18 files changed, 81 insertions, 20 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c9086e6307a5..df9e885eee14 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -277,6 +277,7 @@ config SPARSE_IRQ
 config NUMA_MIGRATE_IRQ_DESC
         bool "Move irq desc when changing irq smp_affinity"
         depends on SPARSE_IRQ && NUMA
+        depends on BROKEN
         default n
         ---help---
           This enables moving irq_desc to cpu/node that irq will use handled.
@@ -664,6 +665,7 @@ config MAXSMP
 
 config NR_CPUS
         int "Maximum number of CPUs" if SMP && !MAXSMP
+        range 2 8 if SMP && X86_32 && !X86_BIGSMP
         range 2 512 if SMP && !MAXSMP
         default "1" if !SMP
         default "4096" if MAXSMP
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index f05d8c91d9e5..8c86b72afdc2 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -153,7 +153,7 @@ endif
 
 boot := arch/x86/boot
 
-BOOT_TARGETS = bzlilo bzdisk fdimage fdimage144 fdimage288 isoimage install
+BOOT_TARGETS = bzlilo bzdisk fdimage fdimage144 fdimage288 isoimage
 
 PHONY += bzImage $(BOOT_TARGETS)
 
@@ -171,6 +171,10 @@ bzImage: vmlinux
 $(BOOT_TARGETS): vmlinux
         $(Q)$(MAKE) $(build)=$(boot) $@
 
+PHONY += install
+install:
+        $(Q)$(MAKE) $(build)=$(boot) $@
+
 PHONY += vdso_install
 vdso_install:
         $(Q)$(MAKE) $(build)=arch/x86/vdso $@
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 892b119dba6f..f44b49abca49 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -200,7 +200,7 @@ static inline void arch_fix_phys_package_id(int num, u32 slot)
 }
 
 struct pci_bus;
-void set_pci_bus_resources_arch_default(struct pci_bus *b);
+void x86_pci_root_bus_res_quirks(struct pci_bus *b);
 
 #ifdef CONFIG_SMP
 #define mc_capable()    (cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index a2789e42e162..30da617d18e4 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3670,12 +3670,14 @@ int arch_setup_hpet_msi(unsigned int irq)
 {
         int ret;
         struct msi_msg msg;
+        struct irq_desc *desc = irq_to_desc(irq);
 
         ret = msi_compose_msg(NULL, irq, &msg);
         if (ret < 0)
                 return ret;
 
         hpet_msi_write(irq, &msg);
+        desc->status |= IRQ_MOVE_PCNTXT;
         set_irq_chip_and_handler_name(irq, &hpet_msi_type, handle_edge_irq,
                 "edge");
 
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index d6bd62407152..ce4fbfa315a1 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -138,7 +138,7 @@ int __init check_nmi_watchdog(void)
         if (!prev_nmi_count)
                 goto error;
 
-        alloc_cpumask_var(&backtrace_mask, GFP_KERNEL);
+        alloc_cpumask_var(&backtrace_mask, GFP_KERNEL|__GFP_ZERO);
         printk(KERN_INFO "Testing NMI watchdog ... ");
 
 #ifdef CONFIG_SMP
@@ -414,7 +414,8 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
                 touched = 1;
         }
 
-        if (cpumask_test_cpu(cpu, backtrace_mask)) {
+        /* We can be called before check_nmi_watchdog, hence NULL check. */
+        if (backtrace_mask != NULL && cpumask_test_cpu(cpu, backtrace_mask)) {
                 static DEFINE_SPINLOCK(lock);   /* Serialise the printks */
 
                 spin_lock(&lock);
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index de1a50af807b..2bda69352976 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -19,6 +19,7 @@
 #include <linux/timer.h>
 #include <linux/cpu.h>
 #include <linux/init.h>
+#include <linux/io.h>
 
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/uv_hub.h>
@@ -34,6 +35,17 @@ DEFINE_PER_CPU(int, x2apic_extra_bits);
 
 static enum uv_system_type uv_system_type;
 
