 10)
 static struct mtrr_cleanup_result __initdata result[NUM_RESULT];
-static struct res_range __initdata range_new[RANGE_NUM];
 static unsigned long __initdata min_loss_pfn[RANGE_NUM];
-static int __init mtrr_cleanup(unsigned address_bits)
+static void __init print_out_mtrr_range_state(void)
 {
-        unsigned long extra_remove_base, extra_remove_size;
-        unsigned long base, size, def, dummy;
-        mtrr_type type;
-        int nr_range, nr_range_new;
-        u64 chunk_size, gran_size;
-        unsigned long range_sums, range_sums_new;
-        int index_good;
-        int num_reg_good;
        int i;
+        char start_factor = 'K', size_factor = 'K';
+        unsigned long start_base, size_base;
+        mtrr_type type;
-        /* extra one for all 0 */
+        for (i = 0; i < num_var_ranges; i++) {
-        int num[MTRR_NUM_TYPES + 1];
-        if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1)
+                size_base = range_state[i].size_pfn << (PAGE_SHIFT - 10);
-                return 0;
+                if (!size_base)
-        rdmsr(MTRRdefType_MSR, def, dummy);
+                        continue;
-        def &= 0xff;
-        if (def != MTRR_TYPE_UNCACHABLE)
-                return 0;
-        /* get it and store it aside */
+                size_base = to_size_factor(size_base, &size_factor),
-        memset(range_state, 0, sizeof(range_state));
+                start_base = range_state[i].base_pfn << (PAGE_SHIFT - 10);
-        for (i = 0; i < num_var_ranges; i++) {
+                start_base = to_size_factor(start_base, &start_factor),
-                mtrr_if->get(i, &base, &size, &type);
+                type = range_state[i].type;
-                range_state[i].base_pfn = base;
-                range_state[i].size_pfn = size;
+                printk(KERN_DEBUG "reg %d, base: %ld%cB, range: %ld%cB, type %s\n",
-                range_state[i].type = type;
+                        i, start_base, start_factor,
+                        size_base, size_factor,
+                        (type == MTRR_TYPE_UNCACHABLE) ? "UC" :
+                            ((type == MTRR_TYPE_WRPROT) ? "WP" :
+                             ((type == MTRR_TYPE_WRBACK) ? "WB" : "Other"))
+                        );
        }
+}
+static int __init mtrr_need_cleanup(void)
+{
+        int i;
+        mtrr_type type;
+        unsigned long size;
+        /* extra one for all 0 */
+        int num[MTRR_NUM_TYPES + 1];
        /* check entries number */
        memset(num, 0, sizeof(num));
@@ -1263,29 +1268,133 @@ static int __init mtrr_cleanup(unsigned address_bits)
                num_var_ranges - num[MTRR_NUM_TYPES])
                return 0;
-        /* print original var MTRRs at first, for debugging: */
+        return 1;
-        printk(KERN_DEBUG "original variable MTRRs\n");
+}
-        for (i = 0; i < num_var_ranges; i++) {
-                char start_factor = 'K', size_factor = 'K';
-                unsigned long start_base, size_base;
-                size_base = range_state[i].size_pfn << (PAGE_SHIFT - 10);
+static unsigned long __initdata range_sums;
-                if (!size_base)
+static void __init mtrr_calc_range_state(u64 chunk_size, u64 gran_size,
-                        continue;
+                                         unsigned long extra_remove_base,
+                                         unsigned long extra_remove_size,
+                                         int i)
+{
+        int num_reg;
+        static struct res_range range_new[RANGE_NUM];
+        static int nr_range_new;
+        unsigned long range_sums_new;
+        /* convert ranges to var ranges state */
+        num_reg = x86_setup_var_mtrrs(range, nr_range,
+                                                chunk_size, gran_size);
+        /* we got new setting in range_state, check it */
+        memset(range_new, 0, sizeof(range_new));
+        nr_range_new = x86_get_mtrr_mem_range(range_new, 0,
+                                extra_remove_base, extra_remove_size);
+        range_sums_new = sum_ranges(range_new, nr_range_new);
+        result[i].chunk_sizek = chunk_size >> 10;
+        result[i].gran_sizek = gran_size >> 10;
+        result[i].num_reg = num_reg;
+        if (range_sums < range_sums_new) {
+                result[i].lose_cover_sizek =
+                        (range_sums_new - range_sums) << PSHIFT;
+                result[i].bad = 1;
+        } else
+                result[i].lose_cover_sizek =
+                        (range_sums - range_sums_new) << PSHIFT;
-                size_base = to_size_factor(size_base, &size_factor),
+        /* double check it */
-                start_base = range_state[i].base_pfn << (PAGE_SHIFT - 10);
+        if (!result[i].bad && !result[i].lose_cover_sizek) {
-                start_base = to_size_factor(start_base, &start_factor),
+                if (nr_range_new != nr_range ||
-                type = range_state[i].type;
+                        memcmp(range, range_new, sizeof(range)))
+                                result[i].bad = 1;
+        }
-                printk(KERN_DEBUG "reg %d, base: %ld%cB, range: %ld%cB, type %s\n",
+        if (!result[i].bad && (range_sums - range_sums_new <
-                        i, start_base, start_factor,
+                                min_loss_pfn[num_reg])) {
-                        size_base, size_factor,
+                min_loss_pfn[num_reg] =
-                        (type == MTRR_TYPE_UNCACHABLE) ? "UC" :
+                        range_sums - range_sums_new;
-                            ((type == MTRR_TYPE_WRPROT) ? "WP" :
-                             ((type == MTRR_TYPE_WRBACK) ? "WB" : "Other"))
-                        );
        }
+}
+static void __init mtrr_print_out_one_result(int i)
+{
+        char gran_factor, chunk_factor, lose_factor;
+        unsigned long gran_base, chunk_base, lose_base;
+        gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
+        chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
+        lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
+        printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t",
+                        result[i].bad ? "*BAD*" : " ",
+                        gran_base, gran_factor, chunk_base, chunk_factor);
+        printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ld%c\n",
+                        result[i].num_reg, result[i].bad ? "-" : "",
+                        lose_base, lose_factor);
+}
+static int __init mtrr_search_optimal_index(void)
+{
+        int i;
+        int num_reg_good;
+        int index_good;
+        if (nr_mtrr_spare_reg >= num_var_ranges)
+                nr_mtrr_spare_reg = num_var_ranges - 1;
+        num_reg_good = -1;
+        for (i = num_var_ranges - nr_mtrr_spare_reg; i > 0; i--) {
+                if (!min_loss_pfn[i])
+                        num_reg_good = i;
+        }
+        index_good = -1;
+        if (num_reg_good != -1) {
+                for (i = 0; i < NUM_RESULT; i++) {
+                        if (!result[i].bad &&
+                            result[i].num_reg == num_reg_good &&
+                            !result[i].lose_cover_sizek) {
+                                index_good = i;
+                                break;
+                        }
+                }
+        }
+        return index_good;
+}
+static int __init mtrr_cleanup(unsigned address_bits)
+{
+        unsigned long extra_remove_base, extra_remove_size;
+        unsigned long base, size, def, dummy;
+        mtrr_type type;
+        u64 chunk_size, gran_size;
+        int index_good;
+        int i;
+        if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1)
+                return 0;
+        rdmsr(MTRRdefType_MSR, def, dummy);
+        def &= 0xff;
+        if (def != MTRR_TYPE_UNCACHABLE)
+                return 0;
+        /* get it and store it aside */
+        memset(range_state, 0, sizeof(range_state));
+        for (i = 0; i < num_var_ranges; i++) {
+                mtrr_if->get(i, &base, &size, &type);
+                range_state[i].base_pfn = base;
+                range_state[i].size_pfn = size;
+                range_state[i].type = type;
+        }
+        /* check if we need handle it and can handle it */
+        if (!mtrr_need_cleanup())
+                return 0;
+        /* print original var MTRRs at first, for debugging: */
+        printk(KERN_DEBUG "original variable MTRRs\n");
+        print_out_mtrr_range_state();
        memset(range, 0, sizeof(range));
        extra_remove_size = 0;
@@ -1309,176 +1418,64 @@ static int __init mtrr_cleanup(unsigned address_bits)
               range_sums >> (20 - PAGE_SHIFT));
        if (mtrr_chunk_size && mtrr_gran_size) {
-                int num_reg;
+                i = 0;
-                char gran_factor, chunk_factor, lose_factor;
+                mtrr_calc_range_state(mtrr_chunk_size, mtrr_gran_size,
-                unsigned long gran_base, chunk_base, lose_base;
+                                      extra_remove_base, extra_remove_size, i);
-                debug_print++;
-                /* convert ranges to var ranges state */
-                num_reg = x86_setup_var_mtrrs(range, nr_range, mtrr_chunk_size,
-                                              mtrr_gran_size);
-                /* we got new setting in range_state, check it */
+                mtrr_print_out_one_result(i);
-                memset(range_new, 0, sizeof(range_new));
-                nr_range_new = x86_get_mtrr_mem_range(range_new, 0,
-                                                      extra_remove_base,
-                                                      extra_remove_size);
-                range_sums_new = sum_ranges(range_new, nr_range_new);
-                i = 0;
-                result[i].chunk_sizek = mtrr_chunk_size >> 10;
-                result[i].gran_sizek = mtrr_gran_size >> 10;
-                result[i].num_reg = num_reg;
-                if (range_sums < range_sums_new) {
-                        result[i].lose_cover_sizek =
-                                (range_sums_new - range_sums) << PSHIFT;
-                        result[i].bad = 1;
-                } else
-                        result[i].lose_cover_sizek =
-                                (range_sums - range_sums_new) << PSHIFT;
-                gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
-                chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
-                lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
-                printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t",
-                         result[i].bad?"*BAD*":" ",
-                         gran_base, gran_factor, chunk_base, chunk_factor);
-                printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ld%c\n",
-                         result[i].num_reg, result[i].bad?"-":"",
-                         lose_base, lose_factor);
                if (!result[i].bad) {
                        set_var_mtrr_all(address_bits);
                        return 1;
                }
                printk(KERN_INFO "invalid mtrr_gran_size or mtrr_chunk_size, "
                       "will find optimal one\n");
-                debug_print--;
-                memset(result, 0, sizeof(result[0]));
        }
        i = 0;
        memset(min_loss_pfn, 0xff, sizeof(min_loss_pfn));
        memset(result, 0, sizeof(result));
        for (gran_size = (1ULL<<16); gran_size < (1ULL<<32); gran_size <<= 1) {
-                char gran_factor;
-                unsigned long gran_base;
-                if (debug_print)
-                        gran_base = to_size_factor(gran_size >> 10, &gran_factor);
                for (chunk_size = gran_size; chunk_size < (1ULL<<32);
                     chunk_size <<= 1) {
-                        int num_reg;
-                        if (debug_print) {
-                                char chunk_factor;
-                                unsigned long chunk_base;
-                                chunk_base = to_size_factor(chunk_size>>10, &chunk_factor),
-                                printk(KERN_INFO "\n");
-                                printk(KERN_INFO "gran_size: %ld%c   chunk_size: %ld%c \n",
-                                       gran_base, gran_factor, chunk_base, chunk_factor);
-                        }
                        if (i >= NUM_RESULT)
                                continue;
-                        /* convert ranges to var ranges state */
+                        mtrr_calc_range_state(chunk_size, gran_size,
-                        num_reg = x86_setup_var_mtrrs(range, nr_range,
+                                      extra_remove_base, extra_remove_size, i);
-                                                         chunk_size, gran_size);
+                        if (debug_print) {
+                                mtrr_print_out_one_result(i);
-                        /* we got new setting in range_state, check it */
+                                printk(KERN_INFO "\n");
-                        memset(range_new, 0, sizeof(range_new));
-                        nr_range_new = x86_get_mtrr_mem_range(range_new, 0,
-                                         extra_remove_base, extra_remove_size);
-                        range_sums_new = sum_ranges(range_new, nr_range_new);
-                        result[i].chunk_sizek = chunk_size >> 10;
-                        result[i].gran_sizek = gran_size >> 10;
-                        result[i].num_reg = num_reg;
-                        if (range_sums < range_sums_new) {
-                                result[i].lose_cover_sizek =
-                                        (range_sums_new - range_sums) << PSHIFT;
-                                result[i].bad = 1;
-                        } else
-                                result[i].lose_cover_sizek =
-                                        (range_sums - range_sums_new) << PSHIFT;
-                        /* double check it */
-                        if (!result[i].bad && !result[i].lose_cover_sizek) {
-                                if (nr_range_new != nr_range ||
-                                        memcmp(range, range_new, sizeof(range)))
-                                                result[i].bad = 1;
                        }
-                        if (!result[i].bad && (range_sums - range_sums_new <
-                                               min_loss_pfn[num_reg])) {
-                                min_loss_pfn[num_reg] =
-                                        range_sums - range_sums_new;
-                        }
                        i++;
                }
        }
-        /* print out all */
-        for (i = 0; i < NUM_RESULT; i++) {
-                char gran_factor, chunk_factor, lose_factor;
-                unsigned long gran_base, chunk_base, lose_base;
-                gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
-                chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
-                lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
-                printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t",
-                         result[i].bad?"*BAD*":" ",
-                         gran_base, gran_factor, chunk_base, chunk_factor);
-                printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ld%c\n",
-                         result[i].num_reg, result[i].bad?"-":"",
-                         lose_base, lose_factor);
-        }
        /* try to find the optimal index */
-        if (nr_mtrr_spare_reg >= num_var_ranges)
+        index_good = mtrr_search_optimal_index();
-                nr_mtrr_spare_reg = num_var_ranges - 1;
-        num_reg_good = -1;
-        for (i = num_var_ranges - nr_mtrr_spare_reg; i > 0; i--) {
-                if (!min_loss_pfn[i])
-                        num_reg_good = i;
-        }
-        index_good = -1;
-        if (num_reg_good != -1) {
-                for (i = 0; i < NUM_RESULT; i++) {
-                        if (!result[i].bad &&
-                            result[i].num_reg == num_reg_good &&
-                            !result[i].lose_cover_sizek) {
-                                index_good = i;
-                                break;
-                        }
-                }
-        }
        if (index_good != -1) {
-                char gran_factor, chunk_factor, lose_factor;
-                unsigned long gran_base, chunk_base, lose_base;
                printk(KERN_INFO "Found optimal setting for mtrr clean up\n");
                i = index_good;
-                gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
+                mtrr_print_out_one_result(i);
-                chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
-                lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
-                printk(KERN_INFO "gran_size: %ld%c \tchunk_size: %ld%c \t",
-                         gran_base, gran_factor, chunk_base, chunk_factor);
-                printk(KERN_CONT "num_reg: %d  \tlose RAM: %ld%c\n",
-                         result[i].num_reg, lose_base, lose_factor);
                /* convert ranges to var ranges state */
                chunk_size = result[i].chunk_sizek;
                chunk_size <<= 10;
                gran_size = result[i].gran_sizek;
                gran_size <<= 10;
-                debug_print++;
                x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size);
-                debug_print--;
                set_var_mtrr_all(address_bits);
+                printk(KERN_DEBUG "New variable MTRRs\n");
+                print_out_mtrr_range_state();
                return 1;
+        } else {
+                /* print out all */
+                for (i = 0; i < NUM_RESULT; i++)
+                        mtrr_print_out_one_result(i);
        }
        printk(KERN_INFO "mtrr_cleanup: can not find optimal value\n");
@@ -1562,7 +1559,6 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 {
        unsigned long i, base, size, highest_pfn = 0, def, dummy;
        mtrr_type type;
-        int nr_range;
        u64 total_trim_size;
        /* extra one for all 0 */
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
new file mode 100644
index 000000000000..284c399e3234
--- /dev/null
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -0,0 +1,112 @@
+/*
+ * VMware Detection code.
+ *
+ * Copyright (C) 2008, VMware, Inc.
+ * Author : Alok N Kataria <akataria@vmware.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#include <linux/dmi.h>
+#include <asm/div64.h>
+#include <asm/vmware.h>
+#define CPUID_VMWARE_INFO_LEAF  0x40000000
+#define VMWARE_HYPERVISOR_MAGIC 0x564D5868
+#define VMWARE_HYPERVISOR_PORT  0x5658
+#define VMWARE_PORT_CMD_GETVERSION      10
+#define VMWARE_PORT_CMD_GETHZ           45
+#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)                            \
+        __asm__("inl (%%dx)" :                                          \
+                        "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :    \
+                        "0"(VMWARE_HYPERVISOR_MAGIC),                   \
+                        "1"(VMWARE_PORT_CMD_##cmd),                     \
+                        "2"(VMWARE_HYPERVISOR_PORT), "3"(UINT_MAX) :    \
+                        "memory");
+static inline int __vmware_platform(void)
+{
+        uint32_t eax, ebx, ecx, edx;
+        VMWARE_PORT(GETVERSION, eax, ebx, ecx, edx);
+        return eax != (uint32_t)-1 && ebx == VMWARE_HYPERVISOR_MAGIC;
+}
+static unsigned long __vmware_get_tsc_khz(void)
+{
+        uint64_t tsc_hz;
+        uint32_t eax, ebx, ecx, edx;
+        VMWARE_PORT(GETHZ, eax, ebx, ecx, edx);
+        if (ebx == UINT_MAX)
+                return 0;
+        tsc_hz = eax | (((uint64_t)ebx) << 32);
+        do_div(tsc_hz, 1000);
+        BUG_ON(tsc_hz >> 32);
+        return tsc_hz;
+}
+/*
+ * While checking the dmi string infomation, just checking the product
+ * serial key should be enough, as this will always have a VMware
+ * specific string when running under VMware hypervisor.
+ */
+int vmware_platform(void)
+{
+        if (cpu_has_hypervisor) {
+                unsigned int eax, ebx, ecx, edx;
+                char hyper_vendor_id[13];
+                cpuid(CPUID_VMWARE_INFO_LEAF, &eax, &ebx, &ecx, &edx);
+                memcpy(hyper_vendor_id + 0, &ebx, 4);
+                memcpy(hyper_vendor_id + 4, &ecx, 4);
+                memcpy(hyper_vendor_id + 8, &edx, 4);
+                hyper_vendor_id[12] = '\0';
+                if (!strcmp(hyper_vendor_id, "VMwareVMware"))
+                        return 1;
+        } else if (dmi_available && dmi_name_in_serial("VMware") &&
+                   __vmware_platform())
+                return 1;
+        return 0;
+}
+unsigned long vmware_get_tsc_khz(void)
+{
+        BUG_ON(!vmware_platform());
+        return __vmware_get_tsc_khz();
+}
+/*
+ * VMware hypervisor takes care of exporting a reliable TSC to the guest.
+ * Still, due to timing difference when running on virtual cpus, the TSC can
+ * be marked as unstable in some cases. For example, the TSC sync check at
+ * bootup can fail due to a marginal offset between vcpus' TSCs (though the
+ * TSCs do not drift from each other).  Also, the ACPI PM timer clocksource
+ * is not suitable as a watchdog when running on a hypervisor because the
+ * kernel may miss a wrap of the counter if the vcpu is descheduled for a
+ * long time. To skip these checks at runtime we set these capability bits,
+ * so that the kernel could just trust the hypervisor with providing a
+ * reliable virtual TSC that is suitable for timekeeping.
+ */
+void __cpuinit vmware_set_feature_bits(struct cpuinfo_x86 *c)
+{
+        set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+        set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE);
+}
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 268553817909..d84a852e4cd7 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -29,34 +29,17 @@
 #include <mach_ipi.h>
-/* This keeps a track of which one is crashing cpu. */
-static int crashing_cpu;
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
-static atomic_t waiting_for_crash_ipi;
-static int crash_nmi_callback(struct notifier_block *self,
+static void kdump_nmi_callback(int cpu, struct die_args *args)
-                        unsigned long val, void *data)
 {
        struct pt_regs *regs;
 #ifdef CONFIG_X86_32
        struct pt_regs fixed_regs;
 #endif
-        int cpu;
-        if (val != DIE_NMI_IPI)
+        regs = args->regs;
-                return NOTIFY_OK;
-        regs = ((struct die_args *)data)->regs;
-        cpu = raw_smp_processor_id();
-        /* Don't do anything if this handler is invoked on crashing cpu.
-         * Otherwise, system will completely hang. Crashing cpu can get
-         * an NMI if system was initially booted with nmi_watchdog parameter.
-         */
-        if (cpu == crashing_cpu)
-                return NOTIFY_STOP;
-        local_irq_disable();
 #ifdef CONFIG_X86_32
        if (!user_mode_vm(regs)) {
@@ -65,54 +48,19 @@ static int crash_nmi_callback(struct notifier_block *self,
        }
 #endif
        crash_save_cpu(regs, cpu);
-        disable_local_APIC();
-        atomic_dec(&waiting_for_crash_ipi);
-        /* Assume hlt works */
-        halt();
-        for (;;)
-                cpu_relax();
-        return 1;
-}
-static void smp_send_nmi_allbutself(void)
+        disable_local_APIC();
-{
-        cpumask_t mask = cpu_online_map;
-        cpu_clear(safe_smp_processor_id(), mask);
-        if (!cpus_empty(mask))
-                send_IPI_mask(mask, NMI_VECTOR);
 }
-static struct notifier_block crash_nmi_nb = {
+static void kdump_nmi_shootdown_cpus(void)
-        .notifier_call = crash_nmi_callback,
-};
-static void nmi_shootdown_cpus(void)
 {
-        unsigned long msecs;
+        nmi_shootdown_cpus(kdump_nmi_callback);
-        atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
-        /* Would it be better to replace the trap vector here? */
-        if (register_die_notifier(&crash_nmi_nb))
-                return;         /* return what? */
-        /* Ensure the new callback function is set before sending
-         * out the NMI
-         */
-        wmb();
-        smp_send_nmi_allbutself();
-        msecs = 1000; /* Wait at most a second for the other cpus to stop */
-        while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
-                mdelay(1);
-                msecs--;
-        }
-        /* Leave the nmi callback set */
        disable_local_APIC();
 }
 #else
-static void nmi_shootdown_cpus(void)
+static void kdump_nmi_shootdown_cpus(void)
 {
        /* There are no cpus to shootdown */
 }
@@ -131,9 +79,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
        /* The kernel is broken so disable interrupts */
        local_irq_disable();
-        /* Make a note of crashing cpu. Will be used in NMI callback.*/
+        kdump_nmi_shootdown_cpus();
-        crashing_cpu = safe_smp_processor_id();
-        nmi_shootdown_cpus();
        lapic_shutdown();
 #if defined(CONFIG_X86_IO_APIC)
        disable_IO_APIC();
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index d1a121443bde..d6938d9351cf 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -21,8 +21,6 @@
 */
-#ifdef CONFIG_X86_DS
 #include <asm/ds.h>
 #include <linux/errno.h>
@@ -211,14 +209,15 @@ static DEFINE_PER_CPU(struct ds_context *, system_context);
 static inline struct ds_context *ds_get_context(struct task_struct *task)
 {
        struct ds_context *context;
+        unsigned long irq;
-        spin_lock(&ds_lock);
+        spin_lock_irqsave(&ds_lock, irq);
        context = (task ? task->thread.ds_ctx : this_system_context);
        if (context)
                context->count++;
-        spin_unlock(&ds_lock);
+        spin_unlock_irqrestore(&ds_lock, irq);
        return context;
 }
@@ -226,55 +225,46 @@ static inline struct ds_context *ds_get_context(struct task_struct *task)
 /*
 * Same as ds_get_context, but allocates the context and it's DS
 * structure, if necessary; returns NULL; if out of memory.
- *
- * pre: requires ds_lock to be held
 */
 static inline struct ds_context *ds_alloc_context(struct task_struct *task)
 {
        struct ds_context **p_context =
                (task ? &task->thread.ds_ctx : &this_system_context);
        struct ds_context *context = *p_context;
+        unsigned long irq;
        if (!context) {
-                spin_unlock(&ds_lock);
                context = kzalloc(sizeof(*context), GFP_KERNEL);
+                if (!context)
-                if (!context) {
-                        spin_lock(&ds_lock);
                        return NULL;
-                }
                context->ds = kzalloc(ds_cfg.sizeof_ds, GFP_KERNEL);
                if (!context->ds) {
                        kfree(context);
-                        spin_lock(&ds_lock);
                        return NULL;
                }
-                spin_lock(&ds_lock);
+                spin_lock_irqsave(&ds_lock, irq);
-                /*
-                 * Check for race - another CPU could have allocated
-                 * it meanwhile:
-                 */
                if (*p_context) {
                        kfree(context->ds);
                        kfree(context);
-                        return *p_context;
-                }
-                *p_context = context;
+                        context = *p_context;
+                } else {
+                        *p_context = context;
-                context->this = p_context;
+                        context->this = p_context;
-                context->task = task;
+                        context->task = task;
-                if (task)
+                        if (task)
-                        set_tsk_thread_flag(task, TIF_DS_AREA_MSR);
+                                set_tsk_thread_flag(task, TIF_DS_AREA_MSR);
-                if (!task || (task == current))
+                        if (!task || (task == current))
-                        wrmsr(MSR_IA32_DS_AREA, (unsigned long)context->ds, 0);
+                                wrmsrl(MSR_IA32_DS_AREA,
+                                       (unsigned long)context->ds);
-                get_tracer(task);
+                }
+                spin_unlock_irqrestore(&ds_lock, irq);
        }
        context->count++;
@@ -288,10 +278,12 @@ static inline struct ds_context *ds_alloc_context(struct task_struct *task)
 */
 static inline void ds_put_context(struct ds_context *context)
 {
+        unsigned long irq;
        if (!context)
                return;
-        spin_lock(&ds_lock);
+        spin_lock_irqsave(&ds_lock, irq);
        if (--context->count)
                goto out;
@@ -313,7 +305,7 @@ static inline void ds_put_context(struct ds_context *context)
        kfree(context->ds);
        kfree(context);
 out:
-        spin_unlock(&ds_lock);
+        spin_unlock_irqrestore(&ds_lock, irq);
 }
@@ -384,6 +376,7 @@ static int ds_request(struct task_struct *task, void *base, size_t size,
        struct ds_context *context;
        unsigned long buffer, adj;
        const unsigned long alignment = (1 << 3);
+        unsigned long irq;
        int error = 0;
        if (!ds_cfg.sizeof_ds)
@@ -398,26 +391,27 @@ static int ds_request(struct task_struct *task, void *base, size_t size,
                return -EOPNOTSUPP;
-        spin_lock(&ds_lock);
-        error = -ENOMEM;
        context = ds_alloc_context(task);
        if (!context)
-                goto out_unlock;
+                return -ENOMEM;
+        spin_lock_irqsave(&ds_lock, irq);
        error = -EPERM;
        if (!check_tracer(task))
                goto out_unlock;
+        get_tracer(task);
        error = -EALREADY;
        if (context->owner[qual] == current)
-                goto out_unlock;
+                goto out_put_tracer;
        error = -EPERM;
        if (context->owner[qual] != NULL)
-                goto out_unlock;
+                goto out_put_tracer;
        context->owner[qual] = current;
-        spin_unlock(&ds_lock);
+        spin_unlock_irqrestore(&ds_lock, irq);
        error = -ENOMEM;
@@ -465,10 +459,17 @@ static int ds_request(struct task_struct *task, void *base, size_t size,
 out_release:
        context->owner[qual] = NULL;
        ds_put_context(context);
+        put_tracer(task);
+        return error;
+ out_put_tracer:
+        spin_unlock_irqrestore(&ds_lock, irq);
+        ds_put_context(context);
+        put_tracer(task);
        return error;
 out_unlock:
-        spin_unlock(&ds_lock);
+        spin_unlock_irqrestore(&ds_lock, irq);
        ds_put_context(context);
        return error;
 }
@@ -818,13 +819,21 @@ static const struct ds_configuration ds_cfg_var = {
        .sizeof_ds    = sizeof(long) * 12,
        .sizeof_field = sizeof(long),
        .sizeof_rec[ds_bts]   = sizeof(long) * 3,
+#ifdef __i386__
        .sizeof_rec[ds_pebs]  = sizeof(long) * 10
+#else
+        .sizeof_rec[ds_pebs]  = sizeof(long) * 18
+#endif
 };
 static const struct ds_configuration ds_cfg_64 = {
        .sizeof_ds    = 8 * 12,
        .sizeof_field = 8,
        .sizeof_rec[ds_bts]   = 8 * 3,
+#ifdef __i386__
        .sizeof_rec[ds_pebs]  = 8 * 10
+#else
+        .sizeof_rec[ds_pebs]  = 8 * 18
+#endif
 };
 static inline void
@@ -838,17 +847,16 @@ void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
        switch (c->x86) {
        case 0x6:
                switch (c->x86_model) {
+                case 0 ... 0xC:
+                        /* sorry, don't know about them */
+                        break;
                case 0xD:
                case 0xE: /* Pentium M */
                        ds_configure(&ds_cfg_var);
                        break;
-                case 0xF: /* Core2 */
+                default: /* Core2, Atom, ... */
-                case 0x1C: /* Atom */
                        ds_configure(&ds_cfg_64);
                        break;
-                default:
-                        /* sorry, don't know about them */
-                        break;
                }
                break;
        case 0xF:
@@ -878,4 +886,3 @@ void ds_free(struct ds_context *context)
        while (leftovers--)
                ds_put_context(context);
 }
-#endif /* CONFIG_X86_DS */
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
new file mode 100644
index 000000000000..5962176dfabb
--- /dev/null
+++ b/arch/x86/kernel/dumpstack.c
@@ -0,0 +1,319 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ */
+#include <linux/kallsyms.h>
+#include <linux/kprobes.h>
+#include <linux/uaccess.h>
+#include <linux/utsname.h>
+#include <linux/hardirq.h>
+#include <linux/kdebug.h>
+#include <linux/module.h>
+#include <linux/ptrace.h>
+#include <linux/kexec.h>
+#include <linux/bug.h>
+#include <linux/nmi.h>
+#include <linux/sysfs.h>
+#include <asm/stacktrace.h>
+#include "dumpstack.h"
+int panic_on_unrecovered_nmi;
+unsigned int code_bytes = 64;
+int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
+static int die_counter;
+void printk_address(unsigned long address, int reliable)
+{
+        printk(" [<%p>] %s%pS\n", (void *) address,
+                        reliable ? "" : "? ", (void *) address);
+}
+/*
+ * x86-64 can have up to three kernel stacks:
+ * process stack
+ * interrupt stack
+ * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
+ */
+static inline int valid_stack_ptr(struct thread_info *tinfo,
+                        void *p, unsigned int size, void *end)
+{
+        void *t = tinfo;
+        if (end) {
+                if (p < end && p >= (end-THREAD_SIZE))
+                        return 1;
+                else
+                        return 0;
+        }
+        return p > t && p < t + THREAD_SIZE - size;
+}
+unsigned long
+print_context_stack(struct thread_info *tinfo,
+                unsigned long *stack, unsigned long bp,
+                const struct stacktrace_ops *ops, void *data,
+                unsigned long *end)
+{
+        struct stack_frame *frame = (struct stack_frame *)bp;
+        while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
+                unsigned long addr;
+                addr = *stack;
+                if (__kernel_text_address(addr)) {
+                        if ((unsigned long) stack == bp + sizeof(long)) {
+                                ops->address(data, addr, 1);
+                                frame = frame->next_frame;
+                                bp = (unsigned long) frame;
+                        } else {
+                                ops->address(data, addr, bp == 0);
+                        }
+                }
+                stack++;
+        }
+        return bp;
+}
+static void
+print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
+{
+        printk(data);
+        print_symbol(msg, symbol);
+        printk("\n");
+}
+static void print_trace_warning(void *data, char *msg)
+{
+        printk("%s%s\n", (char *)data, msg);
+}
+static int print_trace_stack(void *data, char *name)
+{
+        printk("%s <%s> ", (char *)data, name);
+        return 0;
+}
+/*
+ * Print one address/symbol entries per line.
