Merge commit 'b9a7985' into HEAD

Conflicts:
	kernel/time/timekeeping.c

7 files changed, 62 insertions, 144 deletions

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index e756d04..b15162f 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -14,8 +14,8 @@
  */
 
 
-#define ATOMIC_INIT(i)		( (atomic_t) { (i) } )
-#define ATOMIC64_INIT(i)	( (atomic64_t) { (i) } )
+#define ATOMIC_INIT(i)		{ (i) }
+#define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		(*(volatile int *)&(v)->counter)
 #define atomic64_read(v)	(*(volatile long *)&(v)->counter)
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index ac2ef95..310434b 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1236,6 +1236,32 @@ config ARM_ERRATA_754327
 	  This workaround defines cpu_relax() as smp_mb(), preventing correctly
 	  written polling loops from denying visibility of updates to memory.
 
+config ARM_ERRATA_764369
+	bool "ARM errata: Data cache line maintenance operation by MVA may not succeed"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for erratum 764369
+	  affecting Cortex-A9 MPCore with two or more processors (all
+	  current revisions). Under certain timing circumstances, a data
+	  cache line maintenance operation by MVA targeting an Inner
+	  Shareable memory region may fail to proceed up to either the
+	  Point of Coherency or to the Point of Unification of the
+	  system. This workaround adds a DSB instruction before the
+	  relevant cache maintenance functions and sets a specific bit
+	  in the diagnostic control register of the SCU.
+
+config PL310_ERRATA_769419
+	bool "PL310 errata: no automatic Store Buffer drain"
+	depends on CACHE_L2X0
+	help
+	  On revisions of the PL310 prior to r3p2, the Store Buffer does
+	  not automatically drain. This can cause normal, non-cacheable
+	  writes to be retained when the memory system is idle, leading
+	  to suboptimal I/O performance for drivers using coherent DMA.
+	  This option adds a write barrier to the cpu_idle loop so that,
+	  on systems with an outer cache, the store buffer is drained
+	  explicitly.
+
 endmenu
 
 source "arch/arm/common/Kconfig"
@@ -1300,32 +1326,6 @@ source "drivers/pci/Kconfig"
 
 source "drivers/pcmcia/Kconfig"
 
-config ARM_ERRATA_764369
-	bool "ARM errata: Data cache line maintenance operation by MVA may not succeed"
-	depends on CPU_V7 && SMP
-	help
-	  This option enables the workaround for erratum 764369
-	  affecting Cortex-A9 MPCore with two or more processors (all
-	  current revisions). Under certain timing circumstances, a data
-	  cache line maintenance operation by MVA targeting an Inner
-	  Shareable memory region may fail to proceed up to either the
-	  Point of Coherency or to the Point of Unification of the
-	  system. This workaround adds a DSB instruction before the
-	  relevant cache maintenance functions and sets a specific bit
-	  in the diagnostic control register of the SCU.
-
-config PL310_ERRATA_769419
-	bool "PL310 errata: no automatic Store Buffer drain"
-	depends on CACHE_L2X0
-	help
-	  On revisions of the PL310 prior to r3p2, the Store Buffer does
-	  not automatically drain. This can cause normal, non-cacheable
-	  writes to be retained when the memory system is idle, leading
-	  to suboptimal I/O performance for drivers using coherent DMA.
-	  This option adds a write barrier to the cpu_idle loop so that,
-	  on systems with an outer cache, the store buffer is drained
-	  explicitly.
-
 endmenu
 
