Merge branch 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull smp hotplug cleanups from Thomas Gleixner: "This series is merily a cleanup of code copied around in arch/* and not changing any of the real cpu hotplug horrors yet. I wish I'd had something more substantial for 3.5, but I underestimated the lurking horror..." Fix up trivial conflicts in arch/{arm,sparc,x86}/Kconfig and arch/sparc/include/asm/thread_info_32.h * 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (79 commits) um: Remove leftover declaration of alloc_task_struct_node() task_allocator: Use config switches instead of magic defines sparc: Use common threadinfo allocator score: Use common threadinfo allocator sh-use-common-threadinfo-allocator mn10300: Use common threadinfo allocator powerpc: Use common threadinfo allocator mips: Use common threadinfo allocator hexagon: Use common threadinfo allocator m32r: Use common threadinfo allocator frv: Use common threadinfo allocator cris: Use common threadinfo allocator x86: Use common threadinfo allocator c6x: Use common threadinfo allocator fork: Provide kmemcache based thread_info allocator tile: Use common threadinfo allocator fork: Provide weak arch_release_[task_struct|thread_info] functions fork: Move thread info gfp flags to header fork: Remove the weak insanity sh: Remove cpu_idle_wait() ...
2012-05-21 19:43:57 -07:00
parent 226da0dbc8 203dacbdca
commit bf67f3a5c4
157 changed files with 415 additions and 1934 deletions
@@ -43,6 +43,7 @@ obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
 obj-$(CONFIG_SMP) += smp.o
+obj-$(CONFIG_SMP) += smpboot.o
 ifneq ($(CONFIG_SMP),y)
 obj-y += up.o
 endif
@@ -17,6 +17,8 @@
 #include <linux/gfp.h>
 #include <linux/suspend.h>

+#include "smpboot.h"
+
 #ifdef CONFIG_SMP
 /* Serializes the updates to cpu_online_mask, cpu_present_mask */
 static DEFINE_MUTEX(cpu_add_remove_lock);
@@ -295,11 +297,19 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
 	int ret, nr_calls = 0;
 	void *hcpu = (void *)(long)cpu;
 	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
+	struct task_struct *idle;

 	if (cpu_online(cpu) || !cpu_present(cpu))
 		return -EINVAL;

 	cpu_hotplug_begin();
+
+	idle = idle_thread_get(cpu);
+	if (IS_ERR(idle)) {
+		ret = PTR_ERR(idle);
+		goto out;
+	}
+
 	ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls);
 	if (ret) {
 		nr_calls--;
@@ -309,7 +319,7 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
 	}

 	/* Arch-specific enabling code. */
-	ret = __cpu_up(cpu);
+	ret = __cpu_up(cpu, idle);
 	if (ret != 0)
 		goto out_notify;
 	BUG_ON(!cpu_online(cpu));
@@ -320,6 +330,7 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
 out_notify:
 	if (ret != 0)
 		__cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL);
+out:
 	cpu_hotplug_done();

 	return ret;
@@ -112,32 +112,67 @@ int nr_processes(void)
 	return total;
 }

-#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
-# define alloc_task_struct_node(node)		\
-		kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node)
-# define free_task_struct(tsk)			\
-		kmem_cache_free(task_struct_cachep, (tsk))
+#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
 static struct kmem_cache *task_struct_cachep;
+
+static inline struct task_struct *alloc_task_struct_node(int node)
+{
+	return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node);
+}
+
+void __weak arch_release_task_struct(struct task_struct *tsk) { }
+
+static inline void free_task_struct(struct task_struct *tsk)
+{
+	arch_release_task_struct(tsk);
+	kmem_cache_free(task_struct_cachep, tsk);
+}
 #endif

-#ifndef __HAVE_ARCH_THREAD_INFO_ALLOCATOR
+#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
+void __weak arch_release_thread_info(struct thread_info *ti) { }
+
+/*
+ * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
+ * kmemcache based allocator.
+ */
+# if THREAD_SIZE >= PAGE_SIZE
 static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
 						  int node)
 {
-#ifdef CONFIG_DEBUG_STACK_USAGE
-	gfp_t mask = GFP_KERNEL | __GFP_ZERO;
-#else
-	gfp_t mask = GFP_KERNEL;
-#endif
-	struct page *page = alloc_pages_node(node, mask, THREAD_SIZE_ORDER);
+	struct page *page = alloc_pages_node(node, THREADINFO_GFP,
+					     THREAD_SIZE_ORDER);

 	return page ? page_address(page) : NULL;
 }

 static inline void free_thread_info(struct thread_info *ti)
 {
+	arch_release_thread_info(ti);
 	free_pages((unsigned long)ti, THREAD_SIZE_ORDER);
 }
+# else
+static struct kmem_cache *thread_info_cache;
+
+static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+						  int node)
+{
+	return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node);
+}
+
+static void free_thread_info(struct thread_info *ti)
+{
+	arch_release_thread_info(ti);
+	kmem_cache_free(thread_info_cache, ti);
+}
+
+void thread_info_cache_init(void)
+{
+	thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
+					      THREAD_SIZE, 0, NULL);
+	BUG_ON(thread_info_cache == NULL);
+}
+# endif
 #endif

