1 files changed, 127 insertions, 113 deletions

diff --git a/kernel/profile.c b/kernel/profile.c
index 3b7a1b05512..54bf5ba2642 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -8,12 +8,13 @@
  *  Scheduler profiling support, Arjan van de Ven and Ingo Molnar,
  *	Red Hat, July 2004
  *  Consolidation of architecture support code for profiling,
- *	William Irwin, Oracle, July 2004
+ *	Nadia Yvette Chambers, Oracle, July 2004
  *  Amortized hit count accounting via per-cpu open-addressed hashtables
- *	to resolve timer interrupt livelocks, William Irwin, Oracle, 2004
+ *	to resolve timer interrupt livelocks, Nadia Yvette Chambers,
+ *	Oracle, 2004
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/profile.h>
 #include <linux/bootmem.h>
 #include <linux/notifier.h>
@@ -22,8 +23,9 @@
 #include <linux/cpu.h>
 #include <linux/highmem.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <asm/sections.h>
-#include <asm/semaphore.h>
 #include <asm/irq_regs.h>
 #include <asm/ptrace.h>
 
@@ -35,27 +37,24 @@ struct profile_hit {
 #define NR_PROFILE_HIT		(PAGE_SIZE/sizeof(struct profile_hit))
 #define NR_PROFILE_GRP		(NR_PROFILE_HIT/PROFILE_GRPSZ)
 
-/* Oprofile timer tick hook */
-static int (*timer_hook)(struct pt_regs *) __read_mostly;
-
 static atomic_t *prof_buffer;
 static unsigned long prof_len, prof_shift;
 
 int prof_on __read_mostly;
 EXPORT_SYMBOL_GPL(prof_on);
 
-static cpumask_t prof_cpu_mask = CPU_MASK_ALL;
+static cpumask_var_t prof_cpu_mask;
 #ifdef CONFIG_SMP
 static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits);
 static DEFINE_PER_CPU(int, cpu_profile_flip);
 static DEFINE_MUTEX(profile_flip_mutex);
 #endif /* CONFIG_SMP */
 
-static int __init profile_setup(char *str)
+int profile_setup(char *str)
 {
-	static char __initdata schedstr[] = "schedule";
-	static char __initdata sleepstr[] = "sleep";
-	static char __initdata kvmstr[] = "kvm";
+	static const char schedstr[] = "schedule";
+	static const char sleepstr[] = "sleep";
+	static const char kvmstr[] = "kvm";
 	int par;
 
 	if (!strncmp(str, sleepstr, strlen(sleepstr))) {
@@ -65,12 +64,10 @@ static int __init profile_setup(char *str)
 			str += strlen(sleepstr) + 1;
 		if (get_option(&str, &par))
 			prof_shift = par;
-		printk(KERN_INFO
-			"kernel sleep profiling enabled (shift: %ld)\n",
+		pr_info("kernel sleep profiling enabled (shift: %ld)\n",
 			prof_shift);
 #else
-		printk(KERN_WARNING
-			"kernel sleep profiling requires CONFIG_SCHEDSTATS\n");
+		pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n");
 #endif /* CONFIG_SCHEDSTATS */
 	} else if (!strncmp(str, schedstr, strlen(schedstr))) {
 		prof_on = SCHED_PROFILING;
@@ -78,8 +75,7 @@ static int __init profile_setup(char *str)
 			str += strlen(schedstr) + 1;
 		if (get_option(&str, &par))
 			prof_shift = par;
-		printk(KERN_INFO
-			"kernel schedule profiling enabled (shift: %ld)\n",
+		pr_info("kernel schedule profiling enabled (shift: %ld)\n",
 			prof_shift);
 	} else if (!strncmp(str, kvmstr, strlen(kvmstr))) {
 		prof_on = KVM_PROFILING;
@@ -87,13 +83,12 @@ static int __init profile_setup(char *str)
 			str += strlen(kvmstr) + 1;
 		if (get_option(&str, &par))
 			prof_shift = par;
-		printk(KERN_INFO
-			"kernel KVM profiling enabled (shift: %ld)\n",
+		pr_info("kernel KVM profiling enabled (shift: %ld)\n",
 			prof_shift);
 	} else if (get_option(&str, &par)) {
 		prof_shift = par;
 		prof_on = CPU_PROFILING;
-		printk(KERN_INFO "kernel profiling enabled (shift: %ld)\n",
+		pr_info("kernel profiling enabled (shift: %ld)\n",
 			prof_shift);
 	}
 	return 1;
@@ -101,20 +96,40 @@ static int __init profile_setup(char *str)
 __setup("profile=", profile_setup);
 
