16 files changed, 390 insertions, 242 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 8baca3c4871c..02b2f05b371e 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -80,6 +80,7 @@ obj-$(CONFIG_APB_TIMER)		+= apb_timer.o
 obj-$(CONFIG_AMD_NB)		+= amd_nb.o
 obj-$(CONFIG_DEBUG_RODATA_TEST)	+= test_rodata.o
 obj-$(CONFIG_DEBUG_NX_TEST)	+= test_nx.o
+obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
 
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o
 obj-$(CONFIG_KVM_CLOCK)		+= kvmclock.o
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 013c1810ce72..be16854591cc 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -119,6 +119,37 @@ bool __init early_is_amd_nb(u32 device)
 	return false;
 }
 
+struct resource *amd_get_mmconfig_range(struct resource *res)
+{
+	u32 address;
+	u64 base, msr;
+	unsigned segn_busn_bits;
+
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+		return NULL;
+
+	/* assume all cpus from fam10h have mmconfig */
+        if (boot_cpu_data.x86 < 0x10)
+		return NULL;
+
+	address = MSR_FAM10H_MMIO_CONF_BASE;
+	rdmsrl(address, msr);
+
+	/* mmconfig is not enabled */
+	if (!(msr & FAM10H_MMIO_CONF_ENABLE))
+		return NULL;
+
+	base = msr & (FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT);
+
+	segn_busn_bits = (msr >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) &
+			 FAM10H_MMIO_CONF_BUSRANGE_MASK;
+
+	res->flags = IORESOURCE_MEM;
+	res->start = base;
+	res->end = base + (1ULL<<(segn_busn_bits + 20)) - 1;
+	return res;
+}
+
 int amd_get_subcaches(int cpu)
 {
 	struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link;
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 4f13fafc5264..68de2dc962ec 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -67,4 +67,6 @@ void common(void) {
 	OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
 	OFFSET(BP_version, boot_params, hdr.version);
 	OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
+	OFFSET(BP_pref_address, boot_params, hdr.pref_address);
+	OFFSET(BP_code32_start, boot_params, hdr.code32_start);
 }
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 8071e2f3d6eb..174d938d576b 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -19,6 +19,7 @@
 #include <linux/acpi.h>
 #include <linux/firmware-map.h>
 #include <linux/memblock.h>
+#include <linux/sort.h>
 
 #include <asm/e820.h>
 #include <asm/proto.h>
@@ -227,22 +228,38 @@ void __init e820_print_map(char *who)
  *	   ____________________33__
  *	   ______________________4_
  */
+struct change_member {
+	struct e820entry *pbios; /* pointer to original bios entry */
+	unsigned long long addr; /* address for this change point */
+};
+
+static int __init cpcompare(const void *a, const void *b)
+{
+	struct change_member * const *app = a, * const *bpp = b;
+	const struct change_member *ap = *app, *bp = *bpp;
+
+	/*
+	 * Inputs are pointers to two elements of change_point[].  If their
+	 * addresses are unequal, their difference dominates.  If the addresses
+	 * are equal, then consider one that represents the end of its region
+	 * to be greater than one that does not.
+	 */
+	if (ap->addr != bp->addr)
+		return ap->addr > bp->addr ? 1 : -1;
+
+	return (ap->addr != ap->pbios->addr) - (bp->addr != bp->pbios->addr);
+}
 
 int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
 			     u32 *pnr_map)
 {
-	struct change_member {
-		struct e820entry *pbios; /* pointer to original bios entry */
-		unsigned long long addr; /* address for this change point */
-	};
 	static struct change_member change_point_list[2*E820_X_MAX] __initdata;
 	static struct change_member *change_point[2*E820_X_MAX] __initdata;
 	static struct e820entry *overlap_list[E820_X_MAX] __initdata;
 	static struct e820entry new_bios[E820_X_MAX] __initdata;
-	struct change_member *change_tmp;
 	unsigned long current_type, last_type;
 	unsigned long long last_addr;
-	int chgidx, still_changing;
+	int chgidx;
 	int overlap_entries;
 	int new_bios_entry;
 	int old_nr, new_nr, chg_nr;
@@ -279,35 +296,7 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
 	chg_nr = chgidx;
 
