1 files changed, 133 insertions, 19 deletions

diff --git a/kernel/smp.c b/kernel/smp.c
index 9910744f0856..73a195193558 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -194,7 +194,7 @@ void generic_smp_call_function_interrupt(void)
          */
         list_for_each_entry_rcu(data, &call_function.queue, csd.list) {
                 int refs;
-                void (*func) (void *info);
+                smp_call_func_t func;
 
                 /*
                  * Since we walk the list without any locks, we might
@@ -214,17 +214,17 @@ void generic_smp_call_function_interrupt(void)
                 if (atomic_read(&data->refs) == 0)
                         continue;
 
-                func = data->csd.func;                  /* for later warn */
-                data->csd.func(data->csd.info);
+                func = data->csd.func;          /* save for later warn */
+                func(data->csd.info);
 
                 /*
-                 * If the cpu mask is not still set then it enabled interrupts,
-                 * we took another smp interrupt, and executed the function
-                 * twice on this cpu.  In theory that copy decremented refs.
+                 * If the cpu mask is not still set then func enabled
+                 * interrupts (BUG), and this cpu took another smp call
+                 * function interrupt and executed func(info) twice
+                 * on this cpu.  That nested execution decremented refs.
                  */
                 if (!cpumask_test_and_clear_cpu(cpu, data->cpumask)) {
-                        WARN(1, "%pS enabled interrupts and double executed\n",
-                             func);
+                        WARN(1, "%pf enabled interrupts and double executed\n", func);
                         continue;
                 }
 
@@ -450,7 +450,7 @@ void smp_call_function_many(const struct cpumask *mask,
 {
         struct call_function_data *data;
         unsigned long flags;
-        int cpu, next_cpu, this_cpu = smp_processor_id();
+        int refs, cpu, next_cpu, this_cpu = smp_processor_id();
 
         /*
          * Can deadlock when called with interrupts disabled.
@@ -461,7 +461,7 @@ void smp_call_function_many(const struct cpumask *mask,
         WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
                      && !oops_in_progress && !early_boot_irqs_disabled);
 
-        /* So, what's a CPU they want? Ignoring this one. */
+        /* Try to fastpath.  So, what's a CPU they want? Ignoring this one. */
         cpu = cpumask_first_and(mask, cpu_online_mask);
         if (cpu == this_cpu)
                 cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
@@ -483,22 +483,49 @@ void smp_call_function_many(const struct cpumask *mask,
 
         data = &__get_cpu_var(cfd_data);
         csd_lock(&data->csd);
+
+        /* This BUG_ON verifies our reuse assertions and can be removed */
         BUG_ON(atomic_read(&data->refs) || !cpumask_empty(data->cpumask));
 
+        /*
+         * The global call function queue list add and delete are protected
+         * by a lock, but the list is traversed without any lock, relying
+         * on the rcu list add and delete to allow safe concurrent traversal.
+         * We reuse the call function data without waiting for any grace
+         * period after some other cpu removes it from the global queue.
+         * This means a cpu might find our data block as it is being
+         * filled out.
+         *
+         * We hold off the interrupt handler on the other cpu by
+         * ordering our writes to the cpu mask vs our setting of the
+         * refs counter.  We assert only the cpu owning the data block
+         * will set a bit in cpumask, and each bit will only be cleared
+         * by the subject cpu.  Each cpu must first find its bit is
+         * set and then check that refs is set indicating the element is
+         * ready to be processed, otherwise it must skip the entry.
+         *
+         * On the previous iteration refs was set to 0 by another cpu.
+         * To avoid the use of transitivity, set the counter to 0 here
+         * so the wmb will pair with the rmb in the interrupt handler.
+         */
+        atomic_set(&data->refs, 0);     /* convert 3rd to 1st party write */
+
         data->csd.func = func;
         data->csd.info = info;
-        cpumask_and(data->cpumask, mask, cpu_online_mask);
-        cpumask_clear_cpu(this_cpu, data->cpumask);
 
