1 files changed, 186 insertions, 152 deletions

diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index b07ba2a1411..d93b2b6b1f7 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -1,10 +1,12 @@
 /**
  * @file buffer_sync.c
  *
- * @remark Copyright 2002 OProfile authors
+ * @remark Copyright 2002-2009 OProfile authors
  * @remark Read the file COPYING
  *
  * @author John Levon <levon@movementarian.org>
+ * @author Barry Kasindorf
+ * @author Robert Richter <robert.richter@amd.com>
  *
  * This is the core of the buffer management. Each
  * CPU buffer is processed and entered into the
@@ -28,19 +30,19 @@
 #include <linux/fs.h>
 #include <linux/oprofile.h>
 #include <linux/sched.h>
+#include <linux/gfp.h>
 
 #include "oprofile_stats.h"
 #include "event_buffer.h"
 #include "cpu_buffer.h"
 #include "buffer_sync.h"
- 
+
 static LIST_HEAD(dying_tasks);
 static LIST_HEAD(dead_tasks);
-static cpumask_t marked_cpus = CPU_MASK_NONE;
+static cpumask_var_t marked_cpus;
 static DEFINE_SPINLOCK(task_mortuary);
 static void process_task_mortuary(void);
 
-
 /* Take ownership of the task struct and place it on the
  * list for processing. Only after two full buffer syncs
  * does the task eventually get freed, because by then
@@ -48,10 +50,11 @@ static void process_task_mortuary(void);
  * Can be invoked from softirq via RCU callback due to
  * call_rcu() of the task struct, hence the _irqsave.
  */
-static int task_free_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+task_free_notify(struct notifier_block *self, unsigned long val, void *data)
 {
 	unsigned long flags;
-	struct task_struct * task = data;
+	struct task_struct *task = data;
 	spin_lock_irqsave(&task_mortuary, flags);
 	list_add(&task->tasks, &dying_tasks);
 	spin_unlock_irqrestore(&task_mortuary, flags);
@@ -62,13 +65,14 @@ static int task_free_notify(struct notifier_block * self, unsigned long val, voi
 /* The task is on its way out. A sync of the buffer means we can catch
  * any remaining samples for this task.
  */
-static int task_exit_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+task_exit_notify(struct notifier_block *self, unsigned long val, void *data)
 {
 	/* To avoid latency problems, we only process the current CPU,
 	 * hoping that most samples for the task are on this CPU
 	 */
 	sync_buffer(raw_smp_processor_id());
-  	return 0;
+	return 0;
 }
 
 
@@ -77,11 +81,12 @@ static int task_exit_notify(struct notifier_block * self, unsigned long val, voi
  * we don't lose any. This does not have to be exact, it's a QoI issue
  * only.
  */
-static int munmap_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+munmap_notify(struct notifier_block *self, unsigned long val, void *data)
 {
 	unsigned long addr = (unsigned long)data;
-	struct mm_struct * mm = current->mm;
-	struct vm_area_struct * mpnt;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *mpnt;
 
 	down_read(&mm->mmap_sem);
 
@@ -99,11 +104,12 @@ static int munmap_notify(struct notifier_block * self, unsigned long val, void *
 	return 0;
 }
 
- 
+
 /* We need to be told about new modules so we don't attribute to a previously
  * loaded module, or drop the samples on the floor.
  */
-static int module_load_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+module_load_notify(struct notifier_block *self, unsigned long val, void *data)
 {
 #ifdef CONFIG_MODULES
 	if (val != MODULE_STATE_COMING)
@@ -118,7 +124,7 @@ static int module_load_notify(struct notifier_block * self, unsigned long val, v
 	return 0;
 }
 
- 
+
 static struct notifier_block task_free_nb = {
 	.notifier_call	= task_free_notify,
 };
@@ -135,21 +141,19 @@ static struct notifier_block module_load_nb = {
 	.notifier_call = module_load_notify,
 };
 
