50 files changed, 532 insertions, 318 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d1430ef6b4f9..738bdc6b0f8b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1913,25 +1913,26 @@ config DMAR_DEFAULT_ON
          recommended you say N here while the DMAR code remains
          experimental.
-config DMAR_GFX_WA
+config DMAR_BROKEN_GFX_WA
-        def_bool y
+        def_bool n
-        prompt "Support for Graphics workaround"
+        prompt "Workaround broken graphics drivers (going away soon)"
        depends on DMAR
        ---help---
          Current Graphics drivers tend to use physical address
          for DMA and avoid using DMA APIs. Setting this config
          option permits the IOMMU driver to set a unity map for
          all the OS-visible memory. Hence the driver can continue
-          to use physical addresses for DMA.
+          to use physical addresses for DMA, at least until this
+          option is removed in the 2.6.32 kernel.
 config DMAR_FLOPPY_WA
        def_bool y
        depends on DMAR
        ---help---
-          Floppy disk drivers are know to bypass DMA API calls
+          Floppy disk drivers are known to bypass DMA API calls
          thereby failing to work when IOMMU is enabled. This
          workaround will setup a 1:1 mapping for the first
-          16M to make floppy (an ISA device) work.
+          16MiB to make floppy (an ISA device) work.
 config INTR_REMAP
        bool "Support for Interrupt Remapping (EXPERIMENTAL)"
diff --git a/arch/x86/boot/video-bios.c b/arch/x86/boot/video-bios.c
index d660be492363..49e0c18833e0 100644
--- a/arch/x86/boot/video-bios.c
+++ b/arch/x86/boot/video-bios.c
@@ -37,14 +37,13 @@ static int set_bios_mode(u8 mode)
        ireg.al = mode;         /* AH=0x00 Set Video Mode */
        intcall(0x10, &ireg, NULL);
        ireg.ah = 0x0f;         /* Get Current Video Mode */
        intcall(0x10, &ireg, &oreg);
        do_restore = 1;         /* Assume video contents were lost */
        /* Not all BIOSes are clean with the top bit */
-        new_mode = ireg.al & 0x7f;
+        new_mode = oreg.al & 0x7f;
        if (new_mode == mode)
                return 0;       /* Mode change OK */
diff --git a/arch/x86/boot/video-vesa.c b/arch/x86/boot/video-vesa.c
index c700147d6ffb..275dd177f198 100644
--- a/arch/x86/boot/video-vesa.c
+++ b/arch/x86/boot/video-vesa.c
@@ -45,7 +45,7 @@ static int vesa_probe(void)
        ireg.di = (size_t)&vginfo;
        intcall(0x10, &ireg, &oreg);
-        if (ireg.ax != 0x004f ||
+        if (oreg.ax != 0x004f ||
            vginfo.signature != VESA_MAGIC ||
            vginfo.version < 0x0102)
                return 0;       /* Not present */
@@ -70,7 +70,7 @@ static int vesa_probe(void)
                ireg.di = (size_t)&vminfo;
                intcall(0x10, &ireg, &oreg);
-                if (ireg.ax != 0x004f)
+                if (oreg.ax != 0x004f)
                        continue;
                if ((vminfo.mode_attr & 0x15) == 0x05) {
diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h
index 2503d4e64c2a..dc5a667ff791 100644
--- a/arch/x86/include/asm/atomic_32.h
+++ b/arch/x86/include/asm/atomic_32.h
@@ -19,7 +19,10 @@
 *
 * Atomically reads the value of @v.
 */
-#define atomic_read(v)          ((v)->counter)
+static inline int atomic_read(const atomic_t *v)
+{
+        return v->counter;
+}
 /**
 * atomic_set - set atomic variable
@@ -28,7 +31,10 @@
 *
 * Atomically sets the value of @v to @i.
 */
-#define atomic_set(v, i)        (((v)->counter) = (i))
+static inline void atomic_set(atomic_t *v, int i)
+{
+        v->counter = i;
+}
 /**
 * atomic_add - add integer to atomic variable
@@ -200,8 +206,15 @@ static inline int atomic_sub_return(int i, atomic_t *v)
        return atomic_add_return(-i, v);
 }
-#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
+static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
-#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
+{
+        return cmpxchg(&v->counter, old, new);
+}
+static inline int atomic_xchg(atomic_t *v, int new)
+{
+        return xchg(&v->counter, new);
+}
 /**
 * atomic_add_unless - add unless the number is already a given value
@@ -250,45 +263,12 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 /* An 64bit atomic type */
 typedef struct {
-        unsigned long long counter;
+        u64 __aligned(8) counter;
 } atomic64_t;
 #define ATOMIC64_INIT(val)      { (val) }
-/**
+extern u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 new_val);
- * atomic64_read - read atomic64 variable
- * @ptr: pointer of type atomic64_t
- *
- * Atomically reads the value of @v.
- * Doesn't imply a read memory barrier.
- */
-#define __atomic64_read(ptr)            ((ptr)->counter)
-static inline unsigned long long
-cmpxchg8b(unsigned long long *ptr, unsigned long long old, unsigned long long new)
-{
-        asm volatile(
-                LOCK_PREFIX "cmpxchg8b (%[ptr])\n"
-                     :          "=A" (old)
-                     : [ptr]    "D" (ptr),
-                                "A" (old),
-                                "b" (ll_low(new)),
-                                "c" (ll_high(new))
-                     : "memory");
-        return old;
-}
-static inline unsigned long long
-atomic64_cmpxchg(atomic64_t *ptr, unsigned long long old_val,
-                 unsigned long long new_val)
-{
-        return cmpxchg8b(&ptr->counter, old_val, new_val);
-}
 /**
 * atomic64_xchg - xchg atomic64 variable
@@ -298,18 +278,7 @@ atomic64_cmpxchg(atomic64_t *ptr, unsigned long long old_val,
 * Atomically xchgs the value of @ptr to @new_val and returns
 * the old value.
 */
+extern u64 atomic64_xchg(atomic64_t *ptr, u64 new_val);
-static inline unsigned long long
-atomic64_xchg(atomic64_t *ptr, unsigned long long new_val)
-{
-        unsigned long long old_val;
-        do {
-                old_val = atomic_read(ptr);
-        } while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val);
-        return old_val;
-}
 /**
 * atomic64_set - set atomic64 variable
@@ -318,10 +287,7 @@ atomic64_xchg(atomic64_t *ptr, unsigned long long new_val)
 *
 * Atomically sets the value of @ptr to @new_val.
 */
-static inline void atomic64_set(atomic64_t *ptr, unsigned long long new_val)
+extern void atomic64_set(atomic64_t *ptr, u64 new_val);
-{
-        atomic64_xchg(ptr, new_val);
-}
 /**
 * atomic64_read - read atomic64 variable
@@ -329,17 +295,30 @@ static inline void atomic64_set(atomic64_t *ptr, unsigned long long new_val)
 *
 * Atomically reads the value of @ptr and returns it.
