24 files changed, 261 insertions, 231 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0a80d6a5e9f1..6b8fc9003ecc 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -29,6 +29,7 @@ config X86
         select HAVE_FTRACE
         select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
         select HAVE_ARCH_KGDB if !X86_VOYAGER
+        select HAVE_ARCH_TRACEHOOK
         select HAVE_GENERIC_DMA_COHERENT if X86_32
         select HAVE_EFFICIENT_UNALIGNED_ACCESS
 
@@ -577,35 +578,29 @@ config SWIOTLB
 
 config IOMMU_HELPER
         def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU)
+
 config MAXSMP
         bool "Configure Maximum number of SMP Processors and NUMA Nodes"
-        depends on X86_64 && SMP
+        depends on X86_64 && SMP && BROKEN
         default n
         help
           Configure maximum number of CPUS and NUMA Nodes for this architecture.
           If unsure, say N.
 
-if MAXSMP
-config NR_CPUS
-        int
-        default "4096"
-endif
-
-if !MAXSMP
 config NR_CPUS
-        int "Maximum number of CPUs (2-4096)"
-        range 2 4096
+        int "Maximum number of CPUs (2-512)" if !MAXSMP
+        range 2 512
         depends on SMP
+        default "4096" if MAXSMP
         default "32" if X86_NUMAQ || X86_SUMMIT || X86_BIGSMP || X86_ES7000
         default "8"
         help
           This allows you to specify the maximum number of CPUs which this
-          kernel will support.  The maximum supported value is 4096 and the
+          kernel will support.  The maximum supported value is 512 and the
           minimum value which makes sense is 2.
 
           This is purely to save memory - each supported CPU adds
           approximately eight kilobytes to the kernel image.
-endif
 
 config SCHED_SMT
         bool "SMT (Hyperthreading) scheduler support"
@@ -996,17 +991,10 @@ config NUMA_EMU
           into virtual nodes when booted with "numa=fake=N", where N is the
           number of nodes. This is only useful for debugging.
 
-if MAXSMP
-
 config NODES_SHIFT
-        int
-        default "9"
-endif
-
-if !MAXSMP
-config NODES_SHIFT
-        int "Maximum NUMA Nodes (as a power of 2)"
+        int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP
         range 1 9   if X86_64
+        default "9" if MAXSMP
         default "6" if X86_64
         default "4" if X86_NUMAQ
         default "3"
@@ -1014,7 +1002,6 @@ config NODES_SHIFT
         help
           Specify the maximum number of NUMA Nodes available on the target
           system.  Increases memory reserved to accomodate various tables.
-endif
 
 config HAVE_ARCH_BOOTMEM_NODE
         def_bool y
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index b117d7f8a564..58ac5d3d4361 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -729,7 +729,7 @@ struct var_mtrr_range_state {
         mtrr_type type;
 };
 
-struct var_mtrr_range_state __initdata range_state[RANGE_NUM];
+static struct var_mtrr_range_state __initdata range_state[RANGE_NUM];
 static int __initdata debug_print;
 
 static int __init
diff --git a/arch/x86/kernel/io_delay.c b/arch/x86/kernel/io_delay.c
index 1c3a66a67f83..720d2607aacb 100644
--- a/arch/x86/kernel/io_delay.c
+++ b/arch/x86/kernel/io_delay.c
@@ -92,6 +92,14 @@ static struct dmi_system_id __initdata io_delay_0xed_port_dmi_table[] = {
                         DMI_MATCH(DMI_BOARD_NAME, "30BF")
                 }
         },
+        {
+                .callback       = dmi_io_delay_0xed_port,
+                .ident          = "Presario F700",
+                .matches        = {
+                        DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"),
+                        DMI_MATCH(DMI_BOARD_NAME, "30D3")
+                }
+        },
         { }
 };
 
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 50e5e4a31c85..191914302744 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/thread_info.h>
 #include <linux/syscalls.h>
+#include <asm/syscalls.h>
 