+ */
+static void print_trace_address(void *data, unsigned long addr, int reliable)
+{
+        touch_nmi_watchdog();
+        printk(data);
+        printk_address(addr, reliable);
+}
+static const struct stacktrace_ops print_trace_ops = {
+        .warning = print_trace_warning,
+        .warning_symbol = print_trace_warning_symbol,
+        .stack = print_trace_stack,
+        .address = print_trace_address,
+};
+void
+show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+                unsigned long *stack, unsigned long bp, char *log_lvl)
+{
+        printk("%sCall Trace:\n", log_lvl);
+        dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
+}
+void show_trace(struct task_struct *task, struct pt_regs *regs,
+                unsigned long *stack, unsigned long bp)
+{
+        show_trace_log_lvl(task, regs, stack, bp, "");
+}
+void show_stack(struct task_struct *task, unsigned long *sp)
+{
+        show_stack_log_lvl(task, NULL, sp, 0, "");
+}
+/*
+ * The architecture-independent dump_stack generator
+ */
+void dump_stack(void)
+{
+        unsigned long bp = 0;
+        unsigned long stack;
+#ifdef CONFIG_FRAME_POINTER
+        if (!bp)
+                get_bp(bp);
+#endif
+        printk("Pid: %d, comm: %.20s %s %s %.*s\n",
+                current->pid, current->comm, print_tainted(),
+                init_utsname()->release,
+                (int)strcspn(init_utsname()->version, " "),
+                init_utsname()->version);
+        show_trace(NULL, NULL, &stack, bp);
+}
+EXPORT_SYMBOL(dump_stack);
+static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED;
+static int die_owner = -1;
+static unsigned int die_nest_count;
+unsigned __kprobes long oops_begin(void)
+{
+        int cpu;
+        unsigned long flags;
+        oops_enter();
+        /* racy, but better than risking deadlock. */
+        raw_local_irq_save(flags);
+        cpu = smp_processor_id();
+        if (!__raw_spin_trylock(&die_lock)) {
+                if (cpu == die_owner)
+                        /* nested oops. should stop eventually */;
+                else
+                        __raw_spin_lock(&die_lock);
+        }
+        die_nest_count++;
+        die_owner = cpu;
+        console_verbose();
+        bust_spinlocks(1);
+        return flags;
+}
+void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
+{
+        if (regs && kexec_should_crash(current))
+                crash_kexec(regs);
+        bust_spinlocks(0);
+        die_owner = -1;
+        add_taint(TAINT_DIE);
+        die_nest_count--;
+        if (!die_nest_count)
+                /* Nest count reaches zero, release the lock. */
+                __raw_spin_unlock(&die_lock);
+        raw_local_irq_restore(flags);
+        oops_exit();
+        if (!signr)
+                return;
+        if (in_interrupt())
+                panic("Fatal exception in interrupt");
+        if (panic_on_oops)
+                panic("Fatal exception");
+        do_exit(signr);
+}
+int __kprobes __die(const char *str, struct pt_regs *regs, long err)
+{
+#ifdef CONFIG_X86_32
+        unsigned short ss;
+        unsigned long sp;
+#endif
+        printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
+#ifdef CONFIG_PREEMPT
+        printk("PREEMPT ");
+#endif
+#ifdef CONFIG_SMP
+        printk("SMP ");
+#endif
+#ifdef CONFIG_DEBUG_PAGEALLOC
+        printk("DEBUG_PAGEALLOC");
+#endif
+        printk("\n");
+        sysfs_printk_last_file();
+        if (notify_die(DIE_OOPS, str, regs, err,
+                        current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
+                return 1;
+        show_registers(regs);
+#ifdef CONFIG_X86_32
+        sp = (unsigned long) (&regs->sp);
+        savesegment(ss, ss);
+        if (user_mode(regs)) {
+                sp = regs->sp;
+                ss = regs->ss & 0xffff;
+        }
+        printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip);
+        print_symbol("%s", regs->ip);
+        printk(" SS:ESP %04x:%08lx\n", ss, sp);
+#else
+        /* Executive summary in case the oops scrolled away */
+        printk(KERN_ALERT "RIP ");
+        printk_address(regs->ip, 1);
+        printk(" RSP <%016lx>\n", regs->sp);
+#endif
+        return 0;
+}
+/*
+ * This is gone through when something in the kernel has done something bad
+ * and is about to be terminated:
+ */
+void die(const char *str, struct pt_regs *regs, long err)
+{
+        unsigned long flags = oops_begin();
+        int sig = SIGSEGV;
+        if (!user_mode_vm(regs))
+                report_bug(regs->ip, regs);
+        if (__die(str, regs, err))
+                sig = 0;
+        oops_end(flags, regs, sig);
+}
+void notrace __kprobes
+die_nmi(char *str, struct pt_regs *regs, int do_panic)
+{
+        unsigned long flags;
+        if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
+                return;
+        /*
+         * We are in trouble anyway, lets at least try
+         * to get a message out.
+         */
+        flags = oops_begin();
+        printk(KERN_EMERG "%s", str);
+        printk(" on CPU%d, ip %08lx, registers:\n",
+                smp_processor_id(), regs->ip);
+        show_registers(regs);
+        oops_end(flags, regs, 0);
+        if (do_panic || panic_on_oops)
+                panic("Non maskable interrupt");
+        nmi_exit();
+        local_irq_enable();
+        do_exit(SIGBUS);
+}
+static int __init oops_setup(char *s)
+{
+        if (!s)
+                return -EINVAL;
+        if (!strcmp(s, "panic"))
+                panic_on_oops = 1;
+        return 0;
+}
+early_param("oops", oops_setup);
+static int __init kstack_setup(char *s)
+{
+        if (!s)
+                return -EINVAL;
+        kstack_depth_to_print = simple_strtoul(s, NULL, 0);
+        return 0;
+}
+early_param("kstack", kstack_setup);
+static int __init code_bytes_setup(char *s)
+{
+        code_bytes = simple_strtoul(s, NULL, 0);
+        if (code_bytes > 8192)
+                code_bytes = 8192;
+        return 1;
+}
+__setup("code_bytes=", code_bytes_setup);
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
new file mode 100644
index 000000000000..3119a801c32b
--- /dev/null
+++ b/arch/x86/kernel/dumpstack.h
@@ -0,0 +1,39 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ */
+#ifndef DUMPSTACK_H
+#define DUMPSTACK_H
+#ifdef CONFIG_X86_32
+#define STACKSLOTS_PER_LINE 8
+#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
+#else
+#define STACKSLOTS_PER_LINE 4
+#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
+#endif
+extern unsigned long
+print_context_stack(struct thread_info *tinfo,
+                unsigned long *stack, unsigned long bp,
+                const struct stacktrace_ops *ops, void *data,
+                unsigned long *end);
+extern void
+show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+                unsigned long *stack, unsigned long bp, char *log_lvl);
+extern void
+show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
+                unsigned long *sp, unsigned long bp, char *log_lvl);
+extern unsigned int code_bytes;
+extern int kstack_depth_to_print;
+/* The form of the top of the frame on the stack */
+struct stack_frame {
+        struct stack_frame *next_frame;
+        unsigned long return_address;
+};
+#endif
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index b3614752197b..7b031b106ec8 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -17,64 +17,7 @@
 #include <asm/stacktrace.h>
-#define STACKSLOTS_PER_LINE 8
+#include "dumpstack.h"
-#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
-int panic_on_unrecovered_nmi;
-int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
-static unsigned int code_bytes = 64;
-static int die_counter;
-void printk_address(unsigned long address, int reliable)
-{
-        printk(" [<%p>] %s%pS\n", (void *) address,
-                        reliable ? "" : "? ", (void *) address);
-}
-static inline int valid_stack_ptr(struct thread_info *tinfo,
-                        void *p, unsigned int size, void *end)
-{
-        void *t = tinfo;
-        if (end) {
-                if (p < end && p >= (end-THREAD_SIZE))
-                        return 1;
-                else
-                        return 0;
-        }
-        return p > t && p < t + THREAD_SIZE - size;
-}
-/* The form of the top of the frame on the stack */
-struct stack_frame {
-        struct stack_frame *next_frame;
-        unsigned long return_address;
-};
-static inline unsigned long
-print_context_stack(struct thread_info *tinfo,
-                unsigned long *stack, unsigned long bp,
-                const struct stacktrace_ops *ops, void *data,
-                unsigned long *end)
-{
-        struct stack_frame *frame = (struct stack_frame *)bp;
-        while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
-                unsigned long addr;
-                addr = *stack;
-                if (__kernel_text_address(addr)) {
-                        if ((unsigned long) stack == bp + sizeof(long)) {
-                                ops->address(data, addr, 1);
-                                frame = frame->next_frame;
-                                bp = (unsigned long) frame;
-                        } else {
-                                ops->address(data, addr, bp == 0);
-                        }
-                }
-                stack++;
-        }
-        return bp;
-}
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
                unsigned long *stack, unsigned long bp,
@@ -119,57 +62,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 }
 EXPORT_SYMBOL(dump_trace);
-static void
+void
-print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
-{
-        printk(data);
-        print_symbol(msg, symbol);
-        printk("\n");
-}
-static void print_trace_warning(void *data, char *msg)
-{
-        printk("%s%s\n", (char *)data, msg);
-}
-static int print_trace_stack(void *data, char *name)
-{
-        printk("%s <%s> ", (char *)data, name);
-        return 0;
-}
-/*
- * Print one address/symbol entries per line.
- */
-static void print_trace_address(void *data, unsigned long addr, int reliable)
-{
-        touch_nmi_watchdog();
-        printk(data);
-        printk_address(addr, reliable);
-}
-static const struct stacktrace_ops print_trace_ops = {
-        .warning = print_trace_warning,
-        .warning_symbol = print_trace_warning_symbol,
-        .stack = print_trace_stack,
-        .address = print_trace_address,
-};
-static void
-show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-                unsigned long *stack, unsigned long bp, char *log_lvl)
-{
-        printk("%sCall Trace:\n", log_lvl);
-        dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
-}
-void show_trace(struct task_struct *task, struct pt_regs *regs,
-                unsigned long *stack, unsigned long bp)
-{
-        show_trace_log_lvl(task, regs, stack, bp, "");
-}
-static void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
                unsigned long *sp, unsigned long bp, char *log_lvl)
 {
@@ -196,33 +89,6 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
        show_trace_log_lvl(task, regs, sp, bp, log_lvl);
 }
-void show_stack(struct task_struct *task, unsigned long *sp)
-{
-        show_stack_log_lvl(task, NULL, sp, 0, "");
-}
-/*
- * The architecture-independent dump_stack generator
- */
-void dump_stack(void)
-{
-        unsigned long bp = 0;
-        unsigned long stack;
-#ifdef CONFIG_FRAME_POINTER
-        if (!bp)
-                get_bp(bp);
-#endif
-        printk("Pid: %d, comm: %.20s %s %s %.*s\n",
-                current->pid, current->comm, print_tainted(),
-                init_utsname()->release,
-                (int)strcspn(init_utsname()->version, " "),
-                init_utsname()->version);
-        show_trace(NULL, NULL, &stack, bp);
-}
-EXPORT_SYMBOL(dump_stack);
 void show_registers(struct pt_regs *regs)
 {
@@ -283,167 +149,3 @@ int is_valid_bugaddr(unsigned long ip)
        return ud2 == 0x0b0f;
 }
-static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED;
-static int die_owner = -1;
-static unsigned int die_nest_count;
-unsigned __kprobes long oops_begin(void)
-{
-        unsigned long flags;
-        oops_enter();
-        if (die_owner != raw_smp_processor_id()) {
-                console_verbose();
-                raw_local_irq_save(flags);
-                __raw_spin_lock(&die_lock);
-                die_owner = smp_processor_id();
-                die_nest_count = 0;
-                bust_spinlocks(1);
-        } else {
-                raw_local_irq_save(flags);
-        }
-        die_nest_count++;
-        return flags;
-}
-void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
-{
-        bust_spinlocks(0);
-        die_owner = -1;
-        add_taint(TAINT_DIE);
-        __raw_spin_unlock(&die_lock);
-        raw_local_irq_restore(flags);
-        if (!regs)
-                return;
-        if (kexec_should_crash(current))
-                crash_kexec(regs);
-        if (in_interrupt())
-                panic("Fatal exception in interrupt");
-        if (panic_on_oops)
-                panic("Fatal exception");
-        oops_exit();
-        do_exit(signr);
-}
-int __kprobes __die(const char *str, struct pt_regs *regs, long err)
-{
-        unsigned short ss;
-        unsigned long sp;
-        printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
-#ifdef CONFIG_PREEMPT
-        printk("PREEMPT ");
-#endif
-#ifdef CONFIG_SMP
-        printk("SMP ");
-#endif
-#ifdef CONFIG_DEBUG_PAGEALLOC
-        printk("DEBUG_PAGEALLOC");
-#endif
-        printk("\n");
-        sysfs_printk_last_file();
-        if (notify_die(DIE_OOPS, str, regs, err,
-                        current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
-                return 1;
-        show_registers(regs);
-        /* Executive summary in case the oops scrolled away */
-        sp = (unsigned long) (&regs->sp);
-        savesegment(ss, ss);
-        if (user_mode(regs)) {
-                sp = regs->sp;
-                ss = regs->ss & 0xffff;
-        }
-        printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip);
-        print_symbol("%s", regs->ip);
-        printk(" SS:ESP %04x:%08lx\n", ss, sp);
-        return 0;
-}
-/*
- * This is gone through when something in the kernel has done something bad
- * and is about to be terminated:
- */
-void die(const char *str, struct pt_regs *regs, long err)
-{
-        unsigned long flags = oops_begin();
-        if (die_nest_count < 3) {
-                report_bug(regs->ip, regs);
-                if (__die(str, regs, err))
-                        regs = NULL;
-        } else {
-                printk(KERN_EMERG "Recursive die() failure, output suppressed\n");
-        }
-        oops_end(flags, regs, SIGSEGV);
-}
-static DEFINE_SPINLOCK(nmi_print_lock);
-void notrace __kprobes
-die_nmi(char *str, struct pt_regs *regs, int do_panic)
-{
-        if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
-                return;
-        spin_lock(&nmi_print_lock);
-        /*
-        * We are in trouble anyway, lets at least try
-        * to get a message out:
-        */
-        bust_spinlocks(1);
-        printk(KERN_EMERG "%s", str);
-        printk(" on CPU%d, ip %08lx, registers:\n",
-                smp_processor_id(), regs->ip);
-        show_registers(regs);
-        if (do_panic)
-                panic("Non maskable interrupt");
-        console_silent();
-        spin_unlock(&nmi_print_lock);
-        /*
-         * If we are in kernel we are probably nested up pretty bad
-         * and might aswell get out now while we still can:
-         */
-        if (!user_mode_vm(regs)) {
-                current->thread.trap_no = 2;
-                crash_kexec(regs);
-        }
-        bust_spinlocks(0);
-        do_exit(SIGSEGV);
-}
-static int __init oops_setup(char *s)
-{
-        if (!s)
-                return -EINVAL;
-        if (!strcmp(s, "panic"))
-                panic_on_oops = 1;
-        return 0;
-}
-early_param("oops", oops_setup);
-static int __init kstack_setup(char *s)
-{
-        if (!s)
-                return -EINVAL;
-        kstack_depth_to_print = simple_strtoul(s, NULL, 0);
-        return 0;
-}
-early_param("kstack", kstack_setup);
-static int __init code_bytes_setup(char *s)
-{
-        code_bytes = simple_strtoul(s, NULL, 0);
-        if (code_bytes > 8192)
-                code_bytes = 8192;
-        return 1;
-}
-__setup("code_bytes=", code_bytes_setup);
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 96a5db7da8a7..33ff10287a5d 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -17,19 +17,7 @@
 #include <asm/stacktrace.h>
-#define STACKSLOTS_PER_LINE 4
+#include "dumpstack.h"
-#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
-int panic_on_unrecovered_nmi;
-int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
-static unsigned int code_bytes = 64;
-static int die_counter;
-void printk_address(unsigned long address, int reliable)
-{
-        printk(" [<%p>] %s%pS\n", (void *) address,
-                        reliable ? "" : "? ", (void *) address);
-}
 static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
                                        unsigned *usedp, char **idp)
@@ -113,51 +101,6 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
 * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
 */
-static inline int valid_stack_ptr(struct thread_info *tinfo,
-                        void *p, unsigned int size, void *end)
-{
-        void *t = tinfo;
-        if (end) {
-                if (p < end && p >= (end-THREAD_SIZE))
-                        return 1;
-                else
-                        return 0;
-        }
-        return p > t && p < t + THREAD_SIZE - size;
-}
-/* The form of the top of the frame on the stack */
-struct stack_frame {
-        struct stack_frame *next_frame;
-        unsigned long return_address;
-};
-static inline unsigned long
-print_context_stack(struct thread_info *tinfo,
-                unsigned long *stack, unsigned long bp,
-                const struct stacktrace_ops *ops, void *data,
-                unsigned long *end)
-{
-        struct stack_frame *frame = (struct stack_frame *)bp;
-        while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
-                unsigned long addr;
-                addr = *stack;
-                if (__kernel_text_address(addr)) {
-                        if ((unsigned long) stack == bp + sizeof(long)) {
-                                ops->address(data, addr, 1);
-                                frame = frame->next_frame;
-                                bp = (unsigned long) frame;
-                        } else {
-                                ops->address(data, addr, bp == 0);
-                        }
-                }
-                stack++;
-        }
-        return bp;
-}
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
                unsigned long *stack, unsigned long bp,
                const struct stacktrace_ops *ops, void *data)
@@ -248,57 +191,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 }
 EXPORT_SYMBOL(dump_trace);
-static void
+void
-print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
-{
-        printk(data);
-        print_symbol(msg, symbol);
-        printk("\n");
-}
-static void print_trace_warning(void *data, char *msg)
-{
-        printk("%s%s\n", (char *)data, msg);
-}
-static int print_trace_stack(void *data, char *name)
-{
-        printk("%s <%s> ", (char *)data, name);
-        return 0;
-}
-/*
- * Print one address/symbol entries per line.
- */
-static void print_trace_address(void *data, unsigned long addr, int reliable)
-{
-        touch_nmi_watchdog();
-        printk(data);
-        printk_address(addr, reliable);
-}
-static const struct stacktrace_ops print_trace_ops = {
-        .warning = print_trace_warning,
-        .warning_symbol = print_trace_warning_symbol,
-        .stack = print_trace_stack,
-        .address = print_trace_address,
-};
-static void
-show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-                unsigned long *stack, unsigned long bp, char *log_lvl)
-{
-        printk("%sCall Trace:\n", log_lvl);
-        dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
-}
-void show_trace(struct task_struct *task, struct pt_regs *regs,
-                unsigned long *stack, unsigned long bp)
-{
-        show_trace_log_lvl(task, regs, stack, bp, "");
-}
-static void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
                unsigned long *sp, unsigned long bp, char *log_lvl)
 {
@@ -342,33 +235,6 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
        show_trace_log_lvl(task, regs, sp, bp, log_lvl);
 }
-void show_stack(struct task_struct *task, unsigned long *sp)
-{
-        show_stack_log_lvl(task, NULL, sp, 0, "");
-}
-/*
- * The architecture-independent dump_stack generator
- */
-void dump_stack(void)
-{
-        unsigned long bp = 0;
-        unsigned long stack;
-#ifdef CONFIG_FRAME_POINTER
-        if (!bp)
-                get_bp(bp);
-#endif
-        printk("Pid: %d, comm: %.20s %s %s %.*s\n",
-                current->pid, current->comm, print_tainted(),
-                init_utsname()->release,
-                (int)strcspn(init_utsname()->version, " "),
-                init_utsname()->version);
-        show_trace(NULL, NULL, &stack, bp);
-}
-EXPORT_SYMBOL(dump_stack);
 void show_registers(struct pt_regs *regs)
 {
        int i;
@@ -429,147 +295,3 @@ int is_valid_bugaddr(unsigned long ip)
        return ud2 == 0x0b0f;
 }
-static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED;
-static int die_owner = -1;
-static unsigned int die_nest_count;
-unsigned __kprobes long oops_begin(void)
-{
-        int cpu;
-        unsigned long flags;
-        oops_enter();
-        /* racy, but better than risking deadlock. */
-        raw_local_irq_save(flags);
-        cpu = smp_processor_id();
-        if (!__raw_spin_trylock(&die_lock)) {
-                if (cpu == die_owner)
-                        /* nested oops. should stop eventually */;
-                else
-                        __raw_spin_lock(&die_lock);
-        }
-        die_nest_count++;
-        die_owner = cpu;
-        console_verbose();
-        bust_spinlocks(1);
-        return flags;
-}
-void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
-{
-        die_owner = -1;
-        bust_spinlocks(0);
-        die_nest_count--;
-        if (!die_nest_count)
-                /* Nest count reaches zero, release the lock. */
-                __raw_spin_unlock(&die_lock);
-        raw_local_irq_restore(flags);
-        if (!regs) {
-                oops_exit();
-                return;
-        }
-        if (in_interrupt())
-                panic("Fatal exception in interrupt");
-        if (panic_on_oops)
-                panic("Fatal exception");
-        oops_exit();
-        do_exit(signr);
-}
-int __kprobes __die(const char *str, struct pt_regs *regs, long err)
-{
-        printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
-#ifdef CONFIG_PREEMPT
-        printk("PREEMPT ");
-#endif
-#ifdef CONFIG_SMP
-        printk("SMP ");
-#endif
-#ifdef CONFIG_DEBUG_PAGEALLOC
-        printk("DEBUG_PAGEALLOC");
-#endif
-        printk("\n");
-        sysfs_printk_last_file();
-        if (notify_die(DIE_OOPS, str, regs, err,
-                        current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
-                return 1;
-        show_registers(regs);
-        add_taint(TAINT_DIE);
-        /* Executive summary in case the oops scrolled away */
-        printk(KERN_ALERT "RIP ");
-        printk_address(regs->ip, 1);
-        printk(" RSP <%016lx>\n", regs->sp);
-        if (kexec_should_crash(current))
-                crash_kexec(regs);
-        return 0;
-}
-void die(const char *str, struct pt_regs *regs, long err)
-{
-        unsigned long flags = oops_begin();
-        if (!user_mode(regs))
-                report_bug(regs->ip, regs);
-        if (__die(str, regs, err))
-                regs = NULL;
-        oops_end(flags, regs, SIGSEGV);
-}
-notrace __kprobes void
-die_nmi(char *str, struct pt_regs *regs, int do_panic)
-{
-        unsigned long flags;
-        if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
-                return;
-        flags = oops_begin();
-        /*
-         * We are in trouble anyway, lets at least try
-         * to get a message out.
-         */
-        printk(KERN_EMERG "%s", str);
-        printk(" on CPU%d, ip %08lx, registers:\n",
-                smp_processor_id(), regs->ip);
-        show_registers(regs);
-        if (kexec_should_crash(current))
-                crash_kexec(regs);
-        if (do_panic || panic_on_oops)
-                panic("Non maskable interrupt");
-        oops_end(flags, NULL, SIGBUS);
-        nmi_exit();
-        local_irq_enable();
-        do_exit(SIGBUS);
-}
-static int __init oops_setup(char *s)
-{
-        if (!s)
-                return -EINVAL;
-        if (!strcmp(s, "panic"))
-                panic_on_oops = 1;
-        return 0;
-}
-early_param("oops", oops_setup);
-static int __init kstack_setup(char *s)
-{
-        if (!s)
-                return -EINVAL;
-        kstack_depth_to_print = simple_strtoul(s, NULL, 0);
-        return 0;
-}
-early_param("kstack", kstack_setup);
-static int __init code_bytes_setup(char *s)
-{
-        code_bytes = simple_strtoul(s, NULL, 0);
-        if (code_bytes > 8192)
-                code_bytes = 8192;
-        return 1;
-}
-__setup("code_bytes=", code_bytes_setup);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 7aafeb5263ef..65a13943e098 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -677,22 +677,6 @@ struct early_res {
 };
 static struct early_res early_res[MAX_EARLY_RES] __initdata = {
        { 0, PAGE_SIZE, "BIOS data page" },     /* BIOS data page */
-#if defined(CONFIG_X86_64) && defined(CONFIG_X86_TRAMPOLINE)
-        { TRAMPOLINE_BASE, TRAMPOLINE_BASE + 2 * PAGE_SIZE, "TRAMPOLINE" },
-#endif
-#if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
-        /*
-         * But first pinch a few for the stack/trampoline stuff
-         * FIXME: Don't need the extra page at 4K, but need to fix
-         * trampoline before removing it. (see the GDT stuff)
-         */
-        { PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE" },
-        /*
-         * Has to be in very low memory so we can execute
-         * real-mode AP code.
-         */
-        { TRAMPOLINE_BASE, TRAMPOLINE_BASE + PAGE_SIZE, "TRAMPOLINE" },
-#endif
        {}
 };
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 34ad997d3834..23b138e31e9c 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -875,49 +875,6 @@ static struct console early_dbgp_console = {
 };
 #endif
-/* Console interface to a host file on AMD's SimNow! */
-static int simnow_fd;
-enum {
-        MAGIC1 = 0xBACCD00A,
-        MAGIC2 = 0xCA110000,
-        XOPEN = 5,
-        XWRITE = 4,
-};
-static noinline long simnow(long cmd, long a, long b, long c)
-{
-        long ret;
-        asm volatile("cpuid" :
-                     "=a" (ret) :
-                     "b" (a), "c" (b), "d" (c), "0" (MAGIC1), "D" (cmd + MAGIC2));
-        return ret;
-}
-static void __init simnow_init(char *str)
-{
-        char *fn = "klog";
-        if (*str == '=')
-                fn = ++str;
-        /* error ignored */
-        simnow_fd = simnow(XOPEN, (unsigned long)fn, O_WRONLY|O_APPEND|O_CREAT, 0644);
-}
-static void simnow_write(struct console *con, const char *s, unsigned n)
-{
-        simnow(XWRITE, simnow_fd, (unsigned long)s, n);
-}
-static struct console simnow_console = {
-        .name =         "simnow",
-        .write =        simnow_write,
-        .flags =        CON_PRINTBUFFER,
-        .index =        -1,
-};
 /* Direct interface for emergencies */
 static struct console *early_console = &early_vga_console;
 static int __initdata early_console_initialized;
@@ -960,10 +917,6 @@ static int __init setup_early_printk(char *buf)
                max_ypos = boot_params.screen_info.orig_video_lines;
                current_ypos = boot_params.screen_info.orig_y;
                early_console = &early_vga_console;
-        } else if (!strncmp(buf, "simnow", 6)) {
-                simnow_init(buf + 6);
-                early_console = &simnow_console;
-                keep_early = 1;
 #ifdef CONFIG_EARLY_PRINTK_DBGP
        } else if (!strncmp(buf, "dbgp", 4)) {
                if (early_dbgp_init(buf+4) < 0)
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 28b597ef9ca1..f6402c4ba10d 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1051,6 +1051,7 @@ ENTRY(kernel_thread_helper)
        push %eax
        CFI_ADJUST_CFA_OFFSET 4
        call do_exit
+        ud2                     # padding for call trace
        CFI_ENDPROC
 ENDPROC(kernel_thread_helper)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index b86f332c96a6..42571baaca32 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -11,15 +11,15 @@
 *
 * NOTE: This code handles signal-recognition, which happens every time
 * after an interrupt and after each system call.
- * 
+ *
- * Normal syscalls and interrupts don't save a full stack frame, this is 
+ * Normal syscalls and interrupts don't save a full stack frame, this is
 * only done for syscall tracing, signals or fork/exec et.al.
- * 
+ *
- * A note on terminology:        
+ * A note on terminology:
- * - top of stack: Architecture defined interrupt frame from SS to RIP 
+ * - top of stack: Architecture defined interrupt frame from SS to RIP
- * at the top of the kernel process stack.      
+ * at the top of the kernel process stack.
 * - partial stack frame: partially saved registers upto R11.
- * - full stack frame: Like partial stack frame, but all register saved. 
+ * - full stack frame: Like partial stack frame, but all register saved.
 *
 * Some macro usage:
 * - CFI macros are used to generate dwarf2 unwind information for better
@@ -142,7 +142,7 @@ END(mcount)
 #ifndef CONFIG_PREEMPT
 #define retint_kernel retint_restore_args
-#endif  
+#endif
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_usergs_sysret64)
@@ -161,14 +161,14 @@ ENTRY(native_usergs_sysret64)
 .endm
 /*
- * C code is not supposed to know about undefined top of stack. Every time 
+ * C code is not supposed to know about undefined top of stack. Every time
- * a C function with an pt_regs argument is called from the SYSCALL based 
+ * a C function with an pt_regs argument is called from the SYSCALL based
 * fast path FIXUP_TOP_OF_STACK is needed.