+static int early_get_nodeid(void)
+{
+        union uvh_node_id_u node_id;
+        unsigned long *mmr;
+
+        mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_NODE_ID, sizeof(*mmr));
+        node_id.v = *mmr;
+        early_iounmap(mmr, sizeof(*mmr));
+        return node_id.s.node_id;
+}
+
 static int uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
         if (!strcmp(oem_id, "SGI")) {
@@ -42,6 +54,8 @@ static int uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
                 else if (!strcmp(oem_table_id, "UVX"))
                         uv_system_type = UV_X2APIC;
                 else if (!strcmp(oem_table_id, "UVH")) {
+                        __get_cpu_var(x2apic_extra_bits) =
+                                early_get_nodeid() << (UV_APIC_PNODE_SHIFT - 1);
                         uv_system_type = UV_NON_UNIQUE_APIC;
                         return 1;
                 }
@@ -638,6 +652,7 @@ void __init uv_system_init(void)
                 if (uv_node_to_blade[nid] >= 0)
                         continue;
                 paddr = node_start_pfn(nid) << PAGE_SHIFT;
+                paddr = uv_soc_phys_ram_to_gpa(paddr);
                 pnode = (paddr >> m_val) & pnode_mask;
                 blade = boot_pnode_to_blade(pnode);
                 uv_node_to_blade[nid] = blade;
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index a331ec38af9e..38946c6e8433 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1410,7 +1410,10 @@ ENTRY(paranoid_exit)
 paranoid_swapgs:
         TRACE_IRQS_IRETQ 0
         SWAPGS_UNSAFE_STACK
+        RESTORE_ALL 8
+        jmp irq_return
 paranoid_restore:
+        TRACE_IRQS_IRETQ 0
         RESTORE_ALL 8
         jmp irq_return
 paranoid_userspace:
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 3f0019e0a229..81408b93f887 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -236,6 +236,10 @@ static void hpet_stop_counter(void)
         unsigned long cfg = hpet_readl(HPET_CFG);
         cfg &= ~HPET_CFG_ENABLE;
         hpet_writel(cfg, HPET_CFG);
+}
+
+static void hpet_reset_counter(void)
+{
         hpet_writel(0, HPET_COUNTER);
         hpet_writel(0, HPET_COUNTER + 4);
 }
@@ -250,6 +254,7 @@ static void hpet_start_counter(void)
 static void hpet_restart_counter(void)
 {
         hpet_stop_counter();
+        hpet_reset_counter();
         hpet_start_counter();
 }
 
@@ -309,7 +314,7 @@ static int hpet_setup_msi_irq(unsigned int irq);
 static void hpet_set_mode(enum clock_event_mode mode,
                           struct clock_event_device *evt, int timer)
 {
-        unsigned long cfg;
+        unsigned long cfg, cmp, now;
         uint64_t delta;
 
         switch (mode) {
@@ -317,12 +322,23 @@ static void hpet_set_mode(enum clock_event_mode mode,
                 hpet_stop_counter();
                 delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult;
                 delta >>= evt->shift;
+                now = hpet_readl(HPET_COUNTER);
+                cmp = now + (unsigned long) delta;
                 cfg = hpet_readl(HPET_Tn_CFG(timer));
                 /* Make sure we use edge triggered interrupts */
                 cfg &= ~HPET_TN_LEVEL;
                 cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
                        HPET_TN_SETVAL | HPET_TN_32BIT;
                 hpet_writel(cfg, HPET_Tn_CFG(timer));
+                hpet_writel(cmp, HPET_Tn_CMP(timer));
+                udelay(1);
+                /*
+                 * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL
+                 * cleared) to T0_CMP to set the period. The HPET_TN_SETVAL
+                 * bit is automatically cleared after the first write.
+                 * (See AMD-8111 HyperTransport I/O Hub Data Sheet,
+                 * Publication # 24674)
+                 */
                 hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer));
                 hpet_start_counter();
                 hpet_print_config();
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index e95022e4f5d5..7563b31b4f03 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -261,8 +261,6 @@ static void old_ich_force_enable_hpet_user(struct pci_dev *dev)
 {
         if (hpet_force_user)
                 old_ich_force_enable_hpet(dev);
-        else
-                hpet_print_force_info();
 }
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_1,
diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c
index 2ffb6c53326e..583f11d5c480 100644
--- a/arch/x86/kernel/uv_time.c
+++ b/arch/x86/kernel/uv_time.c
@@ -29,7 +29,7 @@
 