 	/* sort change-point list by memory addresses (low -> high) */
-	still_changing = 1;
-	while (still_changing)	{
-		still_changing = 0;
-		for (i = 1; i < chg_nr; i++)  {
-			unsigned long long curaddr, lastaddr;
-			unsigned long long curpbaddr, lastpbaddr;
-
-			curaddr = change_point[i]->addr;
-			lastaddr = change_point[i - 1]->addr;
-			curpbaddr = change_point[i]->pbios->addr;
-			lastpbaddr = change_point[i - 1]->pbios->addr;
-
-			/*
-			 * swap entries, when:
-			 *
-			 * curaddr > lastaddr or
-			 * curaddr == lastaddr and curaddr == curpbaddr and
-			 * lastaddr != lastpbaddr
-			 */
-			if (curaddr < lastaddr ||
-			    (curaddr == lastaddr && curaddr == curpbaddr &&
-			     lastaddr != lastpbaddr)) {
-				change_tmp = change_point[i];
-				change_point[i] = change_point[i-1];
-				change_point[i-1] = change_tmp;
-				still_changing = 1;
-			}
-		}
-	}
+	sort(change_point, chg_nr, sizeof *change_point, cpcompare, NULL);
 
 	/* create a new bios memory map, removing overlaps */
 	overlap_entries = 0;	 /* number of entries in the overlap table */
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index cd28a350f7f9..9b9f18b49918 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -240,14 +240,14 @@ static int __init setup_early_printk(char *buf)
 		if (!strncmp(buf, "xen", 3))
 			early_console_register(&xenboot_console, keep);
 #endif
-#ifdef CONFIG_EARLY_PRINTK_MRST
+#ifdef CONFIG_EARLY_PRINTK_INTEL_MID
 		if (!strncmp(buf, "mrst", 4)) {
 			mrst_early_console_init();
 			early_console_register(&early_mrst_console, keep);
 		}
 
 		if (!strncmp(buf, "hsu", 3)) {
-			hsu_early_console_init();
+			hsu_early_console_init(buf + 3);
 			early_console_register(&early_hsu_console, keep);
 		}
 #endif
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 72090705a656..40fc86161d92 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -28,6 +28,9 @@ DEFINE_PER_CPU(struct pt_regs *, irq_regs);
 EXPORT_PER_CPU_SYMBOL(irq_regs);
 
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
+
+int sysctl_panic_on_stackoverflow __read_mostly;
+
 /* Debugging check for stack overflow: is there less than 1KB free? */
 static int check_stack_overflow(void)
 {
@@ -43,6 +46,8 @@ static void print_stack_overflow(void)
 {
 	printk(KERN_WARNING "low stack detected by irq handler\n");
 	dump_stack();
+	if (sysctl_panic_on_stackoverflow)
+		panic("low stack detected by irq handler - check messages\n");
 }
 
 #else
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 69bca468c47a..d04d3ecded62 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -26,6 +26,8 @@ EXPORT_PER_CPU_SYMBOL(irq_stat);
 DEFINE_PER_CPU(struct pt_regs *, irq_regs);
 EXPORT_PER_CPU_SYMBOL(irq_regs);
 
+int sysctl_panic_on_stackoverflow;
+
 /*
  * Probabilistic stack overflow check:
  *
@@ -36,18 +38,39 @@ EXPORT_PER_CPU_SYMBOL(irq_regs);
 static inline void stack_overflow_check(struct pt_regs *regs)
 {
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
+#define STACK_TOP_MARGIN	128
+	struct orig_ist *oist;
+	u64 irq_stack_top, irq_stack_bottom;
+	u64 estack_top, estack_bottom;
 	u64 curbase = (u64)task_stack_page(current);
 
 	if (user_mode_vm(regs))
 		return;
 