 */
-static inline unsigned long long atomic64_read(atomic64_t *ptr)
+static inline u64 atomic64_read(atomic64_t *ptr)
 {
-        unsigned long long curr_val;
+        u64 res;
-        do {
+        /*
-                curr_val = __atomic64_read(ptr);
+         * Note, we inline this atomic64_t primitive because
-        } while (atomic64_cmpxchg(ptr, curr_val, curr_val) != curr_val);
+         * it only clobbers EAX/EDX and leaves the others
+         * untouched. We also (somewhat subtly) rely on the
-        return curr_val;
+         * fact that cmpxchg8b returns the current 64-bit value
+         * of the memory location we are touching:
+         */
+        asm volatile(
+                "mov %%ebx, %%eax\n\t"
+                "mov %%ecx, %%edx\n\t"
+                LOCK_PREFIX "cmpxchg8b %1\n"
+                        : "=&A" (res)
+                        : "m" (*ptr)
+                );
+        return res;
 }
+extern u64 atomic64_read(atomic64_t *ptr);
 /**
 * atomic64_add_return - add and return
 * @delta: integer value to add
@@ -347,34 +326,14 @@ static inline unsigned long long atomic64_read(atomic64_t *ptr)
 *
 * Atomically adds @delta to @ptr and returns @delta + *@ptr
 */
-static inline unsigned long long
+extern u64 atomic64_add_return(u64 delta, atomic64_t *ptr);
-atomic64_add_return(unsigned long long delta, atomic64_t *ptr)
-{
-        unsigned long long old_val, new_val;
-        do {
-                old_val = atomic_read(ptr);
-                new_val = old_val + delta;
-        } while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val);
-        return new_val;
-}
-static inline long atomic64_sub_return(unsigned long long delta, atomic64_t *ptr)
-{
-        return atomic64_add_return(-delta, ptr);
-}
-static inline long atomic64_inc_return(atomic64_t *ptr)
+/*
-{
+ * Other variants with different arithmetic operators:
-        return atomic64_add_return(1, ptr);
+ */
-}
+extern u64 atomic64_sub_return(u64 delta, atomic64_t *ptr);
+extern u64 atomic64_inc_return(atomic64_t *ptr);
-static inline long atomic64_dec_return(atomic64_t *ptr)
+extern u64 atomic64_dec_return(atomic64_t *ptr);
-{
-        return atomic64_sub_return(1, ptr);
-}
 /**
 * atomic64_add - add integer to atomic64 variable
@@ -383,10 +342,7 @@ static inline long atomic64_dec_return(atomic64_t *ptr)
 *
 * Atomically adds @delta to @ptr.
 */
-static inline void atomic64_add(unsigned long long delta, atomic64_t *ptr)
+extern void atomic64_add(u64 delta, atomic64_t *ptr);
-{
-        atomic64_add_return(delta, ptr);
-}
 /**
 * atomic64_sub - subtract the atomic64 variable
@@ -395,10 +351,7 @@ static inline void atomic64_add(unsigned long long delta, atomic64_t *ptr)
 *
 * Atomically subtracts @delta from @ptr.
 */
-static inline void atomic64_sub(unsigned long long delta, atomic64_t *ptr)
+extern void atomic64_sub(u64 delta, atomic64_t *ptr);
-{
-        atomic64_add(-delta, ptr);
-}
 /**
 * atomic64_sub_and_test - subtract value from variable and test result
@@ -409,13 +362,7 @@ static inline void atomic64_sub(unsigned long long delta, atomic64_t *ptr)
 * true if the result is zero, or false for all
 * other cases.
 */
-static inline int
+extern int atomic64_sub_and_test(u64 delta, atomic64_t *ptr);
-atomic64_sub_and_test(unsigned long long delta, atomic64_t *ptr)
-{
-        unsigned long long old_val = atomic64_sub_return(delta, ptr);
-        return old_val == 0;
-}
 /**
 * atomic64_inc - increment atomic64 variable
@@ -423,10 +370,7 @@ atomic64_sub_and_test(unsigned long long delta, atomic64_t *ptr)
 *
 * Atomically increments @ptr by 1.
 */
-static inline void atomic64_inc(atomic64_t *ptr)
+extern void atomic64_inc(atomic64_t *ptr);
-{
-        atomic64_add(1, ptr);
-}
 /**
 * atomic64_dec - decrement atomic64 variable
@@ -434,10 +378,7 @@ static inline void atomic64_inc(atomic64_t *ptr)
 *
 * Atomically decrements @ptr by 1.
 */
-static inline void atomic64_dec(atomic64_t *ptr)
+extern void atomic64_dec(atomic64_t *ptr);
-{
-        atomic64_sub(1, ptr);
-}
 /**
 * atomic64_dec_and_test - decrement and test
@@ -447,10 +388,7 @@ static inline void atomic64_dec(atomic64_t *ptr)
 * returns true if the result is 0, or false for all other
 * cases.
 */
-static inline int atomic64_dec_and_test(atomic64_t *ptr)
+extern int atomic64_dec_and_test(atomic64_t *ptr);
-{
-        return atomic64_sub_and_test(1, ptr);
-}
 /**
 * atomic64_inc_and_test - increment and test
@@ -460,10 +398,7 @@ static inline int atomic64_dec_and_test(atomic64_t *ptr)
 * and returns true if the result is zero, or false for all
 * other cases.
 */
-static inline int atomic64_inc_and_test(atomic64_t *ptr)
+extern int atomic64_inc_and_test(atomic64_t *ptr);
-{
-        return atomic64_sub_and_test(-1, ptr);
-}
 /**
 * atomic64_add_negative - add and test if negative
@@ -474,13 +409,7 @@ static inline int atomic64_inc_and_test(atomic64_t *ptr)
 * if the result is negative, or false when
 * result is greater than or equal to zero.
 */
-static inline int
+extern int atomic64_add_negative(u64 delta, atomic64_t *ptr);
-atomic64_add_negative(unsigned long long delta, atomic64_t *ptr)
-{
-        long long old_val = atomic64_add_return(delta, ptr);
-        return old_val < 0;
-}
 #include <asm-generic/atomic-long.h>
 #endif /* _ASM_X86_ATOMIC_32_H */
diff --git a/arch/x86/include/asm/atomic_64.h b/arch/x86/include/asm/atomic_64.h
index 0d6360220007..d605dc268e79 100644
--- a/arch/x86/include/asm/atomic_64.h
+++ b/arch/x86/include/asm/atomic_64.h
@@ -18,7 +18,10 @@
 *
 * Atomically reads the value of @v.
 */
-#define atomic_read(v)          ((v)->counter)
+static inline int atomic_read(const atomic_t *v)
+{
+        return v->counter;
+}
 /**
 * atomic_set - set atomic variable
@@ -27,7 +30,10 @@
 *
 * Atomically sets the value of @v to @i.
 */
-#define atomic_set(v, i)                (((v)->counter) = (i))
+static inline void atomic_set(atomic_t *v, int i)
+{
+        v->counter = i;
+}
 /**
 * atomic_add - add integer to atomic variable
@@ -192,7 +198,10 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 * Atomically reads the value of @v.
 * Doesn't imply a read memory barrier.
 */
-#define atomic64_read(v)                ((v)->counter)
+static inline long atomic64_read(const atomic64_t *v)
+{
+        return v->counter;
+}
 /**
 * atomic64_set - set atomic64 variable
@@ -201,7 +210,10 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 *
 * Atomically sets the value of @v to @i.
 */
-#define atomic64_set(v, i)              (((v)->counter) = (i))
+static inline void atomic64_set(atomic64_t *v, long i)
+{
+        v->counter = i;
+}
 /**
 * atomic64_add - add integer to atomic64 variable
@@ -355,11 +367,25 @@ static inline long atomic64_sub_return(long i, atomic64_t *v)
 #define atomic64_inc_return(v)  (atomic64_add_return(1, (v)))
 #define atomic64_dec_return(v)  (atomic64_sub_return(1, (v)))
-#define atomic64_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
+static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
-#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
+{
+        return cmpxchg(&v->counter, old, new);
+}
+static inline long atomic64_xchg(atomic64_t *v, long new)
+{
+        return xchg(&v->counter, new);
+}
-#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
+static inline long atomic_cmpxchg(atomic_t *v, int old, int new)
-#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
+{
+        return cmpxchg(&v->counter, old, new);
+}
+static inline long atomic_xchg(atomic_t *v, int new)
+{
+        return xchg(&v->counter, new);
+}
 /**
 * atomic_add_unless - add unless the number is a given value
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 2d81af3974a0..7b2d71df39a6 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -111,12 +111,9 @@ enum fixed_addresses {
 #ifdef CONFIG_PARAVIRT
        FIX_PARAVIRT_BOOTMAP,
 #endif
-        FIX_TEXT_POKE0, /* reserve 2 pages for text_poke() */
+        FIX_TEXT_POKE1, /* reserve 2 pages for text_poke() */
-        FIX_TEXT_POKE1,
+        FIX_TEXT_POKE0, /* first page is last, because allocation is backward */
        __end_of_permanent_fixed_addresses,
-#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
-        FIX_OHCI1394_BASE,
-#endif
        /*
         * 256 temporary boot-time mappings, used by early_ioremap(),
         * before ioremap() is functional.
@@ -129,6 +126,9 @@ enum fixed_addresses {
        FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
                        (__end_of_permanent_fixed_addresses & 255),
        FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+        FIX_OHCI1394_BASE,
+#endif
 #ifdef CONFIG_X86_32
        FIX_WP_TEST,
 #endif
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index daf866ed0612..330ee807f89e 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -161,6 +161,7 @@ extern int io_apic_set_pci_routing(struct device *dev, int irq,
                 struct io_apic_irq_attr *irq_attr);
 extern int (*ioapic_renumber_irq)(int ioapic, int irq);
 extern void ioapic_init_mappings(void);
+extern void ioapic_insert_resources(void);
 extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
 extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries);
@@ -180,6 +181,7 @@ extern void ioapic_write_entry(int apic, int pin,
 #define io_apic_assign_pci_irqs 0
 static const int timer_through_8259 = 0;
 static inline void ioapic_init_mappings(void)   { }
+static inline void ioapic_insert_resources(void) { }
 static inline void probe_nr_irqs_gsi(void)      { }
 #endif
diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h
index d31c4a684078..33600a66755f 100644
--- a/arch/x86/include/asm/lguest_hcall.h
+++ b/arch/x86/include/asm/lguest_hcall.h
@@ -30,7 +30,7 @@
 #include <asm/hw_irq.h>
 #include <asm/kvm_para.h>
-/*G:031 But first, how does our Guest contact the Host to ask for privileged
+/*G:030 But first, how does our Guest contact the Host to ask for privileged
 * operations?  There are two ways: the direct way is to make a "hypercall",
 * to make requests of the Host Itself.
 *
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1692fb5050e3..6be7fc254b59 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -246,10 +246,6 @@
 #define MSR_IA32_MISC_ENABLE_TURBO_DISABLE      (1ULL << 38)
 #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE    (1ULL << 39)
-/* Intel Model 6 */
-#define MSR_P6_EVNTSEL0                 0x00000186
-#define MSR_P6_EVNTSEL1                 0x00000187
 /* P4/Xeon+ specific */
 #define MSR_IA32_MCG_EAX                0x00000180
 #define MSR_IA32_MCG_EBX                0x00000181
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index c97264409934..c86e5ed4af51 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -72,7 +72,6 @@ void lapic_watchdog_stop(void);
 int lapic_watchdog_init(unsigned nmi_hz);
 int lapic_wd_event(unsigned nmi_hz);
 unsigned lapic_adjust_nmi_hz(unsigned hz);
-int lapic_watchdog_ok(void);
 void disable_lapic_nmi_watchdog(void);
 void enable_lapic_nmi_watchdog(void);
 void stop_nmi(void);
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 927958d13c19..1ff685ca221c 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -91,7 +91,7 @@ extern void pci_iommu_alloc(void);
 #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
-#if defined(CONFIG_X86_64) || defined(CONFIG_DMA_API_DEBUG)
+#if defined(CONFIG_X86_64) || defined(CONFIG_DMAR) || defined(CONFIG_DMA_API_DEBUG)
 #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       \
                dma_addr_t ADDR_NAME;
diff --git a/arch/x86/include/asm/perf_counter.h b/arch/x86/include/asm/perf_counter.h
index 5fb33e160ea0..fa64e401589d 100644
--- a/arch/x86/include/asm/perf_counter.h
+++ b/arch/x86/include/asm/perf_counter.h
@@ -87,6 +87,9 @@ union cpuid10_edx {
 #ifdef CONFIG_PERF_COUNTERS
 extern void init_hw_perf_counters(void);
 extern void perf_counters_lapic_init(void);
+#define PERF_COUNTER_INDEX_OFFSET                       0
 #else
 static inline void init_hw_perf_counters(void)          { }
 static inline void perf_counters_lapic_init(void)       { }
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 49fb3ecf3bb3..621f56d73121 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -22,7 +22,14 @@ extern int reboot_force;
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
-#define round_up(x, y) (((x) + (y) - 1) & ~((y) - 1))
+/*
-#define round_down(x, y) ((x) & ~((y) - 1))
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x,y) ((__typeof__(x))((y)-1))
+#define round_up(x,y) ((((x)-1) | __round_mask(x,y))+1)
+#define round_down(x,y) ((x) & ~__round_mask(x,y))
 #endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index b7e5db876399..4e77853321db 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -302,4 +302,8 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw)
 #define _raw_read_relax(lock)   cpu_relax()
 #define _raw_write_relax(lock)  cpu_relax()
+/* The {read|write|spin}_lock() on x86 are full memory barriers. */
+static inline void smp_mb__after_lock(void) { }
+#define ARCH_HAS_SMP_MB_AFTER_LOCK
 #endif /* _ASM_X86_SPINLOCK_H */
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index f517944b2b17..cf86a5e73815 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -3,6 +3,8 @@
 extern int kstack_depth_to_print;
+int x86_is_stack_id(int id, char *name);
 /* Generic stack tracer with callbacks */
 struct stacktrace_ops {
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index b0783520988b..fad7d40b75f8 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -49,7 +49,7 @@ struct thread_info {
        .exec_domain    = &default_exec_domain, \
        .flags          = 0,                    \
        .cpu            = 0,                    \
-        .preempt_count  = 1,                    \
+        .preempt_count  = INIT_PREEMPT_COUNT,   \
        .addr_limit     = KERNEL_DS,            \
        .restart_block = {                      \
                .fn = do_no_restart_syscall,    \
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 6c327b852e23..430d5b24af7b 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -26,6 +26,8 @@ CFLAGS_tsc.o		:= $(nostackp)
 CFLAGS_paravirt.o       := $(nostackp)
 GCOV_PROFILE_vsyscall_64.o      := n
 GCOV_PROFILE_hpet.o             := n
+GCOV_PROFILE_tsc.o              := n
+GCOV_PROFILE_paravirt.o         := n
 obj-y                   := process_$(BITS).o signal.o entry_$(BITS).o
 obj-y                   += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 9372f0406ad4..6c99f5037801 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1192,7 +1192,7 @@ out:
        return 0;
 }
-struct notifier_block device_nb = {
+static struct notifier_block device_nb = {
        .notifier_call = device_change_notifier,
 };
@@ -1763,7 +1763,7 @@ static void *alloc_coherent(struct device *dev, size_t size,
        flag |= __GFP_ZERO;
        virt_addr = (void *)__get_free_pages(flag, get_order(size));
        if (!virt_addr)
-                return 0;
+                return NULL;
        paddr = virt_to_phys(virt_addr);
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 10b2accd12ea..c1b17e97252e 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -472,6 +472,8 @@ static u8 * __init alloc_event_buffer(struct amd_iommu *iommu)
        if (iommu->evt_buf == NULL)
                return NULL;
+        iommu->evt_buf_size = EVT_BUFFER_SIZE;
        return iommu->evt_buf;
 }
@@ -691,6 +693,7 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
                        devid = e->devid;
                        devid_to = e->ext >> 8;
+                        set_dev_entry_from_acpi(iommu, devid   , e->flags, 0);
                        set_dev_entry_from_acpi(iommu, devid_to, e->flags, 0);
                        amd_iommu_alias_table[devid] = devid_to;
                        break;
@@ -749,11 +752,13 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
                        devid = e->devid;
                        for (dev_i = devid_start; dev_i <= devid; ++dev_i) {
-                                if (alias)
+                                if (alias) {
                                        amd_iommu_alias_table[dev_i] = devid_to;
-                                set_dev_entry_from_acpi(iommu,
+                                        set_dev_entry_from_acpi(iommu,
-                                                amd_iommu_alias_table[dev_i],
+                                                devid_to, flags, ext_flags);
-                                                flags, ext_flags);
+                                }