 /* Set EXTENT bits starting at BASE in BITMAP to value TURN_ON. */
 static void set_bitmap(unsigned long *bitmap, unsigned int base,
diff --git a/arch/x86/kernel/ipi.c b/arch/x86/kernel/ipi.c
index 3f7537b669d3..f1c688e46f35 100644
--- a/arch/x86/kernel/ipi.c
+++ b/arch/x86/kernel/ipi.c
@@ -20,6 +20,8 @@
 
 #ifdef CONFIG_X86_32
 #include <mach_apic.h>
+#include <mach_ipi.h>
+
 /*
  * the following functions deal with sending IPIs between CPUs.
  *
@@ -147,7 +149,6 @@ void send_IPI_mask_sequence(cpumask_t mask, int vector)
 }
 
 /* must come after the send_IPI functions above for inlining */
-#include <mach_ipi.h>
 static int convert_apicid_to_cpu(int apic_id)
 {
         int i;
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index b68e21f06f4f..0ed5f939b905 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -18,6 +18,7 @@
 #include <asm/ldt.h>
 #include <asm/desc.h>
 #include <asm/mmu_context.h>
+#include <asm/syscalls.h>
 
 #ifdef CONFIG_SMP
 static void flush_ldt(void *current_mm)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 3b7a1ddcc0bc..2c9abc95e026 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -55,6 +55,8 @@
 #include <asm/tlbflush.h>
 #include <asm/cpu.h>
 #include <asm/kdebug.h>
+#include <asm/syscalls.h>
+#include <asm/smp.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 71553b664e2a..00263c9e6500 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -51,6 +51,7 @@
 #include <asm/proto.h>
 #include <asm/ia32.h>
 #include <asm/idle.h>
+#include <asm/syscalls.h>
 
 asmlinkage extern void ret_from_fork(void);
 
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index e37dccce85db..9e43a48ad6e0 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -14,6 +14,7 @@
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/regset.h>
+#include <linux/tracehook.h>
 #include <linux/user.h>
 #include <linux/elf.h>
 #include <linux/security.h>
@@ -69,7 +70,7 @@ static inline bool invalid_selector(u16 value)
 
 #define FLAG_MASK               FLAG_MASK_32
 
-static long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
+static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
 {
         BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0);
         regno >>= 2;
@@ -1375,30 +1376,6 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code)
         force_sig_info(SIGTRAP, &info, tsk);
 }
 
-static void syscall_trace(struct pt_regs *regs)
-{
-        if (!(current->ptrace & PT_PTRACED))
-                return;
-
-#if 0
-        printk("trace %s ip %lx sp %lx ax %d origrax %d caller %lx tiflags %x ptrace %x\n",
-               current->comm,
-               regs->ip, regs->sp, regs->ax, regs->orig_ax, __builtin_return_address(0),
-               current_thread_info()->flags, current->ptrace);
-#endif
-
-        ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
-                                ? 0x80 : 0));
-        /*
-         * this isn't the same as continuing with a signal, but it will do
-         * for normal use.  strace only continues with a signal if the
-         * stopping signal is not SIGTRAP.  -brl
-         */
-        if (current->exit_code) {
-                send_sig(current->exit_code, current, 1);
-                current->exit_code = 0;
-        }
-}
 
 #ifdef CONFIG_X86_32
 # define IS_IA32        1
@@ -1432,8 +1409,9 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs)
         if (unlikely(test_thread_flag(TIF_SYSCALL_EMU)))
                 ret = -1L;
 
-        if (ret || test_thread_flag(TIF_SYSCALL_TRACE))
-                syscall_trace(regs);
+        if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) &&
+            tracehook_report_syscall_entry(regs))
+                ret = -1L;
 
         if (unlikely(current->audit_context)) {
                 if (IS_IA32)
@@ -1459,7 +1437,7 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs)
                 audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
 
         if (test_thread_flag(TIF_SYSCALL_TRACE))
-                syscall_trace(regs);
+                tracehook_report_syscall_exit(regs, 0);
 