 
-void __init profile_init(void)
+int __ref profile_init(void)
 {
+	int buffer_bytes;
 	if (!prof_on)
-		return;
+		return 0;
 
 	/* only text is profiled */
 	prof_len = (_etext - _stext) >> prof_shift;
-	prof_buffer = alloc_bootmem(prof_len*sizeof(atomic_t));
+	buffer_bytes = prof_len*sizeof(atomic_t);
+
+	if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	cpumask_copy(prof_cpu_mask, cpu_possible_mask);
+
+	prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL|__GFP_NOWARN);
+	if (prof_buffer)
+		return 0;
+
+	prof_buffer = alloc_pages_exact(buffer_bytes,
+					GFP_KERNEL|__GFP_ZERO|__GFP_NOWARN);
+	if (prof_buffer)
+		return 0;
+
+	prof_buffer = vzalloc(buffer_bytes);
+	if (prof_buffer)
+		return 0;
+
+	free_cpumask_var(prof_cpu_mask);
+	return -ENOMEM;
 }
 
 /* Profile event notifications */
 
-#ifdef CONFIG_PROFILING
-
 static BLOCKING_NOTIFIER_HEAD(task_exit_notifier);
 static ATOMIC_NOTIFIER_HEAD(task_free_notifier);
 static BLOCKING_NOTIFIER_HEAD(munmap_notifier);
@@ -186,27 +201,6 @@ int profile_event_unregister(enum profile_type type, struct notifier_block *n)
 }
 EXPORT_SYMBOL_GPL(profile_event_unregister);
 
-int register_timer_hook(int (*hook)(struct pt_regs *))
-{
-	if (timer_hook)
-		return -EBUSY;
-	timer_hook = hook;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(register_timer_hook);
-
-void unregister_timer_hook(int (*hook)(struct pt_regs *))
-{
-	WARN_ON(hook != timer_hook);
-	timer_hook = NULL;
-	/* make sure all CPUs see the NULL hook */
-	synchronize_sched();  /* Allow ongoing interrupts to complete. */
-}
-EXPORT_SYMBOL_GPL(unregister_timer_hook);
-
-#endif /* CONFIG_PROFILING */
-
-
 #ifdef CONFIG_SMP
 /*
  * Each cpu has a pair of open-addressed hashtables for pending
@@ -237,7 +231,7 @@ EXPORT_SYMBOL_GPL(unregister_timer_hook);
  * pagetable hash functions, but uses a full hashtable full of finite
  * collision chains, not just pairs of them.
  *
- * -- wli
+ * -- nyc
  */
 static void __profile_flip_buffers(void *unused)
 {
@@ -253,7 +247,7 @@ static void profile_flip_buffers(void)
 	mutex_lock(&profile_flip_mutex);
 	j = per_cpu(cpu_profile_flip, get_cpu());
 	put_cpu();
-	on_each_cpu(__profile_flip_buffers, NULL, 0, 1);
+	on_each_cpu(__profile_flip_buffers, NULL, 1);
 	for_each_online_cpu(cpu) {
 		struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[j];
 		for (i = 0; i < NR_PROFILE_HIT; ++i) {
@@ -276,7 +270,7 @@ static void profile_discard_flip_buffers(void)
 	mutex_lock(&profile_flip_mutex);
 	i = per_cpu(cpu_profile_flip, get_cpu());
 	put_cpu();
-	on_each_cpu(__profile_flip_buffers, NULL, 0, 1);
+	on_each_cpu(__profile_flip_buffers, NULL, 1);
 	for_each_online_cpu(cpu) {
 		struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[i];
 		memset(hits, 0, NR_PROFILE_HIT*sizeof(struct profile_hit));
@@ -284,14 +278,12 @@ static void profile_discard_flip_buffers(void)
 	mutex_unlock(&profile_flip_mutex);
 }
 
-void profile_hits(int type, void *__pc, unsigned int nr_hits)
+static void do_profile_hits(int type, void *__pc, unsigned int nr_hits)
 {
 	unsigned long primary, secondary, flags, pc = (unsigned long)__pc;
 	int i, j, cpu;
 	struct profile_hit *hits;
 
