Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

10 files changed, 187 insertions, 83 deletions

diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c
index a75c829c2b02..6fe191c58084 100644
--- a/arch/x86_64/kernel/e820.c
+++ b/arch/x86_64/kernel/e820.c
@@ -278,7 +278,7 @@ e820_register_active_regions(int nid, unsigned long start_pfn,
                                                                 >> PAGE_SHIFT;
 
                 /* Skip map entries smaller than a page */
-                if (ei_startpfn > ei_endpfn)
+                if (ei_startpfn >= ei_endpfn)
                         continue;
 
                 /* Check if end_pfn_map should be updated */
@@ -594,7 +594,9 @@ static int __init parse_memmap_opt(char *p)
                  * size before original memory map is
                  * reset.
                  */
+                e820_register_active_regions(0, 0, -1UL);
                 saved_max_pfn = e820_end_of_ram();
+                remove_all_active_ranges();
 #endif
                 end_pfn_map = 0;
                 e820.nr_map = 0;
diff --git a/arch/x86_64/kernel/early-quirks.c b/arch/x86_64/kernel/early-quirks.c
index 2b1245d86258..68273bff58cc 100644
--- a/arch/x86_64/kernel/early-quirks.c
+++ b/arch/x86_64/kernel/early-quirks.c
@@ -45,7 +45,13 @@ static void nvidia_bugs(void)
         /*
          * All timer overrides on Nvidia are
          * wrong unless HPET is enabled.
+         * Unfortunately that's not true on many Asus boards.
+         * We don't know yet how to detect this automatically, but
+         * at least allow a command line override.
          */
+        if (acpi_use_timer_override)
+                return;
+
         nvidia_hpet_detected = 0;
         acpi_table_parse(ACPI_HPET, nvidia_hpet_check);
         if (nvidia_hpet_detected == 0) {
@@ -53,6 +59,8 @@ static void nvidia_bugs(void)
                 printk(KERN_INFO "Nvidia board "
                        "detected. Ignoring ACPI "
                        "timer override.\n");
+                printk(KERN_INFO "If you got timer trouble "
+                        "try acpi_use_timer_override\n");
         }
 #endif
         /* RED-PEN skip them on mptables too? */
diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c
index b000017e4b5d..14654e682411 100644
--- a/arch/x86_64/kernel/io_apic.c
+++ b/arch/x86_64/kernel/io_apic.c
@@ -63,7 +63,7 @@ int timer_over_8254 __initdata = 1;
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 
 static DEFINE_SPINLOCK(ioapic_lock);
-static DEFINE_SPINLOCK(vector_lock);
+DEFINE_SPINLOCK(vector_lock);
 
 /*
  * # of IRQ routing registers
@@ -88,6 +88,52 @@ static struct irq_pin_list {
         short apic, pin, next;
 } irq_2_pin[PIN_MAP_SIZE];
 
+struct io_apic {
+        unsigned int index;
+        unsigned int unused[3];
+        unsigned int data;
+};
+
+static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
+{
+        return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx)
+                + (mp_ioapics[idx].mpc_apicaddr & ~PAGE_MASK);
+}
+
+static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+{
+        struct io_apic __iomem *io_apic = io_apic_base(apic);
+        writel(reg, &io_apic->index);
+        return readl(&io_apic->data);
+}
+
+static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+{
+        struct io_apic __iomem *io_apic = io_apic_base(apic);
+        writel(reg, &io_apic->index);
+        writel(value, &io_apic->data);
+}
+
+/*
+ * Re-write a value: to be used for read-modify-write
+ * cycles where the read already set up the index register.
+ */
+static inline void io_apic_modify(unsigned int apic, unsigned int value)
+{
+        struct io_apic __iomem *io_apic = io_apic_base(apic);
+        writel(value, &io_apic->data);
+}
+
+/*
+ * Synchronize the IO-APIC and the CPU by doing
+ * a dummy read from the IO-APIC
+ */
+static inline void io_apic_sync(unsigned int apic)
+{
+        struct io_apic __iomem *io_apic = io_apic_base(apic);
+        readl(&io_apic->data);
+}
+
 #define __DO_ACTION(R, ACTION, FINAL)                                   \
                                                                         \
 {                                                                       \
@@ -126,12 +172,34 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin)
         return eu.entry;
 }
 