 * RESTORE_TOP_OF_STACK syncs the syscall state after any possible ptregs
 * manipulation.
- */             
+ */
-                
-        /* %rsp:at FRAMEEND */ 
+        /* %rsp:at FRAMEEND */
        .macro FIXUP_TOP_OF_STACK tmp
        movq    %gs:pda_oldrsp,\tmp
        movq    \tmp,RSP(%rsp)
@@ -244,8 +244,8 @@ ENTRY(native_usergs_sysret64)
        .endm
 /*
 * A newly forked process directly context switches into this.
- */     
+ */
-/* rdi: prev */ 
+/* rdi: prev */
 ENTRY(ret_from_fork)
        CFI_DEFAULT_STACK
        push kernel_eflags(%rip)
@@ -255,8 +255,9 @@ ENTRY(ret_from_fork)
        call schedule_tail
        GET_THREAD_INFO(%rcx)
        testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
+        CFI_REMEMBER_STATE
        jnz rff_trace
-rff_action:     
+rff_action:
        RESTORE_REST
        testl $3,CS-ARGOFFSET(%rsp)     # from kernel_thread?
        je   int_ret_from_sys_call
@@ -264,10 +265,11 @@ rff_action:
        jnz  int_ret_from_sys_call
        RESTORE_TOP_OF_STACK %rdi,ARGOFFSET
        jmp ret_from_sys_call
+        CFI_RESTORE_STATE
 rff_trace:
        movq %rsp,%rdi
        call syscall_trace_leave
-        GET_THREAD_INFO(%rcx)   
+        GET_THREAD_INFO(%rcx)
        jmp rff_action
        CFI_ENDPROC
 END(ret_from_fork)
@@ -278,20 +280,20 @@ END(ret_from_fork)
 * SYSCALL does not save anything on the stack and does not change the
 * stack pointer.
 */
-                
 /*
- * Register setup:      
+ * Register setup:
 * rax  system call number
 * rdi  arg0
- * rcx  return address for syscall/sysret, C arg3 
+ * rcx  return address for syscall/sysret, C arg3
 * rsi  arg1
- * rdx  arg2    
+ * rdx  arg2
 * r10  arg3    (--> moved to rcx for C)
 * r8   arg4
 * r9   arg5
 * r11  eflags for syscall/sysret, temporary for C
- * r12-r15,rbp,rbx saved by C code, not touched.                
+ * r12-r15,rbp,rbx saved by C code, not touched.
- * 
+ *
 * Interrupts are off on entry.
 * Only called from user space.
 *
@@ -301,7 +303,7 @@ END(ret_from_fork)
 * When user can change the frames always force IRET. That is because
 * it deals with uncanonical addresses better. SYSRET has trouble
 * with them due to bugs in both AMD and Intel CPUs.
- */                                     
+ */
 ENTRY(system_call)
        CFI_STARTPROC   simple
@@ -317,7 +319,7 @@ ENTRY(system_call)
         */
 ENTRY(system_call_after_swapgs)
-        movq    %rsp,%gs:pda_oldrsp 
+        movq    %rsp,%gs:pda_oldrsp
        movq    %gs:pda_kernelstack,%rsp
        /*
         * No need to follow this irqs off/on section - it's straight
@@ -325,7 +327,7 @@ ENTRY(system_call_after_swapgs)
         */
        ENABLE_INTERRUPTS(CLBR_NONE)
        SAVE_ARGS 8,1
-        movq  %rax,ORIG_RAX-ARGOFFSET(%rsp) 
+        movq  %rax,ORIG_RAX-ARGOFFSET(%rsp)
        movq  %rcx,RIP-ARGOFFSET(%rsp)
        CFI_REL_OFFSET rip,RIP-ARGOFFSET
        GET_THREAD_INFO(%rcx)
@@ -339,19 +341,19 @@ system_call_fastpath:
        movq %rax,RAX-ARGOFFSET(%rsp)
 /*
 * Syscall return path ending with SYSRET (fast path)
- * Has incomplete stack frame and undefined top of stack. 
+ * Has incomplete stack frame and undefined top of stack.
- */             
+ */
 ret_from_sys_call:
        movl $_TIF_ALLWORK_MASK,%edi
        /* edi: flagmask */
-sysret_check:           
+sysret_check:
        LOCKDEP_SYS_EXIT
        GET_THREAD_INFO(%rcx)
        DISABLE_INTERRUPTS(CLBR_NONE)
        TRACE_IRQS_OFF
        movl TI_flags(%rcx),%edx
        andl %edi,%edx
-        jnz  sysret_careful 
+        jnz  sysret_careful
        CFI_REMEMBER_STATE
        /*
         * sysretq will re-enable interrupts:
@@ -366,7 +368,7 @@ sysret_check:
        CFI_RESTORE_STATE
        /* Handle reschedules */
-        /* edx: work, edi: workmask */  
+        /* edx: work, edi: workmask */
 sysret_careful:
        bt $TIF_NEED_RESCHED,%edx
        jnc sysret_signal
@@ -379,7 +381,7 @@ sysret_careful:
        CFI_ADJUST_CFA_OFFSET -8
        jmp sysret_check
-        /* Handle a signal */ 
+        /* Handle a signal */
 sysret_signal:
        TRACE_IRQS_ON
        ENABLE_INTERRUPTS(CLBR_NONE)
@@ -398,7 +400,7 @@ sysret_signal:
        DISABLE_INTERRUPTS(CLBR_NONE)
        TRACE_IRQS_OFF
        jmp int_with_check
-        
 badsys:
        movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
        jmp ret_from_sys_call
@@ -437,7 +439,7 @@ sysret_audit:
 #endif  /* CONFIG_AUDITSYSCALL */
        /* Do syscall tracing */
-tracesys:                        
+tracesys:
 #ifdef CONFIG_AUDITSYSCALL
        testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
        jz auditsys
@@ -460,8 +462,8 @@ tracesys:
        call *sys_call_table(,%rax,8)
        movq %rax,RAX-ARGOFFSET(%rsp)
        /* Use IRET because user could have changed frame */
-                
-/* 
+/*
 * Syscall return path ending with IRET.
 * Has correct top of stack, but partial stack frame.
 */
@@ -505,18 +507,18 @@ int_very_careful:
        TRACE_IRQS_ON
        ENABLE_INTERRUPTS(CLBR_NONE)
        SAVE_REST
-        /* Check for syscall exit trace */      
+        /* Check for syscall exit trace */
        testl $_TIF_WORK_SYSCALL_EXIT,%edx
        jz int_signal
        pushq %rdi
        CFI_ADJUST_CFA_OFFSET 8
-        leaq 8(%rsp),%rdi       # &ptregs -> arg1       
+        leaq 8(%rsp),%rdi       # &ptregs -> arg1
        call syscall_trace_leave
        popq %rdi
        CFI_ADJUST_CFA_OFFSET -8
        andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
        jmp int_restore_rest
-        
 int_signal:
        testl $_TIF_DO_NOTIFY_MASK,%edx
        jz 1f
@@ -531,11 +533,11 @@ int_restore_rest:
        jmp int_with_check
        CFI_ENDPROC
 END(system_call)
-                
-/* 
+/*
 * Certain special system calls that need to save a complete full stack frame.
- */                                                             
+ */
-        
        .macro PTREGSCALL label,func,arg
        .globl \label
 \label:
@@ -572,7 +574,7 @@ ENTRY(ptregscall_common)
        ret
        CFI_ENDPROC
 END(ptregscall_common)
-        
 ENTRY(stub_execve)
        CFI_STARTPROC
        popq %r11
@@ -588,11 +590,11 @@ ENTRY(stub_execve)
        jmp int_ret_from_sys_call
        CFI_ENDPROC
 END(stub_execve)
-        
 /*
 * sigreturn is special because it needs to restore all registers on return.
 * This cannot be done with SYSRET, so use the IRET return path instead.
- */                
+ */
 ENTRY(stub_rt_sigreturn)
        CFI_STARTPROC
        addq $8, %rsp
@@ -685,12 +687,12 @@ exit_intr:
        GET_THREAD_INFO(%rcx)
        testl $3,CS-ARGOFFSET(%rsp)
        je retint_kernel
-        
        /* Interrupt came from user space */
        /*
         * Has a correct top of stack, but a partial stack frame
         * %rcx: thread info. Interrupts off.
-         */             
+         */
 retint_with_reschedule:
        movl $_TIF_WORK_MASK,%edi
 retint_check:
@@ -763,20 +765,20 @@ retint_careful:
        pushq %rdi
        CFI_ADJUST_CFA_OFFSET   8
        call  schedule
-        popq %rdi               
+        popq %rdi
        CFI_ADJUST_CFA_OFFSET   -8
        GET_THREAD_INFO(%rcx)
        DISABLE_INTERRUPTS(CLBR_NONE)
        TRACE_IRQS_OFF
        jmp retint_check
-        
 retint_signal:
        testl $_TIF_DO_NOTIFY_MASK,%edx
        jz    retint_swapgs
        TRACE_IRQS_ON
        ENABLE_INTERRUPTS(CLBR_NONE)
        SAVE_REST
-        movq $-1,ORIG_RAX(%rsp)                         
+        movq $-1,ORIG_RAX(%rsp)
        xorl %esi,%esi          # oldset
        movq %rsp,%rdi          # &pt_regs
        call do_notify_resume
@@ -798,14 +800,14 @@ ENTRY(retint_kernel)
        jnc  retint_restore_args
        call preempt_schedule_irq
        jmp exit_intr
-#endif  
+#endif
        CFI_ENDPROC
 END(common_interrupt)
-        
 /*
 * APIC interrupts.
- */             
+ */
        .macro apicinterrupt num,func
        INTR_FRAME
        pushq $~(\num)
@@ -823,14 +825,14 @@ ENTRY(threshold_interrupt)
        apicinterrupt THRESHOLD_APIC_VECTOR,mce_threshold_interrupt
 END(threshold_interrupt)
-#ifdef CONFIG_SMP       
+#ifdef CONFIG_SMP
 ENTRY(reschedule_interrupt)
        apicinterrupt RESCHEDULE_VECTOR,smp_reschedule_interrupt
 END(reschedule_interrupt)
        .macro INVALIDATE_ENTRY num
 ENTRY(invalidate_interrupt\num)
-        apicinterrupt INVALIDATE_TLB_VECTOR_START+\num,smp_invalidate_interrupt 
+        apicinterrupt INVALIDATE_TLB_VECTOR_START+\num,smp_invalidate_interrupt
 END(invalidate_interrupt\num)
        .endm
@@ -869,22 +871,22 @@ END(error_interrupt)
 ENTRY(spurious_interrupt)
        apicinterrupt SPURIOUS_APIC_VECTOR,smp_spurious_interrupt
 END(spurious_interrupt)
-                                
 /*
 * Exception entry points.
- */             
+ */
        .macro zeroentry sym
        INTR_FRAME
        PARAVIRT_ADJUST_EXCEPTION_FRAME
-        pushq $0        /* push error code/oldrax */ 
+        pushq $0        /* push error code/oldrax */
        CFI_ADJUST_CFA_OFFSET 8
-        pushq %rax      /* push real oldrax to the rdi slot */ 
+        pushq %rax      /* push real oldrax to the rdi slot */
        CFI_ADJUST_CFA_OFFSET 8
        CFI_REL_OFFSET rax,0
        leaq  \sym(%rip),%rax
        jmp error_entry
        CFI_ENDPROC
-        .endm   
+        .endm
        .macro errorentry sym
        XCPT_FRAME
@@ -998,13 +1000,13 @@ paranoid_schedule\trace:
 /*
 * Exception entry point. This expects an error code/orig_rax on the stack
- * and the exception handler in %rax.   
+ * and the exception handler in %rax.
- */                                             
+ */
 KPROBE_ENTRY(error_entry)
        _frame RDI
        CFI_REL_OFFSET rax,0
        /* rdi slot contains rax, oldrax contains error code */
-        cld     
+        cld
        subq  $14*8,%rsp
        CFI_ADJUST_CFA_OFFSET   (14*8)
        movq %rsi,13*8(%rsp)
@@ -1015,7 +1017,7 @@ KPROBE_ENTRY(error_entry)
        CFI_REL_OFFSET  rdx,RDX
        movq %rcx,11*8(%rsp)
        CFI_REL_OFFSET  rcx,RCX
-        movq %rsi,10*8(%rsp)    /* store rax */ 
+        movq %rsi,10*8(%rsp)    /* store rax */
        CFI_REL_OFFSET  rax,RAX
        movq %r8, 9*8(%rsp)
        CFI_REL_OFFSET  r8,R8
@@ -1025,29 +1027,29 @@ KPROBE_ENTRY(error_entry)
        CFI_REL_OFFSET  r10,R10
        movq %r11,6*8(%rsp)
        CFI_REL_OFFSET  r11,R11
-        movq %rbx,5*8(%rsp) 
+        movq %rbx,5*8(%rsp)
        CFI_REL_OFFSET  rbx,RBX
-        movq %rbp,4*8(%rsp) 
+        movq %rbp,4*8(%rsp)
        CFI_REL_OFFSET  rbp,RBP
-        movq %r12,3*8(%rsp) 
+        movq %r12,3*8(%rsp)
        CFI_REL_OFFSET  r12,R12
-        movq %r13,2*8(%rsp) 
+        movq %r13,2*8(%rsp)
        CFI_REL_OFFSET  r13,R13
-        movq %r14,1*8(%rsp) 
+        movq %r14,1*8(%rsp)
        CFI_REL_OFFSET  r14,R14
-        movq %r15,(%rsp) 
+        movq %r15,(%rsp)
        CFI_REL_OFFSET  r15,R15
-        xorl %ebx,%ebx  
+        xorl %ebx,%ebx
        testl $3,CS(%rsp)
        je  error_kernelspace
-error_swapgs:   
+error_swapgs:
        SWAPGS
 error_sti:
        TRACE_IRQS_OFF
-        movq %rdi,RDI(%rsp)     
+        movq %rdi,RDI(%rsp)
        CFI_REL_OFFSET  rdi,RDI
        movq %rsp,%rdi
-        movq ORIG_RAX(%rsp),%rsi        /* get error code */ 
+        movq ORIG_RAX(%rsp),%rsi        /* get error code */
        movq $-1,ORIG_RAX(%rsp)
        call *%rax
        /* ebx: no swapgs flag (1: don't need swapgs, 0: need it) */
@@ -1056,7 +1058,7 @@ error_exit:
        RESTORE_REST
        DISABLE_INTERRUPTS(CLBR_NONE)
        TRACE_IRQS_OFF
-        GET_THREAD_INFO(%rcx)   
+        GET_THREAD_INFO(%rcx)
        testl %eax,%eax
        jne  retint_kernel
        LOCKDEP_SYS_EXIT_IRQ
@@ -1072,7 +1074,7 @@ error_kernelspace:
       /* There are two places in the kernel that can potentially fault with
          usergs. Handle them here. The exception handlers after
           iret run with kernel gs again, so don't set the user space flag.
-           B stepping K8s sometimes report an truncated RIP for IRET 
+           B stepping K8s sometimes report an truncated RIP for IRET
           exceptions returning to compat mode. Check for these here too. */
        leaq irq_return(%rip),%rcx
        cmpq %rcx,RIP(%rsp)
@@ -1084,17 +1086,17 @@ error_kernelspace:
        je   error_swapgs
        jmp  error_sti
 KPROBE_END(error_entry)
-        
       /* Reload gs selector with exception handling */
-       /* edi:  new selector */ 
+       /* edi:  new selector */
 ENTRY(native_load_gs_index)
        CFI_STARTPROC
        pushf
        CFI_ADJUST_CFA_OFFSET 8
        DISABLE_INTERRUPTS(CLBR_ANY | ~(CLBR_RDI))
        SWAPGS
-gs_change:     
+gs_change:
-        movl %edi,%gs   
+        movl %edi,%gs
 2:      mfence          /* workaround */
        SWAPGS
        popf
@@ -1102,20 +1104,20 @@ gs_change:
        ret
        CFI_ENDPROC
 ENDPROC(native_load_gs_index)
-       
        .section __ex_table,"a"
        .align 8
        .quad gs_change,bad_gs
        .previous
        .section .fixup,"ax"
        /* running with kernelgs */
-bad_gs: 
+bad_gs:
        SWAPGS                  /* switch back to user gs */
        xorl %eax,%eax
        movl %eax,%gs
        jmp  2b
-        .previous       
+        .previous
-        
 /*
 * Create a kernel thread.
 *
@@ -1138,7 +1140,7 @@ ENTRY(kernel_thread)
        xorl %r8d,%r8d
        xorl %r9d,%r9d
-        
        # clone now
        call do_fork
        movq %rax,RAX(%rsp)
@@ -1149,14 +1151,14 @@ ENTRY(kernel_thread)
         * so internally to the x86_64 port you can rely on kernel_thread()
         * not to reschedule the child before returning, this avoids the need
         * of hacks for example to fork off the per-CPU idle tasks.
-         * [Hopefully no generic code relies on the reschedule -AK]     
+         * [Hopefully no generic code relies on the reschedule -AK]
         */
        RESTORE_ALL
        UNFAKE_STACK_FRAME
        ret
        CFI_ENDPROC
 ENDPROC(kernel_thread)
-        
 child_rip:
        pushq $0                # fake return address
        CFI_STARTPROC
@@ -1170,6 +1172,7 @@ child_rip:
        # exit
        mov %eax, %edi
        call do_exit
+        ud2                     # padding for call trace
        CFI_ENDPROC
 ENDPROC(child_rip)
@@ -1191,10 +1194,10 @@ ENDPROC(child_rip)
 ENTRY(kernel_execve)
        CFI_STARTPROC
        FAKE_STACK_FRAME $0
-        SAVE_ALL        
+        SAVE_ALL
        movq %rsp,%rcx
        call sys_execve
-        movq %rax, RAX(%rsp)    
+        movq %rax, RAX(%rsp)
        RESTORE_REST
        testq %rax,%rax
        je int_ret_from_sys_call
@@ -1213,7 +1216,7 @@ ENTRY(coprocessor_error)
 END(coprocessor_error)
 ENTRY(simd_coprocessor_error)
-        zeroentry do_simd_coprocessor_error     
+        zeroentry do_simd_coprocessor_error
 END(simd_coprocessor_error)
 ENTRY(device_not_available)
@@ -1225,12 +1228,12 @@ KPROBE_ENTRY(debug)
        INTR_FRAME
        PARAVIRT_ADJUST_EXCEPTION_FRAME
        pushq $0
-        CFI_ADJUST_CFA_OFFSET 8         
+        CFI_ADJUST_CFA_OFFSET 8
        paranoidentry do_debug, DEBUG_STACK
        paranoidexit
 KPROBE_END(debug)
-        /* runs on exception stack */   
+        /* runs on exception stack */
 KPROBE_ENTRY(nmi)
        INTR_FRAME
        PARAVIRT_ADJUST_EXCEPTION_FRAME
@@ -1264,7 +1267,7 @@ ENTRY(bounds)
 END(bounds)
 ENTRY(invalid_op)
-        zeroentry do_invalid_op 
+        zeroentry do_invalid_op
 END(invalid_op)
 ENTRY(coprocessor_segment_overrun)
@@ -1319,7 +1322,7 @@ ENTRY(machine_check)
        INTR_FRAME
        PARAVIRT_ADJUST_EXCEPTION_FRAME
        pushq $0
-        CFI_ADJUST_CFA_OFFSET 8 
+        CFI_ADJUST_CFA_OFFSET 8
        paranoidentry do_machine_check
        jmp paranoid_exit1
        CFI_ENDPROC
diff --git a/arch/x86/kernel/es7000_32.c b/arch/x86/kernel/es7000_32.c
index 0aa2c443d600..53699c931ad4 100644
--- a/arch/x86/kernel/es7000_32.c
+++ b/arch/x86/kernel/es7000_32.c
@@ -38,8 +38,11 @@
 #include <asm/io.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
+#include <asm/atomic.h>
 #include <asm/apicdef.h>
 #include <mach_mpparse.h>
+#include <asm/genapic.h>
+#include <asm/setup.h>
 /*
 * ES7000 chipsets
@@ -161,6 +164,43 @@ es7000_rename_gsi(int ioapic, int gsi)
        return gsi;
 }
+static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
+{
+        unsigned long vect = 0, psaival = 0;
+        if (psai == NULL)
+                return -1;
+        vect = ((unsigned long)__pa(eip)/0x1000) << 16;
+        psaival = (0x1000000 | vect | cpu);
+        while (*psai & 0x1000000)
+                ;
+        *psai = psaival;
+        return 0;
+}
+static void noop_wait_for_deassert(atomic_t *deassert_not_used)
+{
+}
+static int __init es7000_update_genapic(void)
+{
+        genapic->wakeup_cpu = wakeup_secondary_cpu_via_mip;
+        /* MPENTIUMIII */
+        if (boot_cpu_data.x86 == 6 &&
+            (boot_cpu_data.x86_model >= 7 || boot_cpu_data.x86_model <= 11)) {
+                es7000_update_genapic_to_cluster();
+                genapic->wait_for_init_deassert = noop_wait_for_deassert;
+                genapic->wakeup_cpu = wakeup_secondary_cpu_via_mip;
+        }
+        return 0;
+}
 void __init
 setup_unisys(void)
 {
@@ -176,6 +216,8 @@ setup_unisys(void)
        else
                es7000_plat = ES7000_CLASSIC;
        ioapic_renumber_irq = es7000_rename_gsi;
+        x86_quirks->update_genapic = es7000_update_genapic;
 }
 /*
@@ -317,26 +359,6 @@ es7000_mip_write(struct mip_reg *mip_reg)
        return status;
 }
-int
-es7000_start_cpu(int cpu, unsigned long eip)
-{
-        unsigned long vect = 0, psaival = 0;
-        if (psai == NULL)
-                return -1;
-        vect = ((unsigned long)__pa(eip)/0x1000) << 16;
-        psaival = (0x1000000 | vect | cpu);
-        while (*psai & 0x1000000)
-                ;
-        *psai = psaival;
-        return 0;
-}
 void __init
 es7000_sw_apic(void)
 {
diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c
index 6c9bfc9e1e95..2bced78b0b8e 100644
--- a/arch/x86/kernel/genapic_64.c
+++ b/arch/x86/kernel/genapic_64.c
@@ -21,6 +21,7 @@
 #include <asm/smp.h>
 #include <asm/ipi.h>
 #include <asm/genapic.h>
+#include <asm/setup.h>
 extern struct genapic apic_flat;
 extern struct genapic apic_physflat;
@@ -53,6 +54,9 @@ void __init setup_apic_routing(void)
                        genapic = &apic_physflat;
                printk(KERN_INFO "Setting APIC routing to %s\n", genapic->name);
        }
+        if (x86_quirks->update_genapic)
+                x86_quirks->update_genapic();
 }
 /* Same for both flat and physical. */
diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c
index 2c7dbdb98278..dece17289731 100644
--- a/arch/x86/kernel/genx2apic_uv_x.c
+++ b/arch/x86/kernel/genx2apic_uv_x.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/threads.h>
+#include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/string.h>
 #include <linux/ctype.h>
@@ -17,6 +18,9 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/hardirq.h>
+#include <linux/timer.h>
+#include <linux/proc_fs.h>
+#include <asm/current.h>
 #include <asm/smp.h>
 #include <asm/ipi.h>
 #include <asm/genapic.h>
@@ -356,6 +360,103 @@ static __init void uv_rtc_init(void)
 }
 /*
+ * percpu heartbeat timer
+ */
+static void uv_heartbeat(unsigned long ignored)
+{
+        struct timer_list *timer = &uv_hub_info->scir.timer;
+        unsigned char bits = uv_hub_info->scir.state;
+        /* flip heartbeat bit */
+        bits ^= SCIR_CPU_HEARTBEAT;
+        /* is this cpu idle? */
+        if (idle_cpu(raw_smp_processor_id()))
+                bits &= ~SCIR_CPU_ACTIVITY;
+        else
+                bits |= SCIR_CPU_ACTIVITY;
+        /* update system controller interface reg */
+        uv_set_scir_bits(bits);
+        /* enable next timer period */
+        mod_timer(timer, jiffies + SCIR_CPU_HB_INTERVAL);
+}
+static void __cpuinit uv_heartbeat_enable(int cpu)
+{
+        if (!uv_cpu_hub_info(cpu)->scir.enabled) {
+                struct timer_list *timer = &uv_cpu_hub_info(cpu)->scir.timer;
+                uv_set_cpu_scir_bits(cpu, SCIR_CPU_HEARTBEAT|SCIR_CPU_ACTIVITY);
+                setup_timer(timer, uv_heartbeat, cpu);
+                timer->expires = jiffies + SCIR_CPU_HB_INTERVAL;
+                add_timer_on(timer, cpu);
+                uv_cpu_hub_info(cpu)->scir.enabled = 1;
+        }
+        /* check boot cpu */
+        if (!uv_cpu_hub_info(0)->scir.enabled)
+                uv_heartbeat_enable(0);
+}
+#ifdef CONFIG_HOTPLUG_CPU
+static void __cpuinit uv_heartbeat_disable(int cpu)
+{
+        if (uv_cpu_hub_info(cpu)->scir.enabled) {
+                uv_cpu_hub_info(cpu)->scir.enabled = 0;
+                del_timer(&uv_cpu_hub_info(cpu)->scir.timer);
+        }
+        uv_set_cpu_scir_bits(cpu, 0xff);
+}
+/*
+ * cpu hotplug notifier
+ */
+static __cpuinit int uv_scir_cpu_notify(struct notifier_block *self,
+                                       unsigned long action, void *hcpu)
+{
+        long cpu = (long)hcpu;
+        switch (action) {
+        case CPU_ONLINE:
+                uv_heartbeat_enable(cpu);
+                break;
+        case CPU_DOWN_PREPARE:
+                uv_heartbeat_disable(cpu);
+                break;
+        default:
+                break;
+        }
+        return NOTIFY_OK;
+}
+static __init void uv_scir_register_cpu_notifier(void)
+{
+        hotcpu_notifier(uv_scir_cpu_notify, 0);
+}
+#else /* !CONFIG_HOTPLUG_CPU */
+static __init void uv_scir_register_cpu_notifier(void)
+{
+}
+static __init int uv_init_heartbeat(void)
+{
+        int cpu;
+        if (is_uv_system())
+                for_each_online_cpu(cpu)
+                        uv_heartbeat_enable(cpu);
+        return 0;
+}
+late_initcall(uv_init_heartbeat);
+#endif /* !CONFIG_HOTPLUG_CPU */
+/*
 * Called on each cpu to initialize the per_cpu UV data area.
 *      ZZZ hotplug not supported yet
 */
@@ -428,7 +529,7 @@ void __init uv_system_init(void)
        uv_bios_init();
        uv_bios_get_sn_info(0, &uv_type, &sn_partition_id,
-                            &uv_coherency_id, &uv_region_size);
+                            &sn_coherency_id, &sn_region_size);
        uv_rtc_init();
        for_each_present_cpu(cpu) {
@@ -439,8 +540,7 @@ void __init uv_system_init(void)
                uv_blade_info[blade].nr_possible_cpus++;
                uv_cpu_hub_info(cpu)->lowmem_remap_base = lowmem_redir_base;
-                uv_cpu_hub_info(cpu)->lowmem_remap_top =
+                uv_cpu_hub_info(cpu)->lowmem_remap_top = lowmem_redir_size;
-                                        lowmem_redir_base + lowmem_redir_size;
                uv_cpu_hub_info(cpu)->m_val = m_val;
                uv_cpu_hub_info(cpu)->n_val = m_val;
                uv_cpu_hub_info(cpu)->numa_blade_id = blade;
@@ -450,7 +550,8 @@ void __init uv_system_init(void)
                uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
                uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
                uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
-                uv_cpu_hub_info(cpu)->coherency_domain_number = uv_coherency_id;
+                uv_cpu_hub_info(cpu)->coherency_domain_number = sn_coherency_id;
+                uv_cpu_hub_info(cpu)->scir.offset = SCIR_LOCAL_MMR_BASE + lcpu;
                uv_node_to_blade[nid] = blade;
                uv_cpu_to_blade[cpu] = blade;
                max_pnode = max(pnode, max_pnode);
@@ -467,4 +568,6 @@ void __init uv_system_init(void)
        map_mmioh_high(max_pnode);
        uv_cpu_init();
+        uv_scir_register_cpu_notifier();
+        proc_mkdir("sgi_uv", NULL);
 }
diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c
index 1dcb0f13897e..3e66bd364a9d 100644
--- a/arch/x86/kernel/head.c
+++ b/arch/x86/kernel/head.c
@@ -35,7 +35,6 @@ void __init reserve_ebda_region(void)
        /* start of EBDA area */
        ebda_addr = get_bios_ebda();
-        printk(KERN_INFO "BIOS EBDA/lowmem at: %08x/%08x\n", ebda_addr, lowmem);
        /* Fixup: bios puts an EBDA in the top 64K segment */
        /* of conventional memory, but does not adjust lowmem. */
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index fa1d25dd83e3..ac108d1fe182 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -12,9 +12,12 @@
 #include <asm/sections.h>
 #include <asm/e820.h>
 #include <asm/bios_ebda.h>
+#include <asm/trampoline.h>
 void __init i386_start_kernel(void)
 {
+        reserve_trampoline_memory();
        reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS");
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index d16084f90649..388e05a5fc17 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -24,6 +24,7 @@
 #include <asm/kdebug.h>
 #include <asm/e820.h>
 #include <asm/bios_ebda.h>
+#include <asm/trampoline.h>
 /* boot cpu pda */
 static struct x8664_pda _boot_cpu_pda __read_mostly;
@@ -120,6 +121,8 @@ void __init x86_64_start_reservations(char *real_mode_data)
 {
        copy_bootdata(__va(real_mode_data));
+        reserve_trampoline_memory();
        reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS");
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 067d8de913f6..3f0a3edf0a57 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -33,7 +33,9 @@
 * HPET address is set in acpi/boot.c, when an ACPI entry exists
 */
 unsigned long                           hpet_address;
-unsigned long                           hpet_num_timers;
+#ifdef CONFIG_PCI_MSI
+static unsigned long                    hpet_num_timers;
+#endif
 static void __iomem                     *hpet_virt_address;
 struct hpet_dev {
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 1f20608d4ca8..b0f61f0dcd0a 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -58,7 +58,7 @@ void __cpuinit mxcsr_feature_mask_init(void)
        stts();
 }
-void __init init_thread_xstate(void)
+void __cpuinit init_thread_xstate(void)
 {
        if (!HAVE_HWFP) {
                xstate_size = sizeof(struct i387_soft_struct);
diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c
index a4f93b4120c1..d39918076bb4 100644
--- a/arch/x86/kernel/init_task.c
+++ b/arch/x86/kernel/init_task.c
@@ -14,7 +14,6 @@ static struct fs_struct init_fs = INIT_FS;
 static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
 static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
 struct mm_struct init_mm = INIT_MM(init_mm);
-EXPORT_UNUSED_SYMBOL(init_mm); /* will be removed in 2.6.26 */
 /*
 * Initial thread structure.