-	if (prof_on != type || !prof_buffer)
-		return;
 	pc = min((pc - (unsigned long)_stext) >> prof_shift, prof_len - 1);
 	i = primary = (pc & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT;
 	secondary = (~(pc << 1) & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT;
@@ -335,7 +327,7 @@ out:
 	put_cpu();
 }
 
-static int __devinit profile_cpu_callback(struct notifier_block *info,
+static int profile_cpu_callback(struct notifier_block *info,
 					unsigned long action, void *__cpu)
 {
 	int node, cpu = (unsigned long)__cpu;
@@ -344,18 +336,18 @@ static int __devinit profile_cpu_callback(struct notifier_block *info,
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		node = cpu_to_node(cpu);
+		node = cpu_to_mem(cpu);
 		per_cpu(cpu_profile_flip, cpu) = 0;
 		if (!per_cpu(cpu_profile_hits, cpu)[1]) {
-			page = alloc_pages_node(node,
+			page = alloc_pages_exact_node(node,
 					GFP_KERNEL | __GFP_ZERO,
 					0);
 			if (!page)
-				return NOTIFY_BAD;
+				return notifier_from_errno(-ENOMEM);
 			per_cpu(cpu_profile_hits, cpu)[1] = page_address(page);
 		}
 		if (!per_cpu(cpu_profile_hits, cpu)[0]) {
-			page = alloc_pages_node(node,
+			page = alloc_pages_exact_node(node,
 					GFP_KERNEL | __GFP_ZERO,
 					0);
 			if (!page)
@@ -367,16 +359,18 @@ out_free:
 		page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[1]);
 		per_cpu(cpu_profile_hits, cpu)[1] = NULL;
 		__free_page(page);
-		return NOTIFY_BAD;
+		return notifier_from_errno(-ENOMEM);
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		cpu_set(cpu, prof_cpu_mask);
+		if (prof_cpu_mask != NULL)
+			cpumask_set_cpu(cpu, prof_cpu_mask);
 		break;
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		cpu_clear(cpu, prof_cpu_mask);
+		if (prof_cpu_mask != NULL)
+			cpumask_clear_cpu(cpu, prof_cpu_mask);
 		if (per_cpu(cpu_profile_hits, cpu)[0]) {
 			page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[0]);
 			per_cpu(cpu_profile_hits, cpu)[0] = NULL;
@@ -396,69 +390,78 @@ out_free:
 #define profile_discard_flip_buffers()	do { } while (0)
 #define profile_cpu_callback		NULL
 
-void profile_hits(int type, void *__pc, unsigned int nr_hits)
+static void do_profile_hits(int type, void *__pc, unsigned int nr_hits)
 {
 	unsigned long pc;
-
-	if (prof_on != type || !prof_buffer)
-		return;
 	pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift;
 	atomic_add(nr_hits, &prof_buffer[min(pc, prof_len - 1)]);
 }
 #endif /* !CONFIG_SMP */
+
+void profile_hits(int type, void *__pc, unsigned int nr_hits)
+{
+	if (prof_on != type || !prof_buffer)
+		return;
+	do_profile_hits(type, __pc, nr_hits);
+}
 EXPORT_SYMBOL_GPL(profile_hits);
 
 void profile_tick(int type)
 {
 	struct pt_regs *regs = get_irq_regs();
 
-	if (type == CPU_PROFILING && timer_hook)
-		timer_hook(regs);
-	if (!user_mode(regs) && cpu_isset(smp_processor_id(), prof_cpu_mask))
+	if (!user_mode(regs) && prof_cpu_mask != NULL &&
+	    cpumask_test_cpu(smp_processor_id(), prof_cpu_mask))
 		profile_hit(type, (void *)profile_pc(regs));
 }
 
 #ifdef CONFIG_PROC_FS
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <asm/uaccess.h>
-#include <asm/ptrace.h>
 
-static int prof_cpu_mask_read_proc(char *page, char **start, off_t off,
-			int count, int *eof, void *data)
+static int prof_cpu_mask_proc_show(struct seq_file *m, void *v)
 {
-	int len = cpumask_scnprintf(page, count, *(cpumask_t *)data);
-	if (count - len < 2)
-		return -EINVAL;
-	len += sprintf(page + len, "\n");
-	return len;
+	seq_cpumask(m, prof_cpu_mask);
+	seq_putc(m, '\n');
+	return 0;
 }
 