-	WARN_ONCE(regs->sp >= curbase &&
-		  regs->sp <= curbase + THREAD_SIZE &&
-		  regs->sp <  curbase + sizeof(struct thread_info) +
-					sizeof(struct pt_regs) + 128,
+	if (regs->sp >= curbase + sizeof(struct thread_info) +
+				  sizeof(struct pt_regs) + STACK_TOP_MARGIN &&
+	    regs->sp <= curbase + THREAD_SIZE)
+		return;
+
+	irq_stack_top = (u64)__get_cpu_var(irq_stack_union.irq_stack) +
+			STACK_TOP_MARGIN;
+	irq_stack_bottom = (u64)__get_cpu_var(irq_stack_ptr);
+	if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom)
+		return;
+
+	oist = &__get_cpu_var(orig_ist);
+	estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN;
+	estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1];
+	if (regs->sp >= estack_top && regs->sp <= estack_bottom)
+		return;
+
+	WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n",
+		current->comm, curbase, regs->sp,
+		irq_stack_top, irq_stack_bottom,
+		estack_top, estack_bottom);
 
-		  "do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n",
-			current->comm, curbase, regs->sp);
+	if (sysctl_panic_on_stackoverflow)
+		panic("low stack detected by irq handler - check messages\n");
 #endif
 }
 
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index a9c2116001d6..f0c6fd6f176b 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -39,8 +39,6 @@
 #include <asm/desc.h>
 #include <asm/tlbflush.h>
 
-#define MMU_QUEUE_SIZE 1024
-
 static int kvmapf = 1;
 
 static int parse_no_kvmapf(char *arg)
@@ -60,21 +58,10 @@ static int parse_no_stealacc(char *arg)
 
 early_param("no-steal-acc", parse_no_stealacc);
 
-struct kvm_para_state {
-	u8 mmu_queue[MMU_QUEUE_SIZE];
-	int mmu_queue_len;
-};
-
-static DEFINE_PER_CPU(struct kvm_para_state, para_state);
 static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
 static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64);
 static int has_steal_clock = 0;
 
-static struct kvm_para_state *kvm_para_state(void)
-{
-	return &per_cpu(para_state, raw_smp_processor_id());
-}
-
 /*
  * No need for any "IO delay" on KVM
  */
@@ -271,151 +258,6 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 	}
 }
 
-static void kvm_mmu_op(void *buffer, unsigned len)
-{
-	int r;
-	unsigned long a1, a2;
-
-	do {
-		a1 = __pa(buffer);
-		a2 = 0;   /* on i386 __pa() always returns <4G */
-		r = kvm_hypercall3(KVM_HC_MMU_OP, len, a1, a2);
-		buffer += r;
-		len -= r;
-	} while (len);
-}
-
-static void mmu_queue_flush(struct kvm_para_state *state)
-{
-	if (state->mmu_queue_len) {
-		kvm_mmu_op(state->mmu_queue, state->mmu_queue_len);
-		state->mmu_queue_len = 0;
-	}
-}
-
-static void kvm_deferred_mmu_op(void *buffer, int len)
-{
-	struct kvm_para_state *state = kvm_para_state();
-
-	if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU) {
-		kvm_mmu_op(buffer, len);
-		return;
-	}
-	if (state->mmu_queue_len + len > sizeof state->mmu_queue)
-		mmu_queue_flush(state);
-	memcpy(state->mmu_queue + state->mmu_queue_len, buffer, len);
-	state->mmu_queue_len += len;
-}
-
-static void kvm_mmu_write(void *dest, u64 val)
-{
-	__u64 pte_phys;
-	struct kvm_mmu_op_write_pte wpte;
-
-#ifdef CONFIG_HIGHPTE
-	struct page *page;
-	unsigned long dst = (unsigned long) dest;
-
-	page = kmap_atomic_to_page(dest);
-	pte_phys = page_to_pfn(page);
-	pte_phys <<= PAGE_SHIFT;
-	pte_phys += (dst & ~(PAGE_MASK));
-#else
-	pte_phys = (unsigned long)__pa(dest);
-#endif
-	wpte.header.op = KVM_MMU_OP_WRITE_PTE;
-	wpte.pte_val = val;
-	wpte.pte_phys = pte_phys;
-
-	kvm_deferred_mmu_op(&wpte, sizeof wpte);
-}
-
-/*
- * We only need to hook operations that are MMU writes.  We hook these so that
- * we can use lazy MMU mode to batch these operations.  We could probably
- * improve the performance of the host code if we used some of the information
- * here to simplify processing of batched writes.
- */
-static void kvm_set_pte(pte_t *ptep, pte_t pte)
-{
-	kvm_mmu_write(ptep, pte_val(pte));
-}
-
-static void kvm_set_pte_at(struct mm_struct *mm, unsigned long addr,
-			   pte_t *ptep, pte_t pte)
-{
-	kvm_mmu_write(ptep, pte_val(pte));
-}
-
-static void kvm_set_pmd(pmd_t *pmdp, pmd_t pmd)
-{
-	kvm_mmu_write(pmdp, pmd_val(pmd));
-}
-
-#if PAGETABLE_LEVELS >= 3
-#ifdef CONFIG_X86_PAE
-static void kvm_set_pte_atomic(pte_t *ptep, pte_t pte)
-{
-	kvm_mmu_write(ptep, pte_val(pte));
-}
-
-static void kvm_pte_clear(struct mm_struct *mm,
-			  unsigned long addr, pte_t *ptep)
-{
-	kvm_mmu_write(ptep, 0);
-}
-
-static void kvm_pmd_clear(pmd_t *pmdp)
-{
-	kvm_mmu_write(pmdp, 0);
-}
-#endif
-
-static void kvm_set_pud(pud_t *pudp, pud_t pud)
-{
-	kvm_mmu_write(pudp, pud_val(pud));
-}
-
-#if PAGETABLE_LEVELS == 4
-static void kvm_set_pgd(pgd_t *pgdp, pgd_t pgd)
-{
-	kvm_mmu_write(pgdp, pgd_val(pgd));
-}
-#endif
-#endif /* PAGETABLE_LEVELS >= 3 */
-
-static void kvm_flush_tlb(void)
-{
-	struct kvm_mmu_op_flush_tlb ftlb = {
-		.header.op = KVM_MMU_OP_FLUSH_TLB,
-	};
-
-	kvm_deferred_mmu_op(&ftlb, sizeof ftlb);
-}
-
-static void kvm_release_pt(unsigned long pfn)
-{
-	struct kvm_mmu_op_release_pt rpt = {
-		.header.op = KVM_MMU_OP_RELEASE_PT,
-		.pt_phys = (u64)pfn << PAGE_SHIFT,
-	};
-
-	kvm_mmu_op(&rpt, sizeof rpt);
-}
-
-static void kvm_enter_lazy_mmu(void)
-{
-	paravirt_enter_lazy_mmu();
-}
-
-static void kvm_leave_lazy_mmu(void)
-{
-	struct kvm_para_state *state = kvm_para_state();
-
-	mmu_queue_flush(state);
-	paravirt_leave_lazy_mmu();
-}
-
 static void __init paravirt_ops_setup(void)
 {
 	pv_info.name = "KVM";
@@ -424,29 +266,6 @@ static void __init paravirt_ops_setup(void)
 	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
 		pv_cpu_ops.io_delay = kvm_io_delay;
 