 #define RTC_NAME                "sgi_rtc"
 
-static cycle_t uv_read_rtc(void);
+static cycle_t uv_read_rtc(struct clocksource *cs);
 static int uv_rtc_next_event(unsigned long, struct clock_event_device *);
 static void uv_rtc_timer_setup(enum clock_event_mode,
                                 struct clock_event_device *);
@@ -123,7 +123,7 @@ static int uv_setup_intr(int cpu, u64 expires)
         /* Initialize comparator value */
         uv_write_global_mmr64(pnode, UVH_INT_CMPB, expires);
 
-        return (expires < uv_read_rtc() && !uv_intr_pending(pnode));
+        return (expires < uv_read_rtc(NULL) && !uv_intr_pending(pnode));
 }
 
 /*
@@ -256,7 +256,7 @@ static int uv_rtc_unset_timer(int cpu)
 
         spin_lock_irqsave(&head->lock, flags);
 
-        if (head->next_cpu == bcpu && uv_read_rtc() >= *t)
+        if (head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t)
                 rc = 1;
 
         *t = ULLONG_MAX;
@@ -278,7 +278,7 @@ static int uv_rtc_unset_timer(int cpu)
 /*
  * Read the RTC.
  */
-static cycle_t uv_read_rtc(void)
+static cycle_t uv_read_rtc(struct clocksource *cs)
 {
         return (cycle_t)uv_read_local_mmr(UVH_RTC);
 }
@@ -291,7 +291,7 @@ static int uv_rtc_next_event(unsigned long delta,
 {
         int ced_cpu = cpumask_first(ced->cpumask);
 
-        return uv_rtc_set_timer(ced_cpu, delta + uv_read_rtc());
+        return uv_rtc_set_timer(ced_cpu, delta + uv_read_rtc(NULL));
 }
 
 /*
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 0a5b04aa98f1..c5ee17e8c6d9 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -89,7 +89,7 @@ int save_i387_xstate(void __user *buf)
 
         if (!used_math())
                 return 0;
-        clear_used_math(); /* trigger finit */
+
         if (task_thread_info(tsk)->status & TS_USEDFPU) {
                 /*
                  * Start with clearing the user buffer. This will present a
@@ -114,6 +114,8 @@ int save_i387_xstate(void __user *buf)
                         return -1;
         }
 
+        clear_used_math(); /* trigger finit */
+
         if (task_thread_info(tsk)->status & TS_XSAVE) {
                 struct _fpstate __user *fx = buf;
                 struct _xstate __user *x = buf;
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 3daefa04ace5..d2530062fe00 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -257,7 +257,7 @@ void resume_map_numa_kva(pgd_t *pgd_base)
 }
 #endif
 
-static unsigned long calculate_numa_remap_pages(void)
+static __init unsigned long calculate_numa_remap_pages(void)
 {
         int nid;
         unsigned long size, reserve_pages = 0;
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index d73aaa892371..2d05a12029dc 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -188,6 +188,9 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
         const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
         int nid;
 