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 7a3f2028e2eb..679e7bbbbcd6 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -1140,6 +1140,20 @@ static void __clear_irq_vector(int irq)
        cfg->vector = 0;
        cpus_clear(cfg->domain);
+        if (likely(!cfg->move_in_progress))
+                return;
+        cpus_and(mask, cfg->old_domain, cpu_online_map);
+        for_each_cpu_mask_nr(cpu, mask) {
+                for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
+                                                                vector++) {
+                        if (per_cpu(vector_irq, cpu)[vector] != irq)
+                                continue;
+                        per_cpu(vector_irq, cpu)[vector] = -1;
+                        break;
+                }
+        }
+        cfg->move_in_progress = 0;
 }
 void __setup_vector_irq(int cpu)
@@ -2202,10 +2216,9 @@ static void set_ir_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
 asmlinkage void smp_irq_move_cleanup_interrupt(void)
 {
        unsigned vector, me;
        ack_APIC_irq();
-#ifdef CONFIG_X86_64
        exit_idle();
-#endif
        irq_enter();
        me = smp_processor_id();
@@ -3594,27 +3607,7 @@ int __init io_apic_get_redir_entries (int ioapic)
 int __init probe_nr_irqs(void)
 {
-        int idx;
+        return NR_IRQS;
-        int nr = 0;
-#ifndef CONFIG_XEN
-        int nr_min = 32;
-#else
-        int nr_min = NR_IRQS;
-#endif
-        for (idx = 0; idx < nr_ioapics; idx++)
-                nr += io_apic_get_redir_entries(idx) + 1;
-        /* double it for hotplug and msi and nmi */
-        nr <<= 1;
-        /* something wrong ? */
-        if (nr < nr_min)
-                nr = nr_min;
-        if (WARN_ON(nr > NR_IRQS))
-                nr = NR_IRQS;
-        return nr;
 }
 /* --------------------------------------------------------------------------
@@ -3761,7 +3754,9 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
 void __init setup_ioapic_dest(void)
 {
        int pin, ioapic, irq, irq_entry;
+        struct irq_desc *desc;
        struct irq_cfg *cfg;
+        cpumask_t mask;
        if (skip_ioapic_setup == 1)
                return;
@@ -3778,16 +3773,30 @@ void __init setup_ioapic_dest(void)
                         * cpu is online.
                         */
                        cfg = irq_cfg(irq);
-                        if (!cfg->vector)
+                        if (!cfg->vector) {
                                setup_IO_APIC_irq(ioapic, pin, irq,
                                                  irq_trigger(irq_entry),
                                                  irq_polarity(irq_entry));
+                                continue;
+                        }
+                        /*
+                         * Honour affinities which have been set in early boot
+                         */
+                        desc = irq_to_desc(irq);
+                        if (desc->status &
+                            (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
+                                mask = desc->affinity;
+                        else
+                                mask = TARGET_CPUS;
 #ifdef CONFIG_INTR_REMAP
-                        else if (intr_remapping_enabled)
+                        if (intr_remapping_enabled)
-                                set_ir_ioapic_affinity_irq(irq, TARGET_CPUS);
+                                set_ir_ioapic_affinity_irq(irq, mask);
-#endif
                        else
-                                set_ioapic_affinity_irq(irq, TARGET_CPUS);
+#endif
+                                set_ioapic_affinity_irq(irq, mask);
                }
        }
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 60eb84eb77a0..1d3d0e71b044 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -18,7 +18,6 @@
 #include <asm/idle.h>
 #include <asm/smp.h>
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
 /*
 * Probabilistic stack overflow check:
 *
@@ -28,19 +27,18 @@
 */
 static inline void stack_overflow_check(struct pt_regs *regs)
 {
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
        u64 curbase = (u64)task_stack_page(current);
-        static unsigned long warned = -60*HZ;
+        WARN_ONCE(regs->sp >= curbase &&
-        if (regs->sp >= curbase && regs->sp <= curbase + THREAD_SIZE &&
+                  regs->sp <= curbase + THREAD_SIZE &&
-            regs->sp <  curbase + sizeof(struct thread_info) + 128 &&
+                  regs->sp <  curbase + sizeof(struct thread_info) +
-            time_after(jiffies, warned + 60*HZ)) {
+                                        sizeof(struct pt_regs) + 128,
-                printk("do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n",
-                       current->comm, curbase, regs->sp);
+                  "do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n",
-                show_stack(NULL,NULL);
+                        current->comm, curbase, regs->sp);
-                warned = jiffies;
-        }
-}
 #endif
+}
 /*
 * do_IRQ handles all normal device IRQ's (the special
@@ -60,9 +58,7 @@ asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
        irq_enter();
        irq = __get_cpu_var(vector_irq)[vector];
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
        stack_overflow_check(regs);
-#endif
        desc = irq_to_desc(irq);
        if (likely(desc))
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 1c9cc431ea4f..e169ae9b6a62 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -128,7 +128,7 @@ static int kvm_register_clock(char *txt)
 }
 #ifdef CONFIG_X86_LOCAL_APIC
-static void __devinit kvm_setup_secondary_clock(void)
+static void __cpuinit kvm_setup_secondary_clock(void)
 {
        /*
         * Now that the first cpu already had this clocksource initialized,
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 7a385746509a..37f420018a41 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -13,6 +13,7 @@
 #include <linux/numa.h>
 #include <linux/ftrace.h>
 #include <linux/suspend.h>
+#include <linux/gfp.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -25,15 +26,6 @@
 #include <asm/system.h>
 #include <asm/cacheflush.h>
-#define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE)))
-static u32 kexec_pgd[1024] PAGE_ALIGNED;
-#ifdef CONFIG_X86_PAE
-static u32 kexec_pmd0[1024] PAGE_ALIGNED;
-static u32 kexec_pmd1[1024] PAGE_ALIGNED;
-#endif
-static u32 kexec_pte0[1024] PAGE_ALIGNED;
-static u32 kexec_pte1[1024] PAGE_ALIGNED;
 static void set_idt(void *newidt, __u16 limit)
 {
        struct desc_ptr curidt;
@@ -76,6 +68,76 @@ static void load_segments(void)
 #undef __STR
 }
+static void machine_kexec_free_page_tables(struct kimage *image)
+{
+        free_page((unsigned long)image->arch.pgd);
+#ifdef CONFIG_X86_PAE
+        free_page((unsigned long)image->arch.pmd0);
+        free_page((unsigned long)image->arch.pmd1);
+#endif
+        free_page((unsigned long)image->arch.pte0);
+        free_page((unsigned long)image->arch.pte1);
+}
+static int machine_kexec_alloc_page_tables(struct kimage *image)
+{
+        image->arch.pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL);
+#ifdef CONFIG_X86_PAE
+        image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
+        image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
+#endif
+        image->arch.pte0 = (pte_t *)get_zeroed_page(GFP_KERNEL);
+        image->arch.pte1 = (pte_t *)get_zeroed_page(GFP_KERNEL);
+        if (!image->arch.pgd ||
+#ifdef CONFIG_X86_PAE
+            !image->arch.pmd0 || !image->arch.pmd1 ||
+#endif
+            !image->arch.pte0 || !image->arch.pte1) {
+                machine_kexec_free_page_tables(image);
+                return -ENOMEM;
+        }
+        return 0;
+}
+static void machine_kexec_page_table_set_one(
+        pgd_t *pgd, pmd_t *pmd, pte_t *pte,
+        unsigned long vaddr, unsigned long paddr)
+{
+        pud_t *pud;
+        pgd += pgd_index(vaddr);
+#ifdef CONFIG_X86_PAE
+        if (!(pgd_val(*pgd) & _PAGE_PRESENT))
+                set_pgd(pgd, __pgd(__pa(pmd) | _PAGE_PRESENT));
+#endif
+        pud = pud_offset(pgd, vaddr);
+        pmd = pmd_offset(pud, vaddr);
+        if (!(pmd_val(*pmd) & _PAGE_PRESENT))
+                set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE));
+        pte = pte_offset_kernel(pmd, vaddr);
+        set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC));
+}
+static void machine_kexec_prepare_page_tables(struct kimage *image)
+{
+        void *control_page;
+        pmd_t *pmd = 0;
+        control_page = page_address(image->control_code_page);
+#ifdef CONFIG_X86_PAE
+        pmd = image->arch.pmd0;
+#endif
+        machine_kexec_page_table_set_one(
+                image->arch.pgd, pmd, image->arch.pte0,
+                (unsigned long)control_page, __pa(control_page));
+#ifdef CONFIG_X86_PAE
+        pmd = image->arch.pmd1;
+#endif
+        machine_kexec_page_table_set_one(
+                image->arch.pgd, pmd, image->arch.pte1,
+                __pa(control_page), __pa(control_page));
+}
 /*
 * A architecture hook called to validate the
 * proposed image and prepare the control pages
@@ -87,12 +149,20 @@ static void load_segments(void)
 * reboot code buffer to allow us to avoid allocations
 * later.
 *
- * Make control page executable.
+ * - Make control page executable.
+ * - Allocate page tables
+ * - Setup page tables
 */
 int machine_kexec_prepare(struct kimage *image)
 {
+        int error;
        if (nx_enabled)
                set_pages_x(image->control_code_page, 1);
+        error = machine_kexec_alloc_page_tables(image);
+        if (error)
+                return error;
+        machine_kexec_prepare_page_tables(image);
        return 0;
 }
@@ -104,6 +174,7 @@ void machine_kexec_cleanup(struct kimage *image)
 {
        if (nx_enabled)
                set_pages_nx(image->control_code_page, 1);
+        machine_kexec_free_page_tables(image);
 }
 /*
@@ -150,18 +221,7 @@ void machine_kexec(struct kimage *image)
        relocate_kernel_ptr = control_page;
        page_list[PA_CONTROL_PAGE] = __pa(control_page);
        page_list[VA_CONTROL_PAGE] = (unsigned long)control_page;
-        page_list[PA_PGD] = __pa(kexec_pgd);
+        page_list[PA_PGD] = __pa(image->arch.pgd);
-        page_list[VA_PGD] = (unsigned long)kexec_pgd;
-#ifdef CONFIG_X86_PAE
-        page_list[PA_PMD_0] = __pa(kexec_pmd0);
-        page_list[VA_PMD_0] = (unsigned long)kexec_pmd0;
-        page_list[PA_PMD_1] = __pa(kexec_pmd1);
-        page_list[VA_PMD_1] = (unsigned long)kexec_pmd1;
-#endif
-        page_list[PA_PTE_0] = __pa(kexec_pte0);
-        page_list[VA_PTE_0] = (unsigned long)kexec_pte0;
-        page_list[PA_PTE_1] = __pa(kexec_pte1);
-        page_list[VA_PTE_1] = (unsigned long)kexec_pte1;
        if (image->type == KEXEC_TYPE_DEFAULT)
                page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page)
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 5f8e5d75a254..c25fdb382292 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -10,7 +10,7 @@
 *  This driver allows to upgrade microcode on AMD
 *  family 0x10 and 0x11 processors.
 *
- *  Licensed unter the terms of the GNU General Public
+ *  Licensed under the terms of the GNU General Public
 *  License version 2. See file COPYING for details.
 */
@@ -32,9 +32,9 @@
 #include <linux/platform_device.h>
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
+#include <linux/uaccess.h>
 #include <asm/msr.h>
-#include <asm/uaccess.h>
 #include <asm/processor.h>
 #include <asm/microcode.h>
@@ -47,43 +47,38 @@ MODULE_LICENSE("GPL v2");
 #define UCODE_UCODE_TYPE           0x00000001
 struct equiv_cpu_entry {
-        unsigned int installed_cpu;
+        u32     installed_cpu;
-        unsigned int fixed_errata_mask;
+        u32     fixed_errata_mask;
-        unsigned int fixed_errata_compare;
+        u32     fixed_errata_compare;
-        unsigned int equiv_cpu;
+        u16     equiv_cpu;
-};
+        u16     res;
+} __attribute__((packed));
 struct microcode_header_amd {
-        unsigned int  data_code;
+        u32     data_code;
-        unsigned int  patch_id;
+        u32     patch_id;
-        unsigned char mc_patch_data_id[2];
+        u16     mc_patch_data_id;
-        unsigned char mc_patch_data_len;
+        u8      mc_patch_data_len;
-        unsigned char init_flag;
+        u8      init_flag;
-        unsigned int  mc_patch_data_checksum;
+        u32     mc_patch_data_checksum;
-        unsigned int  nb_dev_id;
+        u32     nb_dev_id;
-        unsigned int  sb_dev_id;
+        u32     sb_dev_id;
-        unsigned char processor_rev_id[2];
+        u16     processor_rev_id;
-        unsigned char nb_rev_id;
+        u8      nb_rev_id;
-        unsigned char sb_rev_id;
+        u8      sb_rev_id;
-        unsigned char bios_api_rev;
+        u8      bios_api_rev;
-        unsigned char reserved1[3];
+        u8      reserved1[3];
-        unsigned int  match_reg[8];
+        u32     match_reg[8];
-};
+} __attribute__((packed));
 struct microcode_amd {
        struct microcode_header_amd hdr;
        unsigned int mpb[0];
 };
-#define UCODE_MAX_SIZE          (2048)
+#define UCODE_MAX_SIZE                  2048
-#define DEFAULT_UCODE_DATASIZE  (896)
+#define UCODE_CONTAINER_SECTION_HDR     8
-#define MC_HEADER_SIZE          (sizeof(struct microcode_header_amd))
+#define UCODE_CONTAINER_HEADER_SIZE     12
-#define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE)
-#define DWSIZE                  (sizeof(u32))
-/* For now we support a fixed ucode total size only */
-#define get_totalsize(mc) \
-        ((((struct microcode_amd *)mc)->hdr.mc_patch_data_len * 28) \
-         + MC_HEADER_SIZE)
 /* serialize access to the physical write */
 static DEFINE_SPINLOCK(microcode_update_lock);
@@ -93,31 +88,24 @@ static struct equiv_cpu_entry *equiv_cpu_table;
 static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 {
        struct cpuinfo_x86 *c = &cpu_data(cpu);
+        u32 dummy;
        memset(csig, 0, sizeof(*csig));
        if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
-                printk(KERN_ERR "microcode: CPU%d not a capable AMD processor\n",
+                printk(KERN_WARNING "microcode: CPU%d: AMD CPU family 0x%x not "
-                       cpu);
+                       "supported\n", cpu, c->x86);
                return -1;
        }
+        rdmsr(MSR_AMD64_PATCH_LEVEL, csig->rev, dummy);
-        asm volatile("movl %1, %%ecx; rdmsr"
+        printk(KERN_INFO "microcode: CPU%d: patch_level=0x%x\n", cpu, csig->rev);
-                     : "=a" (csig->rev)
-                     : "i" (0x0000008B) : "ecx");
-        printk(KERN_INFO "microcode: collect_cpu_info_amd : patch_id=0x%x\n",
-                csig->rev);
        return 0;
 }
 static int get_matching_microcode(int cpu, void *mc, int rev)
 {
        struct microcode_header_amd *mc_header = mc;
-        struct pci_dev *nb_pci_dev, *sb_pci_dev;
        unsigned int current_cpu_id;
-        unsigned int equiv_cpu_id = 0x00;
+        u16 equiv_cpu_id = 0;
        unsigned int i = 0;
        BUG_ON(equiv_cpu_table == NULL);
@@ -132,57 +120,25 @@ static int get_matching_microcode(int cpu, void *mc, int rev)
        }
        if (!equiv_cpu_id) {
-                printk(KERN_ERR "microcode: CPU%d cpu_id "
+                printk(KERN_WARNING "microcode: CPU%d: cpu revision "
-                       "not found in equivalent cpu table \n", cpu);
+                       "not listed in equivalent cpu table\n", cpu);
                return 0;
        }
-        if ((mc_header->processor_rev_id[0]) != (equiv_cpu_id & 0xff)) {
+        if (mc_header->processor_rev_id != equiv_cpu_id) {
-                printk(KERN_ERR
+                printk(KERN_ERR "microcode: CPU%d: patch mismatch "
-                        "microcode: CPU%d patch does not match "
+                       "(processor_rev_id: %x, equiv_cpu_id: %x)\n",
-                        "(patch is %x, cpu extended is %x) \n",
+                       cpu, mc_header->processor_rev_id, equiv_cpu_id);
-                        cpu, mc_header->processor_rev_id[0],
-                        (equiv_cpu_id & 0xff));
                return 0;
        }
-        if ((mc_header->processor_rev_id[1]) != ((equiv_cpu_id >> 16) & 0xff)) {
+        /* ucode might be chipset specific -- currently we don't support this */
-                printk(KERN_ERR "microcode: CPU%d patch does not match "
+        if (mc_header->nb_dev_id || mc_header->sb_dev_id) {
-                        "(patch is %x, cpu base id is %x) \n",
+                printk(KERN_ERR "microcode: CPU%d: loading of chipset "
-                        cpu, mc_header->processor_rev_id[1],
+                       "specific code not yet supported\n", cpu);
-                        ((equiv_cpu_id >> 16) & 0xff));
                return 0;
        }
-        /* ucode may be northbridge specific */
-        if (mc_header->nb_dev_id) {
-                nb_pci_dev = pci_get_device(PCI_VENDOR_ID_AMD,
-                                            (mc_header->nb_dev_id & 0xff),
-                                            NULL);
-                if ((!nb_pci_dev) ||
-                    (mc_header->nb_rev_id != nb_pci_dev->revision)) {
-                        printk(KERN_ERR "microcode: CPU%d NB mismatch \n", cpu);
-                        pci_dev_put(nb_pci_dev);
-                        return 0;
-                }
-                pci_dev_put(nb_pci_dev);
-        }
-        /* ucode may be southbridge specific */
-        if (mc_header->sb_dev_id) {
-                sb_pci_dev = pci_get_device(PCI_VENDOR_ID_AMD,
-                                            (mc_header->sb_dev_id & 0xff),
-                                            NULL);
-                if ((!sb_pci_dev) ||
-                    (mc_header->sb_rev_id != sb_pci_dev->revision)) {
-                        printk(KERN_ERR "microcode: CPU%d SB mismatch \n", cpu);
-                        pci_dev_put(sb_pci_dev);
-                        return 0;
-                }
-                pci_dev_put(sb_pci_dev);
-        }
        if (mc_header->patch_id <= rev)
                return 0;
@@ -192,12 +148,10 @@ static int get_matching_microcode(int cpu, void *mc, int rev)
 static void apply_microcode_amd(int cpu)
 {
        unsigned long flags;
-        unsigned int eax, edx;
+        u32 rev, dummy;
-        unsigned int rev;
        int cpu_num = raw_smp_processor_id();
        struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num;
        struct microcode_amd *mc_amd = uci->mc;
-        unsigned long addr;
        /* We should bind the task to the CPU */
        BUG_ON(cpu_num != cpu);
@@ -206,42 +160,34 @@ static void apply_microcode_amd(int cpu)
                return;
        spin_lock_irqsave(&microcode_update_lock, flags);
+        wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code);
-        addr = (unsigned long)&mc_amd->hdr.data_code;
-        edx = (unsigned int)(((unsigned long)upper_32_bits(addr)));
-        eax = (unsigned int)(((unsigned long)lower_32_bits(addr)));
-        asm volatile("movl %0, %%ecx; wrmsr" :
-                     : "i" (0xc0010020), "a" (eax), "d" (edx) : "ecx");
        /* get patch id after patching */
-        asm volatile("movl %1, %%ecx; rdmsr"
+        rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-                     : "=a" (rev)
-                     : "i" (0x0000008B) : "ecx");
        spin_unlock_irqrestore(&microcode_update_lock, flags);
        /* check current patch id and patch's id for match */
        if (rev != mc_amd->hdr.patch_id) {
-                printk(KERN_ERR "microcode: CPU%d update from revision "
+                printk(KERN_ERR "microcode: CPU%d: update failed "
-                       "0x%x to 0x%x failed\n", cpu_num,
+                       "(for patch_level=0x%x)\n", cpu, mc_amd->hdr.patch_id);
-                       mc_amd->hdr.patch_id, rev);
                return;
        }
-        printk(KERN_INFO "microcode: CPU%d updated from revision "
+        printk(KERN_INFO "microcode: CPU%d: updated (new patch_level=0x%x)\n",
-               "0x%x to 0x%x \n",
+               cpu, rev);
-               cpu_num, uci->cpu_sig.rev, mc_amd->hdr.patch_id);
        uci->cpu_sig.rev = rev;
 }
-static void * get_next_ucode(u8 *buf, unsigned int size,
+static int get_ucode_data(void *to, const u8 *from, size_t n)
-                        int (*get_ucode_data)(void *, const void *, size_t),
+{
-                        unsigned int *mc_size)
+        memcpy(to, from, n);
+        return 0;
+}
+static void *get_next_ucode(const u8 *buf, unsigned int size,
+                            unsigned int *mc_size)
 {
        unsigned int total_size;
-#define UCODE_CONTAINER_SECTION_HDR     8
        u8 section_hdr[UCODE_CONTAINER_SECTION_HDR];
        void *mc;
@@ -249,39 +195,37 @@ static void * get_next_ucode(u8 *buf, unsigned int size,
                return NULL;
        if (section_hdr[0] != UCODE_UCODE_TYPE) {
-                printk(KERN_ERR "microcode: error! "
+                printk(KERN_ERR "microcode: error: invalid type field in "
-                       "Wrong microcode payload type field\n");
+                       "container file section header\n");
                return NULL;
        }
        total_size = (unsigned long) (section_hdr[4] + (section_hdr[5] << 8));
-        printk(KERN_INFO "microcode: size %u, total_size %u\n",
+        printk(KERN_DEBUG "microcode: size %u, total_size %u\n",
-                size, total_size);
+               size, total_size);
        if (total_size > size || total_size > UCODE_MAX_SIZE) {
-                printk(KERN_ERR "microcode: error! Bad data in microcode data file\n");
+                printk(KERN_ERR "microcode: error: size mismatch\n");
                return NULL;
        }
        mc = vmalloc(UCODE_MAX_SIZE);
        if (mc) {
                memset(mc, 0, UCODE_MAX_SIZE);
-                if (get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, total_size)) {
+                if (get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR,
+                                   total_size)) {
                        vfree(mc);
                        mc = NULL;
                } else
                        *mc_size = total_size + UCODE_CONTAINER_SECTION_HDR;
        }
-#undef UCODE_CONTAINER_SECTION_HDR
        return mc;
 }
-static int install_equiv_cpu_table(u8 *buf,
+static int install_equiv_cpu_table(const u8 *buf)
-                int (*get_ucode_data)(void *, const void *, size_t))
 {
-#define UCODE_CONTAINER_HEADER_SIZE     12
        u8 *container_hdr[UCODE_CONTAINER_HEADER_SIZE];
        unsigned int *buf_pos = (unsigned int *)container_hdr;
        unsigned long size;
@@ -292,14 +236,15 @@ static int install_equiv_cpu_table(u8 *buf,
        size = buf_pos[2];
        if (buf_pos[1] != UCODE_EQUIV_CPU_TABLE_TYPE || !size) {
-                printk(KERN_ERR "microcode: error! "
+                printk(KERN_ERR "microcode: error: invalid type field in "
-                       "Wrong microcode equivalnet cpu table\n");
+                       "container file section header\n");
                return 0;
        }
        equiv_cpu_table = (struct equiv_cpu_entry *) vmalloc(size);
        if (!equiv_cpu_table) {
-                printk(KERN_ERR "microcode: error, can't allocate memory for equiv CPU table\n");
+                printk(KERN_ERR "microcode: failed to allocate "
+                       "equivalent CPU table\n");
                return 0;
        }
@@ -310,7 +255,6 @@ static int install_equiv_cpu_table(u8 *buf,
        }
        return size + UCODE_CONTAINER_HEADER_SIZE; /* add header length */
-#undef UCODE_CONTAINER_HEADER_SIZE
 }
 static void free_equiv_cpu_table(void)
@@ -321,18 +265,20 @@ static void free_equiv_cpu_table(void)
        }
 }
-static int generic_load_microcode(int cpu, void *data, size_t size,
+static int generic_load_microcode(int cpu, const u8 *data, size_t size)
-                int (*get_ucode_data)(void *, const void *, size_t))
 {
        struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-        u8 *ucode_ptr = data, *new_mc = NULL, *mc;
+        const u8 *ucode_ptr = data;
+        void *new_mc = NULL;
+        void *mc;
        int new_rev = uci->cpu_sig.rev;
        unsigned int leftover;
        unsigned long offset;
-        offset = install_equiv_cpu_table(ucode_ptr, get_ucode_data);
+        offset = install_equiv_cpu_table(ucode_ptr);
        if (!offset) {
-                printk(KERN_ERR "microcode: installing equivalent cpu table failed\n");
+                printk(KERN_ERR "microcode: failed to create "
+                       "equivalent cpu table\n");
                return -EINVAL;
        }
@@ -343,7 +289,7 @@ static int generic_load_microcode(int cpu, void *data, size_t size,
                unsigned int uninitialized_var(mc_size);
                struct microcode_header_amd *mc_header;
-                mc = get_next_ucode(ucode_ptr, leftover, get_ucode_data, &mc_size);
+                mc = get_next_ucode(ucode_ptr, leftover, &mc_size);
                if (!mc)
                        break;
@@ -353,7 +299,7 @@ static int generic_load_microcode(int cpu, void *data, size_t size,
                                vfree(new_mc);
                        new_rev = mc_header->patch_id;
                        new_mc  = mc;
-                } else 
+                } else
                        vfree(mc);
                ucode_ptr += mc_size;
@@ -365,9 +311,9 @@ static int generic_load_microcode(int cpu, void *data, size_t size,
                        if (uci->mc)
                                vfree(uci->mc);
                        uci->mc = new_mc;
-                        pr_debug("microcode: CPU%d found a matching microcode update with"
+                        pr_debug("microcode: CPU%d found a matching microcode "
-                                " version 0x%x (current=0x%x)\n",
+                                 "update with version 0x%x (current=0x%x)\n",
-                                cpu, new_rev, uci->cpu_sig.rev);
+                                 cpu, new_rev, uci->cpu_sig.rev);
                } else
                        vfree(new_mc);
        }
@@ -377,12 +323,6 @@ static int generic_load_microcode(int cpu, void *data, size_t size,
        return (int)leftover;
 }
-static int get_ucode_fw(void *to, const void *from, size_t n)
-{
-        memcpy(to, from, n);
-        return 0;
-}
 static int request_microcode_fw(int cpu, struct device *device)
 {
        const char *fw_name = "amd-ucode/microcode_amd.bin";
@@ -394,12 +334,11 @@ static int request_microcode_fw(int cpu, struct device *device)
        ret = request_firmware(&firmware, fw_name, device);
        if (ret) {
-                printk(KERN_ERR "microcode: ucode data file %s load failed\n", fw_name);
+                printk(KERN_ERR "microcode: failed to load file %s\n", fw_name);
                return ret;
        }
-        ret = generic_load_microcode(cpu, (void*)firmware->data, firmware->size,
+        ret = generic_load_microcode(cpu, firmware->data, firmware->size);
-                        &get_ucode_fw);
        release_firmware(firmware);
@@ -408,8 +347,8 @@ static int request_microcode_fw(int cpu, struct device *device)
 static int request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
-        printk(KERN_WARNING "microcode: AMD microcode update via /dev/cpu/microcode"
+        printk(KERN_INFO "microcode: AMD microcode update via "
-                        "is not supported\n");
+               "/dev/cpu/microcode not supported\n");
        return -1;
 }
@@ -433,3 +372,4 @@ struct microcode_ops * __init init_amd_microcode(void)
 {
        return &microcode_amd_ops;
 }
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 82fb2809ce32..c9b721ba968c 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -99,7 +99,7 @@ MODULE_LICENSE("GPL");
 #define MICROCODE_VERSION       "2.00"
-struct microcode_ops *microcode_ops;
+static struct microcode_ops *microcode_ops;
 /* no concurrent ->write()s are allowed on /dev/cpu/microcode */
 static DEFINE_MUTEX(microcode_mutex);
@@ -203,7 +203,7 @@ MODULE_ALIAS_MISCDEV(MICROCODE_MINOR);
 #endif
 /* fake device for request_firmware */
-struct platform_device *microcode_pdev;
+static struct platform_device *microcode_pdev;
 static ssize_t reload_store(struct sys_device *dev,
                            struct sysdev_attribute *attr,
@@ -272,13 +272,18 @@ static struct attribute_group mc_attr_group = {
        .name = "microcode",
 };
-static void microcode_fini_cpu(int cpu)
+static void __microcode_fini_cpu(int cpu)
 {
        struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-        mutex_lock(&microcode_mutex);
        microcode_ops->microcode_fini_cpu(cpu);
        uci->valid = 0;
+}
+static void microcode_fini_cpu(int cpu)
+{
+        mutex_lock(&microcode_mutex);
+        __microcode_fini_cpu(cpu);
        mutex_unlock(&microcode_mutex);
 }
@@ -306,12 +311,16 @@ static int microcode_resume_cpu(int cpu)
         * to this cpu (a bit of paranoia):
         */
        if (microcode_ops->collect_cpu_info(cpu, &nsig)) {
-                microcode_fini_cpu(cpu);
+                __microcode_fini_cpu(cpu);
+                printk(KERN_ERR "failed to collect_cpu_info for resuming cpu #%d\n",
+                                cpu);
                return -1;
        }
-        if (memcmp(&nsig, &uci->cpu_sig, sizeof(nsig))) {
+        if ((nsig.sig != uci->cpu_sig.sig) || (nsig.pf != uci->cpu_sig.pf)) {
-                microcode_fini_cpu(cpu);
+                __microcode_fini_cpu(cpu);
+                printk(KERN_ERR "cached ucode doesn't match the resuming cpu #%d\n",
+                                cpu);
                /* Should we look for a new ucode here? */
                return 1;
        }
@@ -319,7 +328,7 @@ static int microcode_resume_cpu(int cpu)
        return 0;
 }
-void microcode_update_cpu(int cpu)
+static void microcode_update_cpu(int cpu)
 {
        struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
        int err = 0;
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 622dc4a21784..b7f4c929e615 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -155,6 +155,7 @@ static DEFINE_SPINLOCK(microcode_update_lock);
 static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 {
        struct cpuinfo_x86 *c = &cpu_data(cpu_num);
+        unsigned long flags;
        unsigned int val[2];
        memset(csig, 0, sizeof(*csig));
@@ -174,11 +175,16 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
                csig->pf = 1 << ((val[1] >> 18) & 7);
        }
+        /* serialize access to the physical write to MSR 0x79 */
+        spin_lock_irqsave(&microcode_update_lock, flags);
        wrmsr(MSR_IA32_UCODE_REV, 0, 0);
        /* see notes above for revision 1.07.  Apparent chip bug */
        sync_core();
        /* get the current revision from MSR 0x8B */
        rdmsr(MSR_IA32_UCODE_REV, val[0], csig->rev);
+        spin_unlock_irqrestore(&microcode_update_lock, flags);
        pr_debug("microcode: collect_cpu_info : sig=0x%x, pf=0x%x, rev=0x%x\n",
                        csig->sig, csig->pf, csig->rev);
@@ -465,7 +471,7 @@ static void microcode_fini_cpu(int cpu)
        uci->mc = NULL;
 }
-struct microcode_ops microcode_intel_ops = {
+static struct microcode_ops microcode_intel_ops = {
        .request_microcode_user           = request_microcode_user,
        .request_microcode_fw             = request_microcode_fw,
        .collect_cpu_info                 = collect_cpu_info,
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index f98f4e1dba09..45e3b69808ba 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -586,23 +586,23 @@ static void __init __get_smp_config(unsigned int early)
 {
        struct intel_mp_floating *mpf = mpf_found;
-        if (x86_quirks->mach_get_smp_config) {
+        if (!mpf)
-                if (x86_quirks->mach_get_smp_config(early))
+                return;
-                        return;
-        }
        if (acpi_lapic && early)
                return;
        /*
-         * ACPI supports both logical (e.g. Hyper-Threading) and physical
+         * MPS doesn't support hyperthreading, aka only have
-         * processors, where MPS only supports physical.
