Merge branch 'linus' into x86/gart

22 files changed, 96 insertions, 72 deletions

diff --git a/arch/x86/boot/a20.c b/arch/x86/boot/a20.c
index 90943f83e84..e01aafd03bd 100644
--- a/arch/x86/boot/a20.c
+++ b/arch/x86/boot/a20.c
@@ -115,8 +115,6 @@ static void enable_a20_fast(void)
 
 int enable_a20(void)
 {
-	int loops = A20_ENABLE_LOOPS;
-
 #if defined(CONFIG_X86_ELAN)
 	/* Elan croaks if we try to touch the KBC */
 	enable_a20_fast();
@@ -128,6 +126,7 @@ int enable_a20(void)
 	enable_a20_kbc();
 	return 0;
 #else
+       int loops = A20_ENABLE_LOOPS;
 	while (loops--) {
 		/* First, check to see if A20 is already enabled
 		   (legacy free, etc.) */
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 2a609dc3271..c778e4fa55a 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -248,6 +248,7 @@ ENTRY(resume_userspace)
  	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
 					# setting need_resched or sigpending
 					# between sampling and the iret
+	TRACE_IRQS_OFF
 	movl TI_flags(%ebp), %ecx
 	andl $_TIF_WORK_MASK, %ecx	# is there any work to be done on
 					# int/exception return?
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index b2cc73768a9..f7357cc0162 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -189,7 +189,7 @@ default_entry:
 	 * this stage.
 	 */
 
-#define KPMDS ((0x100000000-__PAGE_OFFSET) >> 30) /* Number of kernel PMDs */
+#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
 
 	xorl %ebx,%ebx				/* %ebx is kept at zero */
 
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index a40d54fc1fd..4dc8600d9d2 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -2130,14 +2130,10 @@ static inline void __init check_timer(void)
 {
 	int apic1, pin1, apic2, pin2;
 	int vector;
-	unsigned int ver;
 	unsigned long flags;
 
 	local_irq_save(flags);
 
-	ver = apic_read(APIC_LVR);
-	ver = GET_APIC_VERSION(ver);
-
 	/*
 	 * get/set the timer IRQ vector:
 	 */
@@ -2150,15 +2146,11 @@ static inline void __init check_timer(void)
 	 * mode for the 8259A whenever interrupts are routed
 	 * through I/O APICs.  Also IRQ0 has to be enabled in
 	 * the 8259A which implies the virtual wire has to be
-	 * disabled in the local APIC.  Finally timer interrupts
-	 * need to be acknowledged manually in the 8259A for
-	 * timer_interrupt() and for the i82489DX when using
-	 * the NMI watchdog.
+	 * disabled in the local APIC.
 	 */
 	apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
 	init_8259A(1);
-	timer_ack = !cpu_has_tsc;
-	timer_ack |= (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
+	timer_ack = 1;
 	if (timer_over_8254 > 0)
 		enable_8259A_irq(0);
 
diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c
index 3cad17fe026..07c0f828f48 100644
--- a/arch/x86/kernel/mfgpt_32.c
+++ b/arch/x86/kernel/mfgpt_32.c
@@ -155,6 +155,7 @@ int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable)
 	wrmsr(msr, value, dummy);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(geode_mfgpt_toggle_event);
 
 int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable)
 {
@@ -222,6 +223,7 @@ int geode_mfgpt_alloc_timer(int timer, int domain)
 	/* No timers available - too bad */
 	return -1;
 }
+EXPORT_SYMBOL_GPL(geode_mfgpt_alloc_timer);
 
 
 #ifdef CONFIG_GEODE_MFGPT_TIMER
diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c
index 11b14bbaa61..84160f74eeb 100644
--- a/arch/x86/kernel/nmi_32.c
+++ b/arch/x86/kernel/nmi_32.c
@@ -26,7 +26,6 @@
 
 #include <asm/smp.h>
 #include <asm/nmi.h>
-#include <asm/timer.h>
 
 #include "mach_traps.h"
 