+        if (!end)
+                return;
+
         start = roundup(start, ZONE_ALIGN);
 
         printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index c7d272b8574c..33c5fa57e43d 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -28,6 +28,7 @@ int acpi_numa __initdata;
 static struct acpi_table_slit *acpi_slit;
 
 static nodemask_t nodes_parsed __initdata;
+static nodemask_t cpu_nodes_parsed __initdata;
 static struct bootnode nodes[MAX_NUMNODES] __initdata;
 static struct bootnode nodes_add[MAX_NUMNODES];
 static int found_add_area __initdata;
@@ -141,6 +142,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 
         apic_id = pa->apic_id;
         apicid_to_node[apic_id] = node;
+        node_set(node, cpu_nodes_parsed);
         acpi_numa = 1;
         printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n",
                pxm, apic_id, node);
@@ -174,6 +176,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
         else
                 apic_id = pa->apic_id;
         apicid_to_node[apic_id] = node;
+        node_set(node, cpu_nodes_parsed);
         acpi_numa = 1;
         printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n",
                pxm, apic_id, node);
@@ -402,7 +405,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
                 return -1;
         }
 
-        node_possible_map = nodes_parsed;
+        /* Account for nodes with cpus and no memory */
+        nodes_or(node_possible_map, nodes_parsed, cpu_nodes_parsed);
 
         /* Finally register nodes */
         for_each_node_mask(i, node_possible_map)
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 9bb09823b362..f893d6a6e803 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -94,12 +94,16 @@ struct pci_root_info {
 static int pci_root_num;
 static struct pci_root_info pci_root_info[PCI_ROOT_NR];
 
-void set_pci_bus_resources_arch_default(struct pci_bus *b)
+void x86_pci_root_bus_res_quirks(struct pci_bus *b)
 {
         int i;
         int j;
         struct pci_root_info *info;
 
+        /* don't go for it if _CRS is used */
+        if (pci_probe & PCI_USE__CRS)
+                return;
+
         /* if only one root bus, don't need to anything */
         if (pci_root_num < 2)
                 return;
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 8c362b96b644..2202b6257b82 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -147,10 +147,13 @@ static void __devinit pcibios_fixup_device_resources(struct pci_dev *dev)
  *  are examined.
  */
 
-void __devinit  pcibios_fixup_bus(struct pci_bus *b)
+void __devinit pcibios_fixup_bus(struct pci_bus *b)
 {
         struct pci_dev *dev;
 
+        /* root bus? */
+        if (!b->parent)
+                x86_pci_root_bus_res_quirks(b);
         pci_read_bridge_bases(b);
         list_for_each_entry(dev, &b->devices, bus_list)
                 pcibios_fixup_device_resources(dev);
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index f1817f71e009..a85bef20a3b9 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -238,6 +238,10 @@ void __init pcibios_resource_survey(void)
  */
 fs_initcall(pcibios_assign_resources);
 
+void __weak x86_pci_root_bus_res_quirks(struct pci_bus *b)
+{
+}
+
 /*
  *  If we set up a device for bus mastering, we need to check the latency
  *  timer as certain crappy BIOSes forget to set it properly.
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 905bb526b133..5fa10bb9604f 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -375,7 +375,7 @@ static acpi_status __init check_mcfg_resource(struct acpi_resource *res,
                 if (!fixmem32)
                         return AE_OK;
                 if ((mcfg_res->start >= fixmem32->address) &&
-                    (mcfg_res->end < (fixmem32->address +
+                    (mcfg_res->end <= (fixmem32->address +
                                       fixmem32->address_length))) {
                         mcfg_res->flags = 1;
                         return AE_CTRL_TERMINATE;
@@ -392,7 +392,7 @@ static acpi_status __init check_mcfg_resource(struct acpi_resource *res,
                 return AE_OK;
 
         if ((mcfg_res->start >= address.minimum) &&
-            (mcfg_res->end < (address.minimum + address.address_length))) {
+            (mcfg_res->end <= (address.minimum + address.address_length))) {
                 mcfg_res->flags = 1;
                 return AE_CTRL_TERMINATE;
         }
@@ -439,7 +439,7 @@ static int __init is_mmconf_reserved(check_reserved_t is_reserved,
         u64 old_size = size;
         int valid = 0;
 
-        while (!is_reserved(addr, addr + size - 1, E820_RESERVED)) {
+        while (!is_reserved(addr, addr + size, E820_RESERVED)) {
                 size >>= 1;
                 if (size < (16UL<<20))
                         break;