- 
-static void end_sync(void)
+static void free_all_tasks(void)
 {
-	end_cpu_work();
 	/* make sure we don't leak task structs */
 	process_task_mortuary();
 	process_task_mortuary();
 }
 
-
 int sync_start(void)
 {
 	int err;
 
-	start_cpu_work();
+	if (!zalloc_cpumask_var(&marked_cpus, GFP_KERNEL))
+		return -ENOMEM;
 
 	err = task_handoff_register(&task_free_nb);
 	if (err)
@@ -164,6 +168,8 @@ int sync_start(void)
 	if (err)
 		goto out4;
 
+	start_cpu_work();
+
 out:
 	return err;
 out4:
@@ -172,19 +178,26 @@ out3:
 	profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb);
 out2:
 	task_handoff_unregister(&task_free_nb);
+	free_all_tasks();
 out1:
-	end_sync();
+	free_cpumask_var(marked_cpus);
 	goto out;
 }
 
 
 void sync_stop(void)
 {
+	end_cpu_work();
 	unregister_module_notifier(&module_load_nb);
 	profile_event_unregister(PROFILE_MUNMAP, &munmap_nb);
 	profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb);
 	task_handoff_unregister(&task_free_nb);
-	end_sync();
+	barrier();			/* do all of the above first */
+
+	flush_cpu_work();
+
+	free_all_tasks();
+	free_cpumask_var(marked_cpus);
 }
 
 
@@ -196,36 +209,25 @@ static inline unsigned long fast_get_dcookie(struct path *path)
 {
 	unsigned long cookie;
 
-	if (path->dentry->d_cookie)
+	if (path->dentry->d_flags & DCACHE_COOKIE)
 		return (unsigned long)path->dentry;
 	get_dcookie(path, &cookie);
 	return cookie;
 }
 
 
-/* Look up the dcookie for the task's first VM_EXECUTABLE mapping,
+/* Look up the dcookie for the task's mm->exe_file,
  * which corresponds loosely to "application name". This is
  * not strictly necessary but allows oprofile to associate
  * shared-library samples with particular applications
  */
-static unsigned long get_exec_dcookie(struct mm_struct * mm)
+static unsigned long get_exec_dcookie(struct mm_struct *mm)
 {
 	unsigned long cookie = NO_COOKIE;
-	struct vm_area_struct * vma;
- 
-	if (!mm)
-		goto out;
- 
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
-		if (!vma->vm_file)
-			continue;
-		if (!(vma->vm_flags & VM_EXECUTABLE))
-			continue;
-		cookie = fast_get_dcookie(&vma->vm_file->f_path);
-		break;
-	}
 
-out:
+	if (mm && mm->exe_file)
+		cookie = fast_get_dcookie(&mm->exe_file->f_path);
+
 	return cookie;
 }
 
@@ -235,13 +237,14 @@ out:
  * sure to do this lookup before a mm->mmap modification happens so
  * we don't lose track.
  */
-static unsigned long lookup_dcookie(struct mm_struct * mm, unsigned long addr, off_t * offset)
+static unsigned long
+lookup_dcookie(struct mm_struct *mm, unsigned long addr, off_t *offset)
 {
 	unsigned long cookie = NO_COOKIE;
-	struct vm_area_struct * vma;
+	struct vm_area_struct *vma;
 
 	for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) {
- 
+
 		if (addr < vma->vm_start || addr >= vma->vm_end)
 			continue;
 
@@ -263,9 +266,8 @@ static unsigned long lookup_dcookie(struct mm_struct * mm, unsigned long addr, o
 	return cookie;
 }
 