+/*
+ * When we write a new IO APIC routing entry, we need to write the high
+ * word first! If the mask bit in the low word is clear, we will enable
+ * the interrupt, and we need to make sure the entry is fully populated
+ * before that happens.
+ */
 static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
         unsigned long flags;
         union entry_union eu;
         eu.entry = e;
         spin_lock_irqsave(&ioapic_lock, flags);
+        io_apic_write(apic, 0x11 + 2*pin, eu.w2);
+        io_apic_write(apic, 0x10 + 2*pin, eu.w1);
+        spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+/*
+ * When we mask an IO APIC routing entry, we need to write the low
+ * word first, in order to set the mask bit before we change the
+ * high bits!
+ */
+static void ioapic_mask_entry(int apic, int pin)
+{
+        unsigned long flags;
+        union entry_union eu = { .entry.mask = 1 };
+
+        spin_lock_irqsave(&ioapic_lock, flags);
         io_apic_write(apic, 0x10 + 2*pin, eu.w1);
         io_apic_write(apic, 0x11 + 2*pin, eu.w2);
         spin_unlock_irqrestore(&ioapic_lock, flags);
@@ -256,9 +324,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
         /*
          * Disable it in the IO-APIC irq-routing table:
          */
-        memset(&entry, 0, sizeof(entry));
-        entry.mask = 1;
-        ioapic_write_entry(apic, pin, entry);
+        ioapic_mask_entry(apic, pin);
 }
 
 static void clear_IO_APIC (void)
@@ -612,15 +678,15 @@ static int __assign_irq_vector(int irq, cpumask_t mask, cpumask_t *result)
          * Also, we've got to be careful not to trash gate
          * 0x80, because int 0x80 is hm, kind of importantish. ;)
          */
-        static struct {
-                int vector;
-                int offset;
-        } pos[NR_CPUS] = { [ 0 ... NR_CPUS - 1] = {FIRST_DEVICE_VECTOR, 0} };
+        static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0;
         int old_vector = -1;
         int cpu;
 
         BUG_ON((unsigned)irq >= NR_IRQ_VECTORS);
 
+        /* Only try and allocate irqs on cpus that are present */
+        cpus_and(mask, mask, cpu_online_map);
+
         if (irq_vector[irq] > 0)
                 old_vector = irq_vector[irq];
         if (old_vector > 0) {
@@ -630,15 +696,15 @@ static int __assign_irq_vector(int irq, cpumask_t mask, cpumask_t *result)
         }
 
         for_each_cpu_mask(cpu, mask) {
-                cpumask_t domain;
-                int first, new_cpu;
+                cpumask_t domain, new_mask;
+                int new_cpu;
                 int vector, offset;
 
                 domain = vector_allocation_domain(cpu);
-                first = first_cpu(domain);
+                cpus_and(new_mask, domain, cpu_online_map);
 
-                vector = pos[first].vector;
-                offset = pos[first].offset;
+                vector = current_vector;
+                offset = current_offset;
 next:
                 vector += 8;
                 if (vector >= FIRST_SYSTEM_VECTOR) {
@@ -646,24 +712,24 @@ next:
                         offset = (offset + 1) % 8;
                         vector = FIRST_DEVICE_VECTOR + offset;
                 }
-                if (unlikely(pos[first].vector == vector))
+                if (unlikely(current_vector == vector))
                         continue;
                 if (vector == IA32_SYSCALL_VECTOR)
                         goto next;
-                for_each_cpu_mask(new_cpu, domain)
+                for_each_cpu_mask(new_cpu, new_mask)
                         if (per_cpu(vector_irq, new_cpu)[vector] != -1)
                                 goto next;
                 /* Found one! */
-                for_each_cpu_mask(new_cpu, domain) {
-                        pos[new_cpu].vector = vector;
-                        pos[new_cpu].offset = offset;
-                }
+                current_vector = vector;
+                current_offset = offset;
                 if (old_vector >= 0) {
+                        cpumask_t old_mask;
                         int old_cpu;
-                        for_each_cpu_mask(old_cpu, irq_domain[irq])
+                        cpus_and(old_mask, irq_domain[irq], cpu_online_map);
+                        for_each_cpu_mask(old_cpu, old_mask)
                                 per_cpu(vector_irq, old_cpu)[old_vector] = -1;
                 }
-                for_each_cpu_mask(new_cpu, domain)
+                for_each_cpu_mask(new_cpu, new_mask)
                         per_cpu(vector_irq, new_cpu)[vector] = irq;
                 irq_vector[irq] = vector;
                 irq_domain[irq] = domain;
@@ -684,6 +750,32 @@ static int assign_irq_vector(int irq, cpumask_t mask, cpumask_t *result)
         return vector;
 }
 
+void __setup_vector_irq(int cpu)
+{
+        /* Initialize vector_irq on a new cpu */
+        /* This function must be called with vector_lock held */
+        unsigned long flags;
+        int irq, vector;
+
+
+        /* Mark the inuse vectors */
+        for (irq = 0; irq < NR_IRQ_VECTORS; ++irq) {
+                if (!cpu_isset(cpu, irq_domain[irq]))
+                        continue;
+                vector = irq_vector[irq];
+                per_cpu(vector_irq, cpu)[vector] = irq;
+        }
+        /* Mark the free vectors */
+        for (vector = 0; vector < NR_VECTORS; ++vector) {
+                irq = per_cpu(vector_irq, cpu)[vector];
+                if (irq < 0)
+                        continue;
+                if (!cpu_isset(cpu, irq_domain[irq]))
+                        per_cpu(vector_irq, cpu)[vector] = -1;
+        }
+}
+
+
 extern void (*interrupt[NR_IRQS])(void);
 
 static struct irq_chip ioapic_chip;
@@ -698,9 +790,11 @@ static void ioapic_register_intr(int irq, int vector, unsigned long trigger)
                         trigger == IOAPIC_LEVEL)
                 set_irq_chip_and_handler_name(irq, &ioapic_chip,
                                               handle_fasteoi_irq, "fasteoi");
-        else
+        else {
+                irq_desc[irq].status |= IRQ_DELAYED_DISABLE;
                 set_irq_chip_and_handler_name(irq, &ioapic_chip,
                                               handle_edge_irq, "edge");
+        }
 }
 
 static void __init setup_IO_APIC_irqs(void)
@@ -1863,18 +1957,16 @@ void arch_teardown_msi_irq(unsigned int irq)
 
 static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
 {
-        u32 low, high;
-        low  = read_ht_irq_low(irq);
-        high = read_ht_irq_high(irq);
+        struct ht_irq_msg msg;
+        fetch_ht_irq_msg(irq, &msg);
 
-        low  &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK);
-        high &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
+        msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK);
+        msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
 
-        low  |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest);
-        high |= HT_IRQ_HIGH_DEST_ID(dest);
+        msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest);
+        msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest);
 
-        write_ht_irq_low(irq, low);
-        write_ht_irq_high(irq, high);
+        write_ht_irq_msg(irq, &msg);
 }
 
 static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
@@ -1895,7 +1987,7 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 
         dest = cpu_mask_to_apicid(tmp);
 
-        target_ht_irq(irq, dest, vector & 0xff);
+        target_ht_irq(irq, dest, vector);
         set_native_irq_info(irq, mask);
 }
 #endif
@@ -1918,14 +2010,15 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 
         vector = assign_irq_vector(irq, TARGET_CPUS, &tmp);
         if (vector >= 0) {
-                u32 low, high;
+                struct ht_irq_msg msg;
                 unsigned dest;
 
                 dest = cpu_mask_to_apicid(tmp);
 
-                high =  HT_IRQ_HIGH_DEST_ID(dest);
+                msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest);
 
-                low =   HT_IRQ_LOW_BASE |
+                msg.address_lo =
+                        HT_IRQ_LOW_BASE |
                         HT_IRQ_LOW_DEST_ID(dest) |
                         HT_IRQ_LOW_VECTOR(vector) |
                         ((INT_DEST_MODE == 0) ?
@@ -1934,10 +2027,10 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
                         HT_IRQ_LOW_RQEOI_EDGE |
                         ((INT_DELIVERY_MODE != dest_LowestPrio) ?
                                 HT_IRQ_LOW_MT_FIXED :
-                                HT_IRQ_LOW_MT_ARBITRATED);
+                                HT_IRQ_LOW_MT_ARBITRATED) |
+                        HT_IRQ_LOW_IRQ_MASKED;
 