@@ -82,7 +81,7 @@ int __init check_nmi_watchdog(void)
 
 	prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL);
 	if (!prev_nmi_count)
-		goto error;
+		return -1;
 
 	printk(KERN_INFO "Testing NMI watchdog ... ");
 
@@ -119,7 +118,7 @@ int __init check_nmi_watchdog(void)
 	if (!atomic_read(&nmi_active)) {
 		kfree(prev_nmi_count);
 		atomic_set(&nmi_active, -1);
-		goto error;
+		return -1;
 	}
 	printk("OK.\n");
 
@@ -130,10 +129,6 @@ int __init check_nmi_watchdog(void)
 
 	kfree(prev_nmi_count);
 	return 0;
-error:
-	timer_ack = !cpu_has_tsc;
-
-	return -1;
 }
 
 static int __init setup_nmi_watchdog(char *str)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 7747bc82b11..09c4dac11b5 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -379,6 +379,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	struct page *page;
 	unsigned long dma_mask = 0;
 	dma_addr_t bus;
+	int noretry = 0;
 
 	/* ignore region specifiers */
 	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
@@ -398,20 +399,25 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	if (dev->dma_mask == NULL)
 		return NULL;
 
-	/* Don't invoke OOM killer */
-	gfp |= __GFP_NORETRY;
+	/* Don't invoke OOM killer or retry in lower 16MB DMA zone */
+	if (gfp & __GFP_DMA)
+		noretry = 1;
 
 #ifdef CONFIG_X86_64
 	/* Why <=? Even when the mask is smaller than 4GB it is often
 	   larger than 16MB and in this case we have a chance of
 	   finding fitting memory in the next higher zone first. If
 	   not retry with true GFP_DMA. -AK */
-	if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA))
+	if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA)) {
 		gfp |= GFP_DMA32;
+		if (dma_mask < DMA_32BIT_MASK)
+			noretry = 1;
+	}
 #endif
 
  again:
-	page = dma_alloc_pages(dev, gfp, get_order(size));
+	page = dma_alloc_pages(dev,
+		noretry ? gfp | __GFP_NORETRY : gfp, get_order(size));
 	if (page == NULL)
 		return NULL;
 
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 9615eee9b77..05191bbc68b 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -4,6 +4,8 @@
 #include <linux/acpi.h>
 #include <linux/bcd.h>
 #include <linux/mc146818rtc.h>
+#include <linux/platform_device.h>
+#include <linux/pnp.h>
 
 #include <asm/time.h>
 #include <asm/vsyscall.h>
@@ -197,3 +199,35 @@ unsigned long long native_read_tsc(void)
 }
 EXPORT_SYMBOL(native_read_tsc);
 
+
+static struct resource rtc_resources[] = {
+	[0] = {
+		.start	= RTC_PORT(0),
+		.end	= RTC_PORT(1),
+		.flags	= IORESOURCE_IO,
+	},
+	[1] = {
+		.start	= RTC_IRQ,
+		.end	= RTC_IRQ,
+		.flags	= IORESOURCE_IRQ,
+	}
+};
+
+static struct platform_device rtc_device = {
+	.name		= "rtc_cmos",
+	.id		= -1,
+	.resource	= rtc_resources,
+	.num_resources	= ARRAY_SIZE(rtc_resources),
+};
+
+static __init int add_rtc_cmos(void)
+{
+#ifdef CONFIG_PNP
+	if (!pnp_platform_devices)
+		platform_device_register(&rtc_device);
+#else
+	platform_device_register(&rtc_device);
+#endif /* CONFIG_PNP */
+	return 0;
+}
+device_initcall(add_rtc_cmos);
diff --git a/arch/x86/kernel/traps_32.c b/arch/x86/kernel/traps_32.c
index bde6f63e15d..08d752de4ee 100644
--- a/arch/x86/kernel/traps_32.c
+++ b/arch/x86/kernel/traps_32.c
@@ -544,6 +544,7 @@ vm86_trap:
 #define DO_ERROR(trapnr, signr, str, name)				\
 void do_##name(struct pt_regs *regs, long error_code)			\
 {									\
+	trace_hardirqs_fixup();						\
 	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr)	\
 						== NOTIFY_STOP)		\
 		return;							\
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 7c077a9d977..f2f5d260874 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -200,7 +200,6 @@ int __pit_timer_fn(struct kvm_kpit_state *ps)
 