 menu "Kernel Features"
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index e58603b..caddb9d 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -539,6 +539,7 @@ __armv7_mmu_cache_on:
 		mcrne	p15, 0, r0, c8, c7, 0	@ flush I,D TLBs
 #endif
 		mrc	p15, 0, r0, c1, c0, 0	@ read control reg
+		bic	r0, r0, #1 << 28	@ clear SCTLR.TRE
 		orr	r0, r0, #0x5000		@ I-cache enable, RR cache replacement
 		orr	r0, r0, #0x003c		@ write buffer
 #ifdef CONFIG_MMU
diff --git a/arch/arm/include/asm/mutex.h b/arch/arm/include/asm/mutex.h
index 93226cf..b1479fd 100644
--- a/arch/arm/include/asm/mutex.h
+++ b/arch/arm/include/asm/mutex.h
@@ -7,121 +7,10 @@
  */
 #ifndef _ASM_MUTEX_H
 #define _ASM_MUTEX_H
-
-#if __LINUX_ARM_ARCH__ < 6
-/* On pre-ARMv6 hardware the swp based implementation is the most efficient. */
-# include <asm-generic/mutex-xchg.h>
-#else
-
 /*
- * Attempting to lock a mutex on ARMv6+ can be done with a bastardized
- * atomic decrement (it is not a reliable atomic decrement but it satisfies
- * the defined semantics for our purpose, while being smaller and faster
- * than a real atomic decrement or atomic swap.  The idea is to attempt
- * decrementing the lock value only once.  If once decremented it isn't zero,
- * or if its store-back fails due to a dispute on the exclusive store, we
- * simply bail out immediately through the slow path where the lock will be
- * reattempted until it succeeds.
+ * On pre-ARMv6 hardware this results in a swp-based implementation,
+ * which is the most efficient. For ARMv6+, we emit a pair of exclusive
+ * accesses instead.
  */
-static inline void
-__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res;
-
-	__asm__ (
-
-		"ldrex	%0, [%2]	\n\t"
-		"sub	%0, %0, #1	\n\t"
-		"strex	%1, %0, [%2]	"
-
-		: "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&(count)->counter)
-		: "cc","memory" );
-
-	__res |= __ex_flag;
-	if (unlikely(__res != 0))
-		fail_fn(count);
-}
-
-static inline int
-__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res;
-
-	__asm__ (
-
-		"ldrex	%0, [%2]	\n\t"
-		"sub	%0, %0, #1	\n\t"
-		"strex	%1, %0, [%2]	"
-
-		: "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&(count)->counter)
-		: "cc","memory" );
-
-	__res |= __ex_flag;
-	if (unlikely(__res != 0))
-		__res = fail_fn(count);
-	return __res;
-}
-
-/*
- * Same trick is used for the unlock fast path. However the original value,
- * rather than the result, is used to test for success in order to have
- * better generated assembly.
- */
-static inline void
-__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res, __orig;
-
-	__asm__ (
-
-		"ldrex	%0, [%3]	\n\t"
-		"add	%1, %0, #1	\n\t"
-		"strex	%2, %1, [%3]	"
-
-		: "=&r" (__orig), "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&(count)->counter)
-		: "cc","memory" );
-
-	__orig |= __ex_flag;
-	if (unlikely(__orig != 0))
-		fail_fn(count);
-}
-
-/*
- * If the unlock was done on a contended lock, or if the unlock simply fails
- * then the mutex remains locked.
- */
-#define __mutex_slowpath_needs_to_unlock()	1
-
-/*
- * For __mutex_fastpath_trylock we use another construct which could be
- * described as a "single value cmpxchg".
- *
- * This provides the needed trylock semantics like cmpxchg would, but it is
- * lighter and less generic than a true cmpxchg implementation.
- */
-static inline int
-__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res, __orig;
-
-	__asm__ (
-
-		"1: ldrex	%0, [%3]	\n\t"
-		"subs		%1, %0, #1	\n\t"
-		"strexeq	%2, %1, [%3]	\n\t"
-		"movlt		%0, #0		\n\t"
-		"cmpeq		%2, #0		\n\t"
-		"bgt		1b		"
-
-		: "=&r" (__orig), "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&count->counter)
-		: "cc", "memory" );
-
-	return __orig;
-}
-
-#endif
+#include <asm-generic/mutex-xchg.h>
 #endif
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 942bda2..1396edf 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -451,6 +451,13 @@ static inline void mce_get_rip(struct mce *m, struct pt_regs *regs)
 	if (regs && (m->mcgstatus & (MCG_STATUS_RIPV|MCG_STATUS_EIPV))) {
 		m->ip = regs->ip;
 		m->cs = regs->cs;
+		/*
+		 * When in VM86 mode make the cs look like ring 3
+		 * always. This is a lie, but it's better than passing
+		 * the additional vm86 bit around everywhere.
+		 */
+		if (v8086_mode(regs))
+			m->cs |= 3;
 	} else {
 		m->ip = 0;
 		m->cs = 0;
@@ -988,6 +995,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		 */
 		add_taint(TAINT_MACHINE_CHECK);
 
+		mce_get_rip(&m, regs);
 		severity = mce_severity(&m, tolerant, NULL);
 
 		/*
@@ -1026,7 +1034,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		if (severity == MCE_AO_SEVERITY && mce_usable_address(&m))
 			mce_ring_add(m.addr >> PAGE_SHIFT);
 
-		mce_get_rip(&m, regs);
 		mce_log(&m);
 
 		if (severity > worst) {
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 6dd8955..0951b81 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -521,3 +521,20 @@ static void sb600_disable_hpet_bar(struct pci_dev *dev)
 	}
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_ATI, 0x4385, sb600_disable_hpet_bar);
+
+/*
+ * Twinhead H12Y needs us to block out a region otherwise we map devices
+ * there and any access kills the box.
+ *
+ *   See: https://bugzilla.kernel.org/show_bug.cgi?id=10231
+ *
+ * Match off the LPC and svid/sdid (older kernels lose the bridge subvendor)
+ */
+static void __devinit twinhead_reserve_killing_zone(struct pci_dev *dev)
+{
+        if (dev->subsystem_vendor == 0x14FF && dev->subsystem_device == 0xA003) {
+                pr_info("Reserving memory on Twinhead H12Y\n");
+                request_mem_region(0xFFB00000, 0x100000, "twinhead");
+        }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index f8dcda4..5669564 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -15,6 +15,7 @@
 #include <asm/e820.h>
 #include <asm/setup.h>
 #include <asm/acpi.h>
+#include <asm/numa.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
@@ -463,4 +464,7 @@ void __init xen_arch_setup(void)
 	boot_option_idle_override = IDLE_HALT;
 
 	fiddle_vdso();
+#ifdef CONFIG_NUMA
+	numa_off = 1;
+#endif
 }