-                write_ht_irq_low(irq, low);
-                write_ht_irq_high(irq, high);
+                write_ht_irq_msg(irq, &msg);
 
                 set_irq_chip_and_handler_name(irq, &ht_irq_chip,
                                               handle_edge_irq, "edge");
diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 49f7fac6229e..7451a4c43c16 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -88,9 +88,8 @@ void enter_idle(void)
 
 static void __exit_idle(void)
 {
-        if (read_pda(isidle) == 0)
+        if (test_and_clear_bit_pda(0, isidle) == 0)
                 return;
-        write_pda(isidle, 0);
         atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
 }
 
@@ -145,7 +144,7 @@ static void poll_idle (void)
 void cpu_idle_wait(void)
 {
         unsigned int cpu, this_cpu = get_cpu();
-        cpumask_t map;
+        cpumask_t map, tmp = current->cpus_allowed;
 
         set_cpus_allowed(current, cpumask_of_cpu(this_cpu));
         put_cpu();
@@ -168,6 +167,8 @@ void cpu_idle_wait(void)
                 }
                 cpus_and(map, map, cpu_online_map);
         } while (!cpus_empty(map));
+
+        set_cpus_allowed(current, tmp);
 }
 EXPORT_SYMBOL_GPL(cpu_idle_wait);
 
diff --git a/arch/x86_64/kernel/smp.c b/arch/x86_64/kernel/smp.c
index 4f67697f5036..9f74c883568c 100644
--- a/arch/x86_64/kernel/smp.c
+++ b/arch/x86_64/kernel/smp.c
@@ -376,9 +376,8 @@ int smp_call_function_single (int cpu, void (*func) (void *info), void *info,
         /* prevent preemption and reschedule on another processor */
         int me = get_cpu();
         if (cpu == me) {
-                WARN_ON(1);
                 put_cpu();
-                return -EBUSY;
+                return 0;
         }
         spin_lock_bh(&call_lock);
         __smp_call_function_single(cpu, func, info, nonatomic, wait);
diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c
index 7b7a6870288a..62c2e747af58 100644
--- a/arch/x86_64/kernel/smpboot.c
+++ b/arch/x86_64/kernel/smpboot.c
@@ -581,12 +581,16 @@ void __cpuinit start_secondary(void)
          * smp_call_function().
          */
         lock_ipi_call_lock();
+        spin_lock(&vector_lock);
 
+        /* Setup the per cpu irq handling data structures */
+        __setup_vector_irq(smp_processor_id());
         /*
          * Allow the master to continue.
          */
         cpu_set(smp_processor_id(), cpu_online_map);
         per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
+        spin_unlock(&vector_lock);
         unlock_ipi_call_lock();
 
         cpu_idle();
@@ -799,7 +803,6 @@ static int __cpuinit do_boot_cpu(int cpu, int apicid)
                                 cpu, node);
         }
 
-
         alternatives_smp_switch(1);
 
         c_idle.idle = get_idle_for_cpu(cpu);
@@ -1246,8 +1249,10 @@ int __cpu_disable(void)
         local_irq_disable();
         remove_siblinginfo(cpu);
 
+        spin_lock(&vector_lock);
         /* It's now safe to remove this processor from the online map */
         cpu_clear(cpu, cpu_online_map);
+        spin_unlock(&vector_lock);
         remove_cpu_from_maps();
         fixup_irqs(cpu_online_map);
         return 0;
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index 88722f11ca13..e3ef544d2cfb 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -876,15 +876,6 @@ static struct irqaction irq0 = {
         timer_interrupt, IRQF_DISABLED, CPU_MASK_NONE, "timer", NULL, NULL
 };
 
-static int __cpuinit
-time_cpu_notifier(struct notifier_block *nb, unsigned long action, void *hcpu)
-{
-        unsigned cpu = (unsigned long) hcpu;
-        if (action == CPU_ONLINE)
-                vsyscall_set_cpu(cpu);
-        return NOTIFY_DONE;
-}
-
 void __init time_init(void)
 {
         if (nohpet)
@@ -925,8 +916,6 @@ void __init time_init(void)
         vxtime.last_tsc = get_cycles_sync();
         set_cyc2ns_scale(cpu_khz);
         setup_irq(0, &irq0);
-        hotcpu_notifier(time_cpu_notifier, 0);
-        time_cpu_notifier(NULL, CPU_ONLINE, (void *)(long)smp_processor_id());
 