+                                set_dev_entry_from_acpi(iommu, dev_i,
+                                                        flags, ext_flags);
                        }
                        break;
                default:
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 8c7c042ecad1..0a1c2830ec66 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -140,7 +140,6 @@ int x2apic_mode;
 #ifdef CONFIG_X86_X2APIC
 /* x2apic enabled before OS handover */
 static int x2apic_preenabled;
-static int disable_x2apic;
 static __init int setup_nox2apic(char *str)
 {
        if (x2apic_enabled()) {
@@ -149,7 +148,6 @@ static __init int setup_nox2apic(char *str)
                return 0;
        }
-        disable_x2apic = 1;
        setup_clear_cpu_cap(X86_FEATURE_X2APIC);
        return 0;
 }
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 69328ac8de9c..8952a5890281 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -652,7 +652,8 @@ static int es7000_mps_oem_check_cluster(struct mpc_table *mpc, char *oem,
        return ret && es7000_apic_is_cluster();
 }
-struct apic apic_es7000_cluster = {
+/* We've been warned by a false positive warning.Use __refdata to keep calm. */
+struct apic __refdata apic_es7000_cluster = {
        .name                           = "es7000",
        .probe                          = probe_es7000,
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 4d0216fcb36c..2284a4812b68 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1716,25 +1716,19 @@ __apicdebuginit(void) print_IO_APIC(void)
        return;
 }
-__apicdebuginit(void) print_APIC_bitfield(int base)
+__apicdebuginit(void) print_APIC_field(int base)
 {
-        unsigned int v;
+        int i;
-        int i, j;
        if (apic_verbosity == APIC_QUIET)
                return;
-        printk(KERN_DEBUG "0123456789abcdef0123456789abcdef\n" KERN_DEBUG);
+        printk(KERN_DEBUG);
-        for (i = 0; i < 8; i++) {
-                v = apic_read(base + i*0x10);
+        for (i = 0; i < 8; i++)
-                for (j = 0; j < 32; j++) {
+                printk(KERN_CONT "%08x", apic_read(base + i*0x10));
-                        if (v & (1<<j))
-                                printk("1");
+        printk(KERN_CONT "\n");
-                        else
-                                printk("0");
-                }
-                printk("\n");
-        }
 }
 __apicdebuginit(void) print_local_APIC(void *dummy)
@@ -1745,7 +1739,7 @@ __apicdebuginit(void) print_local_APIC(void *dummy)
        if (apic_verbosity == APIC_QUIET)
                return;
-        printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
+        printk(KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
                smp_processor_id(), hard_smp_processor_id());
        v = apic_read(APIC_ID);
        printk(KERN_INFO "... APIC ID:      %08x (%01x)\n", v, read_apic_id());
@@ -1786,11 +1780,11 @@ __apicdebuginit(void) print_local_APIC(void *dummy)
        printk(KERN_DEBUG "... APIC SPIV: %08x\n", v);
        printk(KERN_DEBUG "... APIC ISR field:\n");
-        print_APIC_bitfield(APIC_ISR);
+        print_APIC_field(APIC_ISR);
        printk(KERN_DEBUG "... APIC TMR field:\n");
-        print_APIC_bitfield(APIC_TMR);
+        print_APIC_field(APIC_TMR);
        printk(KERN_DEBUG "... APIC IRR field:\n");
-        print_APIC_bitfield(APIC_IRR);
+        print_APIC_field(APIC_IRR);
        if (APIC_INTEGRATED(ver)) {             /* !82489DX */
                if (maxlvt > 3)         /* Due to the Pentium erratum 3AP. */
@@ -4187,28 +4181,20 @@ fake_ioapic_page:
        }
 }
-static int __init ioapic_insert_resources(void)
+void __init ioapic_insert_resources(void)
 {
        int i;
        struct resource *r = ioapic_resources;
        if (!r) {
-                if (nr_ioapics > 0) {
+                if (nr_ioapics > 0)
                        printk(KERN_ERR
                                "IO APIC resources couldn't be allocated.\n");
-                        return -1;
+                return;
-                }
-                return 0;
        }
        for (i = 0; i < nr_ioapics; i++) {
                insert_resource(&iomem_resource, r);
                r++;
        }
-        return 0;
 }
-/* Insert the IO APIC resources after PCI initialization has occured to handle
- * IO APICS that are mapped in on a BAR in PCI space. */
-late_initcall(ioapic_insert_resources);
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 533e59c6fc82..ca96e68f0d23 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -493,7 +493,8 @@ static void numaq_setup_portio_remap(void)
                (u_long) xquad_portio, (u_long) num_quads*XQUAD_PORTIO_QUAD);
 }
-struct apic apic_numaq = {
+/* Use __refdata to keep false positive warning calm.   */
+struct apic __refdata apic_numaq = {
        .name                           = "NUMAQ",
        .probe                          = probe_numaq,
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 6b26d4deada0..f1961c07af9a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -848,9 +848,6 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
        numa_add_cpu(smp_processor_id());
 #endif
-        /* Cap the iomem address space to what is addressable on all CPUs */
-        iomem_resource.end &= (1ULL << c->x86_phys_bits) - 1;
 }
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 81cbe64ed6b4..2a50ef891000 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -299,7 +299,7 @@ static int transition_pstate(struct powernow_k8_data *data, u32 pstate)
 static int transition_fid_vid(struct powernow_k8_data *data,
                u32 reqfid, u32 reqvid)
 {
-        if (core_voltage_pre_transition(data, reqvid))
+        if (core_voltage_pre_transition(data, reqvid, reqfid))
                return 1;
        if (core_frequency_transition(data, reqfid))
@@ -327,17 +327,20 @@ static int transition_fid_vid(struct powernow_k8_data *data,
 /* Phase 1 - core voltage transition ... setup voltage */
 static int core_voltage_pre_transition(struct powernow_k8_data *data,
-                u32 reqvid)
+                u32 reqvid, u32 reqfid)
 {
        u32 rvosteps = data->rvo;
        u32 savefid = data->currfid;
-        u32 maxvid, lo;
+        u32 maxvid, lo, rvomult = 1;
        dprintk("ph1 (cpu%d): start, currfid 0x%x, currvid 0x%x, "
                "reqvid 0x%x, rvo 0x%x\n",
                smp_processor_id(),
                data->currfid, data->currvid, reqvid, data->rvo);
+        if ((savefid < LO_FID_TABLE_TOP) && (reqfid < LO_FID_TABLE_TOP))
+                rvomult = 2;
+        rvosteps *= rvomult;
        rdmsr(MSR_FIDVID_STATUS, lo, maxvid);
        maxvid = 0x1f & (maxvid >> 16);
        dprintk("ph1 maxvid=0x%x\n", maxvid);
@@ -351,7 +354,8 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data,
                        return 1;
        }
-        while ((rvosteps > 0) && ((data->rvo + data->currvid) > reqvid)) {
+        while ((rvosteps > 0) &&
+                        ((rvomult * data->rvo + data->currvid) > reqvid)) {
                if (data->currvid == maxvid) {
                        rvosteps = 0;
                } else {
@@ -384,13 +388,6 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid)
        u32 vcoreqfid, vcocurrfid, vcofiddiff;
        u32 fid_interval, savevid = data->currvid;
-        if ((reqfid < HI_FID_TABLE_BOTTOM) &&
-            (data->currfid < HI_FID_TABLE_BOTTOM)) {
-                printk(KERN_ERR PFX "ph2: illegal lo-lo transition "
-                                "0x%x 0x%x\n", reqfid, data->currfid);
-                return 1;
-        }
        if (data->currfid == reqfid) {
                printk(KERN_ERR PFX "ph2 null fid transition 0x%x\n",
                                data->currfid);
@@ -407,6 +404,9 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid)
        vcofiddiff = vcocurrfid > vcoreqfid ? vcocurrfid - vcoreqfid
            : vcoreqfid - vcocurrfid;
+        if ((reqfid <= LO_FID_TABLE_TOP) && (data->currfid <= LO_FID_TABLE_TOP))
+                vcofiddiff = 0;
        while (vcofiddiff > 2) {
                (data->currfid & 1) ? (fid_interval = 1) : (fid_interval = 2);
@@ -1081,14 +1081,6 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data,