-	if (kvm_para_has_feature(KVM_FEATURE_MMU_OP)) {
-		pv_mmu_ops.set_pte = kvm_set_pte;
-		pv_mmu_ops.set_pte_at = kvm_set_pte_at;
-		pv_mmu_ops.set_pmd = kvm_set_pmd;
-#if PAGETABLE_LEVELS >= 3
-#ifdef CONFIG_X86_PAE
-		pv_mmu_ops.set_pte_atomic = kvm_set_pte_atomic;
-		pv_mmu_ops.pte_clear = kvm_pte_clear;
-		pv_mmu_ops.pmd_clear = kvm_pmd_clear;
-#endif
-		pv_mmu_ops.set_pud = kvm_set_pud;
-#if PAGETABLE_LEVELS == 4
-		pv_mmu_ops.set_pgd = kvm_set_pgd;
-#endif
-#endif
-		pv_mmu_ops.flush_tlb_user = kvm_flush_tlb;
-		pv_mmu_ops.release_pte = kvm_release_pt;
-		pv_mmu_ops.release_pmd = kvm_release_pt;
-		pv_mmu_ops.release_pud = kvm_release_pt;
-
-		pv_mmu_ops.lazy_mode.enter = kvm_enter_lazy_mmu;
-		pv_mmu_ops.lazy_mode.leave = kvm_leave_lazy_mmu;
-	}
 #ifdef CONFIG_X86_IO_APIC
 	no_timer_check = 1;
 #endif
diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c
new file mode 100644
index 000000000000..0d01a8ea4e11
--- /dev/null
+++ b/arch/x86/kernel/nmi_selftest.c
@@ -0,0 +1,180 @@
+/*
+ * arch/x86/kernel/nmi-selftest.c
+ *
+ * Testsuite for NMI: IPIs
+ *
+ * Started by Don Zickus:
+ * (using lib/locking-selftest.c as a guide)
+ *
+ *   Copyright (C) 2011 Red Hat, Inc., Don Zickus <dzickus@redhat.com>
+ */
+
+#include <linux/smp.h>
+#include <linux/cpumask.h>
+#include <linux/delay.h>
+
+#include <asm/apic.h>
+#include <asm/nmi.h>
+
+#define SUCCESS		0
+#define FAILURE		1
+#define TIMEOUT		2
+
+static int nmi_fail;
+
+/* check to see if NMI IPIs work on this machine */
+static DECLARE_BITMAP(nmi_ipi_mask, NR_CPUS) __read_mostly;
+
+static int testcase_total;
+static int testcase_successes;
+static int expected_testcase_failures;
+static int unexpected_testcase_failures;
+static int unexpected_testcase_unknowns;
+
+static int nmi_unk_cb(unsigned int val, struct pt_regs *regs)
+{
+	unexpected_testcase_unknowns++;
+	return NMI_HANDLED;
+}
+
+static void init_nmi_testsuite(void)
+{
+	/* trap all the unknown NMIs we may generate */
+	register_nmi_handler(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
+}
+
+static void cleanup_nmi_testsuite(void)
+{
+	unregister_nmi_handler(NMI_UNKNOWN, "nmi_selftest_unk");
+}
+
+static int test_nmi_ipi_callback(unsigned int val, struct pt_regs *regs)
+{
+        int cpu = raw_smp_processor_id();
+
+        if (cpumask_test_and_clear_cpu(cpu, to_cpumask(nmi_ipi_mask)))
+                return NMI_HANDLED;
+
+        return NMI_DONE;
+}
+
+static void test_nmi_ipi(struct cpumask *mask)
+{
+	unsigned long timeout;
+
+	if (register_nmi_handler(NMI_LOCAL, test_nmi_ipi_callback,
+				 NMI_FLAG_FIRST, "nmi_selftest")) {
+		nmi_fail = FAILURE;
+		return;
+	}
+
+	/* sync above data before sending NMI */
+	wmb();
+
+	apic->send_IPI_mask(mask, NMI_VECTOR);
+
+	/* Don't wait longer than a second */
+	timeout = USEC_PER_SEC;
+	while (!cpumask_empty(mask) && timeout--)