-
 static unsigned long last_cookie = INVALID_COOKIE;
- 
+
 static void add_cpu_switch(int i)
 {
 	add_event_entry(ESCAPE_CODE);
@@ -278,16 +280,16 @@ static void add_kernel_ctx_switch(unsigned int in_kernel)
 {
 	add_event_entry(ESCAPE_CODE);
 	if (in_kernel)
-		add_event_entry(KERNEL_ENTER_SWITCH_CODE); 
+		add_event_entry(KERNEL_ENTER_SWITCH_CODE);
 	else
-		add_event_entry(KERNEL_EXIT_SWITCH_CODE); 
+		add_event_entry(KERNEL_EXIT_SWITCH_CODE);
 }
- 
+
 static void
-add_user_ctx_switch(struct task_struct const * task, unsigned long cookie)
+add_user_ctx_switch(struct task_struct const *task, unsigned long cookie)
 {
 	add_event_entry(ESCAPE_CODE);
-	add_event_entry(CTX_SWITCH_CODE); 
+	add_event_entry(CTX_SWITCH_CODE);
 	add_event_entry(task->pid);
 	add_event_entry(cookie);
 	/* Another code for daemon back-compat */
@@ -296,7 +298,7 @@ add_user_ctx_switch(struct task_struct const * task, unsigned long cookie)
 	add_event_entry(task->tgid);
 }
 
- 
+
 static void add_cookie_switch(unsigned long cookie)
 {
 	add_event_entry(ESCAPE_CODE);
@@ -304,28 +306,82 @@ static void add_cookie_switch(unsigned long cookie)
 	add_event_entry(cookie);
 }
 
- 
+
 static void add_trace_begin(void)
 {
 	add_event_entry(ESCAPE_CODE);
 	add_event_entry(TRACE_BEGIN_CODE);
 }
 
+static void add_data(struct op_entry *entry, struct mm_struct *mm)
+{
+	unsigned long code, pc, val;
+	unsigned long cookie;
+	off_t offset;
+
+	if (!op_cpu_buffer_get_data(entry, &code))
+		return;
+	if (!op_cpu_buffer_get_data(entry, &pc))
+		return;
+	if (!op_cpu_buffer_get_size(entry))
+		return;
+
+	if (mm) {
+		cookie = lookup_dcookie(mm, pc, &offset);
+
+		if (cookie == NO_COOKIE)
+			offset = pc;
+		if (cookie == INVALID_COOKIE) {
+			atomic_inc(&oprofile_stats.sample_lost_no_mapping);
+			offset = pc;
+		}
+		if (cookie != last_cookie) {
+			add_cookie_switch(cookie);
+			last_cookie = cookie;
+		}
+	} else
+		offset = pc;
+
+	add_event_entry(ESCAPE_CODE);
+	add_event_entry(code);
+	add_event_entry(offset);	/* Offset from Dcookie */
+
+	while (op_cpu_buffer_get_data(entry, &val))
+		add_event_entry(val);
+}
 
-static void add_sample_entry(unsigned long offset, unsigned long event)
+static inline void add_sample_entry(unsigned long offset, unsigned long event)
 {
 	add_event_entry(offset);
 	add_event_entry(event);
 }
 
 
-static int add_us_sample(struct mm_struct * mm, struct op_sample * s)
+/*
+ * Add a sample to the global event buffer. If possible the
+ * sample is converted into a persistent dentry/offset pair
+ * for later lookup from userspace. Return 0 on failure.
+ */
+static int
+add_sample(struct mm_struct *mm, struct op_sample *s, int in_kernel)
 {
 	unsigned long cookie;
 	off_t offset;
- 
- 	cookie = lookup_dcookie(mm, s->eip, &offset);
- 
+
+	if (in_kernel) {
+		add_sample_entry(s->eip, s->event);
+		return 1;
+	}
+
+	/* add userspace sample */
+
+	if (!mm) {
+		atomic_inc(&oprofile_stats.sample_lost_no_mm);
+		return 0;
+	}
+
+	cookie = lookup_dcookie(mm, s->eip, &offset);
+
 	if (cookie == INVALID_COOKIE) {
 		atomic_inc(&oprofile_stats.sample_lost_no_mapping);
 		return 0;
@@ -341,27 +397,8 @@ static int add_us_sample(struct mm_struct * mm, struct op_sample * s)
 	return 1;
 }
 