-        /*
-         * To ensure the interrupt handler gets an complete view
-         * we order the cpumask and refs writes and order the read
-         * of them in the interrupt handler.  In addition we may
-         * only clear our own cpu bit from the mask.
-         */
+        /* Ensure 0 refs is visible before mask.  Also orders func and info */
         smp_wmb();
 
-        atomic_set(&data->refs, cpumask_weight(data->cpumask));
+        /* We rely on the "and" being processed before the store */
+        cpumask_and(data->cpumask, mask, cpu_online_mask);
+        cpumask_clear_cpu(this_cpu, data->cpumask);
+        refs = cpumask_weight(data->cpumask);
+
+        /* Some callers race with other cpus changing the passed mask */
+        if (unlikely(!refs)) {
+                csd_unlock(&data->csd);
+                return;
+        }
 
         raw_spin_lock_irqsave(&call_function.lock, flags);
         /*
@@ -507,6 +534,12 @@ void smp_call_function_many(const struct cpumask *mask,
          * will not miss any other list entries:
          */
         list_add_rcu(&data->csd.list, &call_function.queue);
+        /*
+         * We rely on the wmb() in list_add_rcu to complete our writes
+         * to the cpumask before this write to refs, which indicates
+         * data is on the list and is ready to be processed.
+         */
+        atomic_set(&data->refs, refs);
         raw_spin_unlock_irqrestore(&call_function.lock, flags);
 
         /*
@@ -571,6 +604,87 @@ void ipi_call_unlock_irq(void)
 }
 #endif /* USE_GENERIC_SMP_HELPERS */
 
+/* Setup configured maximum number of CPUs to activate */
+unsigned int setup_max_cpus = NR_CPUS;
+EXPORT_SYMBOL(setup_max_cpus);
+
+
+/*
+ * Setup routine for controlling SMP activation
+ *
+ * Command-line option of "nosmp" or "maxcpus=0" will disable SMP
+ * activation entirely (the MPS table probe still happens, though).
+ *
+ * Command-line option of "maxcpus=<NUM>", where <NUM> is an integer
+ * greater than 0, limits the maximum number of CPUs activated in
+ * SMP mode to <NUM>.
+ */
+
+void __weak arch_disable_smp_support(void) { }
+
+static int __init nosmp(char *str)
+{
+        setup_max_cpus = 0;
+        arch_disable_smp_support();
+
+        return 0;
+}
+
+early_param("nosmp", nosmp);
+
+/* this is hard limit */
+static int __init nrcpus(char *str)
+{
+        int nr_cpus;
+
+        get_option(&str, &nr_cpus);
+        if (nr_cpus > 0 && nr_cpus < nr_cpu_ids)
+                nr_cpu_ids = nr_cpus;
+
+        return 0;
+}
+
+early_param("nr_cpus", nrcpus);
+
+static int __init maxcpus(char *str)
+{
+        get_option(&str, &setup_max_cpus);
+        if (setup_max_cpus == 0)
+                arch_disable_smp_support();
+
+        return 0;
+}
+
+early_param("maxcpus", maxcpus);
+
+/* Setup number of possible processor ids */
+int nr_cpu_ids __read_mostly = NR_CPUS;
+EXPORT_SYMBOL(nr_cpu_ids);
+
+/* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */
+void __init setup_nr_cpu_ids(void)
+{
+        nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
+}
+
+/* Called by boot processor to activate the rest. */
+void __init smp_init(void)
+{
+        unsigned int cpu;
+
+        /* FIXME: This should be done in userspace --RR */
+        for_each_present_cpu(cpu) {
+                if (num_online_cpus() >= setup_max_cpus)
+                        break;
+                if (!cpu_online(cpu))
+                        cpu_up(cpu);
+        }
+
+        /* Any cleanup work */
+        printk(KERN_INFO "Brought up %ld CPUs\n", (long)num_online_cpus());
+        smp_cpus_done(setup_max_cpus);
+}
+
 /*
  * Call a function on all processors.  May be used during early boot while
  * early_boot_irqs_disabled is set.  Use local_irq_save/restore() instead