 /* SLAB cache for signal_struct structures (tsk->signal) */
@@ -204,17 +239,11 @@ void __put_task_struct(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(__put_task_struct);

-/*
- * macro override instead of weak attribute alias, to workaround
- * gcc 4.1.0 and 4.1.1 bugs with weak attribute and empty functions.
- */
-#ifndef arch_task_cache_init
-#define arch_task_cache_init()
-#endif
+void __init __weak arch_task_cache_init(void) { }

 void __init fork_init(unsigned long mempages)
 {
-#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
+#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
 #ifndef ARCH_MIN_TASKALIGN
 #define ARCH_MIN_TASKALIGN	L1_CACHE_BYTES
 #endif
@@ -16,5 +16,3 @@ obj-$(CONFIG_SMP) += cpupri.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
-
-
@@ -83,6 +83,7 @@

 #include "sched.h"
 #include "../workqueue_sched.h"
+#include "../smpboot.h"

 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
@@ -7062,6 +7063,7 @@ void __init sched_init(void)
 	/* May be allocated at isolcpus cmdline parse time */
 	if (cpu_isolated_map == NULL)
 		zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+	idle_thread_set_boot_cpu();
 #endif
 	init_sched_fair_class();

@@ -13,6 +13,8 @@
 #include <linux/smp.h>
 #include <linux/cpu.h>

+#include "smpboot.h"
+
 #ifdef CONFIG_USE_GENERIC_SMP_HELPERS
 static struct {
 	struct list_head	queue;
@@ -669,6 +671,8 @@ void __init smp_init(void)
 {
 	unsigned int cpu;

+	idle_threads_init();
+
 	/* FIXME: This should be done in userspace --RR */
 	for_each_present_cpu(cpu) {
 		if (num_online_cpus() >= setup_max_cpus)
@@ -791,3 +795,26 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 	}
 }
 EXPORT_SYMBOL(on_each_cpu_cond);
+
+static void do_nothing(void *unused)
+{
+}
+
+/**
+ * kick_all_cpus_sync - Force all cpus out of idle
+ *
+ * Used to synchronize the update of pm_idle function pointer. It's
+ * called after the pointer is updated and returns after the dummy
+ * callback function has been executed on all cpus. The execution of
+ * the function can only happen on the remote cpus after they have
+ * left the idle function which had been called via pm_idle function
+ * pointer. So it's guaranteed that nothing uses the previous pointer
+ * anymore.
+ */
+void kick_all_cpus_sync(void)
+{
+	/* Make sure the change is visible before we kick the cpus */
+	smp_mb();
+	smp_call_function(do_nothing, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(kick_all_cpus_sync);
@@ -0,0 +1,62 @@
+/*
+ * Common SMP CPU bringup/teardown functions
+ */
+#include <linux/err.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/percpu.h>
+
+#include "smpboot.h"
+
+#ifdef CONFIG_GENERIC_SMP_IDLE_THREAD
+/*
+ * For the hotplug case we keep the task structs around and reuse
+ * them.
+ */
+static DEFINE_PER_CPU(struct task_struct *, idle_threads);
+
+struct task_struct * __cpuinit idle_thread_get(unsigned int cpu)
+{
+	struct task_struct *tsk = per_cpu(idle_threads, cpu);
+
+	if (!tsk)
+		return ERR_PTR(-ENOMEM);
+	init_idle(tsk, cpu);
+	return tsk;
+}
+
+void __init idle_thread_set_boot_cpu(void)
+{
+	per_cpu(idle_threads, smp_processor_id()) = current;
+}
+
+static inline void idle_init(unsigned int cpu)
+{
+	struct task_struct *tsk = per_cpu(idle_threads, cpu);
+
+	if (!tsk) {
+		tsk = fork_idle(cpu);
+		if (IS_ERR(tsk))
+			pr_err("SMP: fork_idle() failed for CPU %u\n", cpu);
+		else
+			per_cpu(idle_threads, cpu) = tsk;
+	}
+}
+
+/**
+ * idle_thread_init - Initialize the idle thread for a cpu
+ * @cpu:	The cpu for which the idle thread should be initialized
+ *
+ * Creates the thread if it does not exist.
+ */
+void __init idle_threads_init(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu != smp_processor_id())
+			idle_init(cpu);
+	}
+}
+#endif
@@ -0,0 +1,18 @@
+#ifndef SMPBOOT_H
+#define SMPBOOT_H
+
+struct task_struct;
+
+int smpboot_prepare(unsigned int cpu);
+
+#ifdef CONFIG_GENERIC_SMP_IDLE_THREAD
+struct task_struct *idle_thread_get(unsigned int cpu);
+void idle_thread_set_boot_cpu(void);
+void idle_threads_init(void);
+#else
+static inline struct task_struct *idle_thread_get(unsigned int cpu) { return NULL; }
+static inline void idle_thread_set_boot_cpu(void) { }
+static inline void idle_threads_init(void) { }
+#endif
+
+#endif