+         * thread 0 apic id in MPS table
         */
-        if (acpi_lapic && acpi_ioapic) {
+        if (acpi_lapic && acpi_ioapic)
-                printk(KERN_INFO "Using ACPI (MADT) for SMP configuration "
-                       "information\n");
                return;
-        } else if (acpi_lapic)
-                printk(KERN_INFO "Using ACPI for processor (LAPIC) "
+        if (x86_quirks->mach_get_smp_config) {
-                       "configuration information\n");
+                if (x86_quirks->mach_get_smp_config(early))
+                        return;
+        }
        printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n",
               mpf->mpf_specification);
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 2c97f07f1c2c..8bd1bf9622a7 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -131,6 +131,11 @@ static void report_broken_nmi(int cpu, int *prev_nmi_count)
        atomic_dec(&nmi_active);
 }
+static void __acpi_nmi_disable(void *__unused)
+{
+        apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
+}
 int __init check_nmi_watchdog(void)
 {
        unsigned int *prev_nmi_count;
@@ -179,8 +184,12 @@ int __init check_nmi_watchdog(void)
        kfree(prev_nmi_count);
        return 0;
 error:
-        if (nmi_watchdog == NMI_IO_APIC && !timer_through_8259)
+        if (nmi_watchdog == NMI_IO_APIC) {
-                disable_8259A_irq(0);
+                if (!timer_through_8259)
+                        disable_8259A_irq(0);
+                on_each_cpu(__acpi_nmi_disable, NULL, 1);
+        }
 #ifdef CONFIG_X86_32
        timer_ack = 0;
 #endif
@@ -199,12 +208,17 @@ static int __init setup_nmi_watchdog(char *str)
                ++str;
        }
-        get_option(&str, &nmi);
+        if (!strncmp(str, "lapic", 5))
+                nmi_watchdog = NMI_LOCAL_APIC;
-        if (nmi >= NMI_INVALID)
+        else if (!strncmp(str, "ioapic", 6))
-                return 0;
+                nmi_watchdog = NMI_IO_APIC;
+        else {
+                get_option(&str, &nmi);
+                if (nmi >= NMI_INVALID)
+                        return 0;
+                nmi_watchdog = nmi;
+        }
-        nmi_watchdog = nmi;
        return 1;
 }
 __setup("nmi_watchdog=", setup_nmi_watchdog);
@@ -285,11 +299,6 @@ void acpi_nmi_enable(void)
                on_each_cpu(__acpi_nmi_enable, NULL, 1);
 }
-static void __acpi_nmi_disable(void *__unused)
-{
-        apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
-}
 /*
 * Disable timer based NMIs on all CPUs:
 */
@@ -340,6 +349,8 @@ void stop_apic_nmi_watchdog(void *unused)
                return;
        if (nmi_watchdog == NMI_LOCAL_APIC)
                lapic_watchdog_stop();
+        else
+                __acpi_nmi_disable(NULL);
        __get_cpu_var(wd_enabled) = 0;
        atomic_dec(&nmi_active);
 }
@@ -465,6 +476,24 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 #ifdef CONFIG_SYSCTL
+static void enable_ioapic_nmi_watchdog_single(void *unused)
+{
+        __get_cpu_var(wd_enabled) = 1;
+        atomic_inc(&nmi_active);
+        __acpi_nmi_enable(NULL);
+}
+static void enable_ioapic_nmi_watchdog(void)
+{
+        on_each_cpu(enable_ioapic_nmi_watchdog_single, NULL, 1);
+        touch_nmi_watchdog();
+}
+static void disable_ioapic_nmi_watchdog(void)
+{
+        on_each_cpu(stop_apic_nmi_watchdog, NULL, 1);
+}
 static int __init setup_unknown_nmi_panic(char *str)
 {
        unknown_nmi_panic = 1;
@@ -507,6 +536,11 @@ int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
                        enable_lapic_nmi_watchdog();
                else
                        disable_lapic_nmi_watchdog();
+        } else if (nmi_watchdog == NMI_IO_APIC) {
+                if (nmi_watchdog_enabled)
+                        enable_ioapic_nmi_watchdog();
+                else
+                        disable_ioapic_nmi_watchdog();
        } else {
                printk(KERN_WARNING
                        "NMI watchdog doesn't know what hardware to touch\n");
diff --git a/arch/x86/kernel/numaq_32.c b/arch/x86/kernel/numaq_32.c
index 4caff39078e0..0deea37a53cf 100644
--- a/arch/x86/kernel/numaq_32.c
+++ b/arch/x86/kernel/numaq_32.c
@@ -31,7 +31,7 @@
 #include <asm/numaq.h>
 #include <asm/topology.h>
 #include <asm/processor.h>
-#include <asm/mpspec.h>
+#include <asm/genapic.h>
 #include <asm/e820.h>
 #include <asm/setup.h>
@@ -235,6 +235,13 @@ static int __init numaq_setup_ioapic_ids(void)
        return 1;
 }
+static int __init numaq_update_genapic(void)
+{
+        genapic->wakeup_cpu = wakeup_secondary_cpu_via_nmi;
+        return 0;
+}
 static struct x86_quirks numaq_x86_quirks __initdata = {
        .arch_pre_time_init     = numaq_pre_time_init,
        .arch_time_init         = NULL,
@@ -250,6 +257,7 @@ static struct x86_quirks numaq_x86_quirks __initdata = {
        .mpc_oem_pci_bus        = mpc_oem_pci_bus,
        .smp_read_mpc_oem       = smp_read_mpc_oem,
        .setup_ioapic_ids       = numaq_setup_ioapic_ids,
+        .update_genapic         = numaq_update_genapic,
 };
 void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 0e9f1982b1dd..95777b0faa73 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -7,7 +7,8 @@
 #include <asm/paravirt.h>
-static void default_spin_lock_flags(struct raw_spinlock *lock, unsigned long flags)
+static inline void
+default_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags)
 {
        __raw_spin_lock(lock);
 }
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index e1e731d78f38..d28bbdc35e4e 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -1567,7 +1567,7 @@ static int __init calgary_parse_options(char *p)
                                ++p;
                        if (*p == '\0')
                                break;
-                        bridge = simple_strtol(p, &endp, 0);
+                        bridge = simple_strtoul(p, &endp, 0);
                        if (p == endp)
                                break;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 192624820217..dc572994703d 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -300,8 +300,8 @@ fs_initcall(pci_iommu_init);
 static __devinit void via_no_dac(struct pci_dev *dev)
 {
        if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) {
-                printk(KERN_INFO "PCI: VIA PCI bridge detected."
+                printk(KERN_INFO
-                                 "Disabling DAC.\n");
+                        "PCI: VIA PCI bridge detected. Disabling DAC.\n");
                forbid_dac = 1;
        }
 }
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index a42b02b4df68..a35eaa379ff6 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -123,6 +123,8 @@ static void free_iommu(unsigned long offset, int size)
        spin_lock_irqsave(&iommu_bitmap_lock, flags);
        iommu_area_free(iommu_gart_bitmap, offset, size);
+        if (offset >= next_bit)
+                next_bit = offset + size;
        spin_unlock_irqrestore(&iommu_bitmap_lock, flags);
 }
@@ -743,10 +745,8 @@ void __init gart_iommu_init(void)
        unsigned long scratch;
        long i;
-        if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0) {
+        if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0)
-                printk(KERN_INFO "PCI-GART: No AMD GART found.\n");
                return;
-        }
 #ifndef CONFIG_AGP_AMD64
        no_agp = 1;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index c622772744d8..9bfc3f719d47 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -1,6 +1,7 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <asm/idle.h>
 #include <linux/smp.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
@@ -8,6 +9,7 @@
 #include <linux/pm.h>
 #include <linux/clockchips.h>
 #include <asm/system.h>
+#include <asm/apic.h>
 unsigned long idle_halt;
 EXPORT_SYMBOL(idle_halt);
@@ -122,6 +124,21 @@ void default_idle(void)
 EXPORT_SYMBOL(default_idle);
 #endif
+void stop_this_cpu(void *dummy)
+{
+        local_irq_disable();
+        /*
+         * Remove this CPU:
+         */
+        cpu_clear(smp_processor_id(), cpu_online_map);
+        disable_local_APIC();
+        for (;;) {
+                if (hlt_works(smp_processor_id()))
+                        halt();
+        }
+}
 static void do_nothing(void *unused)
 {
 }
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 0a6d8c12e10d..06180dff5b2e 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -929,17 +929,16 @@ void __cpuinit ptrace_bts_init_intel(struct cpuinfo_x86 *c)
        switch (c->x86) {
        case 0x6:
                switch (c->x86_model) {
+                case 0 ... 0xC:
+                        /* sorry, don't know about them */
+                        break;
                case 0xD:
                case 0xE: /* Pentium M */
                        bts_configure(&bts_cfg_pentium_m);
                        break;
-                case 0xF: /* Core2 */
+                default: /* Core2, Atom, ... */
-        case 0x1C: /* Atom */
                        bts_configure(&bts_cfg_core2);
                        break;
-                default:
-                        /* sorry, don't know about them */
-                        break;
                }
                break;
        case 0xF:
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 724adfc63cb9..61f718df6eec 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -21,6 +21,9 @@
 # include <asm/iommu.h>
 #endif
+#include <mach_ipi.h>
 /*
 * Power off function, if any
 */
@@ -36,7 +39,10 @@ int reboot_force;
 static int reboot_cpu = -1;
 #endif
-/* reboot=b[ios] | s[mp] | t[riple] | k[bd] | e[fi] [, [w]arm | [c]old]
+/* This is set by the PCI code if either type 1 or type 2 PCI is detected */
+bool port_cf9_safe = false;
+/* reboot=b[ios] | s[mp] | t[riple] | k[bd] | e[fi] [, [w]arm | [c]old] | p[ci]
   warm   Don't set the cold reboot flag
   cold   Set the cold reboot flag
   bios   Reboot by jumping through the BIOS (only for X86_32)
@@ -45,6 +51,7 @@ static int reboot_cpu = -1;
   kbd    Use the keyboard controller. cold reset (default)
   acpi   Use the RESET_REG in the FADT
   efi    Use efi reset_system runtime service
+   pci    Use the so-called "PCI reset register", CF9
   force  Avoid anything that could hang.
 */
 static int __init reboot_setup(char *str)
@@ -79,6 +86,7 @@ static int __init reboot_setup(char *str)
                case 'k':
                case 't':
                case 'e':
+                case 'p':
                        reboot_type = *str;
                        break;
@@ -169,6 +177,15 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
                        DMI_MATCH(DMI_BOARD_NAME, "0KW626"),
                },
        },
+        {   /* Handle problems with rebooting on Dell Optiplex 330 with 0KP561 */
+                .callback = set_bios_reboot,
+                .ident = "Dell OptiPlex 330",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 330"),
+                        DMI_MATCH(DMI_BOARD_NAME, "0KP561"),
+                },
+        },
        {       /* Handle problems with rebooting on Dell 2400's */
                .callback = set_bios_reboot,
                .ident = "Dell PowerEdge 2400",
@@ -395,12 +412,27 @@ static void native_machine_emergency_restart(void)
                        reboot_type = BOOT_KBD;
                        break;
                case BOOT_EFI:
                        if (efi_enabled)
-                                efi.reset_system(reboot_mode ? EFI_RESET_WARM : EFI_RESET_COLD,
+                                efi.reset_system(reboot_mode ?
+                                                 EFI_RESET_WARM :
+                                                 EFI_RESET_COLD,
                                                 EFI_SUCCESS, 0, NULL);
+                        reboot_type = BOOT_KBD;
+                        break;
+                case BOOT_CF9:
+                        port_cf9_safe = true;
+                        /* fall through */
+                case BOOT_CF9_COND:
+                        if (port_cf9_safe) {
+                                u8 cf9 = inb(0xcf9) & ~6;
+                                outb(cf9|2, 0xcf9); /* Request hard reset */
+                                udelay(50);
+                                outb(cf9|6, 0xcf9); /* Actually do the reset */
+                                udelay(50);
+                        }
                        reboot_type = BOOT_KBD;
                        break;
                }
@@ -461,6 +493,11 @@ static void native_machine_restart(char *__unused)
 static void native_machine_halt(void)
 {
+        /* stop other cpus and apics */
+        machine_shutdown();
+        /* stop this cpu */
+        stop_this_cpu(NULL);
 }
 static void native_machine_power_off(void)
@@ -514,3 +551,95 @@ void machine_crash_shutdown(struct pt_regs *regs)
        machine_ops.crash_shutdown(regs);
 }
 #endif
+#if defined(CONFIG_SMP)
+/* This keeps a track of which one is crashing cpu. */
+static int crashing_cpu;
+static nmi_shootdown_cb shootdown_callback;
+static atomic_t waiting_for_crash_ipi;
+static int crash_nmi_callback(struct notifier_block *self,
+                        unsigned long val, void *data)
+{
+        int cpu;
+        if (val != DIE_NMI_IPI)
+                return NOTIFY_OK;
+        cpu = raw_smp_processor_id();
+        /* Don't do anything if this handler is invoked on crashing cpu.
+         * Otherwise, system will completely hang. Crashing cpu can get
+         * an NMI if system was initially booted with nmi_watchdog parameter.
+         */
+        if (cpu == crashing_cpu)
+                return NOTIFY_STOP;
+        local_irq_disable();
+        shootdown_callback(cpu, (struct die_args *)data);
+        atomic_dec(&waiting_for_crash_ipi);
+        /* Assume hlt works */
+        halt();
+        for (;;)
+                cpu_relax();
+        return 1;
+}
+static void smp_send_nmi_allbutself(void)
+{
+        cpumask_t mask = cpu_online_map;
+        cpu_clear(safe_smp_processor_id(), mask);
+        if (!cpus_empty(mask))
+                send_IPI_mask(mask, NMI_VECTOR);
+}
+static struct notifier_block crash_nmi_nb = {
+        .notifier_call = crash_nmi_callback,
+};
+/* Halt all other CPUs, calling the specified function on each of them
+ *
+ * This function can be used to halt all other CPUs on crash
+ * or emergency reboot time. The function passed as parameter
+ * will be called inside a NMI handler on all CPUs.
+ */
+void nmi_shootdown_cpus(nmi_shootdown_cb callback)
+{
+        unsigned long msecs;
+        local_irq_disable();
+        /* Make a note of crashing cpu. Will be used in NMI callback.*/
+        crashing_cpu = safe_smp_processor_id();
+        shootdown_callback = callback;
+        atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+        /* Would it be better to replace the trap vector here? */
+        if (register_die_notifier(&crash_nmi_nb))
+                return;         /* return what? */
+        /* Ensure the new callback function is set before sending
+         * out the NMI
+         */
+        wmb();
+        smp_send_nmi_allbutself();
+        msecs = 1000; /* Wait at most a second for the other cpus to stop */
+        while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
+                mdelay(1);
+                msecs--;
+        }
+        /* Leave the nmi callback set */
+}
+#else /* !CONFIG_SMP */
+void nmi_shootdown_cpus(nmi_shootdown_cb callback)
+{
+        /* No other CPUs to shoot down */
+}
+#endif
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index 6f50664b2ba5..a160f3119725 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -10,15 +10,12 @@
 #include <asm/page.h>
 #include <asm/kexec.h>
 #include <asm/processor-flags.h>
-#include <asm/pgtable.h>
 /*
 * Must be relocatable PIC code callable as a C function
 */
 #define PTR(x) (x << 2)
-#define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
-#define PAE_PGD_ATTR (_PAGE_PRESENT)
 /* control_page + KEXEC_CONTROL_CODE_MAX_SIZE
 * ~ control_page + PAGE_SIZE are used as data storage and stack for
@@ -39,7 +36,6 @@
 #define CP_PA_BACKUP_PAGES_MAP  DATA(0x1c)
        .text
-        .align PAGE_SIZE
        .globl relocate_kernel
 relocate_kernel:
        /* Save the CPU context, used for jumping back */
@@ -60,117 +56,6 @@ relocate_kernel:
        movl    %cr4, %eax
        movl    %eax, CR4(%edi)
-#ifdef CONFIG_X86_PAE
-        /* map the control page at its virtual address */
-        movl    PTR(VA_PGD)(%ebp), %edi
-        movl    PTR(VA_CONTROL_PAGE)(%ebp), %eax
-        andl    $0xc0000000, %eax
-        shrl    $27, %eax
-        addl    %edi, %eax
-        movl    PTR(PA_PMD_0)(%ebp), %edx
-        orl     $PAE_PGD_ATTR, %edx
-        movl    %edx, (%eax)
-        movl    PTR(VA_PMD_0)(%ebp), %edi
-        movl    PTR(VA_CONTROL_PAGE)(%ebp), %eax
-        andl    $0x3fe00000, %eax
-        shrl    $18, %eax
-        addl    %edi, %eax
-        movl    PTR(PA_PTE_0)(%ebp), %edx
-        orl     $PAGE_ATTR, %edx
-        movl    %edx, (%eax)
-        movl    PTR(VA_PTE_0)(%ebp), %edi
-        movl    PTR(VA_CONTROL_PAGE)(%ebp), %eax
-        andl    $0x001ff000, %eax
-        shrl    $9, %eax
-        addl    %edi, %eax
-        movl    PTR(PA_CONTROL_PAGE)(%ebp), %edx
-        orl     $PAGE_ATTR, %edx
-        movl    %edx, (%eax)
-        /* identity map the control page at its physical address */
-        movl    PTR(VA_PGD)(%ebp), %edi
-        movl    PTR(PA_CONTROL_PAGE)(%ebp), %eax
-        andl    $0xc0000000, %eax
-        shrl    $27, %eax
-        addl    %edi, %eax
-        movl    PTR(PA_PMD_1)(%ebp), %edx
-        orl     $PAE_PGD_ATTR, %edx
-        movl    %edx, (%eax)
-        movl    PTR(VA_PMD_1)(%ebp), %edi
-        movl    PTR(PA_CONTROL_PAGE)(%ebp), %eax
-        andl    $0x3fe00000, %eax
-        shrl    $18, %eax
-        addl    %edi, %eax
-        movl    PTR(PA_PTE_1)(%ebp), %edx
-        orl     $PAGE_ATTR, %edx
-        movl    %edx, (%eax)
-        movl    PTR(VA_PTE_1)(%ebp), %edi
-        movl    PTR(PA_CONTROL_PAGE)(%ebp), %eax
-        andl    $0x001ff000, %eax
-        shrl    $9, %eax
-        addl    %edi, %eax
-        movl    PTR(PA_CONTROL_PAGE)(%ebp), %edx
-        orl     $PAGE_ATTR, %edx
-        movl    %edx, (%eax)
-#else
-        /* map the control page at its virtual address */
-        movl    PTR(VA_PGD)(%ebp), %edi
-        movl    PTR(VA_CONTROL_PAGE)(%ebp), %eax
-        andl    $0xffc00000, %eax
-        shrl    $20, %eax
-        addl    %edi, %eax
-        movl    PTR(PA_PTE_0)(%ebp), %edx
-        orl     $PAGE_ATTR, %edx
-        movl    %edx, (%eax)
-        movl    PTR(VA_PTE_0)(%ebp), %edi
-        movl    PTR(VA_CONTROL_PAGE)(%ebp), %eax
-        andl    $0x003ff000, %eax
-        shrl    $10, %eax
-        addl    %edi, %eax
-        movl    PTR(PA_CONTROL_PAGE)(%ebp), %edx
-        orl     $PAGE_ATTR, %edx
-        movl    %edx, (%eax)
-        /* identity map the control page at its physical address */
-        movl    PTR(VA_PGD)(%ebp), %edi
-        movl    PTR(PA_CONTROL_PAGE)(%ebp), %eax
-        andl    $0xffc00000, %eax
-        shrl    $20, %eax
-        addl    %edi, %eax
-        movl    PTR(PA_PTE_1)(%ebp), %edx
-        orl     $PAGE_ATTR, %edx
-        movl    %edx, (%eax)
-        movl    PTR(VA_PTE_1)(%ebp), %edi
-        movl    PTR(PA_CONTROL_PAGE)(%ebp), %eax
-        andl    $0x003ff000, %eax
-        shrl    $10, %eax
-        addl    %edi, %eax
-        movl    PTR(PA_CONTROL_PAGE)(%ebp), %edx
-        orl     $PAGE_ATTR, %edx
-        movl    %edx, (%eax)
-#endif
-relocate_new_kernel:
        /* read the arguments and say goodbye to the stack */
        movl  20+4(%esp), %ebx /* page_list */
        movl  20+8(%esp), %ebp /* list of pages */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 13a5f592ac28..a31223828597 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -98,6 +98,7 @@
 #include <mach_apic.h>
 #include <asm/paravirt.h>
+#include <asm/hypervisor.h>
 #include <asm/percpu.h>
 #include <asm/topology.h>
@@ -448,6 +449,7 @@ static void __init reserve_early_setup_data(void)
 * @size: Size of the crashkernel memory to reserve.
 * Returns the base address on success, and -1ULL on failure.
 */
+static
 unsigned long long __init find_and_reserve_crashkernel(unsigned long long size)
 {
        const unsigned long long alignment = 16<<20;    /* 16M */
@@ -583,7 +585,20 @@ static int __init setup_elfcorehdr(char *arg)
 early_param("elfcorehdr", setup_elfcorehdr);
 #endif
-static struct x86_quirks default_x86_quirks __initdata;
+static int __init default_update_genapic(void)
+{
+#ifdef CONFIG_X86_SMP
+# if defined(CONFIG_X86_GENERICARCH) || defined(CONFIG_X86_64)
+        genapic->wakeup_cpu = wakeup_secondary_cpu_via_init;
+# endif
+#endif
+        return 0;
+}
+static struct x86_quirks default_x86_quirks __initdata = {
+        .update_genapic         = default_update_genapic,
+};
 struct x86_quirks *x86_quirks __initdata = &default_x86_quirks;
@@ -645,6 +660,9 @@ void __init setup_arch(char **cmdline_p)
        printk(KERN_INFO "Command line: %s\n", boot_command_line);
 #endif
+        /* VMI may relocate the fixmap; do this before touching ioremap area */
+        vmi_init();
        early_cpu_init();
        early_ioremap_init();
@@ -731,13 +749,8 @@ void __init setup_arch(char **cmdline_p)
        check_efer();
 #endif
-#if defined(CONFIG_VMI) && defined(CONFIG_X86_32)
+        /* Must be before kernel pagetables are setup */
-        /*
+        vmi_activate();
-         * Must be before kernel pagetables are setup
-         * or fixmap area is touched.
-         */
-        vmi_init();
-#endif
        /* after early param, so could get panic from serial */
        reserve_early_setup_data();
@@ -760,6 +773,12 @@ void __init setup_arch(char **cmdline_p)
        dmi_check_system(bad_bios_dmi_table);
+        /*
+         * VMware detection requires dmi to be available, so this
+         * needs to be done after dmi_scan_machine, for the BP.
+         */
+        init_hypervisor(&boot_cpu_data);
 #ifdef CONFIG_X86_32
        probe_roms();
 #endif
diff --git a/arch/x86/kernel/sigframe.h b/arch/x86/kernel/sigframe.h
deleted file mode 100644
index cc673aa55ce4..000000000000
--- a/arch/x86/kernel/sigframe.h
+++ /dev/null
@@ -1,42 +0,0 @@
-#ifdef CONFIG_X86_32
-struct sigframe {
-        char __user *pretcode;
-        int sig;
-        struct sigcontext sc;
-        /*
-         * 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 {
-        char __user *pretcode;
-        int sig;
-        struct siginfo __user *pinfo;
-        void __user *puc;
-        struct siginfo info;
-        struct ucontext uc;
-        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,
-                sigset_t *set, struct pt_regs *regs);
-int ia32_setup_frame(int sig, struct k_sigaction *ka,
-                sigset_t *set, struct pt_regs *regs);
-#endif
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal.c
index d6dd057d0f22..89bb7668041d 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal.c
@@ -1,36 +1,41 @@
 /*
 *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs
 *
 *  1997-11-28  Modified for POSIX.1b signals by Richard Henderson
 *  2000-06-20  Pentium III FXSR, SSE support by Gareth Hughes
+ *  2000-2002   x86-64 support by Andi Kleen
 */
-#include <linux/list.h>
-#include <linux/personality.h>
+#include <linux/sched.h>
-#include <linux/binfmts.h>
+#include <linux/mm.h>
-#include <linux/suspend.h>
+#include <linux/smp.h>
 #include <linux/kernel.h>
-#include <linux/ptrace.h>
 #include <linux/signal.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
 #include <linux/errno.h>
-#include <linux/sched.h>
 #include <linux/wait.h>
+#include <linux/ptrace.h>
 #include <linux/tracehook.h>
-#include <linux/elf.h>
+#include <linux/unistd.h>
-#include <linux/smp.h>
+#include <linux/stddef.h>
-#include <linux/mm.h>
+#include <linux/personality.h>
+#include <linux/uaccess.h>
 #include <asm/processor.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
 #include <asm/i387.h>
 #include <asm/vdso.h>
+#ifdef CONFIG_X86_64
+#include <asm/proto.h>
+#include <asm/ia32_unistd.h>
+#include <asm/mce.h>
+#endif /* CONFIG_X86_64 */
 #include <asm/syscall.h>
 #include <asm/syscalls.h>
-#include "sigframe.h"
+#include <asm/sigframe.h>
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
@@ -45,74 +50,6 @@
 # define FIX_EFLAGS     __FIX_EFLAGS
 #endif
-/*
- * Atomically swap in the new signal mask, and wait for a signal.
- */
-asmlinkage int
-sys_sigsuspend(int history0, int history1, old_sigset_t mask)
-{
-        mask &= _BLOCKABLE;
-        spin_lock_irq(&current->sighand->siglock);
-        current->saved_sigmask = current->blocked;
-        siginitset(&current->blocked, mask);
-        recalc_sigpending();
-        spin_unlock_irq(&current->sighand->siglock);
-        current->state = TASK_INTERRUPTIBLE;
-        schedule();
-        set_restore_sigmask();
-        return -ERESTARTNOHAND;
-}
-asmlinkage int
-sys_sigaction(int sig, const struct old_sigaction __user *act,
-              struct old_sigaction __user *oact)
-{
-        struct k_sigaction new_ka, old_ka;
-        int ret;
-        if (act) {
-                old_sigset_t mask;
-                if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
-                    __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
-                    __get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
-                        return -EFAULT;
-                __get_user(new_ka.sa.sa_flags, &act->sa_flags);
-                __get_user(mask, &act->sa_mask);
-                siginitset(&new_ka.sa.sa_mask, mask);
-        }
-        ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
-        if (!ret && oact) {
-                if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
-                    __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
-                    __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
-                        return -EFAULT;
-                __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
-                __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
-        }
-        return ret;
-}
-asmlinkage int sys_sigaltstack(unsigned long bx)
-{
-        /*
-         * This is needed to make gcc realize it doesn't own the
-         * "struct pt_regs"
-         */
-        struct pt_regs *regs = (struct pt_regs *)&bx;
-        const stack_t __user *uss = (const stack_t __user *)bx;
-        stack_t __user *uoss = (stack_t __user *)regs->cx;
-        return do_sigaltstack(uss, uoss, regs->sp);
-}
 #define COPY(x)                 {               \
        err |= __get_user(regs->x, &sc->x);     \
 }
@@ -123,7 +60,7 @@ asmlinkage int sys_sigaltstack(unsigned long bx)
                regs->seg = tmp;                        \
 }
-#define COPY_SEG_STRICT(seg)    {                       \
+#define COPY_SEG_CPL3(seg)      {                       \
                unsigned short tmp;                     \
                err |= __get_user(tmp, &sc->seg);       \
                regs->seg = tmp | 3;                    \
@@ -135,9 +72,6 @@ asmlinkage int sys_sigaltstack(unsigned long bx)
                loadsegment(seg, tmp);                  \
 }
-/*
- * Do a signal return; undo the signal stack.