         /*
          * If TIF_SYSCALL_EMU is set, we only get here because of
@@ -1475,6 +1453,6 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs)
          * system call instruction.
          */
         if (test_thread_flag(TIF_SINGLESTEP) &&
-            (current->ptrace & PT_PTRACED))
+            tracehook_consider_fatal_signal(current, SIGTRAP, SIG_DFL))
                 send_sigtrap(current, regs, 0);
 }
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index 0f98d69fbdb0..b21070ea33a4 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
+#include <linux/tracehook.h>
 #include <linux/elf.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
@@ -26,6 +27,7 @@
 #include <asm/uaccess.h>
 #include <asm/i387.h>
 #include <asm/vdso.h>
+#include <asm/syscalls.h>
 
 #include "sigframe.h"
 
@@ -555,8 +557,6 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
          * handler too.
          */
         regs->flags &= ~X86_EFLAGS_TF;
-        if (test_thread_flag(TIF_SINGLESTEP))
-                ptrace_notify(SIGTRAP);
 
         spin_lock_irq(&current->sighand->siglock);
         sigorsets(&current->blocked, &current->blocked, &ka->sa.sa_mask);
@@ -565,6 +565,9 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
         recalc_sigpending();
         spin_unlock_irq(&current->sighand->siglock);
 
+        tracehook_signal_handler(sig, info, ka, regs,
+                                 test_thread_flag(TIF_SINGLESTEP));
+
         return 0;
 }
 
@@ -658,5 +661,10 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
         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);
+        }
+
         clear_thread_flag(TIF_IRET);
 }
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index 6c581698ab56..2f28252d2d26 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -15,6 +15,7 @@
 #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>
@@ -26,6 +27,8 @@
 #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)))
@@ -278,35 +281,6 @@ give_sigsegv:
 }
 
 /*
- * Return -1L or the syscall number that @regs is executing.
- */
-static long current_syscall(struct pt_regs *regs)
-{
-        /*
-         * We always sign-extend a -1 value being set here,
-         * so this is always either -1L or a syscall number.
-         */
-        return regs->orig_ax;
-}
-
-/*
- * Return a value that is -EFOO if the system call in @regs->orig_ax
- * returned an error.  This only works for @regs from @current.
- */
-static long current_syscall_ret(struct pt_regs *regs)
-{
-#ifdef CONFIG_IA32_EMULATION
-        if (test_thread_flag(TIF_IA32))
-                /*
-                 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
-                 * and will match correctly in comparisons.
-                 */
-                return (int) regs->ax;
-#endif
-        return regs->ax;
-}
-
-/*
  * OK, we're invoking a handler
  */     
 
@@ -317,9 +291,9 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
         int ret;
 
         /* Are we from a system call? */
-        if (current_syscall(regs) >= 0) {
+        if (syscall_get_nr(current, regs) >= 0) {
                 /* If so, check system call restarting.. */
-                switch (current_syscall_ret(regs)) {
+                switch (syscall_get_error(current, regs)) {
                 case -ERESTART_RESTARTBLOCK:
                 case -ERESTARTNOHAND:
                         regs->ax = -EINTR;
@@ -376,8 +350,6 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
                  * handler too.
                  */
                 regs->flags &= ~X86_EFLAGS_TF;
-                if (test_thread_flag(TIF_SINGLESTEP))
-                        ptrace_notify(SIGTRAP);
 
                 spin_lock_irq(&current->sighand->siglock);
                 sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
@@ -385,6 +357,9 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
                         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 ret;
@@ -441,9 +416,9 @@ static void do_signal(struct pt_regs *regs)
         }
 
         /* Did we come from a system call? */
-        if (current_syscall(regs) >= 0) {
+        if (syscall_get_nr(current, regs) >= 0) {
                 /* Restart the system call - no handlers present */
-                switch (current_syscall_ret(regs)) {
+                switch (syscall_get_error(current, regs)) {
                 case -ERESTARTNOHAND:
                 case -ERESTARTSYS:
                 case -ERESTARTNOINTR:
@@ -481,6 +456,11 @@ void do_notify_resume(struct pt_regs *regs, void *unused,
         /* 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);
+        }
 }
 
