8 files changed, 26 insertions, 22 deletions
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 6e76c191a835..d5fd66f0d4cd 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -20,7 +20,6 @@
 #include <linux/bitops.h>
 #include <linux/ioport.h>
 #include <linux/suspend.h>
-#include <linux/kmemleak.h>
 #include <asm/e820.h>
 #include <asm/io.h>
 #include <asm/iommu.h>
@@ -95,11 +94,6 @@ static u32 __init allocate_aperture(void)
 		return 0;
 	}
 	memblock_reserve(addr, aper_size);
-	/*
-	 * Kmemleak should not scan this block as it may not be mapped via the
-	 * kernel direct mapping.
-	 */
-	kmemleak_ignore(phys_to_virt(addr));
 	printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
 			aper_size >> 10, addr);
 	insert_aperture_resource((u32)addr, aper_size);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index ac96561d1a99..5f0ff597437c 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1195,7 +1195,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
 	BUG_ON(!cfg->vector);
 
 	vector = cfg->vector;
-	for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+	for_each_cpu(cpu, cfg->domain)
 		per_cpu(vector_irq, cpu)[vector] = -1;
 
 	cfg->vector = 0;
@@ -1203,7 +1203,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
 
 	if (likely(!cfg->move_in_progress))
 		return;
-	for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+	for_each_cpu(cpu, cfg->old_domain) {
 		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
 								vector++) {
 			if (per_cpu(vector_irq, cpu)[vector] != irq)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 0a687fd185e6..da27c5d2168a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1274,7 +1274,7 @@ static void mce_timer_fn(unsigned long data)
 	 */
 	iv = __this_cpu_read(mce_next_interval);
 	if (mce_notify_irq())
-		iv = max(iv, (unsigned long) HZ/100);
+		iv = max(iv / 2, (unsigned long) HZ/100);
 	else
 		iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));
 	__this_cpu_write(mce_next_interval, iv);
@@ -1557,7 +1557,7 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 static void __mcheck_cpu_init_timer(void)
 {
 	struct timer_list *t = &__get_cpu_var(mce_timer);
-	unsigned long iv = __this_cpu_read(mce_next_interval);
+	unsigned long iv = check_interval * HZ;
 
 	setup_timer(t, mce_timer_fn, smp_processor_id());
 
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 086eb58c6e80..f1b42b3a186c 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -120,11 +120,6 @@ bool kvm_check_and_clear_guest_paused(void)
 	bool ret = false;
 	struct pvclock_vcpu_time_info *src;
 
-	/*
-	 * per_cpu() is safe here because this function is only called from
-	 * timer functions where preemption is already disabled.
-	 */
-	WARN_ON(!in_atomic());
 	src = &__get_cpu_var(hv_clock);
 	if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) {
 		__this_cpu_and(hv_clock.flags, ~PVCLOCK_GUEST_STOPPED);
diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c
index e31bf8d5c4d2..149b8d9c6ad4 100644
--- a/arch/x86/kernel/nmi_selftest.c
+++ b/arch/x86/kernel/nmi_selftest.c
@@ -42,7 +42,7 @@ static int __init nmi_unk_cb(unsigned int val, struct pt_regs *regs)
 static void __init init_nmi_testsuite(void)
 {
 	/* trap all the unknown NMIs we may generate */
-	register_nmi_handler(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
+	register_nmi_handler_initonly(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
 }
 
 static void __init cleanup_nmi_testsuite(void)
@@ -64,7 +64,7 @@ static void __init test_nmi_ipi(struct cpumask *mask)
 {
 	unsigned long timeout;
 
-	if (register_nmi_handler(NMI_LOCAL, test_nmi_ipi_callback,
+	if (register_nmi_handler_initonly(NMI_LOCAL, test_nmi_ipi_callback,
 				 NMI_FLAG_FIRST, "nmi_selftest")) {
 		nmi_fail = FAILURE;
 		return;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 62c9457ccd2f..c0f420f76cd3 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -100,7 +100,7 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 				 struct dma_attrs *attrs)
 {
 	unsigned long dma_mask;
-	struct page *page = NULL;
+	struct page *page;
 	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	dma_addr_t addr;
 
@@ -108,6 +108,7 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 
 	flag |= __GFP_ZERO;
 again:
+	page = NULL;
 	if (!(flag & GFP_ATOMIC))
 		page = dma_alloc_from_contiguous(dev, count, get_order(size));
 	if (!page)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 79c45af81604..25b48edb847c 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -639,9 +639,11 @@ void native_machine_shutdown(void)
 	set_cpus_allowed_ptr(current, cpumask_of(reboot_cpu_id));
 
 	/*
-	 * O.K Now that I'm on the appropriate processor,
-	 * stop all of the others.
+	 * O.K Now that I'm on the appropriate processor, stop all of the
+	 * others. Also disable the local irq to not receive the per-cpu
+	 * timer interrupt which may trigger scheduler's load balance.
 	 */
+	local_irq_disable();
 	stop_other_cpus();
 #endif
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fd019d78b1f4..7bd8a0823654 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -349,9 +349,12 @@ static bool __cpuinit match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 
 static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
-	if (c->phys_proc_id == o->phys_proc_id)
-		return topology_sane(c, o, "mc");
+	if (c->phys_proc_id == o->phys_proc_id) {
+		if (cpu_has(c, X86_FEATURE_AMD_DCM))
+			return true;
 
+		return topology_sane(c, o, "mc");
+	}
 	return false;
 }
 
@@ -382,6 +385,15 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 		if ((i == cpu) || (has_mc && match_llc(c, o)))
 			link_mask(llc_shared, cpu, i);
 
+	}
+
+	/*
+	 * This needs a separate iteration over the cpus because we rely on all
+	 * cpu_sibling_mask links to be set-up.
+	 */
+	for_each_cpu(i, cpu_sibling_setup_mask) {
+		o = &cpu_data(i);
+
 		if ((i == cpu) || (has_mc && match_mc(c, o))) {
 			link_mask(core, cpu, i);