-static int prof_cpu_mask_write_proc(struct file *file,
-	const char __user *buffer,  unsigned long count, void *data)
+static int prof_cpu_mask_proc_open(struct inode *inode, struct file *file)
 {
-	cpumask_t *mask = (cpumask_t *)data;
-	unsigned long full_count = count, err;
-	cpumask_t new_value;
+	return single_open(file, prof_cpu_mask_proc_show, NULL);
+}
 
-	err = cpumask_parse_user(buffer, count, new_value);
-	if (err)
-		return err;
+static ssize_t prof_cpu_mask_proc_write(struct file *file,
+	const char __user *buffer, size_t count, loff_t *pos)
+{
+	cpumask_var_t new_value;
+	int err;
 
-	*mask = new_value;
-	return full_count;
+	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+		return -ENOMEM;
+
+	err = cpumask_parse_user(buffer, count, new_value);
+	if (!err) {
+		cpumask_copy(prof_cpu_mask, new_value);
+		err = count;
+	}
+	free_cpumask_var(new_value);
+	return err;
 }
 
-void create_prof_cpu_mask(struct proc_dir_entry *root_irq_dir)
-{
-	struct proc_dir_entry *entry;
+static const struct file_operations prof_cpu_mask_proc_fops = {
+	.open		= prof_cpu_mask_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+	.write		= prof_cpu_mask_proc_write,
+};
 
+void create_prof_cpu_mask(void)
+{
 	/* create /proc/irq/prof_cpu_mask */
-	entry = create_proc_entry("prof_cpu_mask", 0600, root_irq_dir);
-	if (!entry)
-		return;
-	entry->data = (void *)&prof_cpu_mask;
-	entry->read_proc = prof_cpu_mask_read_proc;
-	entry->write_proc = prof_cpu_mask_write_proc;
+	proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_fops);
 }
 
 /*
@@ -525,30 +528,31 @@ static ssize_t write_profile(struct file *file, const char __user *buf,
 static const struct file_operations proc_profile_operations = {
 	.read		= read_profile,
 	.write		= write_profile,
+	.llseek		= default_llseek,
 };
 
 #ifdef CONFIG_SMP
-static void __init profile_nop(void *unused)
+static void profile_nop(void *unused)
 {
 }
 
-static int __init create_hash_tables(void)
+static int create_hash_tables(void)
 {
 	int cpu;
 
 	for_each_online_cpu(cpu) {
-		int node = cpu_to_node(cpu);
+		int node = cpu_to_mem(cpu);
 		struct page *page;
 
-		page = alloc_pages_node(node,
-				GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+		page = alloc_pages_exact_node(node,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				0);
 		if (!page)
 			goto out_cleanup;
 		per_cpu(cpu_profile_hits, cpu)[1]
 				= (struct profile_hit *)page_address(page);
-		page = alloc_pages_node(node,
-				GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+		page = alloc_pages_exact_node(node,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				0);
 		if (!page)
 			goto out_cleanup;
@@ -559,7 +563,7 @@ static int __init create_hash_tables(void)
 out_cleanup:
 	prof_on = 0;
 	smp_mb();
-	on_each_cpu(profile_nop, NULL, 0, 1);
+	on_each_cpu(profile_nop, NULL, 1);
 	for_each_online_cpu(cpu) {
 		struct page *page;
 
@@ -580,21 +584,31 @@ out_cleanup:
 #define create_hash_tables()			({ 0; })
 #endif
 
-static int __init create_proc_profile(void)
+int __ref create_proc_profile(void) /* false positive from hotcpu_notifier */
 {
 	struct proc_dir_entry *entry;
+	int err = 0;
 
 	if (!prof_on)
 		return 0;
-	if (create_hash_tables())
-		return -1;
-	entry = create_proc_entry("profile", S_IWUSR | S_IRUGO, NULL);
+
+	cpu_notifier_register_begin();
+
+	if (create_hash_tables()) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	entry = proc_create("profile", S_IWUSR | S_IRUGO,
+			    NULL, &proc_profile_operations);
 	if (!entry)
-		return 0;
-	entry->proc_fops = &proc_profile_operations;
-	entry->size = (1+prof_len) * sizeof(atomic_t);
-	hotcpu_notifier(profile_cpu_callback, 0);
-	return 0;
+		goto out;
+	proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t));
+	__hotcpu_notifier(profile_cpu_callback, 0);
+
+out:
+	cpu_notifier_register_done();
+	return err;
 }
-module_init(create_proc_profile);
+subsys_initcall(create_proc_profile);
 #endif /* CONFIG_PROC_FS */