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index b25097c599a5..aa804c64b167 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -88,7 +88,7 @@ static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
 #define get_idle_for_cpu(x)      (per_cpu(idle_thread_array, x))
 #define set_idle_for_cpu(x, p)   (per_cpu(idle_thread_array, x) = (p))
 #else
-struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
+static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
 #define get_idle_for_cpu(x)      (idle_thread_array[(x)])
 #define set_idle_for_cpu(x, p)   (idle_thread_array[(x)] = (p))
 #endif
@@ -128,7 +128,7 @@ static atomic_t init_deasserted;
 static cpumask_t cpu_sibling_setup_map;
 
 /* Set if we find a B stepping CPU */
-int __cpuinitdata smp_b_stepping;
+static int __cpuinitdata smp_b_stepping;
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_32)
 
diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c
index 7066cb855a60..1884a8d12bfa 100644
--- a/arch/x86/kernel/sys_i386_32.c
+++ b/arch/x86/kernel/sys_i386_32.c
@@ -22,6 +22,8 @@
 #include <linux/uaccess.h>
 #include <linux/unistd.h>
 
+#include <asm/syscalls.h>
+
 asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
                           unsigned long prot, unsigned long flags,
                           unsigned long fd, unsigned long pgoff)
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index 3b360ef33817..c9288c883e20 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -16,6 +16,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/ia32.h>
+#include <asm/syscalls.h>
 
 asmlinkage long sys_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags,
         unsigned long fd, unsigned long off)
diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c
index ffe3c664afc0..bbecf8b6bf96 100644
--- a/arch/x86/kernel/time_32.c
+++ b/arch/x86/kernel/time_32.c
@@ -36,6 +36,7 @@
 #include <asm/arch_hooks.h>
 #include <asm/hpet.h>
 #include <asm/time.h>
+#include <asm/timer.h>
 
 #include "do_timer.h"
 
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index ab6bf375a307..6bb7b8579e70 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -10,6 +10,7 @@
 #include <asm/ldt.h>
 #include <asm/processor.h>
 #include <asm/proto.h>
+#include <asm/syscalls.h>
 
 #include "tls.h"
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 8e786b0d665a..8f98e9de1b82 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -122,80 +122,216 @@ static u64 tsc_read_refs(u64 *pm, u64 *hpet)
         return ULLONG_MAX;
 }
 
-/**
- * native_calibrate_tsc - calibrate the tsc on boot
+/*
+ * Try to calibrate the TSC against the Programmable
+ * Interrupt Timer and return the frequency of the TSC
+ * in kHz.
+ *
+ * Return ULONG_MAX on failure to calibrate.
  */
-unsigned long native_calibrate_tsc(void)
+static unsigned long pit_calibrate_tsc(void)
 {
-        unsigned long flags;
-        u64 tsc1, tsc2, tr1, tr2, delta, pm1, pm2, hpet1, hpet2;
-        int hpet = is_hpet_enabled();
-        unsigned int tsc_khz_val = 0;
-
-        local_irq_save(flags);
-
-        tsc1 = tsc_read_refs(&pm1, hpet ? &hpet1 : NULL);
+        u64 tsc, t1, t2, delta;
+        unsigned long tscmin, tscmax;
+        int pitcnt;
 
+        /* Set the Gate high, disable speaker */
         outb((inb(0x61) & ~0x02) | 0x01, 0x61);
 
+        /*
+         * Setup CTC channel 2* for mode 0, (interrupt on terminal
+         * count mode), binary count. Set the latch register to 50ms
+         * (LSB then MSB) to begin countdown.
+         */
         outb(0xb0, 0x43);
         outb((CLOCK_TICK_RATE / (1000 / 50)) & 0xff, 0x42);
         outb((CLOCK_TICK_RATE / (1000 / 50)) >> 8, 0x42);
-        tr1 = get_cycles();
-        while ((inb(0x61) & 0x20) == 0);
-        tr2 = get_cycles();
 
-        tsc2 = tsc_read_refs(&pm2, hpet ? &hpet2 : NULL);
+        tsc = t1 = t2 = get_cycles();
 