- 
-/* Add a sample to the global event buffer. If possible the
- * sample is converted into a persistent dentry/offset pair
- * for later lookup from userspace.
- */
-static int
-add_sample(struct mm_struct * mm, struct op_sample * s, int in_kernel)
-{
-	if (in_kernel) {
-		add_sample_entry(s->eip, s->event);
-		return 1;
-	} else if (mm) {
-		return add_us_sample(mm, s);
-	} else {
-		atomic_inc(&oprofile_stats.sample_lost_no_mm);
-	}
-	return 0;
-}
- 
 
-static void release_mm(struct mm_struct * mm)
+static void release_mm(struct mm_struct *mm)
 {
 	if (!mm)
 		return;
@@ -370,9 +407,9 @@ static void release_mm(struct mm_struct * mm)
 }
 
 
-static struct mm_struct * take_tasks_mm(struct task_struct * task)
+static struct mm_struct *take_tasks_mm(struct task_struct *task)
 {
-	struct mm_struct * mm = get_task_mm(task);
+	struct mm_struct *mm = get_task_mm(task);
 	if (mm)
 		down_read(&mm->mmap_sem);
 	return mm;
@@ -383,46 +420,6 @@ static inline int is_code(unsigned long val)
 {
 	return val == ESCAPE_CODE;
 }
- 
-
-/* "acquire" as many cpu buffer slots as we can */
-static unsigned long get_slots(struct oprofile_cpu_buffer * b)
-{
-	unsigned long head = b->head_pos;
-	unsigned long tail = b->tail_pos;
-
-	/*
-	 * Subtle. This resets the persistent last_task
-	 * and in_kernel values used for switching notes.
-	 * BUT, there is a small window between reading
-	 * head_pos, and this call, that means samples
-	 * can appear at the new head position, but not
-	 * be prefixed with the notes for switching
-	 * kernel mode or a task switch. This small hole
-	 * can lead to mis-attribution or samples where
-	 * we don't know if it's in the kernel or not,
-	 * at the start of an event buffer.
-	 */
-	cpu_buffer_reset(b);
-
-	if (head >= tail)
-		return head - tail;
-
-	return head + (b->buffer_size - tail);
-}
-
-
-static void increment_tail(struct oprofile_cpu_buffer * b)
-{
-	unsigned long new_tail = b->tail_pos + 1;
-
-	rmb();
-
-	if (new_tail < b->buffer_size)
-		b->tail_pos = new_tail;
-	else
-		b->tail_pos = 0;
-}
 
 
 /* Move tasks along towards death. Any tasks on dead_tasks
@@ -435,8 +432,8 @@ static void process_task_mortuary(void)
 {
 	unsigned long flags;
 	LIST_HEAD(local_dead_tasks);
-	struct task_struct * task;
-	struct task_struct * ttask;
+	struct task_struct *task;
+	struct task_struct *ttask;
 
 	spin_lock_irqsave(&task_mortuary, flags);
 
@@ -456,10 +453,10 @@ static void mark_done(int cpu)
 {
 	int i;
 
-	cpu_set(cpu, marked_cpus);
+	cpumask_set_cpu(cpu, marked_cpus);
 
 	for_each_online_cpu(i) {
-		if (!cpu_isset(i, marked_cpus))
+		if (!cpumask_test_cpu(i, marked_cpus))
 			return;
 	}
 
@@ -468,7 +465,7 @@ static void mark_done(int cpu)
 	 */
 	process_task_mortuary();
 
-	cpus_clear(marked_cpus);
+	cpumask_clear(marked_cpus);
 }
 
 
@@ -491,59 +488,72 @@ typedef enum {
  */
 void sync_buffer(int cpu)
 {
-	struct oprofile_cpu_buffer * cpu_buf = &cpu_buffer[cpu];
 	struct mm_struct *mm = NULL;
-	struct task_struct * new;
+	struct mm_struct *oldmm;
+	unsigned long val;
+	struct task_struct *new;
 	unsigned long cookie = 0;
 	int in_kernel = 1;
-	unsigned int i;
 	sync_buffer_state state = sb_buffer_start;
+	unsigned int i;
 	unsigned long available;
+	unsigned long flags;
+	struct op_entry entry;
+	struct op_sample *sample;
 
 	mutex_lock(&buffer_mutex);
- 
-	add_cpu_switch(cpu);
 