 	atomic_inc(&pt->pending);
 	smp_mb__after_atomic_inc();
-	/* FIXME: handle case where the guest is in guest mode */
 	if (vcpu0 && waitqueue_active(&vcpu0->wq)) {
 		vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 		wake_up_interruptible(&vcpu0->wq);
@@ -237,6 +236,19 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 		return HRTIMER_NORESTART;
 }
 
+void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
+	struct hrtimer *timer;
+
+	if (vcpu->vcpu_id != 0 || !pit)
+		return;
+
+	timer = &pit->pit_state.pit_timer.timer;
+	if (hrtimer_cancel(timer))
+		hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS);
+}
+
 static void destroy_pit_timer(struct kvm_kpit_timer *pt)
 {
 	pr_debug("pit: execute del timer!\n");
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index ce1f583459b..76d736b5f66 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -94,3 +94,9 @@ void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
 	/* TODO: PIT, RTC etc. */
 }
 EXPORT_SYMBOL_GPL(kvm_timer_intr_post);
+
+void __kvm_migrate_timers(struct kvm_vcpu *vcpu)
+{
+	__kvm_migrate_apic_timer(vcpu);
+	__kvm_migrate_pit_timer(vcpu);
+}
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 1802134b836..2a15be2275c 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -84,6 +84,8 @@ void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec);
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
 void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu);
+void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu);
+void __kvm_migrate_timers(struct kvm_vcpu *vcpu);
 
 int pit_has_pending_timer(struct kvm_vcpu *vcpu);
 int apic_has_pending_timer(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 7246b60afb9..ee3f53098f0 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -658,7 +658,7 @@ static int is_empty_shadow_page(u64 *spt)
 	u64 *end;
 
 	for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
-		if (*pos != shadow_trap_nonpresent_pte) {
+		if (is_shadow_present_pte(*pos)) {
 			printk(KERN_ERR "%s: %p %llx\n", __func__,
 			       pos, *pos);
 			return 0;
@@ -1858,6 +1858,7 @@ static void free_mmu_pages(struct kvm_vcpu *vcpu)
 		sp = container_of(vcpu->kvm->arch.active_mmu_pages.next,
 				  struct kvm_mmu_page, link);
 		kvm_mmu_zap_page(vcpu->kvm, sp);
+		cond_resched();
 	}
 	free_page((unsigned long)vcpu->arch.mmu.pae_root);
 }
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 156fe10288a..934c7b61939 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -418,7 +418,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 
 	/* mmio */
 	if (is_error_pfn(pfn)) {
-		pgprintk("gfn %x is mmio\n", walker.gfn);
+		pgprintk("gfn %lx is mmio\n", walker.gfn);
 		kvm_release_pfn_clean(pfn);
 		return 1;
 	}
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index ab22615eee8..6b0d5fa5bab 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -688,7 +688,7 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		delta = vcpu->arch.host_tsc - tsc_this;
 		svm->vmcb->control.tsc_offset += delta;
 		vcpu->cpu = cpu;
-		kvm_migrate_apic_timer(vcpu);
+		kvm_migrate_timers(vcpu);
 	}
 
 	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index bfe4db11989..02efbe75f31 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -608,7 +608,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	if (vcpu->cpu != cpu) {
 		vcpu_clear(vmx);
-		kvm_migrate_apic_timer(vcpu);
+		kvm_migrate_timers(vcpu);
 		vpid_sync_vcpu_all(vmx);
 	}
 