-        local_irq_restore(flags);
+        pitcnt = 0;
+        tscmax = 0;
+        tscmin = ULONG_MAX;
+        while ((inb(0x61) & 0x20) == 0) {
+                t2 = get_cycles();
+                delta = t2 - tsc;
+                tsc = t2;
+                if ((unsigned long) delta < tscmin)
+                        tscmin = (unsigned int) delta;
+                if ((unsigned long) delta > tscmax)
+                        tscmax = (unsigned int) delta;
+                pitcnt++;
+        }
 
         /*
-         * Preset the result with the raw and inaccurate PIT
-         * calibration value
+         * Sanity checks:
+         *
+         * If we were not able to read the PIT more than 5000
+         * times, then we have been hit by a massive SMI
+         *
+         * If the maximum is 10 times larger than the minimum,
+         * then we got hit by an SMI as well.
          */
-        delta = (tr2 - tr1);
+        if (pitcnt < 5000 || tscmax > 10 * tscmin)
+                return ULONG_MAX;
+
+        /* Calculate the PIT value */
+        delta = t2 - t1;
         do_div(delta, 50);
-        tsc_khz_val = delta;
+        return delta;
+}
+
+
+/**
+ * native_calibrate_tsc - calibrate the tsc on boot
+ */
+unsigned long native_calibrate_tsc(void)
+{
+        u64 tsc1, tsc2, delta, pm1, pm2, hpet1, hpet2;
+        unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
+        unsigned long flags;
+        int hpet = is_hpet_enabled(), i;
 
-        /* hpet or pmtimer available ? */
+        /*
+         * Run 5 calibration loops to get the lowest frequency value
+         * (the best estimate). We use two different calibration modes
+         * here:
+         *
+         * 1) PIT loop. We set the PIT Channel 2 to oneshot mode and
+         * load a timeout of 50ms. We read the time right after we
+         * started the timer and wait until the PIT count down reaches
+         * zero. In each wait loop iteration we read the TSC and check
+         * the delta to the previous read. We keep track of the min
+         * and max values of that delta. The delta is mostly defined
+         * by the IO time of the PIT access, so we can detect when a
+         * SMI/SMM disturbance happend between the two reads. If the
+         * maximum time is significantly larger than the minimum time,
+         * then we discard the result and have another try.
+         *
+         * 2) Reference counter. If available we use the HPET or the
+         * PMTIMER as a reference to check the sanity of that value.
+         * We use separate TSC readouts and check inside of the
+         * reference read for a SMI/SMM disturbance. We dicard
+         * disturbed values here as well. We do that around the PIT
+         * calibration delay loop as we have to wait for a certain
+         * amount of time anyway.
+         */
+        for (i = 0; i < 5; i++) {
+                unsigned long tsc_pit_khz;
+
+                /*
+                 * Read the start value and the reference count of
+                 * hpet/pmtimer when available. Then do the PIT
+                 * calibration, which will take at least 50ms, and
+                 * read the end value.
+                 */
+                local_irq_save(flags);
+                tsc1 = tsc_read_refs(&pm1, hpet ? &hpet1 : NULL);
+                tsc_pit_khz = pit_calibrate_tsc();
+                tsc2 = tsc_read_refs(&pm2, hpet ? &hpet2 : NULL);
+                local_irq_restore(flags);
+
+                /* Pick the lowest PIT TSC calibration so far */
+                tsc_pit_min = min(tsc_pit_min, tsc_pit_khz);
+
+                /* hpet or pmtimer available ? */
+                if (!hpet && !pm1 && !pm2)
+                        continue;
+
+                /* Check, whether the sampling was disturbed by an SMI */
+                if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX)
+                        continue;
+
+                tsc2 = (tsc2 - tsc1) * 1000000LL;
+
+                if (hpet) {
+                        if (hpet2 < hpet1)
+                                hpet2 += 0x100000000ULL;
+                        hpet2 -= hpet1;
+                        tsc1 = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
+                        do_div(tsc1, 1000000);
+                } else {
+                        if (pm2 < pm1)
+                                pm2 += (u64)ACPI_PM_OVRRUN;
+                        pm2 -= pm1;
+                        tsc1 = pm2 * 1000000000LL;
+                        do_div(tsc1, PMTMR_TICKS_PER_SEC);
+                }
+
+                do_div(tsc2, tsc1);
+                tsc_ref_min = min(tsc_ref_min, (unsigned long) tsc2);
+        }
+
+        /*
+         * Now check the results.
+         */
+        if (tsc_pit_min == ULONG_MAX) {
+                /* PIT gave no useful value */
+                printk(KERN_WARNING "TSC: Unable to calibrate against PIT\n");
+
+                /* We don't have an alternative source, disable TSC */
+                if (!hpet && !pm1 && !pm2) {
+                        printk("TSC: No reference (HPET/PMTIMER) available\n");
+                        return 0;
+                }
+
+                /* The alternative source failed as well, disable TSC */
+                if (tsc_ref_min == ULONG_MAX) {
+                        printk(KERN_WARNING "TSC: HPET/PMTIMER calibration "
+                               "failed due to SMI disturbance.\n");
+                        return 0;
+                }
+
+                /* Use the alternative source */
+                printk(KERN_INFO "TSC: using %s reference calibration\n",
+                       hpet ? "HPET" : "PMTIMER");
+
+                return tsc_ref_min;
+        }
+
+        /* We don't have an alternative source, use the PIT calibration value */
         if (!hpet && !pm1 && !pm2) {
-                printk(KERN_INFO "TSC calibrated against PIT\n");
-                goto out;
+                printk(KERN_INFO "TSC: Using PIT calibration value\n");
+                return tsc_pit_min;
         }
 
-        /* Check, whether the sampling was disturbed by an SMI */
-        if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX) {
-                printk(KERN_WARNING "TSC calibration disturbed by SMI, "
-                                "using PIT calibration result\n");
-                goto out;
+        /* The alternative source failed, use the PIT calibration value */
+        if (tsc_ref_min == ULONG_MAX) {
+                printk(KERN_WARNING "TSC: HPET/PMTIMER calibration failed due "
+                       "to SMI disturbance. Using PIT calibration\n");
+                return tsc_pit_min;
         }
 
-        tsc2 = (tsc2 - tsc1) * 1000000LL;
-
-        if (hpet) {
-                printk(KERN_INFO "TSC calibrated against HPET\n");
-                if (hpet2 < hpet1)
-                        hpet2 += 0x100000000ULL;
-                hpet2 -= hpet1;
-                tsc1 = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
-                do_div(tsc1, 1000000);
-        } else {
-                printk(KERN_INFO "TSC calibrated against PM_TIMER\n");
-                if (pm2 < pm1)
-                        pm2 += (u64)ACPI_PM_OVRRUN;
-                pm2 -= pm1;
-                tsc1 = pm2 * 1000000000LL;
-                do_div(tsc1, PMTMR_TICKS_PER_SEC);
+        /* Check the reference deviation */
+        delta = ((u64) tsc_pit_min) * 100;
+        do_div(delta, tsc_ref_min);
+
+        /*
+         * If both calibration results are inside a 5% window, the we
+         * use the lower frequency of those as it is probably the
+         * closest estimate.
+         */
+        if (delta >= 95 && delta <= 105) {
+                printk(KERN_INFO "TSC: PIT calibration confirmed by %s.\n",
+                       hpet ? "HPET" : "PMTIMER");
+                printk(KERN_INFO "TSC: using %s calibration value\n",
+                       tsc_pit_min <= tsc_ref_min ? "PIT" :
+                       hpet ? "HPET" : "PMTIMER");
+                return tsc_pit_min <= tsc_ref_min ? tsc_pit_min : tsc_ref_min;
         }
 
-        do_div(tsc2, tsc1);
-        tsc_khz_val = tsc2;
+        printk(KERN_WARNING "TSC: PIT calibration deviates from %s: %lu %lu.\n",
+               hpet ? "HPET" : "PMTIMER", tsc_pit_min, tsc_ref_min);
 