- */
 static int
 restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
                   unsigned long *pax)
@@ -149,14 +83,36 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
        /* Always make any pending restarted system calls return -EINTR */
        current_thread_info()->restart_block.fn = do_no_restart_syscall;
+#ifdef CONFIG_X86_32
        GET_SEG(gs);
        COPY_SEG(fs);
        COPY_SEG(es);
        COPY_SEG(ds);
+#endif /* CONFIG_X86_32 */
        COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
        COPY(dx); COPY(cx); COPY(ip);
-        COPY_SEG_STRICT(cs);
-        COPY_SEG_STRICT(ss);
+#ifdef CONFIG_X86_64
+        COPY(r8);
+        COPY(r9);
+        COPY(r10);
+        COPY(r11);
+        COPY(r12);
+        COPY(r13);
+        COPY(r14);
+        COPY(r15);
+#endif /* CONFIG_X86_64 */
+#ifdef CONFIG_X86_32
+        COPY_SEG_CPL3(cs);
+        COPY_SEG_CPL3(ss);
+#else /* !CONFIG_X86_32 */
+        /* Kernel saves and restores only the CS segment register on signals,
+         * which is the bare minimum needed to allow mixed 32/64-bit code.
+         * App's signal handler can save/restore other segments if needed. */
+        COPY_SEG_CPL3(cs);
+#endif /* CONFIG_X86_32 */
        err |= __get_user(tmpflags, &sc->flags);
        regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
@@ -169,102 +125,24 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
        return err;
 }
-asmlinkage unsigned long sys_sigreturn(unsigned long __unused)
-{
-        struct sigframe __user *frame;
-        struct pt_regs *regs;
-        unsigned long ax;
-        sigset_t set;
-        regs = (struct pt_regs *) &__unused;
-        frame = (struct sigframe __user *)(regs->sp - 8);
-        if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
-                goto badframe;
-        if (__get_user(set.sig[0], &frame->sc.oldmask) || (_NSIG_WORDS > 1
-                && __copy_from_user(&set.sig[1], &frame->extramask,
-                                    sizeof(frame->extramask))))
-                goto badframe;
-        sigdelsetmask(&set, ~_BLOCKABLE);
-        spin_lock_irq(&current->sighand->siglock);
-        current->blocked = set;
-        recalc_sigpending();
-        spin_unlock_irq(&current->sighand->siglock);
-        if (restore_sigcontext(regs, &frame->sc, &ax))
-                goto badframe;
-        return ax;
-badframe:
-        if (show_unhandled_signals && printk_ratelimit()) {
-                printk("%s%s[%d] bad frame in sigreturn frame:"
-                        "%p ip:%lx sp:%lx oeax:%lx",
-                    task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG,
-                    current->comm, task_pid_nr(current), frame, regs->ip,
-                    regs->sp, regs->orig_ax);
-                print_vma_addr(" in ", regs->ip);
-                printk(KERN_CONT "\n");
-        }
-        force_sig(SIGSEGV, current);
-        return 0;
-}
-static long do_rt_sigreturn(struct pt_regs *regs)
-{
-        struct rt_sigframe __user *frame;
-        unsigned long ax;
-        sigset_t set;
-        frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
-        if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
-                goto badframe;
-        if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
-                goto badframe;
-        sigdelsetmask(&set, ~_BLOCKABLE);
-        spin_lock_irq(&current->sighand->siglock);
-        current->blocked = set;
-        recalc_sigpending();
-        spin_unlock_irq(&current->sighand->siglock);
-        if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
-                goto badframe;
-        if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->sp) == -EFAULT)
-                goto badframe;
-        return ax;
-badframe:
-        signal_fault(regs, frame, "rt_sigreturn");
-        return 0;
-}
-asmlinkage int sys_rt_sigreturn(unsigned long __unused)
-{
-        struct pt_regs *regs = (struct pt_regs *)&__unused;
-        return do_rt_sigreturn(regs);
-}
-/*
- * Set up a signal frame.
- */
 static int
 setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
                 struct pt_regs *regs, unsigned long mask)
 {
-        int tmp, err = 0;
+        int err = 0;
-        err |= __put_user(regs->fs, (unsigned int __user *)&sc->fs);
+#ifdef CONFIG_X86_32
-        savesegment(gs, tmp);
+        {
-        err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
+                unsigned int tmp;
+                savesegment(gs, tmp);
+                err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
+        }
+        err |= __put_user(regs->fs, (unsigned int __user *)&sc->fs);
        err |= __put_user(regs->es, (unsigned int __user *)&sc->es);
        err |= __put_user(regs->ds, (unsigned int __user *)&sc->ds);
+#endif /* CONFIG_X86_32 */
        err |= __put_user(regs->di, &sc->di);
        err |= __put_user(regs->si, &sc->si);
        err |= __put_user(regs->bp, &sc->bp);
@@ -273,19 +151,33 @@ setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
        err |= __put_user(regs->dx, &sc->dx);
        err |= __put_user(regs->cx, &sc->cx);
        err |= __put_user(regs->ax, &sc->ax);
+#ifdef CONFIG_X86_64
+        err |= __put_user(regs->r8, &sc->r8);
+        err |= __put_user(regs->r9, &sc->r9);
+        err |= __put_user(regs->r10, &sc->r10);
+        err |= __put_user(regs->r11, &sc->r11);
+        err |= __put_user(regs->r12, &sc->r12);
+        err |= __put_user(regs->r13, &sc->r13);
+        err |= __put_user(regs->r14, &sc->r14);
+        err |= __put_user(regs->r15, &sc->r15);
+#endif /* CONFIG_X86_64 */
        err |= __put_user(current->thread.trap_no, &sc->trapno);
        err |= __put_user(current->thread.error_code, &sc->err);
        err |= __put_user(regs->ip, &sc->ip);
+#ifdef CONFIG_X86_32
        err |= __put_user(regs->cs, (unsigned int __user *)&sc->cs);
        err |= __put_user(regs->flags, &sc->flags);
        err |= __put_user(regs->sp, &sc->sp_at_signal);
        err |= __put_user(regs->ss, (unsigned int __user *)&sc->ss);
+#else /* !CONFIG_X86_32 */
+        err |= __put_user(regs->flags, &sc->flags);
+        err |= __put_user(regs->cs, &sc->cs);
+        err |= __put_user(0, &sc->gs);
+        err |= __put_user(0, &sc->fs);
+#endif /* CONFIG_X86_32 */
-        tmp = save_i387_xstate(fpstate);
+        err |= __put_user(fpstate, &sc->fpstate);
-        if (tmp < 0)
-                err = 1;
-        else
-                err |= __put_user(tmp ? fpstate : NULL, &sc->fpstate);
        /* non-iBCS2 extensions.. */
        err |= __put_user(mask, &sc->oldmask);
@@ -295,6 +187,32 @@ setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
 }
 /*
+ * Set up a signal frame.
+ */
+#ifdef CONFIG_X86_32
+static const struct {
+        u16 poplmovl;
+        u32 val;
+        u16 int80;
+} __attribute__((packed)) retcode = {
+        0xb858,         /* popl %eax; movl $..., %eax */
+        __NR_sigreturn,
+        0x80cd,         /* int $0x80 */
+};
+static const struct {
+        u8  movl;
+        u32 val;
+        u16 int80;
+        u8  pad;
+} __attribute__((packed)) rt_retcode = {
+        0xb8,           /* movl $..., %eax */
+        __NR_rt_sigreturn,
+        0x80cd,         /* int $0x80 */
+        0
+};
+/*
 * Determine which stack to use..
 */
 static inline void __user *
@@ -328,6 +246,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
        if (used_math()) {
                sp = sp - sig_xstate_size;
                *fpstate = (struct _fpstate *) sp;
+                if (save_i387_xstate(*fpstate) < 0)
+                        return (void __user *)-1L;
        }
        sp -= frame_size;
@@ -383,9 +303,7 @@ __setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
         * reasons and because gdb uses it as a signature to notice
         * signal handler stack frames.
         */
-        err |= __put_user(0xb858, (short __user *)(frame->retcode+0));
+        err |= __put_user(*((u64 *)&retcode), (u64 *)frame->retcode);
-        err |= __put_user(__NR_sigreturn, (int __user *)(frame->retcode+2));
-        err |= __put_user(0x80cd, (short __user *)(frame->retcode+6));
        if (err)
                return -EFAULT;
@@ -454,9 +372,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
         * reasons and because gdb uses it as a signature to notice
         * signal handler stack frames.
         */
-        err |= __put_user(0xb8, (char __user *)(frame->retcode+0));
+        err |= __put_user(*((u64 *)&rt_retcode), (u64 *)frame->retcode);
-        err |= __put_user(__NR_rt_sigreturn, (int __user *)(frame->retcode+1));
-        err |= __put_user(0x80cd, (short __user *)(frame->retcode+5));
        if (err)
                return -EFAULT;
@@ -475,23 +391,293 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
        return 0;
 }
+#else /* !CONFIG_X86_32 */
+/*
+ * Determine which stack to use..
+ */
+static void __user *
+get_stack(struct k_sigaction *ka, unsigned long sp, unsigned long size)
+{
+        /* Default to using normal stack - redzone*/
+        sp -= 128;
+        /* This is the X/Open sanctioned signal stack switching.  */
+        if (ka->sa.sa_flags & SA_ONSTACK) {
+                if (sas_ss_flags(sp) == 0)
+                        sp = current->sas_ss_sp + current->sas_ss_size;
+        }
+        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;
+        void __user *fp = NULL;
+        int err = 0;
+        struct task_struct *me = current;
+        if (used_math()) {
+                fp = get_stack(ka, regs->sp, sig_xstate_size);
+                frame = (void __user *)round_down(
+                        (unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8;
+                if (save_i387_xstate(fp) < 0)
+                        return -EFAULT;
+        } else
+                frame = get_stack(ka, regs->sp, sizeof(struct rt_sigframe)) - 8;
+        if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+                return -EFAULT;
+        if (ka->sa.sa_flags & SA_SIGINFO) {
+                if (copy_siginfo_to_user(&frame->info, info))
+                        return -EFAULT;
+        }
+        /* Create the ucontext.  */
+        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),
+                          &frame->uc.uc_stack.ss_flags);
+        err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
+        err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]);
+        err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+        /* Set up to return from userspace.  If provided, use a stub
+           already in userspace.  */
+        /* x86-64 should always use SA_RESTORER. */
+        if (ka->sa.sa_flags & SA_RESTORER) {
+                err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
+        } else {
+                /* could use a vstub here */
+                return -EFAULT;
+        }
+        if (err)
+                return -EFAULT;
+        /* Set up registers for signal handler */
+        regs->di = sig;
+        /* In case the signal handler was declared without prototypes */
+        regs->ax = 0;
+        /* This also works for non SA_SIGINFO handlers because they expect the
+           next argument after the signal number on the stack. */
+        regs->si = (unsigned long)&frame->info;
+        regs->dx = (unsigned long)&frame->uc;
+        regs->ip = (unsigned long) ka->sa.sa_handler;
+        regs->sp = (unsigned long)frame;
+        /* Set up the CS register to run signal handlers in 64-bit mode,
+           even if the handler happens to be interrupting 32-bit code. */
+        regs->cs = __USER_CS;
+        return 0;
+}
+#endif /* CONFIG_X86_32 */
+#ifdef CONFIG_X86_32
+/*
+ * Atomically swap in the new signal mask, and wait for a signal.
+ */
+asmlinkage int
+sys_sigsuspend(int history0, int history1, old_sigset_t mask)
+{
+        mask &= _BLOCKABLE;
+        spin_lock_irq(&current->sighand->siglock);
+        current->saved_sigmask = current->blocked;
+        siginitset(&current->blocked, mask);
+        recalc_sigpending();
+        spin_unlock_irq(&current->sighand->siglock);
+        current->state = TASK_INTERRUPTIBLE;
+        schedule();
+        set_restore_sigmask();
+        return -ERESTARTNOHAND;
+}
+asmlinkage int
+sys_sigaction(int sig, const struct old_sigaction __user *act,
+              struct old_sigaction __user *oact)
+{
+        struct k_sigaction new_ka, old_ka;
+        int ret;
+        if (act) {
+                old_sigset_t mask;
+                if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
+                    __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
+                    __get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
+                        return -EFAULT;
+                __get_user(new_ka.sa.sa_flags, &act->sa_flags);
+                __get_user(mask, &act->sa_mask);
+                siginitset(&new_ka.sa.sa_mask, mask);
+        }
+        ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
+        if (!ret && oact) {
+                if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
+                    __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
+                    __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
+                        return -EFAULT;
+                __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
+                __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
+        }
+        return ret;
+}
+#endif /* CONFIG_X86_32 */
+#ifdef CONFIG_X86_32
+asmlinkage int sys_sigaltstack(unsigned long bx)
+{
+        /*
+         * This is needed to make gcc realize it doesn't own the
+         * "struct pt_regs"
+         */
+        struct pt_regs *regs = (struct pt_regs *)&bx;
+        const stack_t __user *uss = (const stack_t __user *)bx;
+        stack_t __user *uoss = (stack_t __user *)regs->cx;
+        return do_sigaltstack(uss, uoss, regs->sp);
+}
+#else /* !CONFIG_X86_32 */
+asmlinkage long
+sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
+                struct pt_regs *regs)
+{
+        return do_sigaltstack(uss, uoss, regs->sp);
+}
+#endif /* CONFIG_X86_32 */
+/*
+ * Do a signal return; undo the signal stack.
+ */
+#ifdef CONFIG_X86_32
+asmlinkage unsigned long sys_sigreturn(unsigned long __unused)
+{
+        struct sigframe __user *frame;
+        struct pt_regs *regs;
+        unsigned long ax;
+        sigset_t set;
+        regs = (struct pt_regs *) &__unused;
+        frame = (struct sigframe __user *)(regs->sp - 8);
+        if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+                goto badframe;
+        if (__get_user(set.sig[0], &frame->sc.oldmask) || (_NSIG_WORDS > 1
+                && __copy_from_user(&set.sig[1], &frame->extramask,
+                                    sizeof(frame->extramask))))
+                goto badframe;
+        sigdelsetmask(&set, ~_BLOCKABLE);
+        spin_lock_irq(&current->sighand->siglock);
+        current->blocked = set;
+        recalc_sigpending();
+        spin_unlock_irq(&current->sighand->siglock);
+        if (restore_sigcontext(regs, &frame->sc, &ax))
+                goto badframe;
+        return ax;
+badframe:
+        signal_fault(regs, frame, "sigreturn");
+        return 0;
+}
+#endif /* CONFIG_X86_32 */
+static long do_rt_sigreturn(struct pt_regs *regs)
+{
+        struct rt_sigframe __user *frame;
+        unsigned long ax;
+        sigset_t set;
+        frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
+        if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+                goto badframe;
+        if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+                goto badframe;
+        sigdelsetmask(&set, ~_BLOCKABLE);
+        spin_lock_irq(&current->sighand->siglock);
+        current->blocked = set;
+        recalc_sigpending();
+        spin_unlock_irq(&current->sighand->siglock);
+        if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
+                goto badframe;
+        if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->sp) == -EFAULT)
+                goto badframe;
+        return ax;
+badframe:
+        signal_fault(regs, frame, "rt_sigreturn");
+        return 0;
+}
+#ifdef CONFIG_X86_32
+asmlinkage int sys_rt_sigreturn(struct pt_regs regs)
+{
+        return do_rt_sigreturn(&regs);
+}
+#else /* !CONFIG_X86_32 */
+asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
+{
+        return do_rt_sigreturn(regs);
+}
+#endif /* CONFIG_X86_32 */
 /*
 * OK, we're invoking a handler:
 */
 static int signr_convert(int sig)
 {
+#ifdef CONFIG_X86_32
        struct thread_info *info = current_thread_info();
        if (info->exec_domain && info->exec_domain->signal_invmap && sig < 32)
                return info->exec_domain->signal_invmap[sig];
+#endif /* CONFIG_X86_32 */
        return sig;
 }
+#ifdef CONFIG_X86_32
 #define is_ia32 1
 #define ia32_setup_frame        __setup_frame
 #define ia32_setup_rt_frame     __setup_rt_frame
+#else /* !CONFIG_X86_32 */
+#ifdef CONFIG_IA32_EMULATION
+#define is_ia32 test_thread_flag(TIF_IA32)
+#else /* !CONFIG_IA32_EMULATION */
+#define is_ia32 0
+#endif /* CONFIG_IA32_EMULATION */
+int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+                sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct k_sigaction *ka,
+                sigset_t *set, struct pt_regs *regs);
+#endif /* CONFIG_X86_32 */
 static int
 setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
               sigset_t *set, struct pt_regs *regs)
@@ -592,7 +778,13 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
        return 0;
 }
+#ifdef CONFIG_X86_32
 #define NR_restart_syscall      __NR_restart_syscall
+#else /* !CONFIG_X86_32 */
+#define NR_restart_syscall      \
+        test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall
+#endif /* CONFIG_X86_32 */
 /*
 * Note that 'init' is a special process: it doesn't get signals it doesn't
 * want to handle. Thus you cannot kill init even with a SIGKILL even by
@@ -704,8 +896,9 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
        struct task_struct *me = current;
        if (show_unhandled_signals && printk_ratelimit()) {
-                printk(KERN_INFO
+                printk("%s"
                       "%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx",
+                       task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG,
                       me->comm, me->pid, where, frame,
                       regs->ip, regs->sp, regs->orig_ax);
                print_vma_addr(" in ", regs->ip);
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
deleted file mode 100644
index a5c9627f4db9..000000000000
--- a/arch/x86/kernel/signal_64.c
+++ /dev/null
@@ -1,516 +0,0 @@
-/*
- *  Copyright (C) 1991, 1992  Linus Torvalds
- *  Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs
- *
- *  1997-11-28  Modified for POSIX.1b signals by Richard Henderson
- *  2000-06-20  Pentium III FXSR, SSE support by Gareth Hughes
- *  2000-2002   x86-64 support by Andi Kleen
- */
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/kernel.h>
-#include <linux/signal.h>
-#include <linux/errno.h>
-#include <linux/wait.h>
-#include <linux/ptrace.h>
-#include <linux/tracehook.h>
-#include <linux/unistd.h>
-#include <linux/stddef.h>
-#include <linux/personality.h>
-#include <linux/compiler.h>
-#include <linux/uaccess.h>
-#include <asm/processor.h>
-#include <asm/ucontext.h>
-#include <asm/i387.h>
-#include <asm/proto.h>
-#include <asm/ia32_unistd.h>
-#include <asm/mce.h>
-#include <asm/syscall.h>
-#include <asm/syscalls.h>
-#include "sigframe.h"
-#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
-#define __FIX_EFLAGS    (X86_EFLAGS_AC | X86_EFLAGS_OF | \
-                         X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
-                         X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
-                         X86_EFLAGS_CF)
-#ifdef CONFIG_X86_32
-# define FIX_EFLAGS     (__FIX_EFLAGS | X86_EFLAGS_RF)
-#else
-# define FIX_EFLAGS     __FIX_EFLAGS
-#endif
-asmlinkage long
-sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
-                struct pt_regs *regs)
-{
-        return do_sigaltstack(uss, uoss, regs->sp);
-}
-#define COPY(x)                 {               \
-        err |= __get_user(regs->x, &sc->x);     \
-}
-#define COPY_SEG_STRICT(seg)    {                       \
-                unsigned short tmp;                     \
-                err |= __get_user(tmp, &sc->seg);       \
-                regs->seg = tmp | 3;                    \
-}
-/*
- * Do a signal return; undo the signal stack.
- */
-static int
-restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
-                   unsigned long *pax)
-{
-        void __user *buf;
-        unsigned int tmpflags;
-        unsigned int err = 0;
-        /* Always make any pending restarted system calls return -EINTR */
-        current_thread_info()->restart_block.fn = do_no_restart_syscall;
-        COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
-        COPY(dx); COPY(cx); COPY(ip);
-        COPY(r8);
-        COPY(r9);
-        COPY(r10);
-        COPY(r11);
-        COPY(r12);
-        COPY(r13);
-        COPY(r14);
-        COPY(r15);
-        /* Kernel saves and restores only the CS segment register on signals,
-         * which is the bare minimum needed to allow mixed 32/64-bit code.
-         * App's signal handler can save/restore other segments if needed. */
-        COPY_SEG_STRICT(cs);
-        err |= __get_user(tmpflags, &sc->flags);
-        regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
-        regs->orig_ax = -1;             /* disable syscall checks */
-        err |= __get_user(buf, &sc->fpstate);
-        err |= restore_i387_xstate(buf);
-        err |= __get_user(*pax, &sc->ax);
-        return err;
-}
-static long do_rt_sigreturn(struct pt_regs *regs)
-{
-        struct rt_sigframe __user *frame;
-        unsigned long ax;
-        sigset_t set;
-        frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
-        if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
-                goto badframe;
-        if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
-                goto badframe;
-        sigdelsetmask(&set, ~_BLOCKABLE);
-        spin_lock_irq(&current->sighand->siglock);
-        current->blocked = set;
-        recalc_sigpending();
-        spin_unlock_irq(&current->sighand->siglock);
-        if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
-                goto badframe;
-        if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->sp) == -EFAULT)
-                goto badframe;
-        return ax;
-badframe:
-        signal_fault(regs, frame, "rt_sigreturn");
-        return 0;
-}
-asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
-{
-        return do_rt_sigreturn(regs);
-}
-/*
- * Set up a signal frame.
- */
-static inline int
-setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
-                unsigned long mask, struct task_struct *me)
-{
-        int err = 0;
-        err |= __put_user(regs->cs, &sc->cs);
-        err |= __put_user(0, &sc->gs);
-        err |= __put_user(0, &sc->fs);
-        err |= __put_user(regs->di, &sc->di);
-        err |= __put_user(regs->si, &sc->si);
-        err |= __put_user(regs->bp, &sc->bp);
-        err |= __put_user(regs->sp, &sc->sp);
-        err |= __put_user(regs->bx, &sc->bx);
-        err |= __put_user(regs->dx, &sc->dx);
-        err |= __put_user(regs->cx, &sc->cx);
-        err |= __put_user(regs->ax, &sc->ax);
-        err |= __put_user(regs->r8, &sc->r8);
-        err |= __put_user(regs->r9, &sc->r9);
-        err |= __put_user(regs->r10, &sc->r10);
-        err |= __put_user(regs->r11, &sc->r11);
-        err |= __put_user(regs->r12, &sc->r12);
-        err |= __put_user(regs->r13, &sc->r13);
-        err |= __put_user(regs->r14, &sc->r14);
-        err |= __put_user(regs->r15, &sc->r15);
-        err |= __put_user(me->thread.trap_no, &sc->trapno);
-        err |= __put_user(me->thread.error_code, &sc->err);
-        err |= __put_user(regs->ip, &sc->ip);
-        err |= __put_user(regs->flags, &sc->flags);
-        err |= __put_user(mask, &sc->oldmask);
-        err |= __put_user(me->thread.cr2, &sc->cr2);
-        return err;
-}
-/*
- * Determine which stack to use..
- */
-static void __user *
-get_stack(struct k_sigaction *ka, struct pt_regs *regs, unsigned long size)
-{
-        unsigned long sp;
-        /* Default to using normal stack - redzone*/
-        sp = regs->sp - 128;
-        /* This is the X/Open sanctioned signal stack switching.  */
-        if (ka->sa.sa_flags & SA_ONSTACK) {
-                if (sas_ss_flags(sp) == 0)
-                        sp = current->sas_ss_sp + current->sas_ss_size;
-        }
-        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;
-        void __user *fp = NULL;
-        int err = 0;
-        struct task_struct *me = current;
-        if (used_math()) {
-                fp = get_stack(ka, regs, sig_xstate_size);
-                frame = (void __user *)round_down(
-                        (unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8;
-                if (save_i387_xstate(fp) < 0)
-                        return -EFAULT;
-        } else
-                frame = get_stack(ka, regs, sizeof(struct rt_sigframe)) - 8;
-        if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
-                return -EFAULT;
-        if (ka->sa.sa_flags & SA_SIGINFO) {
-                if (copy_siginfo_to_user(&frame->info, info))
-                        return -EFAULT;
-        }
-        /* Create the ucontext.  */
-        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),
-                          &frame->uc.uc_stack.ss_flags);
-        err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
-        err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, set->sig[0], me);
-        err |= __put_user(fp, &frame->uc.uc_mcontext.fpstate);
-        if (sizeof(*set) == 16) {
-                __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]);
-                __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
-        } else
-                err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-        /* Set up to return from userspace.  If provided, use a stub
-           already in userspace.  */
-        /* x86-64 should always use SA_RESTORER. */
-        if (ka->sa.sa_flags & SA_RESTORER) {
-                err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
-        } else {
-                /* could use a vstub here */
-                return -EFAULT;
-        }
-        if (err)
-                return -EFAULT;
-        /* Set up registers for signal handler */
-        regs->di = sig;
-        /* In case the signal handler was declared without prototypes */
-        regs->ax = 0;
-        /* This also works for non SA_SIGINFO handlers because they expect the
-           next argument after the signal number on the stack. */
-        regs->si = (unsigned long)&frame->info;
-        regs->dx = (unsigned long)&frame->uc;
-        regs->ip = (unsigned long) ka->sa.sa_handler;
-        regs->sp = (unsigned long)frame;
-        /* Set up the CS register to run signal handlers in 64-bit mode,
-           even if the handler happens to be interrupting 32-bit code. */
-        regs->cs = __USER_CS;
-        return 0;
-}
-/*
- * OK, we're invoking a handler
- */
-static int signr_convert(int sig)
-{
-        return sig;
-}
-#ifdef CONFIG_IA32_EMULATION
-#define is_ia32 test_thread_flag(TIF_IA32)
-#else
-#define is_ia32 0
-#endif
-static int
-setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
-               sigset_t *set, struct pt_regs *regs)
-{
-        int usig = signr_convert(sig);
-        int ret;
-        /* Set up the stack frame */
-        if (is_ia32) {
-                if (ka->sa.sa_flags & SA_SIGINFO)
-                        ret = ia32_setup_rt_frame(usig, ka, info, set, regs);
-                else
-                        ret = ia32_setup_frame(usig, ka, set, regs);
-        } else
-                ret = __setup_rt_frame(sig, ka, info, set, regs);
-        if (ret) {
-                force_sigsegv(sig, current);
-                return -EFAULT;
-        }
-        return ret;
-}
-static int
-handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
-              sigset_t *oldset, struct pt_regs *regs)
-{
-        int ret;
-        /* Are we from a system call? */
-        if (syscall_get_nr(current, regs) >= 0) {
-                /* If so, check system call restarting.. */
-                switch (syscall_get_error(current, regs)) {
-                case -ERESTART_RESTARTBLOCK:
-                case -ERESTARTNOHAND:
-                        regs->ax = -EINTR;
-                        break;
-                case -ERESTARTSYS:
-                        if (!(ka->sa.sa_flags & SA_RESTART)) {
-                                regs->ax = -EINTR;
-                                break;
-                        }
-                /* fallthrough */
-                case -ERESTARTNOINTR:
-                        regs->ax = regs->orig_ax;
-                        regs->ip -= 2;
-                        break;
-                }
-        }
-        /*
-         * If TF is set due to a debugger (TIF_FORCED_TF), clear the TF
-         * flag so that register information in the sigcontext is correct.
-         */
-        if (unlikely(regs->flags & X86_EFLAGS_TF) &&
-            likely(test_and_clear_thread_flag(TIF_FORCED_TF)))
-                regs->flags &= ~X86_EFLAGS_TF;
-        ret = setup_rt_frame(sig, ka, info, oldset, regs);
-        if (ret)
-                return ret;
-#ifdef CONFIG_X86_64
-        /*
-         * This has nothing to do with segment registers,
-         * despite the name.  This magic affects uaccess.h
-         * macros' behavior.  Reset it to the normal setting.
-         */
-        set_fs(USER_DS);
-#endif
-        /*
-         * Clear the direction flag as per the ABI for function entry.
-         */
-        regs->flags &= ~X86_EFLAGS_DF;
-        /*
-         * Clear TF when entering the signal handler, but
-         * notify any tracer that was single-stepping it.
-         * The tracer may want to single-step inside the
-         * handler too.
-         */
-        regs->flags &= ~X86_EFLAGS_TF;
-        spin_lock_irq(&current->sighand->siglock);
-        sigorsets(&current->blocked, &current->blocked, &ka->sa.sa_mask);
-        if (!(ka->sa.sa_flags & SA_NODEFER))
-                sigaddset(&current->blocked, sig);
-        recalc_sigpending();
-        spin_unlock_irq(&current->sighand->siglock);
-        tracehook_signal_handler(sig, info, ka, regs,
-                                 test_thread_flag(TIF_SINGLESTEP));
-        return 0;
-}
-#define NR_restart_syscall      \
-        test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall
-/*
- * Note that 'init' is a special process: it doesn't get signals it doesn't
- * want to handle. Thus you cannot kill init even with a SIGKILL even by
- * mistake.
- */
-static void do_signal(struct pt_regs *regs)
-{
-        struct k_sigaction ka;
-        siginfo_t info;
-        int signr;
-        sigset_t *oldset;
-        /*
-         * We want the common case to go fast, which is why we may in certain
-         * cases get here from kernel mode. Just return without doing anything
-         * if so.