                return 0;
        }
-        if ((fid < HI_FID_TABLE_BOTTOM) &&
-            (data->currfid < HI_FID_TABLE_BOTTOM)) {
-                printk(KERN_ERR PFX
-                       "ignoring illegal change in lo freq table-%x to 0x%x\n",
-                       data->currfid, fid);
-                return 1;
-        }
        dprintk("cpu %d, changing to fid 0x%x, vid 0x%x\n",
                smp_processor_id(), fid, vid);
        freqs.old = find_khz_freq_from_fid(data->currfid);
@@ -1267,7 +1259,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 {
        static const char ACPI_PSS_BIOS_BUG_MSG[] =
                KERN_ERR FW_BUG PFX "No compatible ACPI _PSS objects found.\n"
-                KERN_ERR FW_BUG PFX "Try again with latest BIOS.\n";
+                FW_BUG PFX "Try again with latest BIOS.\n";
        struct powernow_k8_data *data;
        struct init_on_cpu init_on_cpu;
        int rc;
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
index c9c1190b5e1f..02ce824073cb 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
@@ -215,7 +215,8 @@ struct pst_s {
 #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "powernow-k8", msg)
-static int core_voltage_pre_transition(struct powernow_k8_data *data, u32 reqvid);
+static int core_voltage_pre_transition(struct powernow_k8_data *data,
+        u32 reqvid, u32 regfid);
 static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvid);
 static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index af425b83202b..484c1e5f658e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -194,14 +194,14 @@ static void print_mce(struct mce *m)
                       m->cs, m->ip);
                if (m->cs == __KERNEL_CS)
                        print_symbol("{%s}", m->ip);
-                printk("\n");
+                printk(KERN_CONT "\n");
        }
        printk(KERN_EMERG "TSC %llx ", m->tsc);
        if (m->addr)
-                printk("ADDR %llx ", m->addr);
+                printk(KERN_CONT "ADDR %llx ", m->addr);
        if (m->misc)
-                printk("MISC %llx ", m->misc);
+                printk(KERN_CONT "MISC %llx ", m->misc);
-        printk("\n");
+        printk(KERN_CONT "\n");
        printk(KERN_EMERG "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
                        m->cpuvendor, m->cpuid, m->time, m->socketid,
                        m->apicid);
@@ -209,13 +209,13 @@ static void print_mce(struct mce *m)
 static void print_mce_head(void)
 {
-        printk(KERN_EMERG "\n" KERN_EMERG "HARDWARE ERROR\n");
+        printk(KERN_EMERG "\nHARDWARE ERROR\n");
 }
 static void print_mce_tail(void)
 {
        printk(KERN_EMERG "This is not a software problem!\n"
-               KERN_EMERG "Run through mcelog --ascii to decode and contact your hardware vendor\n");
+               "Run through mcelog --ascii to decode and contact your hardware vendor\n");
 }
 #define PANIC_TIMEOUT 5 /* 5 seconds */
diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
index 76dfef23f789..36c3dc7b8991 100644
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -401,7 +401,7 @@ static const u64 amd_hw_cache_event_ids
                [ C(RESULT_MISS)   ] = 0x0041, /* Data Cache Misses          */
        },
        [ C(OP_WRITE) ] = {
-                [ C(RESULT_ACCESS) ] = 0x0042, /* Data Cache Refills from L2 */
+                [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
                [ C(RESULT_MISS)   ] = 0,
        },
        [ C(OP_PREFETCH) ] = {
@@ -912,6 +912,8 @@ x86_perf_counter_set_period(struct perf_counter *counter,
        err = checking_wrmsrl(hwc->counter_base + idx,
                             (u64)(-left) & x86_pmu.counter_mask);
+        perf_counter_update_userpage(counter);
        return ret;
 }
@@ -969,13 +971,6 @@ fixed_mode_idx(struct perf_counter *counter, struct hw_perf_counter *hwc)
        if (!x86_pmu.num_counters_fixed)
                return -1;
-        /*
-         * Quirk, IA32_FIXED_CTRs do not work on current Atom processors:
-         */
-        if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-                                        boot_cpu_data.x86_model == 28)
-                return -1;
        event = hwc->config & ARCH_PERFMON_EVENT_MASK;
        if (unlikely(event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS)))
@@ -1041,6 +1036,8 @@ try_generic:
        x86_perf_counter_set_period(counter, hwc, idx);
        x86_pmu.enable(hwc, idx);
+        perf_counter_update_userpage(counter);
        return 0;
 }
@@ -1133,6 +1130,8 @@ static void x86_pmu_disable(struct perf_counter *counter)
        x86_perf_counter_update(counter, hwc, idx);
        cpuc->counters[idx] = NULL;
        clear_bit(idx, cpuc->used_mask);
+        perf_counter_update_userpage(counter);
 }
 /*
@@ -1428,8 +1427,6 @@ static int intel_pmu_init(void)
         */
        x86_pmu.num_counters_fixed      = max((int)edx.split.num_counters_fixed, 3);
-        rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
        /*
         * Install the hw-cache-events table:
         */
@@ -1499,21 +1496,22 @@ void __init init_hw_perf_counters(void)
        pr_cont("%s PMU driver.\n", x86_pmu.name);
        if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) {
-                x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
                WARN(1, KERN_ERR "hw perf counters %d > max(%d), clipping!",
                     x86_pmu.num_counters, X86_PMC_MAX_GENERIC);
+                x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
        }
        perf_counter_mask = (1 << x86_pmu.num_counters) - 1;
        perf_max_counters = x86_pmu.num_counters;
        if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) {
-                x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
                WARN(1, KERN_ERR "hw perf counters fixed %d > max(%d), clipping!",
                     x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED);
+                x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
        }
        perf_counter_mask |=
                ((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED;
+        x86_pmu.intel_ctrl = perf_counter_mask;
        perf_counters_lapic_init();
        register_die_notifier(&perf_counter_nmi_notifier);
@@ -1563,6 +1561,7 @@ void callchain_store(struct perf_callchain_entry *entry, u64 ip)
 static DEFINE_PER_CPU(struct perf_callchain_entry, irq_entry);
 static DEFINE_PER_CPU(struct perf_callchain_entry, nmi_entry);
+static DEFINE_PER_CPU(int, in_nmi_frame);
 static void
@@ -1578,7 +1577,9 @@ static void backtrace_warning(void *data, char *msg)
 static int backtrace_stack(void *data, char *name)
 {
-        /* Process all stacks: */
+        per_cpu(in_nmi_frame, smp_processor_id()) =
+                        x86_is_stack_id(NMI_STACK, name);
        return 0;
 }
@@ -1586,6 +1587,9 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
 {
        struct perf_callchain_entry *entry = data;
+        if (per_cpu(in_nmi_frame, smp_processor_id()))
+                return;
        if (reliable)
                callchain_store(entry, addr);
 }
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 5c481f6205bf..e60ed740d2b3 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -803,8 +803,3 @@ int __kprobes lapic_wd_event(unsigned nmi_hz)
        wd_ops->rearm(wd, nmi_hz);
        return 1;
 }
-int lapic_watchdog_ok(void)
-{
-        return wd_ops != NULL;
-}
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index d593cd1f58dc..bca5fba91c9e 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -19,6 +19,12 @@
 #include "dumpstack.h"
+/* Just a stub for now */
+int x86_is_stack_id(int id, char *name)
+{
+        return 0;
+}
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
                unsigned long *stack, unsigned long bp,
                const struct stacktrace_ops *ops, void *data)
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index d35db5993fd6..54b0a3276766 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -19,10 +19,8 @@
 #include "dumpstack.h"
-static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
-                                        unsigned *usedp, char **idp)
