* @remark Read the file COPYING
*
* @author John Levon <levon@movementarian.org>
+ * @author Barry Kasindorf
*
* This is the core of the buffer management. Each
* CPU buffer is processed and entered into the
#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 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
* 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);
/* 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;
}
* 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);
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)
return 0;
}
-
+
static struct notifier_block task_free_nb = {
.notifier_call = task_free_notify,
};
.notifier_call = module_load_notify,
};
-
+
static void end_sync(void)
{
end_cpu_work();
end_sync();
}
-
+
/* Optimisation. We can manage without taking the dcookie sem
* because we cannot reach this code without at least one
* dcookie user still being registered (namely, the reader
* of the event buffer). */
-static inline unsigned long fast_get_dcookie(struct dentry * dentry,
- struct vfsmount * vfsmnt)
+static inline unsigned long fast_get_dcookie(struct path *path)
{
unsigned long cookie;
-
- if (dentry->d_cookie)
- return (unsigned long)dentry;
- get_dcookie(dentry, vfsmnt, &cookie);
+
+ if (path->dentry->d_cookie)
+ return (unsigned long)path->dentry;
+ get_dcookie(path, &cookie);
return cookie;
}
-
+
/* Look up the dcookie for the task's first VM_EXECUTABLE mapping,
* 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;
-
+ 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.dentry,
- vma->vm_file->f_path.mnt);
+ cookie = fast_get_dcookie(&vma->vm_file->f_path);
break;
}
* 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;
if (vma->vm_file) {
- cookie = fast_get_dcookie(vma->vm_file->f_path.dentry,
- vma->vm_file->f_path.mnt);
+ cookie = fast_get_dcookie(&vma->vm_file->f_path);
*offset = (vma->vm_pgoff << PAGE_SHIFT) + addr -
vma->vm_start;
} else {
return cookie;
}
-
static unsigned long last_cookie = INVALID_COOKIE;
-
+
static void add_cpu_switch(int i)
{
add_event_entry(ESCAPE_CODE);
{
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 */
add_event_entry(task->tgid);
}
-
+
static void add_cookie_switch(unsigned long cookie)
{
add_event_entry(ESCAPE_CODE);
add_event_entry(cookie);
}
-
+
static void add_trace_begin(void)
{
add_event_entry(ESCAPE_CODE);
add_event_entry(TRACE_BEGIN_CODE);
}
+#ifdef CONFIG_OPROFILE_IBS
+
+#define IBS_FETCH_CODE_SIZE 2
+#define IBS_OP_CODE_SIZE 5
+
+/*
+ * Add IBS fetch and op entries to event buffer
+ */
+static void add_ibs_begin(int cpu, int code, struct mm_struct *mm)
+{
+ unsigned long rip;
+ int i, count;
+ unsigned long ibs_cookie = 0;
+ off_t offset;
+ struct op_sample *sample;
+
+ sample = op_cpu_buffer_read_entry(cpu);
+ if (!sample)
+ goto Error;
+ rip = sample->eip;
+
+#ifdef __LP64__
+ rip += sample->event << 32;
+#endif
+
+ if (mm) {
+ ibs_cookie = lookup_dcookie(mm, rip, &offset);
+
+ if (ibs_cookie == NO_COOKIE)
+ offset = rip;
+ if (ibs_cookie == INVALID_COOKIE) {
+ atomic_inc(&oprofile_stats.sample_lost_no_mapping);
+ offset = rip;
+ }
+ if (ibs_cookie != last_cookie) {
+ add_cookie_switch(ibs_cookie);
+ last_cookie = ibs_cookie;
+ }
+ } else
+ offset = rip;
+
+ add_event_entry(ESCAPE_CODE);
+ add_event_entry(code);
+ add_event_entry(offset); /* Offset from Dcookie */
+
+ /* we send the Dcookie offset, but send the raw Linear Add also*/
+ add_event_entry(sample->eip);
+ add_event_entry(sample->event);
+
+ if (code == IBS_FETCH_CODE)
+ count = IBS_FETCH_CODE_SIZE; /*IBS FETCH is 2 int64s*/
+ else
+ count = IBS_OP_CODE_SIZE; /*IBS OP is 5 int64s*/
+
+ for (i = 0; i < count; i++) {
+ sample = op_cpu_buffer_read_entry(cpu);
+ if (!sample)
+ goto Error;
+ add_event_entry(sample->eip);
+ add_event_entry(sample->event);
+ }
+
+ return;
+
+Error:
+ return;
+}
+
+#endif
static void add_sample_entry(unsigned long offset, unsigned long event)
{
}
-static int add_us_sample(struct mm_struct * mm, struct op_sample * s)
+static int add_us_sample(struct mm_struct *mm, struct op_sample *s)
{
unsigned long cookie;
off_t offset;
-
- cookie = lookup_dcookie(mm, s->eip, &offset);
-
+
+ cookie = lookup_dcookie(mm, s->eip, &offset);
+
if (cookie == INVALID_COOKIE) {
atomic_inc(&oprofile_stats.sample_lost_no_mapping);
return 0;
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)
+add_sample(struct mm_struct *mm, struct op_sample *s, int in_kernel)
{
if (in_kernel) {
add_sample_entry(s->eip, s->event);
}
return 0;
}
-
-static void release_mm(struct mm_struct * mm)
+
+static void release_mm(struct mm_struct *mm)
{
if (!mm)
return;
}
-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;
{
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
{
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);
*/
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;
+ 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;
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];
-
+ struct op_sample *s = op_cpu_buffer_read_entry(cpu);
+ if (!s)
+ break;
+
if (is_code(s->eip)) {
- if (s->event <= CPU_IS_KERNEL) {
+ switch (s->event) {
+ case 0:
+ case CPU_IS_KERNEL:
/* kernel/userspace switch */
in_kernel = s->event;
if (state == sb_buffer_start)
state = sb_sample_start;
add_kernel_ctx_switch(s->event);
- } else if (s->event == CPU_TRACE_BEGIN) {
+ break;
+ case CPU_TRACE_BEGIN:
state = sb_bt_start;
add_trace_begin();
- } else {
- struct mm_struct * oldmm = mm;
-
+ break;
+#ifdef CONFIG_OPROFILE_IBS
+ case IBS_FETCH_BEGIN:
+ state = sb_bt_start;
+ add_ibs_begin(cpu, IBS_FETCH_CODE, mm);
+ break;
+ case IBS_OP_BEGIN:
+ state = sb_bt_start;
+ add_ibs_begin(cpu, IBS_OP_CODE, mm);
+ break;
+#endif
+ default:
/* userspace context switch */
+ oldmm = mm;
new = (struct task_struct *)s->event;
-
release_mm(oldmm);
mm = take_tasks_mm(new);
if (mm != oldmm)
cookie = get_exec_dcookie(mm);
add_user_ctx_switch(new, cookie);
+ break;
}
- } 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);
- }
+ } 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);
}
}
-
- increment_tail(cpu_buf);
}
release_mm(mm);
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);
+}
+
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff