Merge commit 'md/for-linus' into async-tx-next

Conflicts:
	drivers/md/raid5.c

22 files changed, 188 insertions, 178 deletions

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)))
-#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
+static inline int atomic_cmpxchg(atomic_t *v, int old, int 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) }
 
-/**
- * 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);
-}
+extern u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 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.
  */
-
-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;
-}
+extern u64 atomic64_xchg(atomic64_t *ptr, u64 new_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)
-{
-	atomic64_xchg(ptr, new_val);
-}
+extern void atomic64_set(atomic64_t *ptr, u64 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;
-
-	do {
-		curr_val = __atomic64_read(ptr);
-	} while (atomic64_cmpxchg(ptr, curr_val, curr_val) != curr_val);
-
-	return curr_val;
+	u64 res;
+
+	/*
+	 * Note, we inline this atomic64_t primitive because
+	 * it only clobbers EAX/EDX and leaves the others
+	 * untouched. We also (somewhat subtly) rely on the
+	 * 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
-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);
-}
+extern u64 atomic64_add_return(u64 delta, atomic64_t *ptr);
 
-static inline long atomic64_inc_return(atomic64_t *ptr)
-{
-	return atomic64_add_return(1, ptr);
-}
-
-static inline long atomic64_dec_return(atomic64_t *ptr)
-{
-	return atomic64_sub_return(1, ptr);
-}
+/*
+ * Other variants with different arithmetic operators:
+ */
+extern u64 atomic64_sub_return(u64 delta, atomic64_t *ptr);
+extern u64 atomic64_inc_return(atomic64_t *ptr);
+extern u64 atomic64_dec_return(atomic64_t *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)
-{
-	atomic64_add_return(delta, ptr);
-}
+extern void atomic64_add(u64 delta, atomic64_t *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)
-{
-	atomic64_add(-delta, ptr);
-}
+extern void atomic64_sub(u64 delta, atomic64_t *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
-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;
-}
+extern int atomic64_sub_and_test(u64 delta, atomic64_t *ptr);
 
 /**
  * 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)
-{
-	atomic64_add(1, ptr);
-}
+extern void atomic64_inc(atomic64_t *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)
-{
-	atomic64_sub(1, ptr);
-}
+extern void atomic64_dec(atomic64_t *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)
-{
-	return atomic64_sub_and_test(1, ptr);
-}
+extern int atomic64_dec_and_test(atomic64_t *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)
-{
-	return atomic64_sub_and_test(-1, ptr);
-}
+extern int atomic64_inc_and_test(atomic64_t *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
-atomic64_add_negative(unsigned long long delta, atomic64_t *ptr)
-{
-	long long old_val = atomic64_add_return(delta, ptr);
-
-	return old_val < 0;
-}
+extern int atomic64_add_negative(u64 delta, atomic64_t *ptr);
 
 #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)))
-#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
+static inline long atomic64_cmpxchg(atomic64_t *v, long old, long 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)))
-#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
+static inline long atomic_cmpxchg(atomic_t *v, int old, int 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/boot.h b/arch/x86/include/asm/boot.h
index 418e632d4a80..7a1065958ba9 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -8,7 +8,7 @@
 
 #ifdef __KERNEL__
 
-#include <asm/page_types.h>
+#include <asm/pgtable_types.h>
 
 /* Physical address where kernel should be loaded. */
 #define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
@@ -16,10 +16,10 @@
 				& ~(CONFIG_PHYSICAL_ALIGN - 1))
 
 /* Minimum kernel alignment, as a power of two */
-#ifdef CONFIG_x86_64
+#ifdef CONFIG_X86_64
 #define MIN_KERNEL_ALIGN_LG2	PMD_SHIFT
 #else
-#define MIN_KERNEL_ALIGN_LG2	(PAGE_SHIFT+1)
+#define MIN_KERNEL_ALIGN_LG2	(PAGE_SHIFT + THREAD_ORDER)
 #endif
 #define MIN_KERNEL_ALIGN	(_AC(1, UL) << MIN_KERNEL_ALIGN_LG2)
 
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index edc90f23e708..8406ed7f9926 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -33,7 +33,7 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...);
 #define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)	\
 	efi_call_virt(f, a1, a2, a3, a4, a5, a6)
 
-#define efi_ioremap(addr, size)			ioremap_cache(addr, size)
+#define efi_ioremap(addr, size, type)		ioremap_cache(addr, size)
 
 #else /* !CONFIG_X86_32 */
 
@@ -84,7 +84,8 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
 	efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
 		  (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
 
-extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size);
+extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
+				 u32 type);
 
 #endif /* CONFIG_X86_32 */
 
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,
+	FIX_TEXT_POKE1,	/* reserve 2 pages for text_poke() */
+	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/irqflags.h b/arch/x86/include/asm/irqflags.h
index 2bdab21f0898..c6ccbe7e81ad 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -12,9 +12,15 @@ static inline unsigned long native_save_fl(void)
 {
 	unsigned long flags;
 
+	/*
+	 * Note: this needs to be "=r" not "=rm", because we have the
+	 * stack offset from what gcc expects at the time the "pop" is
+	 * executed, and so a memory reference with respect to the stack
+	 * would end up using the wrong address.
+	 */
 	asm volatile("# __raw_save_flags\n\t"
 		     "pushf ; pop %0"
-		     : "=g" (flags)
+		     : "=r" (flags)
 		     : /* no input */
 		     : "memory");
 
diff --git a/arch/x86/include/asm/lguest.h b/arch/x86/include/asm/lguest.h
index 313389cd50d2..5136dad57cbb 100644
--- a/arch/x86/include/asm/lguest.h
+++ b/arch/x86/include/asm/lguest.h
@@ -17,8 +17,7 @@
 /* Pages for switcher itself, then two pages per cpu */
 #define TOTAL_SWITCHER_PAGES (SHARED_SWITCHER_PAGES + 2 * nr_cpu_ids)
 
-/* We map at -4M (-2M when PAE is activated) for ease of mapping
- * into the guest (one PTE page). */
+/* We map at -4M (-2M for PAE) for ease of mapping (one PTE page). */
 #ifdef CONFIG_X86_PAE
 #define SWITCHER_ADDR 0xFFE00000
 #else
diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h
index d31c4a684078..ba0eed8aa1a6 100644
--- a/arch/x86/include/asm/lguest_hcall.h
+++ b/arch/x86/include/asm/lguest_hcall.h
@@ -30,27 +30,27 @@
 #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.
  *
- * We use the KVM hypercall mechanism. Seventeen hypercalls are
- * available: the hypercall number is put in the %eax register, and the
- * arguments (when required) are placed in %ebx, %ecx, %edx and %esi.
- * If a return value makes sense, it's returned in %eax.
+ * We use the KVM hypercall mechanism, though completely different hypercall
+ * numbers. Seventeen hypercalls are available: the hypercall number is put in
+ * the %eax register, and the arguments (when required) are placed in %ebx,
+ * %ecx, %edx and %esi.  If a return value makes sense, it's returned in %eax.
  *
  * Grossly invalid calls result in Sudden Death at the hands of the vengeful
  * Host, rather than returning failure.  This reflects Winston Churchill's
- * definition of a gentleman: "someone who is only rude intentionally". */
-/*:*/
+ * definition of a gentleman: "someone who is only rude intentionally".
+:*/
 
 /* Can't use our min() macro here: needs to be a constant */
 #define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32)
 
 #define LHCALL_RING_SIZE 64
 struct hcall_args {
-	/* These map directly onto eax, ebx, ecx, edx and esi
-	 * in struct lguest_regs */
+	/* These map directly onto eax/ebx/ecx/edx/esi in struct lguest_regs */
 	unsigned long arg0, arg1, arg2, arg3, arg4;
 };
 
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/percpu.h b/arch/x86/include/asm/percpu.h
index 02ecb30982a3..103f1ddb0d85 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -42,6 +42,7 @@
 
 #else /* ...!ASSEMBLY */
 
+#include <linux/kernel.h>
 #include <linux/stringify.h>
 
 #ifdef CONFIG_SMP
@@ -155,6 +156,15 @@ do {							\
 /* We can use this directly for local CPU (faster). */
 DECLARE_PER_CPU(unsigned long, this_cpu_off);
 
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+void *pcpu_lpage_remapped(void *kaddr);
+#else
+static inline void *pcpu_lpage_remapped(void *kaddr)
+{
+	return NULL;
+}
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #ifdef CONFIG_SMP
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/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index dd14c54ac718..0e8c2a0fd922 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -46,7 +46,13 @@ static inline void pte_free(struct mm_struct *mm, struct page *pte)
 	__free_page(pte);
 }
 
-extern void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
+extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte,
+				  unsigned long address)
+{
+	___pte_free_tlb(tlb, pte);
+}
 
 static inline void pmd_populate_kernel(struct mm_struct *mm,
 				       pmd_t *pmd, pte_t *pte)
@@ -78,7 +84,13 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 	free_page((unsigned long)pmd);
 }
 
-extern void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
+extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
+
+static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
+				  unsigned long adddress)
+{
+	___pmd_free_tlb(tlb, pmd);
+}
 
 #ifdef CONFIG_X86_PAE
 extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd);
@@ -108,7 +120,14 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 	free_page((unsigned long)pud);
 }
 
-extern void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud);
+extern void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud);
+
+static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
+				  unsigned long address)
+{
+	___pud_free_tlb(tlb, pud);
+}
+
 #endif	/* PAGETABLE_LEVELS > 3 */
 #endif	/* PAGETABLE_LEVELS > 2 */
 
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/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 20e6a795e160..d2c6c930b491 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -212,9 +212,9 @@ extern int __get_user_bad(void);
 		     : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
 #else
 #define __put_user_asm_u64(x, ptr, retval, errret) \
-	__put_user_asm(x, ptr, retval, "q", "", "Zr", errret)
+	__put_user_asm(x, ptr, retval, "q", "", "er", errret)
 #define __put_user_asm_ex_u64(x, addr)	\
-	__put_user_asm_ex(x, addr, "q", "", "Zr")
+	__put_user_asm_ex(x, addr, "q", "", "er")
 #define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu)
 #endif
 
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 8cc687326eb8..db24b215fc50 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -88,11 +88,11 @@ int __copy_to_user(void __user *dst, const void *src, unsigned size)
 			      ret, "l", "k", "ir", 4);
 		return ret;
 	case 8:__put_user_asm(*(u64 *)src, (u64 __user *)dst,
-			      ret, "q", "", "ir", 8);
+			      ret, "q", "", "er", 8);
 		return ret;
 	case 10:
 		__put_user_asm(*(u64 *)src, (u64 __user *)dst,
-			       ret, "q", "", "ir", 10);
+			       ret, "q", "", "er", 10);
 		if (unlikely(ret))
 			return ret;
 		asm("":::"memory");
@@ -101,12 +101,12 @@ int __copy_to_user(void __user *dst, const void *src, unsigned size)
 		return ret;
 	case 16:
 		__put_user_asm(*(u64 *)src, (u64 __user *)dst,
-			       ret, "q", "", "ir", 16);
+			       ret, "q", "", "er", 16);
 		if (unlikely(ret))
 			return ret;
 		asm("":::"memory");
 		__put_user_asm(1[(u64 *)src], 1 + (u64 __user *)dst,
-			       ret, "q", "", "ir", 8);
+			       ret, "q", "", "er", 8);
 		return ret;
 	default:
 		return copy_user_generic((__force void *)dst, src, size);
@@ -157,7 +157,7 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 			       ret, "q", "", "=r", 8);
 		if (likely(!ret))
 			__put_user_asm(tmp, (u64 __user *)dst,
-				       ret, "q", "", "ir", 8);
+				       ret, "q", "", "er", 8);
 		return ret;
 	}
 	default:
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 341070f7ad5c..77a68505419a 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -175,7 +175,7 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define UV_GLOBAL_MMR32_PNODE_BITS(p)	((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
 
 #define UV_GLOBAL_MMR64_PNODE_BITS(p)					\
-	((unsigned long)(UV_PNODE_TO_GNODE(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT)
+	(((unsigned long)(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT)
 
 #define UV_APIC_PNODE_SHIFT	6
 
@@ -327,6 +327,7 @@ struct uv_blade_info {
 	unsigned short	nr_possible_cpus;
 	unsigned short	nr_online_cpus;
 	unsigned short	pnode;
+	short		memory_nid;
 };
 extern struct uv_blade_info *uv_blade_info;
 extern short *uv_node_to_blade;
@@ -363,6 +364,12 @@ static inline int uv_blade_to_pnode(int bid)
 	return uv_blade_info[bid].pnode;
 }
 
+/* Nid of memory node on blade. -1 if no blade-local memory */
+static inline int uv_blade_to_memory_nid(int bid)
+{
+	return uv_blade_info[bid].memory_nid;
+}
+
 /* Determine the number of possible cpus on a blade */
 static inline int uv_blade_nr_possible_cpus(int bid)
 {