-out:
-        return tsc_khz_val;
+        /*
+         * The calibration values differ too much. In doubt, we use
+         * the PIT value as we know that there are PMTIMERs around
+         * running at double speed.
+         */
+        printk(KERN_INFO "TSC: Using PIT calibration value\n");
+        return tsc_pit_min;
 }
 
-
 #ifdef CONFIG_X86_32
 /* Only called from the Powernow K7 cpu freq driver */
 int recalibrate_cpu_khz(void)
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 38f566fa27d2..4eeb5cf9720d 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -46,6 +46,7 @@
 #include <asm/io.h>
 #include <asm/tlbflush.h>
 #include <asm/irq.h>
+#include <asm/syscalls.h>
 
 /*
  * Known problems:
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index f72ac1fa35f0..4a814bff21f2 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -345,7 +345,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
                 shadow_addr = __pa(shadow_page->spt);
                 shadow_pte = shadow_addr | PT_PRESENT_MASK | PT_ACCESSED_MASK
                         | PT_WRITABLE_MASK | PT_USER_MASK;
-                *shadow_ent = shadow_pte;
+                set_shadow_pte(shadow_ent, shadow_pte);
         }
 
         mmu_set_spte(vcpu, shadow_ent, access, walker->pte_access & access,
diff --git a/arch/x86/mach-default/setup.c b/arch/x86/mach-default/setup.c
index 3d317836be9e..3f2cf11f201a 100644
--- a/arch/x86/mach-default/setup.c
+++ b/arch/x86/mach-default/setup.c
@@ -10,13 +10,15 @@
 #include <asm/e820.h>
 #include <asm/setup.h>
 
+#include <mach_ipi.h>
+
 #ifdef CONFIG_HOTPLUG_CPU
 #define DEFAULT_SEND_IPI        (1)
 #else
 #define DEFAULT_SEND_IPI        (0)
 #endif
 
-int no_broadcast=DEFAULT_SEND_IPI;
+int no_broadcast = DEFAULT_SEND_IPI;
 
 /**
  * pre_intr_init_hook - initialisation prior to setting up interrupt vectors
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 455f3fe67b42..8f92cac4e6db 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -35,6 +35,7 @@
 #include <asm/tlbflush.h>
 #include <asm/proto.h>
 #include <asm-generic/sections.h>
+#include <asm/traps.h>
 
 /*
  * Page fault error code bits
@@ -357,8 +358,6 @@ static int is_errata100(struct pt_regs *regs, unsigned long address)
         return 0;
 }
 
-void do_invalid_op(struct pt_regs *, unsigned long);
-
 static int is_f00f_bug(struct pt_regs *regs, unsigned long address)
 {
 #ifdef CONFIG_X86_F00F_BUG
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index d37f29376b0c..4974e97dedfe 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -47,6 +47,7 @@
 #include <asm/paravirt.h>
 #include <asm/setup.h>
 #include <asm/cacheflush.h>
+#include <asm/smp.h>
 
 unsigned int __VMALLOC_RESERVE = 128 << 20;
 
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index d4b6e6a29ae3..cac6da54203b 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -421,7 +421,7 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr)
         return;
 }
 
-int __initdata early_ioremap_debug;
+static int __initdata early_ioremap_debug;
 
 static int __init early_ioremap_debug_setup(char *str)
 {
@@ -547,7 +547,7 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx)
 }
 
 
-int __initdata early_ioremap_nested;
+static int __initdata early_ioremap_nested;
 
 static int __init check_early_ioremap_leak(void)
 {
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index d765da913842..8791fc55e715 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -31,11 +31,8 @@
 #include <linux/ioport.h>
 #include <linux/errno.h>
 #include <linux/bootmem.h>
-#include <linux/acpi.h>
 
 #include <asm/pat.h>
-#include <asm/hpet.h>
-#include <asm/io_apic.h>
 
 #include "pci.h"
 
@@ -80,77 +77,6 @@ pcibios_align_resource(void *data, struct resource *res,
 }
 EXPORT_SYMBOL(pcibios_align_resource);
 