+static char x86_stack_ids[][8] = {
-{
-        static char ids[][8] = {
                [DEBUG_STACK - 1] = "#DB",
                [NMI_STACK - 1] = "NMI",
                [DOUBLEFAULT_STACK - 1] = "#DF",
@@ -33,6 +31,15 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
                        N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]"
 #endif
        };
+int x86_is_stack_id(int id, char *name)
+{
+        return x86_stack_ids[id - 1] == name;
+}
+static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
+                                        unsigned *usedp, char **idp)
+{
        unsigned k;
        /*
@@ -61,7 +68,7 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
                        if (*usedp & (1U << k))
                                break;
                        *usedp |= 1U << k;
-                        *idp = ids[k];
+                        *idp = x86_stack_ids[k];
                        return (unsigned long *)end;
                }
                /*
@@ -81,12 +88,13 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
                        do {
                                ++j;
                                end -= EXCEPTION_STKSZ;
-                                ids[j][4] = '1' + (j - N_EXCEPTION_STACKS);
+                                x86_stack_ids[j][4] = '1' +
+                                                (j - N_EXCEPTION_STACKS);
                        } while (stack < end - EXCEPTION_STKSZ);
                        if (*usedp & (1U << j))
                                break;
                        *usedp |= 1U << j;
-                        *idp = ids[j];
+                        *idp = x86_stack_ids[j];
                        return (unsigned long *)end;
                }
 #endif
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 7271fa33d791..5cb5725b2bae 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -627,10 +627,9 @@ __init void e820_setup_gap(void)
 #ifdef CONFIG_X86_64
        if (!found) {
                gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
-                printk(KERN_ERR "PCI: Warning: Cannot find a gap in the 32bit "
+                printk(KERN_ERR
-                       "address range\n"
+        "PCI: Warning: Cannot find a gap in the 32bit address range\n"
-                       KERN_ERR "PCI: Unassigned devices with 32bit resource "
+        "PCI: Unassigned devices with 32bit resource registers may break!\n");
-                       "registers may break!\n");
        }
 #endif
@@ -1383,6 +1382,8 @@ static unsigned long ram_alignment(resource_size_t pos)
        return 32*1024*1024;
 }
+#define MAX_RESOURCE_SIZE ((resource_size_t)-1)
 void __init e820_reserve_resources_late(void)
 {
        int i;
@@ -1400,17 +1401,19 @@ void __init e820_reserve_resources_late(void)
         * avoid stolen RAM:
         */
        for (i = 0; i < e820.nr_map; i++) {
-                struct e820entry *entry = &e820_saved.map[i];
+                struct e820entry *entry = &e820.map[i];
-                resource_size_t start, end;
+                u64 start, end;
                if (entry->type != E820_RAM)
                        continue;
                start = entry->addr + entry->size;
-                end = round_up(start, ram_alignment(start));
+                end = round_up(start, ram_alignment(start)) - 1;
-                if (start == end)
+                if (end > MAX_RESOURCE_SIZE)
+                        end = MAX_RESOURCE_SIZE;
+                if (start >= end)
                        continue;
-                reserve_region_with_split(&iomem_resource, start,
+                reserve_region_with_split(&iomem_resource, start, end,
-                                                  end - 1, "RAM buffer");
+                                          "RAM buffer");
        }
 }
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index a78ecad0c900..c664d515f613 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -200,7 +200,7 @@ static void kvm_leave_lazy_mmu(void)
        state->mode = paravirt_get_lazy_mode();
 }
-static void paravirt_ops_setup(void)
+static void __init paravirt_ops_setup(void)
 {
        pv_info.name = "KVM";
        pv_info.paravirt_enabled = 1;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 47630479b067..1a041bcf506b 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -211,11 +211,11 @@ static __init int iommu_setup(char *p)
 #ifdef CONFIG_SWIOTLB
                if (!strncmp(p, "soft", 4))
                        swiotlb = 1;
+#endif
                if (!strncmp(p, "pt", 2)) {
                        iommu_pass_through = 1;
                        return 1;
                }
-#endif
                gart_parse_options(p);
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index cfd9f9063896..d2e56b8f48e7 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -675,7 +675,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 nommu:
        /* Should not happen anymore */
        printk(KERN_WARNING "PCI-DMA: More than 4GB of RAM and no IOMMU\n"
-               KERN_WARNING "falling back to iommu=soft.\n");
+               "falling back to iommu=soft.\n");
        return -1;
 }
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 4f9c55f3a7c0..03801f2f761f 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -60,7 +60,7 @@ static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift)
                "adc  %5,%%edx ; "
                : "=A" (product), "=r" (tmp1), "=r" (tmp2)
                : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
-#elif __x86_64__
+#elif defined(__x86_64__)
        __asm__ (
                "mul %%rdx ; shrd $32,%%rdx,%%rax"
                : "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 7bc65f0f62c4..f2bf1f73d468 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -379,6 +379,11 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx,
        native_cpuid(ax, bx, cx, dx);
        switch (function) {
+        case 0: /* ID and highest CPUID.  Futureproof a little by sticking to
+                 * older ones. */
+                if (*ax > 5)
+                        *ax = 5;
+                break;
        case 1: /* Basic feature request. */
                /* We only allow kernel to see SSE3, CMPXCHG16B and SSSE3 */
                *cx &= 0x00002201;
@@ -1079,7 +1084,7 @@ static unsigned lguest_patch(u8 type, u16 clobber, void *ibuf,
        return insn_len;
 }
-/*G:030 Once we get to lguest_init(), we know we're a Guest.  The various
+/*G:029 Once we get to lguest_init(), we know we're a Guest.  The various
 * pv_ops structures in the kernel provide points for (almost) every routine we
 * have to override to avoid privileged instructions. */
 __init void lguest_init(void)
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index f9d35632666b..07c31899c9c2 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -10,6 +10,7 @@ lib-y += usercopy_$(BITS).o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
 ifeq ($(CONFIG_X86_32),y)
+        obj-y += atomic64_32.o
        lib-y += checksum_32.o
        lib-y += strstr_32.o
        lib-y += semaphore_32.o string_32.o
diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c
new file mode 100644
index 000000000000..824fa0be55a3
--- /dev/null
+++ b/arch/x86/lib/atomic64_32.c
@@ -0,0 +1,230 @@
+#include <linux/compiler.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <asm/processor.h>
+#include <asm/cmpxchg.h>
+#include <asm/atomic.h>
+static noinline u64 cmpxchg8b(u64 *ptr, u64 old, u64 new)
+{
+        u32 low = new;
+        u32 high = new >> 32;
+        asm volatile(
+                LOCK_PREFIX "cmpxchg8b %1\n"
+                     : "+A" (old), "+m" (*ptr)
+                     :  "b" (low),  "c" (high)
+                     );
+        return old;
+}
+u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 new_val)
+{
+        return cmpxchg8b(&ptr->counter, old_val, new_val);
+}
+EXPORT_SYMBOL(atomic64_cmpxchg);
+/**
+ * atomic64_xchg - xchg atomic64 variable
+ * @ptr:      pointer to type atomic64_t
+ * @new_val:  value to assign
+ *
+ * Atomically xchgs the value of @ptr to @new_val and returns
+ * the old value.