 #ifndef CONFIG_SMP
         time_init_gtod();
diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c
index 7819022a8db5..a153d0a01b72 100644
--- a/arch/x86_64/kernel/traps.c
+++ b/arch/x86_64/kernel/traps.c
@@ -290,6 +290,12 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long * s
                 if (tsk && tsk != current)
                         stack = (unsigned long *)tsk->thread.rsp;
         }
+        /*
+         * Align the stack pointer on word boundary, later loops
+         * rely on that (and corruption / debug info bugs can cause
+         * unaligned values here):
+         */
+        stack = (unsigned long *)((unsigned long)stack & ~(sizeof(long)-1));
 
         /*
          * Print function call entries within a stack. 'cond' is the
diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S
index 1283614c9b24..edb24aa714b4 100644
--- a/arch/x86_64/kernel/vmlinux.lds.S
+++ b/arch/x86_64/kernel/vmlinux.lds.S
@@ -175,13 +175,7 @@ SECTIONS
   __setup_end = .;
   __initcall_start = .;
   .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
-        *(.initcall1.init) 
-        *(.initcall2.init) 
-        *(.initcall3.init) 
-        *(.initcall4.init) 
-        *(.initcall5.init) 
-        *(.initcall6.init) 
-        *(.initcall7.init)
+        INITCALLS
   }
   __initcall_end = .;
   __con_initcall_start = .;
diff --git a/arch/x86_64/kernel/vsyscall.c b/arch/x86_64/kernel/vsyscall.c
index a98b460af6a1..92546c1526f1 100644
--- a/arch/x86_64/kernel/vsyscall.c
+++ b/arch/x86_64/kernel/vsyscall.c
@@ -27,6 +27,9 @@
 #include <linux/jiffies.h>
 #include <linux/sysctl.h>
 #include <linux/getcpu.h>
+#include <linux/cpu.h>
+#include <linux/smp.h>
+#include <linux/notifier.h>
 
 #include <asm/vsyscall.h>
 #include <asm/pgtable.h>
@@ -243,32 +246,17 @@ static ctl_table kernel_root_table2[] = {
 
 #endif
 
-static void __cpuinit write_rdtscp_cb(void *info)
-{
-        write_rdtscp_aux((unsigned long)info);
-}
-
-void __cpuinit vsyscall_set_cpu(int cpu)
+/* Assume __initcall executes before all user space. Hopefully kmod
+   doesn't violate that. We'll find out if it does. */
+static void __cpuinit vsyscall_set_cpu(int cpu)
 {
         unsigned long *d;
         unsigned long node = 0;
 #ifdef CONFIG_NUMA
         node = cpu_to_node[cpu];
 #endif
-        if (cpu_has(&cpu_data[cpu], X86_FEATURE_RDTSCP)) {
-                void *info = (void *)((node << 12) | cpu);
-                /* Can happen on preemptive kernel */
-                if (get_cpu() == cpu)
-                        write_rdtscp_cb(info);
-#ifdef CONFIG_SMP
-                else {
-                        /* the notifier is unfortunately not executed on the
-                           target CPU */
-                        smp_call_function_single(cpu,write_rdtscp_cb,info,0,1);
-                }
-#endif
-                put_cpu();
-        }
+        if (cpu_has(&cpu_data[cpu], X86_FEATURE_RDTSCP))
+                write_rdtscp_aux((node << 12) | cpu);
 
         /* Store cpu number in limit so that it can be loaded quickly
            in user space in vgetcpu.
@@ -280,6 +268,23 @@ void __cpuinit vsyscall_set_cpu(int cpu)
         *d |= (node >> 4) << 48;
 }
 
+static void __cpuinit cpu_vsyscall_init(void *arg)
+{
+        /* preemption should be already off */
+        vsyscall_set_cpu(raw_smp_processor_id());
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int __cpuinit
+cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg)
+{
+        long cpu = (long)arg;
+        if (action == CPU_ONLINE)
+                smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 0, 1);
+        return NOTIFY_DONE;
+}
+#endif
+
 static void __init map_vsyscall(void)
 {
         extern char __vsyscall_0;
@@ -299,6 +304,8 @@ static int __init vsyscall_init(void)
 #ifdef CONFIG_SYSCTL
         register_sysctl_table(kernel_root_table2, 0);
 #endif
+        on_each_cpu(cpu_vsyscall_init, NULL, 0, 1);
+        hotcpu_notifier(cpu_vsyscall_notifier, 0);
         return 0;
 }