-static int check_res_with_valid(struct pci_dev *dev, struct resource *res)
-{
-        unsigned long base;
-        unsigned long size;
-        int i;
-
-        base = res->start;
-        size = (res->start == 0 && res->end == res->start) ? 0 :
-                 (res->end - res->start + 1);
-
-        if (!base || !size)
-                return 0;
-
-#ifdef CONFIG_HPET_TIMER
-        /* for hpet */
-        if (base == hpet_address && (res->flags & IORESOURCE_MEM)) {
-                dev_info(&dev->dev, "BAR has HPET at %08lx-%08lx\n",
-                                 base, base + size - 1);
-                return 1;
-        }
-#endif
-
-#ifdef CONFIG_X86_IO_APIC
-        for (i = 0; i < nr_ioapics; i++) {
-                unsigned long ioapic_phys = mp_ioapics[i].mp_apicaddr;
-
-                if (base == ioapic_phys && (res->flags & IORESOURCE_MEM)) {
-                        dev_info(&dev->dev, "BAR has ioapic at %08lx-%08lx\n",
-                                         base, base + size - 1);
-                        return 1;
-                }
-        }
-#endif
-
-#ifdef CONFIG_PCI_MMCONFIG
-        for (i = 0; i < pci_mmcfg_config_num; i++) {
-                unsigned long addr;
-
-                addr = pci_mmcfg_config[i].address;
-                if (base == addr && (res->flags & IORESOURCE_MEM)) {
-                        dev_info(&dev->dev, "BAR has MMCONFIG at %08lx-%08lx\n",
-                                         base, base + size - 1);
-                        return 1;
-                }
-        }
-#endif
-
-        return 0;
-}
-
-static int check_platform(struct pci_dev *dev, struct resource *res)
-{
-        struct resource *root = NULL;
-
-        /*
-         * forcibly insert it into the
-         * resource tree
-         */
-        if (res->flags & IORESOURCE_MEM)
-                root = &iomem_resource;
-        else if (res->flags & IORESOURCE_IO)
-                root = &ioport_resource;
-
-        if (root && check_res_with_valid(dev, res)) {
-                insert_resource(root, res);
-
-                return 1;
-        }
-
-        return 0;
-}
 /*
  *  Handle resources of PCI devices.  If the world were perfect, we could
  *  just allocate all the resource regions and do nothing more.  It isn't.
@@ -202,10 +128,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
                                 pr = pci_find_parent_resource(dev, r);
                                 if (!r->start || !pr ||
                                     request_resource(pr, r) < 0) {
-                                        if (check_platform(dev, r))
-                                                continue;
-                                        dev_err(&dev->dev, "BAR %d: can't "
-                                                "allocate resource\n", idx);
+                                        dev_err(&dev->dev, "BAR %d: can't allocate resource\n", idx);
                                         /*
                                          * Something is wrong with the region.
                                          * Invalidate the resource to prevent
@@ -240,17 +163,13 @@ static void __init pcibios_allocate_resources(int pass)
                         else
                                 disabled = !(command & PCI_COMMAND_MEMORY);
                         if (pass == disabled) {
-                                dev_dbg(&dev->dev, "resource %#08llx-%#08llx "
-                                        "(f=%lx, d=%d, p=%d)\n",
+                                dev_dbg(&dev->dev, "resource %#08llx-%#08llx (f=%lx, d=%d, p=%d)\n",
                                         (unsigned long long) r->start,
                                         (unsigned long long) r->end,
                                         r->flags, disabled, pass);
                                 pr = pci_find_parent_resource(dev, r);
                                 if (!pr || request_resource(pr, r) < 0) {
-                                        if (check_platform(dev, r))
-                                                continue;
-                                        dev_err(&dev->dev, "BAR %d: can't "
-                                                "allocate resource\n", idx);
+                                        dev_err(&dev->dev, "BAR %d: can't allocate resource\n", idx);
                                         /* We'll assign a new address later */
                                         r->end -= r->start;
                                         r->start = 0;