Merge branch 'cpus4096' into core/percpu

Conflicts:
	arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
	arch/x86/kernel/tlb_32.c

Merge it here because both the cpumask changes and the ongoing percpu
work is touching the TLB code. The percpu changes take precedence, as
they eliminate tlb_32.c altogether.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

5 files changed, 43 insertions, 34 deletions

diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index 32f3af1641c5..3193f4417e16 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -84,7 +84,7 @@ void build_cpu_to_node_map(void);
         .child                  = NULL,                 \
         .groups                 = NULL,                 \
         .min_interval           = 8,                    \
-        .max_interval           = 8*(min(num_online_cpus(), 32)), \
+        .max_interval           = 8*(min(num_online_cpus(), 32U)), \
         .busy_factor            = 64,                   \
         .imbalance_pct          = 125,                  \
         .cache_nice_tries       = 2,                    \
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index ffea1fe03a99..10022ed3a4b6 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -190,9 +190,20 @@ extern int __node_distance(int, int);
 
 #else /* !CONFIG_NUMA */
 
-#define numa_node_id()          0
-#define cpu_to_node(cpu)        0
-#define early_cpu_to_node(cpu)  0
+static inline int numa_node_id(void)
+{
+        return 0;
+}
+
+static inline int cpu_to_node(int cpu)
+{
+        return 0;
+}
+
+static inline int early_cpu_to_node(int cpu)
+{
+        return 0;
+}
 
 static inline const cpumask_t *cpumask_of_node(int node)
 {
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index 9ca12af6c876..1df341a528a1 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -1844,6 +1844,11 @@ void __cpuinit generic_processor_info(int apicid, int version)
         num_processors++;
         cpu = cpumask_next_zero(-1, cpu_present_mask);
 
+        if (version != apic_version[boot_cpu_physical_apicid])
+                WARN_ONCE(1,
+                        "ACPI: apic version mismatch, bootcpu: %x cpu %d: %x\n",
+                        apic_version[boot_cpu_physical_apicid], cpu, version);
+
         physid_set(apicid, phys_cpu_present_map);
         if (apicid == boot_cpu_physical_apicid) {
                 /*
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 8f3c95c7e61f..4b1c319d30c3 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -145,13 +145,14 @@ typedef union {
 
 struct drv_cmd {
         unsigned int type;
-        cpumask_var_t mask;
+        const struct cpumask *mask;
         drv_addr_union addr;
         u32 val;
 };
 
-static void do_drv_read(struct drv_cmd *cmd)
+static long do_drv_read(void *_cmd)
 {
+        struct drv_cmd *cmd = _cmd;
         u32 h;
 
         switch (cmd->type) {
@@ -166,10 +167,12 @@ static void do_drv_read(struct drv_cmd *cmd)
         default:
                 break;
         }
+        return 0;
 }
 
-static void do_drv_write(struct drv_cmd *cmd)
+static long do_drv_write(void *_cmd)
 {
+        struct drv_cmd *cmd = _cmd;
         u32 lo, hi;
 
         switch (cmd->type) {
@@ -186,30 +189,23 @@ static void do_drv_write(struct drv_cmd *cmd)
         default:
                 break;
         }
+        return 0;
 }
 
 static void drv_read(struct drv_cmd *cmd)
 {
-        cpumask_t saved_mask = current->cpus_allowed;
         cmd->val = 0;
 
-        set_cpus_allowed_ptr(current, cmd->mask);
-        do_drv_read(cmd);
-        set_cpus_allowed_ptr(current, &saved_mask);
+        work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd);
 }
 
 static void drv_write(struct drv_cmd *cmd)
 {
-        cpumask_t saved_mask = current->cpus_allowed;
         unsigned int i;
 
         for_each_cpu(i, cmd->mask) {
-                set_cpus_allowed_ptr(current, cpumask_of(i));
-                do_drv_write(cmd);
+                work_on_cpu(i, do_drv_write, cmd);
         }
-
-        set_cpus_allowed_ptr(current, &saved_mask);
-        return;
 }
 
 static u32 get_cur_val(const struct cpumask *mask)
@@ -235,6 +231,7 @@ static u32 get_cur_val(const struct cpumask *mask)
                 return 0;
         }
 
+        cmd.mask = mask;
         drv_read(&cmd);
 
         dprintk("get_cur_val = %u\n", cmd.val);
@@ -366,7 +363,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
         return freq;
 }
 
-static unsigned int check_freqs(const cpumask_t *mask, unsigned int freq,
+static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
                                 struct acpi_cpufreq_data *data)
 {
         unsigned int cur_freq;
@@ -401,9 +398,6 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
                 return -ENODEV;
         }
 
-        if (unlikely(!alloc_cpumask_var(&cmd.mask, GFP_KERNEL)))
-                return -ENOMEM;
-
         perf = data->acpi_data;
         result = cpufreq_frequency_table_target(policy,
                                                 data->freq_table,
@@ -448,9 +442,9 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 
         /* cpufreq holds the hotplug lock, so we are safe from here on */
         if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY)
-                cpumask_and(cmd.mask, cpu_online_mask, policy->cpus);
+                cmd.mask = policy->cpus;
         else
-                cpumask_copy(cmd.mask, cpumask_of(policy->cpu));
+                cmd.mask = cpumask_of(policy->cpu);
 
         freqs.old = perf->states[perf->state].core_frequency * 1000;
         freqs.new = data->freq_table[next_state].frequency;
@@ -477,7 +471,6 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
         perf->state = next_perf_state;
 
 out:
-        free_cpumask_var(cmd.mask);
         return result;
 }
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2f445833ae37..1f0c509b40d3 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -971,6 +971,8 @@ undo:
 }
 
 #ifdef CONFIG_SMP
+static struct workqueue_struct *work_on_cpu_wq __read_mostly;
+
 struct work_for_cpu {
         struct work_struct work;
         long (*fn)(void *);
@@ -991,8 +993,8 @@ static void do_work_for_cpu(struct work_struct *w)
  * @fn: the function to run
  * @arg: the function arg
  *
- * This will return -EINVAL in the cpu is not online, or the return value
- * of @fn otherwise.
+ * This will return the value @fn returns.
+ * It is up to the caller to ensure that the cpu doesn't go offline.
  */
 long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 {
@@ -1001,14 +1003,8 @@ long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
         INIT_WORK(&wfc.work, do_work_for_cpu);
         wfc.fn = fn;
         wfc.arg = arg;
-        get_online_cpus();
-        if (unlikely(!cpu_online(cpu)))
-                wfc.ret = -EINVAL;
-        else {
-                schedule_work_on(cpu, &wfc.work);
-                flush_work(&wfc.work);
-        }
-        put_online_cpus();
+        queue_work_on(cpu, work_on_cpu_wq, &wfc.work);
+        flush_work(&wfc.work);
 
         return wfc.ret;
 }
@@ -1025,4 +1021,8 @@ void __init init_workqueues(void)
         hotcpu_notifier(workqueue_cpu_callback, 0);
         keventd_wq = create_workqueue("events");
         BUG_ON(!keventd_wq);
+#ifdef CONFIG_SMP
+        work_on_cpu_wq = create_workqueue("work_on_cpu");
+        BUG_ON(!work_on_cpu_wq);
+#endif
 }