+ */
+u64 atomic64_xchg(atomic64_t *ptr, u64 new_val)
+{
+        /*
+         * Try first with a (possibly incorrect) assumption about
+         * what we have there. We'll do two loops most likely,
+         * but we'll get an ownership MESI transaction straight away
+         * instead of a read transaction followed by a
+         * flush-for-ownership transaction:
+         */
+        u64 old_val, real_val = 0;
+        do {
+                old_val = real_val;
+                real_val = atomic64_cmpxchg(ptr, old_val, new_val);
+        } while (real_val != old_val);
+        return old_val;
+}
+EXPORT_SYMBOL(atomic64_xchg);
+/**
+ * atomic64_set - set atomic64 variable
+ * @ptr:      pointer to type atomic64_t
+ * @new_val:  value to assign
+ *
+ * Atomically sets the value of @ptr to @new_val.
+ */
+void atomic64_set(atomic64_t *ptr, u64 new_val)
+{
+        atomic64_xchg(ptr, new_val);
+}
+EXPORT_SYMBOL(atomic64_set);
+/**
+EXPORT_SYMBOL(atomic64_read);
+ * atomic64_add_return - add and return
+ * @delta: integer value to add
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically adds @delta to @ptr and returns @delta + *@ptr
+ */
+noinline u64 atomic64_add_return(u64 delta, atomic64_t *ptr)
+{
+        /*
+         * Try first with a (possibly incorrect) assumption about
+         * what we have there. We'll do two loops most likely,
+         * but we'll get an ownership MESI transaction straight away
+         * instead of a read transaction followed by a
+         * flush-for-ownership transaction:
+         */
+        u64 old_val, new_val, real_val = 0;
+        do {
+                old_val = real_val;
+                new_val = old_val + delta;
+                real_val = atomic64_cmpxchg(ptr, old_val, new_val);
+        } while (real_val != old_val);
+        return new_val;
+}
+EXPORT_SYMBOL(atomic64_add_return);
+u64 atomic64_sub_return(u64 delta, atomic64_t *ptr)
+{
+        return atomic64_add_return(-delta, ptr);
+}
+EXPORT_SYMBOL(atomic64_sub_return);
+u64 atomic64_inc_return(atomic64_t *ptr)
+{
+        return atomic64_add_return(1, ptr);
+}
+EXPORT_SYMBOL(atomic64_inc_return);
+u64 atomic64_dec_return(atomic64_t *ptr)
+{
+        return atomic64_sub_return(1, ptr);
+}
+EXPORT_SYMBOL(atomic64_dec_return);
+/**
+ * atomic64_add - add integer to atomic64 variable
+ * @delta: integer value to add
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically adds @delta to @ptr.
+ */
+void atomic64_add(u64 delta, atomic64_t *ptr)
+{
+        atomic64_add_return(delta, ptr);
+}
+EXPORT_SYMBOL(atomic64_add);
+/**
+ * atomic64_sub - subtract the atomic64 variable
+ * @delta: integer value to subtract
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically subtracts @delta from @ptr.
+ */
+void atomic64_sub(u64 delta, atomic64_t *ptr)
+{
+        atomic64_add(-delta, ptr);
+}
+EXPORT_SYMBOL(atomic64_sub);
+/**
+ * atomic64_sub_and_test - subtract value from variable and test result
+ * @delta: integer value to subtract
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically subtracts @delta from @ptr and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+int atomic64_sub_and_test(u64 delta, atomic64_t *ptr)
+{
+        u64 new_val = atomic64_sub_return(delta, ptr);
+        return new_val == 0;
+}
+EXPORT_SYMBOL(atomic64_sub_and_test);
+/**
+ * atomic64_inc - increment atomic64 variable
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically increments @ptr by 1.
+ */
+void atomic64_inc(atomic64_t *ptr)
+{
+        atomic64_add(1, ptr);
+}
+EXPORT_SYMBOL(atomic64_inc);
+/**
+ * atomic64_dec - decrement atomic64 variable
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically decrements @ptr by 1.
+ */
+void atomic64_dec(atomic64_t *ptr)
+{
+        atomic64_sub(1, ptr);
+}
+EXPORT_SYMBOL(atomic64_dec);
+/**
+ * atomic64_dec_and_test - decrement and test
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically decrements @ptr by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+int atomic64_dec_and_test(atomic64_t *ptr)
+{
+        return atomic64_sub_and_test(1, ptr);
+}
+EXPORT_SYMBOL(atomic64_dec_and_test);
+/**
+ * atomic64_inc_and_test - increment and test
+ * @ptr: pointer to type atomic64_t
+ *
+ * Atomically increments @ptr by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+int atomic64_inc_and_test(atomic64_t *ptr)
+{
+        return atomic64_sub_and_test(-1, ptr);
+}
+EXPORT_SYMBOL(atomic64_inc_and_test);
+/**
+ * atomic64_add_negative - add and test if negative
+ * @delta: integer value to add
+ * @ptr:   pointer to type atomic64_t
+ *
+ * Atomically adds @delta to @ptr and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+int atomic64_add_negative(u64 delta, atomic64_t *ptr)
+{
+        s64 new_val = atomic64_add_return(delta, ptr);
+        return new_val < 0;
+}
+EXPORT_SYMBOL(atomic64_add_negative);
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index 9a10a78bb4a4..ebeafcce04a9 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -5,15 +5,14 @@
 * Zero a page.         