@@ -1036,6 +1036,7 @@ static void hardware_enable(void *garbage)
 static void hardware_disable(void *garbage)
 {
 	asm volatile (ASM_VMX_VMXOFF : : : "cc");
+	write_cr4(read_cr4() & ~X86_CR4_VMXE);
 }
 
 static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 21338bdb28f..00acf1301a1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2758,7 +2758,7 @@ again:
 
 	if (vcpu->requests) {
 		if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests))
-			__kvm_migrate_apic_timer(vcpu);
+			__kvm_migrate_timers(vcpu);
 		if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS,
 				       &vcpu->requests)) {
 			kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS;
diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index 8a96320ab07..932f216d890 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -1727,7 +1727,8 @@ twobyte_insn:
 			if (rc)
 				goto done;
 
-			kvm_emulate_hypercall(ctxt->vcpu);
+			/* Let the processor re-execute the fixed hypercall */
+			c->eip = ctxt->vcpu->arch.rip;
 			/* Disable writeback. */
 			c->dst.type = OP_NONE;
 			break;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index fd7e1798c75..8bcb6f40ccb 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -497,6 +497,11 @@ static int vmalloc_fault(unsigned long address)
 	unsigned long pgd_paddr;
 	pmd_t *pmd_k;
 	pte_t *pte_k;
+
+	/* Make sure we are in vmalloc area */
+	if (!(address >= VMALLOC_START && address < VMALLOC_END))
+		return -1;
+
 	/*
 	 * Synchronize this task's top level page-table
 	 * with the 'reference' page table.
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 3890234e5b2..99649dccad2 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -97,36 +97,9 @@ static __init inline int srat_disabled(void)
 	return numa_off || acpi_numa < 0;
 }
 
-/*
- * A lot of BIOS fill in 10 (= no distance) everywhere. This messes
- * up the NUMA heuristics which wants the local node to have a smaller
- * distance than the others.
- * Do some quick checks here and only use the SLIT if it passes.
- */
-static __init int slit_valid(struct acpi_table_slit *slit)
-{
-	int i, j;
-	int d = slit->locality_count;
-	for (i = 0; i < d; i++) {
-		for (j = 0; j < d; j++)  {
-			u8 val = slit->entry[d*i + j];
-			if (i == j) {
-				if (val != LOCAL_DISTANCE)
-					return 0;
-			} else if (val <= LOCAL_DISTANCE)
-				return 0;
-		}
-	}
-	return 1;
-}
-
 /* Callback for SLIT parsing */
 void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 {
-	if (!slit_valid(slit)) {
-		printk(KERN_INFO "ACPI: SLIT table looks invalid. Not used.\n");
-		return;
-	}
 	acpi_slit = slit;
 }
 
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 6e64aaf00d1..940185ecaed 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -328,18 +328,18 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = {
 #endif
 	{
 		.callback = set_bf_sort,
-		.ident = "HP ProLiant DL385 G2",
+		.ident = "HP ProLiant DL360",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL385 G2"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL360"),
 		},
 	},
 	{
 		.callback = set_bf_sort,
-		.ident = "HP ProLiant DL585 G2",
+		.ident = "HP ProLiant DL380",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL380"),
 		},
 	},
 	{}
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index c39e1a5aa24..52b2e385698 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -12,6 +12,7 @@
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
 #include <linux/kernel_stat.h>
+#include <linux/math64.h>
 
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
@@ -150,11 +151,7 @@ static void do_stolen_accounting(void)
 	if (stolen < 0)
 		stolen = 0;
 
-	ticks = 0;
-	while (stolen >= NS_PER_TICK) {
-		ticks++;
-		stolen -= NS_PER_TICK;
-	}
+	ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen);
 	__get_cpu_var(residual_stolen) = stolen;
 	account_steal_time(NULL, ticks);
 
@@ -166,11 +163,7 @@ static void do_stolen_accounting(void)
 	if (blocked < 0)
 		blocked = 0;
 
-	ticks = 0;
-	while (blocked >= NS_PER_TICK) {
-		ticks++;
-		blocked -= NS_PER_TICK;
-	}
+	ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked);
 	__get_cpu_var(residual_blocked) = blocked;
 	account_steal_time(idle_task(smp_processor_id()), ticks);
 }