+	        udelay(1);
+
+	/* What happens if we timeout, do we still unregister?? */
+	unregister_nmi_handler(NMI_LOCAL, "nmi_selftest");
+
+	if (!timeout)
+		nmi_fail = TIMEOUT;
+	return;
+}
+
+static void remote_ipi(void)
+{
+	cpumask_copy(to_cpumask(nmi_ipi_mask), cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), to_cpumask(nmi_ipi_mask));
+	if (!cpumask_empty(to_cpumask(nmi_ipi_mask)))
+		test_nmi_ipi(to_cpumask(nmi_ipi_mask));
+}
+
+static void local_ipi(void)
+{
+	cpumask_clear(to_cpumask(nmi_ipi_mask));
+	cpumask_set_cpu(smp_processor_id(), to_cpumask(nmi_ipi_mask));
+	test_nmi_ipi(to_cpumask(nmi_ipi_mask));
+}
+
+static void reset_nmi(void)
+{
+	nmi_fail = 0;
+}
+
+static void dotest(void (*testcase_fn)(void), int expected)
+{
+	testcase_fn();
+	/*
+	 * Filter out expected failures:
+	 */
+	if (nmi_fail != expected) {
+		unexpected_testcase_failures++;
+
+		if (nmi_fail == FAILURE)
+			printk("FAILED |");
+		else if (nmi_fail == TIMEOUT)
+			printk("TIMEOUT|");
+		else
+			printk("ERROR  |");
+		dump_stack();
+	} else {
+		testcase_successes++;
+		printk("  ok  |");
+	}
+	testcase_total++;
+
+	reset_nmi();
+}
+
+static inline void print_testname(const char *testname)
+{
+	printk("%12s:", testname);
+}
+
+void nmi_selftest(void)
+{
+	init_nmi_testsuite();
+
+        /*
+	 * Run the testsuite:
+	 */
+	printk("----------------\n");
+	printk("| NMI testsuite:\n");
+	printk("--------------------\n");
+
+	print_testname("remote IPI");
+	dotest(remote_ipi, SUCCESS);
+	printk("\n");
+	print_testname("local IPI");
+	dotest(local_ipi, SUCCESS);
+	printk("\n");
+
+	cleanup_nmi_testsuite();
+
+	if (unexpected_testcase_failures) {
+		printk("--------------------\n");
+		printk("BUG: %3d unexpected failures (out of %3d) - debugging disabled! |\n",
+			unexpected_testcase_failures, testcase_total);
+		printk("-----------------------------------------------------------------\n");
+	} else if (expected_testcase_failures && testcase_successes) {
+		printk("--------------------\n");
+		printk("%3d out of %3d testcases failed, as expected. |\n",
+			expected_testcase_failures, testcase_total);
+		printk("----------------------------------------------------\n");
+	} else if (expected_testcase_failures && !testcase_successes) {
+		printk("--------------------\n");
+		printk("All %3d testcases failed, as expected. |\n",
+			expected_testcase_failures);
+		printk("----------------------------------------\n");
+	} else {
+		printk("--------------------\n");
+		printk("Good, all %3d testcases passed! |\n",
+			testcase_successes);
+		printk("---------------------------------\n");
+	}
+}
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 80dc793b3f63..1c4d769e21ea 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -45,6 +45,15 @@ int iommu_detected __read_mostly = 0;
  */
 int iommu_pass_through __read_mostly;
 