-	/* Remember, only we can modify tail_pos */
+	add_cpu_switch(cpu);
 
-	available = get_slots(cpu_buf);
+	op_cpu_buffer_reset(cpu);
+	available = op_cpu_buffer_entries(cpu);
 
 	for (i = 0; i < available; ++i) {
-		struct op_sample * s = &cpu_buf->buffer[cpu_buf->tail_pos];
- 
-		if (is_code(s->eip)) {
-			if (s->event <= CPU_IS_KERNEL) {
+		sample = op_cpu_buffer_read_entry(&entry, cpu);
+		if (!sample)
+			break;
+
+		if (is_code(sample->eip)) {
+			flags = sample->event;
+			if (flags & TRACE_BEGIN) {
+				state = sb_bt_start;
+				add_trace_begin();
+			}
+			if (flags & KERNEL_CTX_SWITCH) {
 				/* kernel/userspace switch */
-				in_kernel = s->event;
+				in_kernel = flags & IS_KERNEL;
 				if (state == sb_buffer_start)
 					state = sb_sample_start;
-				add_kernel_ctx_switch(s->event);
-			} else if (s->event == CPU_TRACE_BEGIN) {
-				state = sb_bt_start;
-				add_trace_begin();
-			} else {
-				struct mm_struct * oldmm = mm;
-
+				add_kernel_ctx_switch(flags & IS_KERNEL);
+			}
+			if (flags & USER_CTX_SWITCH
+			    && op_cpu_buffer_get_data(&entry, &val)) {
 				/* userspace context switch */
-				new = (struct task_struct *)s->event;
-
+				new = (struct task_struct *)val;
+				oldmm = mm;
 				release_mm(oldmm);
 				mm = take_tasks_mm(new);
 				if (mm != oldmm)
 					cookie = get_exec_dcookie(mm);
 				add_user_ctx_switch(new, cookie);
 			}
-		} else {
-			if (state >= sb_bt_start &&
-			    !add_sample(mm, s, in_kernel)) {
-				if (state == sb_bt_start) {
-					state = sb_bt_ignore;
-					atomic_inc(&oprofile_stats.bt_lost_no_mapping);
-				}
-			}
+			if (op_cpu_buffer_get_size(&entry))
+				add_data(&entry, mm);
+			continue;
 		}
 
-		increment_tail(cpu_buf);
+		if (state < sb_bt_start)
+			/* ignore sample */
+			continue;
+
+		if (add_sample(mm, sample, in_kernel))
+			continue;
+
+		/* ignore backtraces if failed to add a sample */
+		if (state == sb_bt_start) {
+			state = sb_bt_ignore;
+			atomic_inc(&oprofile_stats.bt_lost_no_mapping);
+		}
 	}
 	release_mm(mm);
 
@@ -551,3 +561,27 @@ void sync_buffer(int cpu)
 
 	mutex_unlock(&buffer_mutex);
 }
+
+/* The function can be used to add a buffer worth of data directly to
+ * the kernel buffer. The buffer is assumed to be a circular buffer.
+ * Take the entries from index start and end at index end, wrapping
+ * at max_entries.
+ */
+void oprofile_put_buff(unsigned long *buf, unsigned int start,
+		       unsigned int stop, unsigned int max)
+{
+	int i;
+
+	i = start;
+
+	mutex_lock(&buffer_mutex);
+	while (i != stop) {
+		add_event_entry(buf[i++]);
+
+		if (i >= max)
+			i = 0;
+	}
+
+	mutex_unlock(&buffer_mutex);
+}
+