-         * X86_32: vm86 regs switched out by assembly code before reaching
-         * here, so testing against kernel CS suffices.
-         */
-        if (!user_mode(regs))
-                return;
-        if (current_thread_info()->status & TS_RESTORE_SIGMASK)
-                oldset = &current->saved_sigmask;
-        else
-                oldset = &current->blocked;
-        signr = get_signal_to_deliver(&info, &ka, regs, NULL);
-        if (signr > 0) {
-                /*
-                 * Re-enable any watchpoints before delivering the
-                 * signal to user space. The processor register will
-                 * have been cleared if the watchpoint triggered
-                 * inside the kernel.
-                 */
-                if (current->thread.debugreg7)
-                        set_debugreg(current->thread.debugreg7, 7);
-                /* Whee! Actually deliver the signal.  */
-                if (handle_signal(signr, &info, &ka, oldset, regs) == 0) {
-                        /*
-                         * A signal was successfully delivered; the saved
-                         * sigmask will have been stored in the signal frame,
-                         * and will be restored by sigreturn, so we can simply
-                         * clear the TS_RESTORE_SIGMASK flag.
-                         */
-                        current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
-                }
-                return;
-        }
-        /* Did we come from a system call? */
-        if (syscall_get_nr(current, regs) >= 0) {
-                /* Restart the system call - no handlers present */
-                switch (syscall_get_error(current, regs)) {
-                case -ERESTARTNOHAND:
-                case -ERESTARTSYS:
-                case -ERESTARTNOINTR:
-                        regs->ax = regs->orig_ax;
-                        regs->ip -= 2;
-                        break;
-                case -ERESTART_RESTARTBLOCK:
-                        regs->ax = NR_restart_syscall;
-                        regs->ip -= 2;
-                        break;
-                }
-        }
-        /*
-         * If there's no signal to deliver, we just put the saved sigmask
-         * back.
-         */
-        if (current_thread_info()->status & TS_RESTORE_SIGMASK) {
-                current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
-                sigprocmask(SIG_SETMASK, &current->saved_sigmask, NULL);
-        }
-}
-/*
- * notification of userspace execution resumption
- * - triggered by the TIF_WORK_MASK flags
- */
-void
-do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
-{
-#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE)
-        /* notify userspace of pending MCEs */
-        if (thread_info_flags & _TIF_MCE_NOTIFY)
-                mce_notify_user();
-#endif /* CONFIG_X86_64 && CONFIG_X86_MCE */
-        /* deal with pending signal delivery */
-        if (thread_info_flags & _TIF_SIGPENDING)
-                do_signal(regs);
-        if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-                clear_thread_flag(TIF_NOTIFY_RESUME);
-                tracehook_notify_resume(regs);
-        }
-#ifdef CONFIG_X86_32
-        clear_thread_flag(TIF_IRET);
-#endif /* CONFIG_X86_32 */
-}
-void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
-{
-        struct task_struct *me = current;
-        if (show_unhandled_signals && printk_ratelimit()) {
-                printk(KERN_INFO
-                       "%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx",
-                       me->comm, me->pid, where, frame,
-                       regs->ip, regs->sp, regs->orig_ax);
-                print_vma_addr(" in ", regs->ip);
-                printk(KERN_CONT "\n");
-        }
-        force_sig(SIGSEGV, me);
-}
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 18f9b19f5f8f..3f92b134ab90 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -140,19 +140,6 @@ void native_send_call_func_ipi(cpumask_t mask)
                send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
 }
-static void stop_this_cpu(void *dummy)
-{
-        local_irq_disable();
-        /*
-         * Remove this CPU:
-         */
-        cpu_clear(smp_processor_id(), cpu_online_map);
-        disable_local_APIC();
-        if (hlt_works(smp_processor_id()))
-                for (;;) halt();
-        for (;;);
-}
 /*
 * this function calls the 'stop' function on all other CPUs in the system.
 */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7b1093397319..7a430c4d1551 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -62,6 +62,7 @@
 #include <asm/mtrr.h>
 #include <asm/vmi.h>
 #include <asm/genapic.h>
+#include <asm/setup.h>
 #include <linux/mc146818rtc.h>
 #include <mach_apic.h>
@@ -294,9 +295,7 @@ static void __cpuinit start_secondary(void *unused)
         * fragile that we want to limit the things done here to the
         * most necessary things.
         */
-#ifdef CONFIG_VMI
        vmi_bringup();
-#endif
        cpu_init();
        preempt_disable();
        smp_callin();
@@ -536,7 +535,7 @@ static void impress_friends(void)
        pr_debug("Before bogocount - setting activated=1.\n");
 }
-static inline void __inquire_remote_apic(int apicid)
+void __inquire_remote_apic(int apicid)
 {
        unsigned i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 };
        char *names[] = { "ID", "VERSION", "SPIV" };
@@ -575,14 +574,13 @@ static inline void __inquire_remote_apic(int apicid)
        }
 }
-#ifdef WAKE_SECONDARY_VIA_NMI
 /*
 * Poke the other CPU in the eye via NMI to wake it up. Remember that the normal
 * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
 * won't ... remember to clear down the APIC, etc later.
 */
-static int __devinit
+int __devinit
-wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
+wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
 {
        unsigned long send_status, accept_status = 0;
        int maxlvt;
@@ -599,7 +597,7 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
         * Give the other CPU some time to accept the IPI.
         */
        udelay(200);
-        if (APIC_INTEGRATED(apic_version[phys_apicid])) {
+        if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
                maxlvt = lapic_get_maxlvt();
                if (maxlvt > 3)                 /* Due to the Pentium erratum 3AP.  */
                        apic_write(APIC_ESR, 0);
@@ -614,11 +612,9 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
        return (send_status | accept_status);
 }
-#endif  /* WAKE_SECONDARY_VIA_NMI */
-#ifdef WAKE_SECONDARY_VIA_INIT
+int __devinit
-static int __devinit
+wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
-wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
 {
        unsigned long send_status, accept_status = 0;
        int maxlvt, num_starts, j;
@@ -737,7 +733,6 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
        return (send_status | accept_status);
 }
-#endif  /* WAKE_SECONDARY_VIA_INIT */
 struct create_idle {
        struct work_struct work;
@@ -1086,8 +1081,10 @@ static int __init smp_sanity_check(unsigned max_cpus)
 #endif
        if (!physid_isset(hard_smp_processor_id(), phys_cpu_present_map)) {
-                printk(KERN_WARNING "weird, boot CPU (#%d) not listed"
+                printk(KERN_WARNING
-                                    "by the BIOS.\n", hard_smp_processor_id());
+                        "weird, boot CPU (#%d) not listed by the BIOS.\n",
+                        hard_smp_processor_id());
                physid_set(hard_smp_processor_id(), phys_cpu_present_map);
        }
diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c
index cb19d650c216..1b7711b31037 100644
--- a/arch/x86/kernel/time_64.c
+++ b/arch/x86/kernel/time_64.c
@@ -49,7 +49,7 @@ unsigned long profile_pc(struct pt_regs *regs)
 }
 EXPORT_SYMBOL(profile_pc);
-irqreturn_t timer_interrupt(int irq, void *dev_id)
+static irqreturn_t timer_interrupt(int irq, void *dev_id)
 {
        add_pda(irq0_irqs, 1);
@@ -80,6 +80,8 @@ unsigned long __init calibrate_cpu(void)
                        break;
        no_ctr_free = (i == 4);
        if (no_ctr_free) {
+                WARN(1, KERN_WARNING "Warning: AMD perfctrs busy ... "
+                     "cpu_khz value may be incorrect.\n");
                i = 3;
                rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
                wrmsrl(MSR_K7_EVNTSEL3, 0);
diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c
index f4049f3513b6..4290d918b58a 100644
--- a/arch/x86/kernel/tlb_32.c
+++ b/arch/x86/kernel/tlb_32.c
@@ -34,9 +34,8 @@ static DEFINE_SPINLOCK(tlbstate_lock);
 */
 void leave_mm(int cpu)
 {
-        if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK)
+        BUG_ON(x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK);
-                BUG();
+        cpu_clear(cpu, x86_read_percpu(cpu_tlbstate.active_mm)->cpu_vm_mask);
-        cpu_clear(cpu, per_cpu(cpu_tlbstate, cpu).active_mm->cpu_vm_mask);
        load_cr3(swapper_pg_dir);
 }
 EXPORT_SYMBOL_GPL(leave_mm);
@@ -104,8 +103,8 @@ void smp_invalidate_interrupt(struct pt_regs *regs)
                 * BUG();
                 */
-        if (flush_mm == per_cpu(cpu_tlbstate, cpu).active_mm) {
+        if (flush_mm == x86_read_percpu(cpu_tlbstate.active_mm)) {
-                if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) {
+                if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK) {
                        if (flush_va == TLB_FLUSH_ALL)
                                local_flush_tlb();
                        else
@@ -238,7 +237,7 @@ static void do_flush_tlb_all(void *info)
        unsigned long cpu = smp_processor_id();
        __flush_tlb_all();
-        if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_LAZY)
+        if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_LAZY)
                leave_mm(cpu);
 }
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 04431f34fd16..6a00e5faaa74 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -566,14 +566,10 @@ static int __init uv_ptc_init(void)
        if (!is_uv_system())
                return 0;
-        if (!proc_mkdir("sgi_uv", NULL))
-                return -EINVAL;
        proc_uv_ptc = create_proc_entry(UV_PTC_BASENAME, 0444, NULL);
        if (!proc_uv_ptc) {
                printk(KERN_ERR "unable to create %s proc entry\n",
                       UV_PTC_BASENAME);
-                remove_proc_entry("sgi_uv", NULL);
                return -EINVAL;
        }
        proc_uv_ptc->proc_fops = &proc_uv_ptc_operations;
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index 1106fac6024d..808031a5ba19 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -1,10 +1,26 @@
 #include <linux/io.h>
 #include <asm/trampoline.h>
+#include <asm/e820.h>
 /* ready for x86_64 and x86 */
 unsigned char *trampoline_base = __va(TRAMPOLINE_BASE);
+void __init reserve_trampoline_memory(void)
+{
+#ifdef CONFIG_X86_32
+        /*
+         * But first pinch a few for the stack/trampoline stuff
+         * FIXME: Don't need the extra page at 4K, but need to fix
+         * trampoline before removing it. (see the GDT stuff)
+         */
+        reserve_early(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE");
+#endif
+        /* Has to be in very low memory so we can execute real-mode AP code. */
+        reserve_early(TRAMPOLINE_BASE, TRAMPOLINE_BASE + TRAMPOLINE_SIZE,
+                        "TRAMPOLINE");
+}
 /*
 * Currently trivial. Write the real->protected mode
 * bootstrap into the page concerned. The caller
@@ -12,7 +28,6 @@ unsigned char *trampoline_base = __va(TRAMPOLINE_BASE);
 */
 unsigned long setup_trampoline(void)
 {
-        memcpy(trampoline_base, trampoline_data,
+        memcpy(trampoline_base, trampoline_data, TRAMPOLINE_SIZE);
-               trampoline_end - trampoline_data);
        return virt_to_phys(trampoline_base);
 }
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 04d242ab0161..c320c29255c2 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -664,7 +664,7 @@ void math_error(void __user *ip)
 {
        struct task_struct *task;
        siginfo_t info;
-        unsigned short cwd, swd;
+        unsigned short cwd, swd, err;
        /*
         * Save the info for the exception handler and clear the error.
@@ -675,7 +675,6 @@ void math_error(void __user *ip)
        task->thread.error_code = 0;
        info.si_signo = SIGFPE;
        info.si_errno = 0;
-        info.si_code = __SI_FAULT;
        info.si_addr = ip;
        /*
         * (~cwd & swd) will mask out exceptions that are not set to unmasked
@@ -689,34 +688,31 @@ void math_error(void __user *ip)
         */
        cwd = get_fpu_cwd(task);
        swd = get_fpu_swd(task);
-        switch (swd & ~cwd & 0x3f) {
-        case 0x000: /* No unmasked exception */
+        err = swd & ~cwd & 0x3f;
-#ifdef CONFIG_X86_32
+#if CONFIG_X86_32
+        if (!err)
                return;
 #endif
-        default: /* Multiple exceptions */
-                break;
+        if (err & 0x001) {      /* Invalid op */
-        case 0x001: /* Invalid Op */
                /*
                 * swd & 0x240 == 0x040: Stack Underflow
                 * swd & 0x240 == 0x240: Stack Overflow
                 * User must clear the SF bit (0x40) if set
                 */
                info.si_code = FPE_FLTINV;
-                break;
+        } else if (err & 0x004) { /* Divide by Zero */
-        case 0x002: /* Denormalize */
-        case 0x010: /* Underflow */
-                info.si_code = FPE_FLTUND;
-                break;
-        case 0x004: /* Zero Divide */
                info.si_code = FPE_FLTDIV;
-                break;
+        } else if (err & 0x008) { /* Overflow */
-        case 0x008: /* Overflow */
                info.si_code = FPE_FLTOVF;
-                break;
+        } else if (err & 0x012) { /* Denormal, Underflow */
-        case 0x020: /* Precision */
+                info.si_code = FPE_FLTUND;
+        } else if (err & 0x020) { /* Precision */
                info.si_code = FPE_FLTRES;
-                break;
+        } else {
+                info.si_code = __SI_FAULT|SI_KERNEL; /* WTF? */
        }
        force_sig_info(SIGFPE, &info, task);
 }
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 424093b157d3..599e58168631 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -15,6 +15,7 @@
 #include <asm/vgtod.h>
 #include <asm/time.h>
 #include <asm/delay.h>
+#include <asm/hypervisor.h>
 unsigned int cpu_khz;           /* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
@@ -31,6 +32,7 @@ static int tsc_unstable;
   erroneous rdtsc usage on !cpu_has_tsc processors */
 static int tsc_disabled = -1;
+static int tsc_clocksource_reliable;
 /*
 * Scheduler clock - returns current time in nanosec units.
 */
@@ -98,6 +100,15 @@ int __init notsc_setup(char *str)
 __setup("notsc", notsc_setup);
+static int __init tsc_setup(char *str)
+{
+        if (!strcmp(str, "reliable"))
+                tsc_clocksource_reliable = 1;
+        return 1;
+}
+__setup("tsc=", tsc_setup);
 #define MAX_RETRIES     5
 #define SMI_TRESHOLD    50000
@@ -352,9 +363,15 @@ unsigned long native_calibrate_tsc(void)
 {
        u64 tsc1, tsc2, delta, ref1, ref2;
        unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
-        unsigned long flags, latch, ms, fast_calibrate;
+        unsigned long flags, latch, ms, fast_calibrate, tsc_khz;
        int hpet = is_hpet_enabled(), i, loopmin;
+        tsc_khz = get_hypervisor_tsc_freq();
+        if (tsc_khz) {
+                printk(KERN_INFO "TSC: Frequency read from the hypervisor\n");
+                return tsc_khz;
+        }
        local_irq_save(flags);
        fast_calibrate = quick_pit_calibrate();
        local_irq_restore(flags);
@@ -731,24 +748,21 @@ static struct dmi_system_id __initdata bad_tsc_dmi_table[] = {
        {}
 };
-/*
+static void __init check_system_tsc_reliable(void)
- * Geode_LX - the OLPC CPU has a possibly a very reliable TSC
+{
- */
 #ifdef CONFIG_MGEODE_LX
-/* RTSC counts during suspend */
+        /* RTSC counts during suspend */
 #define RTSC_SUSP 0x100
-static void __init check_geode_tsc_reliable(void)
-{
        unsigned long res_low, res_high;
        rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
+        /* Geode_LX - the OLPC CPU has a possibly a very reliable TSC */
        if (res_low & RTSC_SUSP)
-                clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+                tsc_clocksource_reliable = 1;
-}
-#else
-static inline void check_geode_tsc_reliable(void) { }
 #endif
+        if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE))
+                tsc_clocksource_reliable = 1;
+}
 /*
 * Make an educated guess if the TSC is trustworthy and synchronized
@@ -783,6 +797,8 @@ static void __init init_tsc_clocksource(void)
 {
        clocksource_tsc.mult = clocksource_khz2mult(tsc_khz,
                        clocksource_tsc.shift);
+        if (tsc_clocksource_reliable)
+                clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
        /* lower the rating if we already know its unstable: */
        if (check_tsc_unstable()) {
                clocksource_tsc.rating = 0;
@@ -843,7 +859,7 @@ void __init tsc_init(void)
        if (unsynchronized_tsc())
                mark_tsc_unstable("TSCs unsynchronized");
-        check_geode_tsc_reliable();
+        check_system_tsc_reliable();
        init_tsc_clocksource();
 }
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 1c0dfbca87c1..bf36328f6ef9 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -112,6 +112,12 @@ void __cpuinit check_tsc_sync_source(int cpu)
        if (unsynchronized_tsc())
                return;
+        if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
+                printk(KERN_INFO
+                       "Skipping synchronization checks as TSC is reliable.\n");
+                return;
+        }
        printk(KERN_INFO "checking TSC synchronization [CPU#%d -> CPU#%d]:",
                          smp_processor_id(), cpu);
@@ -165,7 +171,7 @@ void __cpuinit check_tsc_sync_target(void)
 {
        int cpus = 2;
-        if (unsynchronized_tsc())
+        if (unsynchronized_tsc() || boot_cpu_has(X86_FEATURE_TSC_RELIABLE))
                return;
        /*
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 8b6c393ab9fd..23206ba16874 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -266,109 +266,6 @@ static void vmi_nop(void)
 {
 }
-#ifdef CONFIG_DEBUG_PAGE_TYPE
-#ifdef CONFIG_X86_PAE
-#define MAX_BOOT_PTS (2048+4+1)
-#else
-#define MAX_BOOT_PTS (1024+1)
-#endif
-/*
- * During boot, mem_map is not yet available in paging_init, so stash
- * all the boot page allocations here.
- */
-static struct {
-        u32 pfn;
-        int type;
-} boot_page_allocations[MAX_BOOT_PTS];
-static int num_boot_page_allocations;
-static int boot_allocations_applied;
-void vmi_apply_boot_page_allocations(void)
-{
-        int i;
-        BUG_ON(!mem_map);
-        for (i = 0; i < num_boot_page_allocations; i++) {
-                struct page *page = pfn_to_page(boot_page_allocations[i].pfn);
-                page->type = boot_page_allocations[i].type;
-                page->type = boot_page_allocations[i].type &
-                                ~(VMI_PAGE_ZEROED | VMI_PAGE_CLONE);
-        }
-        boot_allocations_applied = 1;
-}
-static void record_page_type(u32 pfn, int type)
-{
-        BUG_ON(num_boot_page_allocations >= MAX_BOOT_PTS);
-        boot_page_allocations[num_boot_page_allocations].pfn = pfn;
-        boot_page_allocations[num_boot_page_allocations].type = type;
-        num_boot_page_allocations++;
-}
-static void check_zeroed_page(u32 pfn, int type, struct page *page)
-{
-        u32 *ptr;
-        int i;
-        int limit = PAGE_SIZE / sizeof(int);
-        if (page_address(page))
-                ptr = (u32 *)page_address(page);
-        else
-                ptr = (u32 *)__va(pfn << PAGE_SHIFT);
-        /*
-         * When cloning the root in non-PAE mode, only the userspace
-         * pdes need to be zeroed.
-         */
-        if (type & VMI_PAGE_CLONE)
-                limit = KERNEL_PGD_BOUNDARY;
-        for (i = 0; i < limit; i++)
-                BUG_ON(ptr[i]);
-}
-/*
- * We stash the page type into struct page so we can verify the page
- * types are used properly.
- */
-static void vmi_set_page_type(u32 pfn, int type)
-{
-        /* PAE can have multiple roots per page - don't track */
-        if (PTRS_PER_PMD > 1 && (type & VMI_PAGE_PDP))
-                return;
-        if (boot_allocations_applied) {
-                struct page *page = pfn_to_page(pfn);
-                if (type != VMI_PAGE_NORMAL)
-                        BUG_ON(page->type);
-                else
-                        BUG_ON(page->type == VMI_PAGE_NORMAL);
-                page->type = type & ~(VMI_PAGE_ZEROED | VMI_PAGE_CLONE);
-                if (type & VMI_PAGE_ZEROED)
-                        check_zeroed_page(pfn, type, page);
-        } else {
-                record_page_type(pfn, type);
-        }
-}
-static void vmi_check_page_type(u32 pfn, int type)
-{
-        /* PAE can have multiple roots per page - skip checks */
-        if (PTRS_PER_PMD > 1 && (type & VMI_PAGE_PDP))
-                return;
-        type &= ~(VMI_PAGE_ZEROED | VMI_PAGE_CLONE);
-        if (boot_allocations_applied) {
-                struct page *page = pfn_to_page(pfn);
-                BUG_ON((page->type ^ type) & VMI_PAGE_PAE);
-                BUG_ON(type == VMI_PAGE_NORMAL && page->type);
-                BUG_ON((type & page->type) == 0);
-        }
-}
-#else
-#define vmi_set_page_type(p,t) do { } while (0)
-#define vmi_check_page_type(p,t) do { } while (0)
-#endif
 #ifdef CONFIG_HIGHPTE
 static void *vmi_kmap_atomic_pte(struct page *page, enum km_type type)
 {
@@ -395,7 +292,6 @@ static void *vmi_kmap_atomic_pte(struct page *page, enum km_type type)
 static void vmi_allocate_pte(struct mm_struct *mm, unsigned long pfn)
 {
-        vmi_set_page_type(pfn, VMI_PAGE_L1);
        vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0);
 }
@@ -406,27 +302,22 @@ static void vmi_allocate_pmd(struct mm_struct *mm, unsigned long pfn)
         * It is called only for swapper_pg_dir, which already has
         * data on it.
         */
-        vmi_set_page_type(pfn, VMI_PAGE_L2);
        vmi_ops.allocate_page(pfn, VMI_PAGE_L2, 0, 0, 0);
 }
 static void vmi_allocate_pmd_clone(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count)
 {
-        vmi_set_page_type(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE);
-        vmi_check_page_type(clonepfn, VMI_PAGE_L2);
        vmi_ops.allocate_page(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE, clonepfn, start, count);
 }
 static void vmi_release_pte(unsigned long pfn)
 {
        vmi_ops.release_page(pfn, VMI_PAGE_L1);
-        vmi_set_page_type(pfn, VMI_PAGE_NORMAL);
 }
 static void vmi_release_pmd(unsigned long pfn)
 {
        vmi_ops.release_page(pfn, VMI_PAGE_L2);
-        vmi_set_page_type(pfn, VMI_PAGE_NORMAL);
 }
 /*
@@ -450,26 +341,22 @@ static void vmi_release_pmd(unsigned long pfn)
 static void vmi_update_pte(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-        vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE);
        vmi_ops.update_pte(ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
 }
 static void vmi_update_pte_defer(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-        vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE);
        vmi_ops.update_pte(ptep, vmi_flags_addr_defer(mm, addr, VMI_PAGE_PT, 0));
 }
 static void vmi_set_pte(pte_t *ptep, pte_t pte)
 {
        /* XXX because of set_pmd_pte, this can be called on PT or PD layers */
-        vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE | VMI_PAGE_PD);
        vmi_ops.set_pte(pte, ptep, VMI_PAGE_PT);
 }
 static void vmi_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
 {
-        vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE);
        vmi_ops.set_pte(pte, ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
 }
@@ -477,10 +364,8 @@ static void vmi_set_pmd(pmd_t *pmdp, pmd_t pmdval)
 {
 #ifdef CONFIG_X86_PAE
        const pte_t pte = { .pte = pmdval.pmd };
-        vmi_check_page_type(__pa(pmdp) >> PAGE_SHIFT, VMI_PAGE_PMD);
 #else
        const pte_t pte = { pmdval.pud.pgd.pgd };
-        vmi_check_page_type(__pa(pmdp) >> PAGE_SHIFT, VMI_PAGE_PGD);
 #endif
        vmi_ops.set_pte(pte, (pte_t *)pmdp, VMI_PAGE_PD);
 }
@@ -502,7 +387,6 @@ static void vmi_set_pte_atomic(pte_t *ptep, pte_t pteval)
 static void vmi_set_pte_present(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
 {
-        vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE);
        vmi_ops.set_pte(pte, ptep, vmi_flags_addr_defer(mm, addr, VMI_PAGE_PT, 1));
 }
@@ -510,21 +394,18 @@ static void vmi_set_pud(pud_t *pudp, pud_t pudval)
 {
        /* Um, eww */
        const pte_t pte = { .pte = pudval.pgd.pgd };
-        vmi_check_page_type(__pa(pudp) >> PAGE_SHIFT, VMI_PAGE_PGD);
        vmi_ops.set_pte(pte, (pte_t *)pudp, VMI_PAGE_PDP);
 }
 static void vmi_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
        const pte_t pte = { .pte = 0 };
-        vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE);
        vmi_ops.set_pte(pte, ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
 }
 static void vmi_pmd_clear(pmd_t *pmd)
 {
        const pte_t pte = { .pte = 0 };
-        vmi_check_page_type(__pa(pmd) >> PAGE_SHIFT, VMI_PAGE_PMD);
        vmi_ops.set_pte(pte, (pte_t *)pmd, VMI_PAGE_PD);
 }
 #endif
@@ -960,8 +841,6 @@ static inline int __init activate_vmi(void)
 void __init vmi_init(void)
 {
-        unsigned long flags;
        if (!vmi_rom)
                probe_vmi_rom();
        else
@@ -973,13 +852,21 @@ void __init vmi_init(void)
        reserve_top_address(-vmi_rom->virtual_top);
-        local_irq_save(flags);
-        activate_vmi();
 #ifdef CONFIG_X86_IO_APIC
        /* This is virtual hardware; timer routing is wired correctly */
        no_timer_check = 1;
 #endif
+}
+void vmi_activate(void)
+{
+        unsigned long flags;
+        if (!vmi_rom)
+                return;
+        local_irq_save(flags);
+        activate_vmi();
        local_irq_restore(flags & X86_EFLAGS_IF);
 }
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 0b8b6690a86d..ebf2f12900f5 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -128,7 +128,16 @@ static __always_inline void do_vgettimeofday(struct timeval * tv)
                        gettimeofday(tv,NULL);
                        return;
                }
+                /*
+                 * Surround the RDTSC by barriers, to make sure it's not
+                 * speculated to outside the seqlock critical section and
+                 * does not cause time warps:
+                 */
+                rdtsc_barrier();
                now = vread();
+                rdtsc_barrier();
                base = __vsyscall_gtod_data.clock.cycle_last;
                mask = __vsyscall_gtod_data.clock.mask;
                mult = __vsyscall_gtod_data.clock.mult;
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index b13acb75e822..15c3e6999182 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -310,7 +310,7 @@ static void __init setup_xstate_init(void)
 /*
 * Enable and initialize the xsave feature.