+/*
+ * Group multi-function PCI devices into a single device-group for the
+ * iommu_device_group interface.  This tells the iommu driver to pretend
+ * it cannot distinguish between functions of a device, exposing only one
+ * group for the device.  Useful for disallowing use of individual PCI
+ * functions from userspace drivers.
+ */
+int iommu_group_mf __read_mostly;
+
 extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
 
 /* Dummy device used for NULL arguments (normally ISA). */
@@ -169,6 +178,8 @@ static __init int iommu_setup(char *p)
 #endif
 		if (!strncmp(p, "pt", 2))
 			iommu_pass_through = 1;
+		if (!strncmp(p, "group_mf", 8))
+			iommu_group_mf = 1;
 
 		gart_parse_options(p);
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d05444ac2aea..d7d5099fe874 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -749,12 +749,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 #ifdef CONFIG_EFI
 	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
-#ifdef CONFIG_X86_32
-		     "EL32",
-#else
-		     "EL64",
-#endif
-	 4)) {
+		     EFI_LOADER_SIGNATURE, 4)) {
 		efi_enabled = 1;
 		efi_memblock_x86_reserve_range();
 	}
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 54ddaeb221c1..46a01bdc27e2 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -682,7 +682,6 @@ static int
 handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
 		struct pt_regs *regs)
 {
-	sigset_t blocked;
 	int ret;
 
 	/* Are we from a system call? */
@@ -733,10 +732,7 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
 	 */
 	regs->flags &= ~X86_EFLAGS_TF;
 
-	sigorsets(&blocked, &current->blocked, &ka->sa.sa_mask);
-	if (!(ka->sa.sa_flags & SA_NODEFER))
-		sigaddset(&blocked, sig);
-	set_current_blocked(&blocked);
+	block_sigmask(ka, sig);
 
 	tracehook_signal_handler(sig, info, ka, regs,
 				 test_thread_flag(TIF_SINGLESTEP));
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 16204dc15484..66c74f481cab 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -29,6 +29,7 @@
 #include <asm/mmu_context.h>
 #include <asm/proto.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
 /*
  *	Some notes on x86 processor bugs affecting SMP operation:
  *
@@ -148,6 +149,60 @@ void native_send_call_func_ipi(const struct cpumask *mask)
 	free_cpumask_var(allbutself);
 }
 
+static atomic_t stopping_cpu = ATOMIC_INIT(-1);
+
+static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
+{
+	/* We are registered on stopping cpu too, avoid spurious NMI */
+	if (raw_smp_processor_id() == atomic_read(&stopping_cpu))
+		return NMI_HANDLED;
+
+	stop_this_cpu(NULL);
+
+	return NMI_HANDLED;
+}
+
+static void native_nmi_stop_other_cpus(int wait)
+{
+	unsigned long flags;
+	unsigned long timeout;
+
+	if (reboot_force)
+		return;
+
+	/*
+	 * Use an own vector here because smp_call_function
+	 * does lots of things not suitable in a panic situation.
+	 */
+	if (num_online_cpus() > 1) {
+		/* did someone beat us here? */
+		if (atomic_cmpxchg(&stopping_cpu, -1, safe_smp_processor_id()) != -1)
+			return;
+
+		if (register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback,
+					 NMI_FLAG_FIRST, "smp_stop"))
+			/* Note: we ignore failures here */
+			return;
+
+		/* sync above data before sending NMI */
+		wmb();
+
+		apic->send_IPI_allbutself(NMI_VECTOR);
+
+		/*
+		 * Don't wait longer than a second if the caller
+		 * didn't ask us to wait.
+		 */
+		timeout = USEC_PER_SEC;
+		while (num_online_cpus() > 1 && (wait || timeout--))
+			udelay(1);
+	}
+
+	local_irq_save(flags);
+	disable_local_APIC();
+	local_irq_restore(flags);
+}
+
 /*
  * this function calls the 'stop' function on all other CPUs in the system.
  */
@@ -160,7 +215,7 @@ asmlinkage void smp_reboot_interrupt(void)
 	irq_exit();
 }
 
-static void native_stop_other_cpus(int wait)
+static void native_irq_stop_other_cpus(int wait)
 {
 	unsigned long flags;
 	unsigned long timeout;
@@ -194,6 +249,11 @@ static void native_stop_other_cpus(int wait)
 	local_irq_restore(flags);
 }
 