 * rdi  page
 */                     
-        ALIGN
+ENTRY(clear_page_c)
-clear_page_c:
        CFI_STARTPROC
        movl $4096/8,%ecx
        xorl %eax,%eax
        rep stosq
        ret
        CFI_ENDPROC
-ENDPROC(clear_page)
+ENDPROC(clear_page_c)
 ENTRY(clear_page)
        CFI_STARTPROC
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index f118c110af32..6ba0f7bb85ea 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -75,6 +75,7 @@ ENTRY(copy_to_user)
        jae bad_to_user
        ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
        CFI_ENDPROC
+ENDPROC(copy_to_user)
 /* Standard copy_from_user with segment limit checking */
 ENTRY(copy_from_user)
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 7c8ca91bb9ec..1f118d462acc 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -751,7 +751,7 @@ survive:
                        if (retval == -ENOMEM && is_global_init(current)) {
                                up_read(&current->mm->mmap_sem);
-                                congestion_wait(WRITE, HZ/50);
+                                congestion_wait(BLK_RW_ASYNC, HZ/50);
                                goto survive;
                        }
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 78a5fff857be..bfae139182ff 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -426,10 +426,11 @@ static noinline int vmalloc_fault(unsigned long address)
 }
 static const char errata93_warning[] =
-KERN_ERR "******* Your BIOS seems to not contain a fix for K8 errata #93\n"
+KERN_ERR 
-KERN_ERR "******* Working around it, but it may cause SEGVs or burn power.\n"
+"******* Your BIOS seems to not contain a fix for K8 errata #93\n"
-KERN_ERR "******* Please consider a BIOS update.\n"
+"******* Working around it, but it may cause SEGVs or burn power.\n"
-KERN_ERR "******* Disabling USB legacy in the BIOS may also help.\n";
+"******* Please consider a BIOS update.\n"
+"******* Disabling USB legacy in the BIOS may also help.\n";
 /*
 * No vm86 mode in 64-bit mode:
@@ -696,7 +697,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
        if (!printk_ratelimit())
                return;
-        printk(KERN_CONT "%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
+        printk("%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
                task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
                tsk->comm, task_pid_nr(tsk), address,
                (void *)regs->ip, (void *)regs->sp, error_code);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 47ce9a2ce5e7..0607119cef94 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -12,6 +12,7 @@
 #include <asm/system.h>
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
+#include <asm/proto.h>
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index c4378f4fd4a5..6176fe8f29e0 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -598,6 +598,15 @@ void __init paging_init(void)
        sparse_memory_present_with_active_regions(MAX_NUMNODES);
        sparse_init();
+        /*
+         * clear the default setting with node 0
+         * note: don't use nodes_clear here, that is really clearing when
+         *       numa support is not compiled in, and later node_set_state
+         *       will not set it back.
+         */
+        node_clear_state(0, N_NORMAL_MEMORY);
        free_area_init_nodes(max_zone_pfns);
 }
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index b07dd8d0b321..89b9a5cd63da 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -390,7 +390,7 @@ static int __init p4_init(char **cpu_type)
 static int force_arch_perfmon;
 static int force_cpu_type(const char *str, struct kernel_param *kp)
 {
-        if (!strcmp(str, "archperfmon")) {
+        if (!strcmp(str, "arch_perfmon")) {
                force_arch_perfmon = 1;
                printk(KERN_INFO "oprofile: forcing architectural perfmon\n");
        }
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index b26626dc517c..1014eb4bfc37 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -68,6 +68,10 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
        unsigned long flags;
        struct resource *root;
        int max_root_bus_resources = PCI_BUS_NUM_RESOURCES;
+        u64 start, end;
+        if (bus_has_transparent_bridge(info->bus))
+                max_root_bus_resources -= 3;
        status = resource_to_addr(acpi_res, &addr);
        if (!ACPI_SUCCESS(status))
@@ -84,25 +88,24 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
        } else
                return AE_OK;
-        res = &info->res[info->res_num];
+        start = addr.minimum + addr.translation_offset;
-        res->name = info->name;
+        end = start + addr.address_length - 1;
-        res->flags = flags;
-        res->start = addr.minimum + addr.translation_offset;
-        res->end = res->start + addr.address_length - 1;
-        res->child = NULL;
-        if (bus_has_transparent_bridge(info->bus))
-                max_root_bus_resources -= 3;
        if (info->res_num >= max_root_bus_resources) {
                printk(KERN_WARNING "PCI: Failed to allocate 0x%lx-0x%lx "
                        "from %s for %s due to _CRS returning more than "
-                        "%d resource descriptors\n", (unsigned long) res->start,
+                        "%d resource descriptors\n", (unsigned long) start,
-                        (unsigned long) res->end, root->name, info->name,
+                        (unsigned long) end, root->name, info->name,
                        max_root_bus_resources);
-                info->res_num++;
                return AE_OK;
        }
+        res = &info->res[info->res_num];
+        res->name = info->name;
+        res->flags = flags;
+        res->start = start;
+        res->end = end;
+        res->child = NULL;
        if (insert_resource(root, res)) {
                printk(KERN_ERR "PCI: Failed to allocate 0x%lx-0x%lx "
                        "from %s for %s\n", (unsigned long) res->start,
@@ -115,23 +118,6 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 }
 static void
-adjust_transparent_bridge_resources(struct pci_bus *bus)
-{
-        struct pci_dev *dev;
-        list_for_each_entry(dev, &bus->devices, bus_list) {
-                int i;
-                u16 class = dev->class >> 8;
-                if (class == PCI_CLASS_BRIDGE_PCI && dev->transparent) {
-                        for(i = 3; i < PCI_BUS_NUM_RESOURCES; i++)
-                                dev->subordinate->resource[i] =
-                                                dev->bus->resource[i - 3];
-                }
-        }
-}
-static void
 get_current_resources(struct acpi_device *device, int busnum,
                        int domain, struct pci_bus *bus)
 {
@@ -158,8 +144,6 @@ get_current_resources(struct acpi_device *device, int busnum,
        info.res_num = 0;
        acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource,
                                &info);
-        if (info.res_num)
-                adjust_transparent_bridge_resources(bus);
        return;
@@ -222,8 +206,15 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do
                 */
                memcpy(bus->sysdata, sd, sizeof(*sd));
                kfree(sd);
-        } else
+        } else {
-                bus = pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd);
+                bus = pci_create_bus(NULL, busnum, &pci_root_ops, sd);
+                if (bus) {
+                        if (pci_probe & PCI_USE__CRS)
+                                get_current_resources(device, busnum, domain,
+                                                        bus);
+                        bus->subordinate = pci_scan_child_bus(bus);
+                }
+        }
        if (!bus)
                kfree(sd);
@@ -238,8 +229,6 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do
 #endif
        }
-        if (bus && (pci_probe & PCI_USE__CRS))
-                get_current_resources(device, busnum, domain, bus);
        return bus;
 }
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index f893d6a6e803..3ffa10df20b9 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -100,8 +100,9 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b)
        int j;
        struct pci_root_info *info;
-        /* don't go for it if _CRS is used */
+        /* don't go for it if _CRS is used already */
-        if (pci_probe & PCI_USE__CRS)
+        if (b->resource[0] != &ioport_resource ||
+            b->resource[1] != &iomem_resource)
                return;
        /* if only one root bus, don't need to anything */
@@ -116,6 +117,9 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b)
        if (i == pci_root_num)
                return;
+        printk(KERN_DEBUG "PCI: peer root bus %02x res updated from pci conf\n",
+                        b->number);
        info = &pci_root_info[i];
        for (j = 0; j < info->res_num; j++) {
                struct resource *res;
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 0fb56db16d18..52e62e57fedd 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -35,6 +35,7 @@
 #include <asm/pat.h>
 #include <asm/e820.h>
 #include <asm/pci_x86.h>
+#include <asm/io_apic.h>
 static int
@@ -227,6 +228,12 @@ void __init pcibios_resource_survey(void)
        pcibios_allocate_resources(1);
        e820_reserve_resources_late();
+        /*
+         * Insert the IO APIC resources after PCI initialization has
+         * occured to handle IO APICS that are mapped in on a BAR in
+         * PCI space, but before trying to assign unassigned pci res.
+         */
+        ioapic_insert_resources();
 }
 /**
diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile
index de2abbd07544..a6a198c33623 100644
--- a/arch/x86/power/Makefile
+++ b/arch/x86/power/Makefile
@@ -1,7 +1,7 @@
 # __restore_processor_state() restores %gs after S3 resume and so should not
 # itself be stack-protected
 nostackp := $(call cc-option, -fno-stack-protector)
-CFLAGS_cpu_$(BITS).o    := $(nostackp)
+CFLAGS_cpu.o    := $(nostackp)
 obj-$(CONFIG_PM_SLEEP)          += cpu.o
 obj-$(CONFIG_HIBERNATION)       += hibernate_$(BITS).o hibernate_asm_$(BITS).o