 */
-void __init xsave_cntxt_init(void)
+void __ref xsave_cntxt_init(void)
 {
        unsigned int eax, ebx, ecx, edx;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index f1983d9477cd..410ddbc1aa2e 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1038,13 +1038,13 @@ static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
        }
        rmap_write_protect(vcpu->kvm, sp->gfn);
+        kvm_unlink_unsync_page(vcpu->kvm, sp);
        if (vcpu->arch.mmu.sync_page(vcpu, sp)) {
                kvm_mmu_zap_page(vcpu->kvm, sp);
                return 1;
        }
        kvm_mmu_flush_tlb(vcpu);
-        kvm_unlink_unsync_page(vcpu->kvm, sp);
        return 0;
 }
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 613ec9aa674a..84eee43bbe74 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -331,6 +331,7 @@ static int FNAME(shadow_walk_entry)(struct kvm_shadow_walk *_sw,
                r = kvm_read_guest_atomic(vcpu->kvm, gw->pte_gpa[level - 2],
                                          &curr_pte, sizeof(curr_pte));
                if (r || curr_pte != gw->ptes[level - 2]) {
+                        kvm_mmu_put_page(shadow_page, sptep);
                        kvm_release_pfn_clean(sw->pfn);
                        sw->sptep = NULL;
                        return 1;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index d06b4dc0e2ea..a4018b01e1f9 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3149,7 +3149,9 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu)
        if (cpu_has_virtual_nmis()) {
                if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) {
-                        if (vmx_nmi_enabled(vcpu)) {
+                        if (vcpu->arch.interrupt.pending) {
+                                enable_nmi_window(vcpu);
+                        } else if (vmx_nmi_enabled(vcpu)) {
                                vcpu->arch.nmi_pending = false;
                                vcpu->arch.nmi_injected = true;
                        } else {
diff --git a/arch/x86/mach-generic/bigsmp.c b/arch/x86/mach-generic/bigsmp.c
index 3c3b471ea496..3624a364b7f3 100644
--- a/arch/x86/mach-generic/bigsmp.c
+++ b/arch/x86/mach-generic/bigsmp.c
@@ -17,6 +17,7 @@
 #include <asm/bigsmp/apic.h>
 #include <asm/bigsmp/ipi.h>
 #include <asm/mach-default/mach_mpparse.h>
+#include <asm/mach-default/mach_wakecpu.h>
 static int dmi_bigsmp; /* can be set by dmi scanners */
diff --git a/arch/x86/mach-generic/default.c b/arch/x86/mach-generic/default.c
index 9e835a11a13a..e63a4a76d8cd 100644
--- a/arch/x86/mach-generic/default.c
+++ b/arch/x86/mach-generic/default.c
@@ -16,6 +16,7 @@
 #include <asm/mach-default/mach_apic.h>
 #include <asm/mach-default/mach_ipi.h>
 #include <asm/mach-default/mach_mpparse.h>
+#include <asm/mach-default/mach_wakecpu.h>
 /* should be called last. */
 static int probe_default(void)
diff --git a/arch/x86/mach-generic/es7000.c b/arch/x86/mach-generic/es7000.c
index 28459cab3ddb..7b4e6d0d1690 100644
--- a/arch/x86/mach-generic/es7000.c
+++ b/arch/x86/mach-generic/es7000.c
@@ -16,7 +16,19 @@
 #include <asm/es7000/apic.h>
 #include <asm/es7000/ipi.h>
 #include <asm/es7000/mpparse.h>
-#include <asm/es7000/wakecpu.h>
+#include <asm/mach-default/mach_wakecpu.h>
+void __init es7000_update_genapic_to_cluster(void)
+{
+        genapic->target_cpus = target_cpus_cluster;
+        genapic->int_delivery_mode = INT_DELIVERY_MODE_CLUSTER;
+        genapic->int_dest_mode = INT_DEST_MODE_CLUSTER;
+        genapic->no_balance_irq = NO_BALANCE_IRQ_CLUSTER;
+        genapic->init_apic_ldr = init_apic_ldr_cluster;
+        genapic->cpu_mask_to_apicid = cpu_mask_to_apicid_cluster;
+}
 static int probe_es7000(void)
 {
diff --git a/arch/x86/mach-generic/probe.c b/arch/x86/mach-generic/probe.c
index 5a7e4619e1c4..c346d9d0226f 100644
--- a/arch/x86/mach-generic/probe.c
+++ b/arch/x86/mach-generic/probe.c
@@ -15,6 +15,7 @@
 #include <asm/mpspec.h>
 #include <asm/apicdef.h>
 #include <asm/genapic.h>
+#include <asm/setup.h>
 extern struct genapic apic_numaq;
 extern struct genapic apic_summit;
@@ -57,6 +58,9 @@ static int __init parse_apic(char *arg)
                }
        }
+        if (x86_quirks->update_genapic)
+                x86_quirks->update_genapic();
        /* Parsed again by __setup for debug/verbose */
        return 0;
 }
@@ -72,12 +76,15 @@ void __init generic_bigsmp_probe(void)
         * - we find more than 8 CPUs in acpi LAPIC listing with xAPIC support
         */
-        if (!cmdline_apic && genapic == &apic_default)
+        if (!cmdline_apic && genapic == &apic_default) {
                if (apic_bigsmp.probe()) {
                        genapic = &apic_bigsmp;
+                        if (x86_quirks->update_genapic)
+                                x86_quirks->update_genapic();
                        printk(KERN_INFO "Overriding APIC driver with %s\n",
                               genapic->name);
                }
+        }
 #endif
 }
@@ -94,6 +101,9 @@ void __init generic_apic_probe(void)
                /* Not visible without early console */
                if (!apic_probe[i])
                        panic("Didn't find an APIC driver");
+                if (x86_quirks->update_genapic)
+                        x86_quirks->update_genapic();
        }
        printk(KERN_INFO "Using APIC driver %s\n", genapic->name);
 }
@@ -108,6 +118,8 @@ int __init mps_oem_check(struct mp_config_table *mpc, char *oem,
                if (apic_probe[i]->mps_oem_check(mpc, oem, productid)) {
                        if (!cmdline_apic) {
                                genapic = apic_probe[i];
+                                if (x86_quirks->update_genapic)
+                                        x86_quirks->update_genapic();
                                printk(KERN_INFO "Switched to APIC driver `%s'.\n",
                                       genapic->name);
                        }
@@ -124,6 +136,8 @@ int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id)
                if (apic_probe[i]->acpi_madt_oem_check(oem_id, oem_table_id)) {
                        if (!cmdline_apic) {
                                genapic = apic_probe[i];
+                                if (x86_quirks->update_genapic)
+                                        x86_quirks->update_genapic();
                                printk(KERN_INFO "Switched to APIC driver `%s'.\n",
                                       genapic->name);
                        }
diff --git a/arch/x86/mach-generic/summit.c b/arch/x86/mach-generic/summit.c
index 6272b5e69da6..2c6d234e0009 100644
--- a/arch/x86/mach-generic/summit.c
+++ b/arch/x86/mach-generic/summit.c
@@ -16,6 +16,7 @@
 #include <asm/summit/apic.h>
 #include <asm/summit/ipi.h>
 #include <asm/summit/mpparse.h>
+#include <asm/mach-default/mach_wakecpu.h>
 static int probe_summit(void)
 {
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 31e8730fa246..20ef272c412c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -413,6 +413,7 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
                                 unsigned long error_code)
 {
        unsigned long flags = oops_begin();
+        int sig = SIGKILL;
        struct task_struct *tsk;
        printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
@@ -423,8 +424,8 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
        tsk->thread.trap_no = 14;
        tsk->thread.error_code = error_code;
        if (__die("Bad pagetable", regs, error_code))
-                regs = NULL;
+                sig = 0;
-        oops_end(flags, regs, SIGKILL);
+        oops_end(flags, regs, sig);
 }
 #endif
@@ -590,6 +591,7 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
        int fault;
 #ifdef CONFIG_X86_64
        unsigned long flags;
+        int sig;
 #endif
        tsk = current;
@@ -849,11 +851,12 @@ no_context:
        bust_spinlocks(0);
        do_exit(SIGKILL);
 #else
+        sig = SIGKILL;
        if (__die("Oops", regs, error_code))
-                regs = NULL;
+                sig = 0;
        /* Executive summary in case the body of the oops scrolled away */
        printk(KERN_EMERG "CR2: %016lx\n", address);
-        oops_end(flags, regs, SIGKILL);
+        oops_end(flags, regs, sig);
 #endif
 /*
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8110d484b02c..800e1d94c1b5 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -67,7 +67,7 @@ static unsigned long __meminitdata table_top;
 static int __initdata after_init_bootmem;
-static __init void *alloc_low_page(unsigned long *phys)
+static __init void *alloc_low_page(void)
 {
        unsigned long pfn = table_end++;
        void *adr;
@@ -77,7 +77,6 @@ static __init void *alloc_low_page(unsigned long *phys)
        adr = __va(pfn * PAGE_SIZE);
        memset(adr, 0, PAGE_SIZE);
-        *phys  = pfn * PAGE_SIZE;
        return adr;
 }
@@ -92,16 +91,17 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
        pmd_t *pmd_table;
 #ifdef CONFIG_X86_PAE
-        unsigned long phys;
        if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
                if (after_init_bootmem)
                        pmd_table = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
                else
-                        pmd_table = (pmd_t *)alloc_low_page(&phys);
+                        pmd_table = (pmd_t *)alloc_low_page();
                paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
                set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
                pud = pud_offset(pgd, 0);
                BUG_ON(pmd_table != pmd_offset(pud, 0));
+                return pmd_table;
        }
 #endif
        pud = pud_offset(pgd, 0);
@@ -126,10 +126,8 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
                        if (!page_table)
                                page_table =
                                (pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
-                } else {
+                } else
-                        unsigned long phys;
+                        page_table = (pte_t *)alloc_low_page();
-                        page_table = (pte_t *)alloc_low_page(&phys);
-                }
                paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT);
                set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
@@ -1038,11 +1036,25 @@ void __init mem_init(void)
                (unsigned long)&_text, (unsigned long)&_etext,
                ((unsigned long)&_etext - (unsigned long)&_text) >> 10);
+        /*
+         * Check boundaries twice: Some fundamental inconsistencies can
+         * be detected at build time already.
+         */
+#define __FIXADDR_TOP (-PAGE_SIZE)
+#ifdef CONFIG_HIGHMEM
+        BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE  > FIXADDR_START);
+        BUILD_BUG_ON(VMALLOC_END                        > PKMAP_BASE);
+#endif
+#define high_memory (-128UL << 20)
+        BUILD_BUG_ON(VMALLOC_START                      >= VMALLOC_END);
+#undef high_memory
+#undef __FIXADDR_TOP
 #ifdef CONFIG_HIGHMEM
        BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE        > FIXADDR_START);
        BUG_ON(VMALLOC_END                              > PKMAP_BASE);
 #endif
-        BUG_ON(VMALLOC_START                            > VMALLOC_END);
+        BUG_ON(VMALLOC_START                            >= VMALLOC_END);
        BUG_ON((unsigned long)high_memory               > VMALLOC_START);
        if (boot_cpu_data.wp_works_ok < 0)
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index d4c4307ff3e0..bd85d42819e1 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -223,7 +223,8 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
         * Check if the request spans more than any BAR in the iomem resource
         * tree.
         */
-        WARN_ON(iomem_map_sanity_check(phys_addr, size));
+        WARN_ONCE(iomem_map_sanity_check(phys_addr, size),
+                  KERN_INFO "Info: mapping multiple BARs. Your kernel is fine.");
        /*
         * Don't allow anybody to remap normal RAM that we're using..
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index eb1bf000d12e..541bcc944a5b 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -596,6 +596,242 @@ void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
        free_memtype(addr, addr + size);
 }
+/*
+ * Internal interface to reserve a range of physical memory with prot.
+ * Reserved non RAM regions only and after successful reserve_memtype,
+ * this func also keeps identity mapping (if any) in sync with this new prot.
+ */
+static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t vma_prot)
+{
+        int is_ram = 0;
+        int id_sz, ret;
+        unsigned long flags;
+        unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK);
+        is_ram = pagerange_is_ram(paddr, paddr + size);
+        if (is_ram != 0) {
+                /*
+                 * For mapping RAM pages, drivers need to call
+                 * set_memory_[uc|wc|wb] directly, for reserve and free, before
+                 * setting up the PTE.
+                 */
+                WARN_ON_ONCE(1);
+                return 0;
+        }
+        ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
+        if (ret)
+                return ret;
+        if (flags != want_flags) {
+                free_memtype(paddr, paddr + size);
+                printk(KERN_ERR
+                "%s:%d map pfn expected mapping type %s for %Lx-%Lx, got %s\n",
+                        current->comm, current->pid,
+                        cattr_name(want_flags),
+                        (unsigned long long)paddr,
+                        (unsigned long long)(paddr + size),
+                        cattr_name(flags));
+                return -EINVAL;
+        }
+        /* Need to keep identity mapping in sync */
+        if (paddr >= __pa(high_memory))
+                return 0;
+        id_sz = (__pa(high_memory) < paddr + size) ?
+                                __pa(high_memory) - paddr :
+                                size;
+        if (ioremap_change_attr((unsigned long)__va(paddr), id_sz, flags) < 0) {
+                free_memtype(paddr, paddr + size);
+                printk(KERN_ERR
+                        "%s:%d reserve_pfn_range ioremap_change_attr failed %s "
+                        "for %Lx-%Lx\n",
+                        current->comm, current->pid,
+                        cattr_name(flags),
+                        (unsigned long long)paddr,
+                        (unsigned long long)(paddr + size));
+                return -EINVAL;
+        }
+        return 0;
+}
+/*
+ * Internal interface to free a range of physical memory.
+ * Frees non RAM regions only.
+ */
+static void free_pfn_range(u64 paddr, unsigned long size)
+{
+        int is_ram;
+        is_ram = pagerange_is_ram(paddr, paddr + size);
+        if (is_ram == 0)
+                free_memtype(paddr, paddr + size);
+}
+/*
+ * track_pfn_vma_copy is called when vma that is covering the pfnmap gets
+ * copied through copy_page_range().
+ *
+ * If the vma has a linear pfn mapping for the entire range, we get the prot
+ * from pte and reserve the entire vma range with single reserve_pfn_range call.
+ * Otherwise, we reserve the entire vma range, my ging through the PTEs page
+ * by page to get physical address and protection.
+ */
+int track_pfn_vma_copy(struct vm_area_struct *vma)
+{
+        int retval = 0;
+        unsigned long i, j;
+        u64 paddr;
+        unsigned long prot;
+        unsigned long vma_start = vma->vm_start;
+        unsigned long vma_end = vma->vm_end;
+        unsigned long vma_size = vma_end - vma_start;
+        if (!pat_enabled)
+                return 0;
+        if (is_linear_pfn_mapping(vma)) {
+                /*
+                 * reserve the whole chunk covered by vma. We need the
+                 * starting address and protection from pte.
+                 */
+                if (follow_phys(vma, vma_start, 0, &prot, &paddr)) {
+                        WARN_ON_ONCE(1);
+                        return -EINVAL;
+                }
+                return reserve_pfn_range(paddr, vma_size, __pgprot(prot));
+        }
+        /* reserve entire vma page by page, using pfn and prot from pte */
+        for (i = 0; i < vma_size; i += PAGE_SIZE) {
+                if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
+                        continue;
+                retval = reserve_pfn_range(paddr, PAGE_SIZE, __pgprot(prot));
+                if (retval)
+                        goto cleanup_ret;
+        }
+        return 0;
+cleanup_ret:
+        /* Reserve error: Cleanup partial reservation and return error */
+        for (j = 0; j < i; j += PAGE_SIZE) {
+                if (follow_phys(vma, vma_start + j, 0, &prot, &paddr))
+                        continue;
+                free_pfn_range(paddr, PAGE_SIZE);
+        }
+        return retval;
+}
+/*
+ * track_pfn_vma_new is called when a _new_ pfn mapping is being established
+ * for physical range indicated by pfn and size.
+ *
+ * prot is passed in as a parameter for the new mapping. If the vma has a
+ * linear pfn mapping for the entire range reserve the entire vma range with
+ * single reserve_pfn_range call.
+ * Otherwise, we look t the pfn and size and reserve only the specified range
+ * page by page.
+ *
+ * Note that this function can be called with caller trying to map only a
+ * subrange/page inside the vma.
+ */
+int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
+                        unsigned long pfn, unsigned long size)
+{
+        int retval = 0;
+        unsigned long i, j;
+        u64 base_paddr;
+        u64 paddr;
+        unsigned long vma_start = vma->vm_start;
+        unsigned long vma_end = vma->vm_end;
+        unsigned long vma_size = vma_end - vma_start;
+        if (!pat_enabled)
+                return 0;
+        if (is_linear_pfn_mapping(vma)) {
+                /* reserve the whole chunk starting from vm_pgoff */
+                paddr = (u64)vma->vm_pgoff << PAGE_SHIFT;
+                return reserve_pfn_range(paddr, vma_size, prot);
+        }
+        /* reserve page by page using pfn and size */
+        base_paddr = (u64)pfn << PAGE_SHIFT;
+        for (i = 0; i < size; i += PAGE_SIZE) {
+                paddr = base_paddr + i;
+                retval = reserve_pfn_range(paddr, PAGE_SIZE, prot);
+                if (retval)
+                        goto cleanup_ret;
+        }
+        return 0;
+cleanup_ret:
+        /* Reserve error: Cleanup partial reservation and return error */
+        for (j = 0; j < i; j += PAGE_SIZE) {
+                paddr = base_paddr + j;
+                free_pfn_range(paddr, PAGE_SIZE);
+        }
+        return retval;
+}
+/*
+ * untrack_pfn_vma is called while unmapping a pfnmap for a region.
+ * untrack can be called for a specific region indicated by pfn and size or
+ * can be for the entire vma (in which case size can be zero).
+ */
+void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
+                        unsigned long size)
+{
+        unsigned long i;
+        u64 paddr;
+        unsigned long prot;
+        unsigned long vma_start = vma->vm_start;
+        unsigned long vma_end = vma->vm_end;
+        unsigned long vma_size = vma_end - vma_start;
+        if (!pat_enabled)
+                return;
+        if (is_linear_pfn_mapping(vma)) {
+                /* free the whole chunk starting from vm_pgoff */
+                paddr = (u64)vma->vm_pgoff << PAGE_SHIFT;
+                free_pfn_range(paddr, vma_size);
+                return;
+        }
+        if (size != 0 && size != vma_size) {
+                /* free page by page, using pfn and size */
+                paddr = (u64)pfn << PAGE_SHIFT;
+                for (i = 0; i < size; i += PAGE_SIZE) {
+                        paddr = paddr + i;
+                        free_pfn_range(paddr, PAGE_SIZE);
+                }
+        } else {
+                /* free entire vma, page by page, using the pfn from pte */
+                for (i = 0; i < vma_size; i += PAGE_SIZE) {
+                        if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
+                                continue;
+                        free_pfn_range(paddr, PAGE_SIZE);
+                }
+        }
+}
+pgprot_t pgprot_writecombine(pgprot_t prot)
+{
+        if (pat_enabled)
+                return __pgprot(pgprot_val(prot) | _PAGE_CACHE_WC);
+        else
+                return pgprot_noncached(prot);
+}
 #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
 /* get Nth element of the linked list */
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 022cd41ea9b4..202864ad49a7 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -401,14 +401,13 @@ static int __init ppro_init(char **cpu_type)
                *cpu_type = "i386/pii";
                break;
        case 6 ... 8:
+        case 10 ... 11:
                *cpu_type = "i386/piii";
                break;
        case 9:
+        case 13:
                *cpu_type = "i386/p6_mobile";
                break;
-        case 10 ... 13:
-                *cpu_type = "i386/p6";
-                break;
        case 14:
                *cpu_type = "i386/core";
                break;
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 3f1b81a83e2e..e9f80c744cf3 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -69,7 +69,7 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
        int i;
        if (!reset_value) {
-                reset_value = kmalloc(sizeof(unsigned) * num_counters,
+                reset_value = kmalloc(sizeof(reset_value[0]) * num_counters,
                                        GFP_ATOMIC);
                if (!reset_value)
                        return;
@@ -156,6 +156,8 @@ static void ppro_start(struct op_msrs const * const msrs)
        unsigned int low, high;
        int i;
+        if (!reset_value)
+                return;
        for (i = 0; i < num_counters; ++i) {
                if (reset_value[i]) {
                        CTRL_READ(low, high, msrs, i);
@@ -171,6 +173,8 @@ static void ppro_stop(struct op_msrs const * const msrs)
        unsigned int low, high;
        int i;
+        if (!reset_value)
+                return;
        for (i = 0; i < num_counters; ++i) {
                if (!reset_value[i])
                        continue;
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index b67732bbb85a..bb1a01f089e2 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -23,6 +23,12 @@ unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 |
 unsigned int pci_early_dump_regs;
 static int pci_bf_sort;
 int pci_routeirq;
+int noioapicquirk;
+#ifdef CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS
+int noioapicreroute = 0;
+#else
+int noioapicreroute = 1;
+#endif
 int pcibios_last_bus = -1;
 unsigned long pirq_table_addr;
 struct pci_bus *pci_root_bus;
@@ -519,6 +525,17 @@ char * __devinit  pcibios_setup(char *str)
        } else if (!strcmp(str, "skip_isa_align")) {
                pci_probe |= PCI_CAN_SKIP_ISA_ALIGN;
                return NULL;
+        } else if (!strcmp(str, "noioapicquirk")) {
+                noioapicquirk = 1;
+                return NULL;
+        } else if (!strcmp(str, "ioapicreroute")) {
+                if (noioapicreroute != -1)
+                        noioapicreroute = 0;
+                return NULL;
+        } else if (!strcmp(str, "noioapicreroute")) {
+                if (noioapicreroute != -1)
+                        noioapicreroute = 1;
+                return NULL;
        }
        return str;
 }
diff --git a/arch/x86/pci/direct.c b/arch/x86/pci/direct.c
index 9915293500fb..9a5af6c8fbe9 100644
--- a/arch/x86/pci/direct.c
+++ b/arch/x86/pci/direct.c
@@ -173,7 +173,7 @@ static int pci_conf2_write(unsigned int seg, unsigned int bus,
 #undef PCI_CONF2_ADDRESS
-static struct pci_raw_ops pci_direct_conf2 = {
+struct pci_raw_ops pci_direct_conf2 = {
        .read =         pci_conf2_read,
        .write =        pci_conf2_write,
 };
@@ -289,6 +289,7 @@ int __init pci_direct_probe(void)
        if (pci_check_type1()) {
                raw_pci_ops = &pci_direct_conf1;
+                port_cf9_safe = true;
                return 1;
        }
        release_resource(region);
@@ -305,6 +306,7 @@ int __init pci_direct_probe(void)
        if (pci_check_type2()) {
                raw_pci_ops = &pci_direct_conf2;
+                port_cf9_safe = true;
                return 2;
        }
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 3c27a809393b..2051dc96b8e9 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -496,21 +496,24 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SIEMENS, 0x0015,
                          pci_siemens_interrupt_controller);
 /*
- * Regular PCI devices have 256 bytes, but AMD Family 10h Opteron ext config
+ * Regular PCI devices have 256 bytes, but AMD Family 10h/11h CPUs have
- * have 4096 bytes.  Even if the device is capable, that doesn't mean we can
+ * 4096 bytes configuration space for each function of their processor
- * access it.  Maybe we don't have a way to generate extended config space
+ * configuration space.
- * accesses.   So check it
 */
-static void fam10h_pci_cfg_space_size(struct pci_dev *dev)
+static void amd_cpu_pci_cfg_space_size(struct pci_dev *dev)
 {
        dev->cfg_size = pci_cfg_space_size_ext(dev);
 }
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1200, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1200, fam10h_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1201, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1201, fam10h_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1202, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1202, fam10h_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1203, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1203, fam10h_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1204, amd_cpu_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1204, fam10h_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1300, amd_cpu_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1301, amd_cpu_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1302, amd_cpu_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1303, amd_cpu_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1304, amd_cpu_pci_cfg_space_size);
 /*
 * SB600: Disable BAR1 on device 14.0 to avoid HPET resources from
diff --git a/arch/x86/pci/pci.h b/arch/x86/pci/pci.h
index 15b9cf6be729..1959018aac02 100644
--- a/arch/x86/pci/pci.h
+++ b/arch/x86/pci/pci.h
@@ -96,6 +96,7 @@ extern struct pci_raw_ops *raw_pci_ops;
 extern struct pci_raw_ops *raw_pci_ext_ops;
 extern struct pci_raw_ops pci_direct_conf1;
+extern bool port_cf9_safe;
 /* arch_initcall level */
 extern int pci_direct_probe(void);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 5e4686d70f62..bea215230b20 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -28,6 +28,7 @@
 #include <linux/console.h>
 #include <xen/interface/xen.h>
+#include <xen/interface/version.h>
 #include <xen/interface/physdev.h>
 #include <xen/interface/vcpu.h>
 #include <xen/features.h>
@@ -793,7 +794,7 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
        ret = 0;
-        switch(msr) {
+        switch (msr) {
 #ifdef CONFIG_X86_64
                unsigned which;
                u64 base;
@@ -1453,7 +1454,7 @@ static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
        ident_pte = 0;
        pfn = 0;
-        for(pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
+        for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
                pte_t *pte_page;
                /* Reuse or allocate a page of ptes */
@@ -1471,7 +1472,7 @@ static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
                }
                /* Install mappings */
-                for(pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
+                for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
                        pte_t pte;
                        if (pfn > max_pfn_mapped)
@@ -1485,7 +1486,7 @@ static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
                }
        }
-        for(pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
+        for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
                set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO);
        set_page_prot(pmd, PAGE_KERNEL_RO);
@@ -1499,7 +1500,7 @@ static void convert_pfn_mfn(void *v)
        /* All levels are converted the same way, so just treat them
           as ptes. */
-        for(i = 0; i < PTRS_PER_PTE; i++)
+        for (i = 0; i < PTRS_PER_PTE; i++)
                pte[i] = xen_make_pte(pte[i].pte);
 }
@@ -1514,7 +1515,8 @@ static void convert_pfn_mfn(void *v)
 * of the physical mapping once some sort of allocator has been set
 * up.
 */
-static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
+static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
+                                                unsigned long max_pfn)
 {
        pud_t *l3;
        pmd_t *l2;
@@ -1577,7 +1579,8 @@ static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pf
 #else   /* !CONFIG_X86_64 */
 static pmd_t level2_kernel_pgt[PTRS_PER_PMD] __page_aligned_bss;
-static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
+static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
+                                                unsigned long max_pfn)
 {
        pmd_t *kernel_pmd;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 688936044dc9..773d68d3e912 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -154,13 +154,13 @@ void xen_setup_mfn_list_list(void)
 {
        unsigned pfn, idx;
-        for(pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_ENTRIES_PER_PAGE) {
+        for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_ENTRIES_PER_PAGE) {
                unsigned topidx = p2m_top_index(pfn);
                p2m_top_mfn[topidx] = virt_to_mfn(p2m_top[topidx]);
        }
-        for(idx = 0; idx < ARRAY_SIZE(p2m_top_mfn_list); idx++) {
+        for (idx = 0; idx < ARRAY_SIZE(p2m_top_mfn_list); idx++) {
                unsigned topidx = idx * P2M_ENTRIES_PER_PAGE;
                p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]);
        }
@@ -179,7 +179,7 @@ void __init xen_build_dynamic_phys_to_machine(void)
        unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
        unsigned pfn;
-        for(pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) {
+        for (pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) {
                unsigned topidx = p2m_top_index(pfn);
                p2m_top[topidx] = &mfn_list[pfn];
@@ -207,7 +207,7 @@ static void alloc_p2m(unsigned long **pp, unsigned long *mfnp)
        p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL);
        BUG_ON(p == NULL);
-        for(i = 0; i < P2M_ENTRIES_PER_PAGE; i++)
+        for (i = 0; i < P2M_ENTRIES_PER_PAGE; i++)
                p[i] = INVALID_P2M_ENTRY;
        if (cmpxchg(pp, p2m_missing, p) != p2m_missing)
@@ -407,7 +407,8 @@ out:
                preempt_enable();
 }
-pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
+                                 unsigned long addr, pte_t *ptep)
 {
        /* Just return the pte as-is.  We preserve the bits on commit */
        return *ptep;
@@ -661,12 +662,11 @@ void xen_set_pgd(pgd_t *ptr, pgd_t val)
 * For 64-bit, we must skip the Xen hole in the middle of the address
 * space, just after the big x86-64 virtual hole.
 */
-static int xen_pgd_walk(struct mm_struct *mm,
+static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
-                        int (*func)(struct mm_struct *mm, struct page *,
+                          int (*func)(struct mm_struct *mm, struct page *,
-                                    enum pt_level),
+                                      enum pt_level),
-                        unsigned long limit)
+                          unsigned long limit)
 {
-        pgd_t *pgd = mm->pgd;
        int flush = 0;
        unsigned hole_low, hole_high;
        unsigned pgdidx_limit, pudidx_limit, pmdidx_limit;
@@ -753,6 +753,14 @@ out:
        return flush;
 }
+static int xen_pgd_walk(struct mm_struct *mm,
+                        int (*func)(struct mm_struct *mm, struct page *,
+                                    enum pt_level),
+                        unsigned long limit)
+{
+        return __xen_pgd_walk(mm, mm->pgd, func, limit);
+}
 /* If we're using split pte locks, then take the page's lock and
   return a pointer to it.  Otherwise return NULL. */
 static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm)
@@ -854,7 +862,7 @@ static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
        xen_mc_batch();
-         if (xen_pgd_walk(mm, xen_pin_page, USER_LIMIT)) {
+        if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) {
                /* re-enable interrupts for flushing */
                xen_mc_issue(0);
@@ -871,7 +879,8 @@ static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
                if (user_pgd) {
                        xen_pin_page(mm, virt_to_page(user_pgd), PT_PGD);
-                        xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(user_pgd)));
+                        xen_do_pin(MMUEXT_PIN_L4_TABLE,
+                                   PFN_DOWN(__pa(user_pgd)));
                }
        }
 #else /* CONFIG_X86_32 */
@@ -986,7 +995,8 @@ static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
                pgd_t *user_pgd = xen_get_user_pgd(pgd);
                if (user_pgd) {
-                        xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(user_pgd)));
+                        xen_do_pin(MMUEXT_UNPIN_TABLE,
+                                   PFN_DOWN(__pa(user_pgd)));
                        xen_unpin_page(mm, virt_to_page(user_pgd), PT_PGD);
                }
        }
@@ -998,7 +1008,7 @@ static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
                       PT_PMD);
 #endif
-        xen_pgd_walk(mm, xen_unpin_page, USER_LIMIT);
+        __xen_pgd_walk(mm, pgd, xen_unpin_page, USER_LIMIT);
        xen_mc_issue(0);
 }
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 8ea8a0d0b0de..c738644b5435 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -154,7 +154,7 @@ void xen_mc_flush(void)
                               ret, smp_processor_id());
                        dump_stack();
                        for (i = 0; i < b->mcidx; i++) {
-                                printk("  call %2d/%d: op=%lu arg=[%lx] result=%ld\n",
+                                printk(KERN_DEBUG "  call %2d/%d: op=%lu arg=[%lx] result=%ld\n",
                                       i+1, b->mcidx,
                                       b->debug[i].op,
                                       b->debug[i].args[0],
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index d67901083888..15c6c68db6a2 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -28,6 +28,9 @@
 /* These are code, but not functions.  Defined in entry.S */
 extern const char xen_hypervisor_callback[];
 extern const char xen_failsafe_callback[];
+extern void xen_sysenter_target(void);
+extern void xen_syscall_target(void);
+extern void xen_syscall32_target(void);
 /**
@@ -110,7 +113,6 @@ static __cpuinit int register_callback(unsigned type, const void *func)
 void __cpuinit xen_enable_sysenter(void)
 {
-        extern void xen_sysenter_target(void);
        int ret;
        unsigned sysenter_feature;
@@ -132,8 +134,6 @@ void __cpuinit xen_enable_syscall(void)
 {
 #ifdef CONFIG_X86_64
        int ret;
-        extern void xen_syscall_target(void);
-        extern void xen_syscall32_target(void);
        ret = register_callback(CALLBACKTYPE_syscall, xen_syscall_target);
        if (ret != 0) {
@@ -160,7 +160,8 @@ void __init xen_arch_setup(void)
        HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_writable_pagetables);
        if (!xen_feature(XENFEAT_auto_translated_physmap))
-                HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_pae_extended_cr3);
+                HYPERVISOR_vm_assist(VMASST_CMD_enable,
+                                     VMASST_TYPE_pae_extended_cr3);
        if (register_callback(CALLBACKTYPE_event, xen_hypervisor_callback) ||
            register_callback(CALLBACKTYPE_failsafe, xen_failsafe_callback))
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index d77da613b1d2..acd9b6705e02 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -362,7 +362,7 @@ static void xen_cpu_die(unsigned int cpu)
                alternatives_smp_switch(0);
 }
-static void xen_play_dead(void)
+static void __cpuinit xen_play_dead(void) /* used only with CPU_HOTPLUG */
 {
        play_dead_common();
        HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index d7422dc2a55c..9e1afae8461f 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -49,7 +49,7 @@ bool xen_vcpu_stolen(int vcpu);
 void xen_mark_init_mm_pinned(void);
-void __init xen_setup_vcpu_info_placement(void);
+void xen_setup_vcpu_info_placement(void);
 #ifdef CONFIG_SMP
 void xen_smp_init(void);