+static void native_smp_disable_nmi_ipi(void)
+{
+	smp_ops.stop_other_cpus = native_irq_stop_other_cpus;
+}
+
 /*
  * Reschedule call back.
  */
@@ -225,12 +285,20 @@ void smp_call_function_single_interrupt(struct pt_regs *regs)
 	irq_exit();
 }
 
+static int __init nonmi_ipi_setup(char *str)
+{
+        native_smp_disable_nmi_ipi();
+        return 1;
+}
+
+__setup("nonmi_ipi", nonmi_ipi_setup);
+
 struct smp_ops smp_ops = {
 	.smp_prepare_boot_cpu	= native_smp_prepare_boot_cpu,
 	.smp_prepare_cpus	= native_smp_prepare_cpus,
 	.smp_cpus_done		= native_smp_cpus_done,
 
-	.stop_other_cpus	= native_stop_other_cpus,
+	.stop_other_cpus	= native_nmi_stop_other_cpus,
 	.smp_send_reschedule	= native_smp_send_reschedule,
 
 	.cpu_up			= native_cpu_up,
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index e38e21754eea..66d250c00d11 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -207,23 +207,29 @@ static void __cpuinit smp_callin(void)
 	 * Need to setup vector mappings before we enable interrupts.
 	 */
 	setup_vector_irq(smp_processor_id());
+
+	/*
+	 * Save our processor parameters. Note: this information
+	 * is needed for clock calibration.
+	 */
+	smp_store_cpu_info(cpuid);
+
 	/*
 	 * Get our bogomips.
+	 * Update loops_per_jiffy in cpu_data. Previous call to
+	 * smp_store_cpu_info() stored a value that is close but not as
+	 * accurate as the value just calculated.
 	 *
 	 * Need to enable IRQs because it can take longer and then
 	 * the NMI watchdog might kill us.
 	 */
 	local_irq_enable();
 	calibrate_delay();
+	cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy;
 	local_irq_disable();
 	pr_debug("Stack at about %p\n", &cpuid);
 
 	/*
-	 * Save our processor parameters
-	 */
-	smp_store_cpu_info(cpuid);
-
-	/*
 	 * This must be done before setting cpu_online_mask
 	 * or calling notify_cpu_starting.
 	 */
@@ -1143,6 +1149,7 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 {
 	pr_debug("Boot done.\n");
 
+	nmi_selftest();
 	impress_friends();
 #ifdef CONFIG_X86_IO_APIC
 	setup_ioapic_dest();
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 2c9cf0fd78f5..c0dd5b603749 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -995,3 +995,23 @@ void __init tsc_init(void)
 	check_system_tsc_reliable();
 }
 
+#ifdef CONFIG_SMP
+/*
+ * If we have a constant TSC and are using the TSC for the delay loop,
+ * we can skip clock calibration if another cpu in the same socket has already
+ * been calibrated. This assumes that CONSTANT_TSC applies to all
+ * cpus in the socket - this should be a safe assumption.
+ */
+unsigned long __cpuinit calibrate_delay_is_known(void)
+{
+	int i, cpu = smp_processor_id();
+
+	if (!tsc_disabled && !cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC))
+		return 0;
+
+	for_each_online_cpu(i)
+		if (cpu_data(i).phys_proc_id == cpu_data(cpu).phys_proc_id)
+			return cpu_data(i).loops_per_jiffy;
+	return 0;
+}
+#endif
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 91f83e21b989..947a06ccc673 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -115,4 +115,5 @@ struct x86_msi_ops x86_msi = {
 	.setup_msi_irqs = native_setup_msi_irqs,
 	.teardown_msi_irq = native_teardown_msi_irq,
 	.teardown_msi_irqs = default_teardown_msi_irqs,
+	.restore_msi_irqs = default_restore_msi_irqs,
 };