summaryrefslogtreecommitdiffstats
path: root/drivers/oprofile
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/oprofile')
-rw-r--r--drivers/oprofile/buffer_sync.c209
-rw-r--r--drivers/oprofile/cpu_buffer.c74
-rw-r--r--drivers/oprofile/cpu_buffer.h2
3 files changed, 217 insertions, 68 deletions
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index 9304c455507..ed982273fb8 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -5,6 +5,7 @@
* @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
@@ -33,7 +34,7 @@
#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;
@@ -48,10 +49,11 @@ 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 +64,14 @@ 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 +80,12 @@ 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 +103,12 @@ 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 +123,7 @@ 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,
};
@@ -135,7 +140,7 @@ static struct notifier_block module_load_nb = {
.notifier_call = module_load_notify,
};
-
+
static void end_sync(void)
{
end_cpu_work();
@@ -208,14 +213,14 @@ static inline unsigned long fast_get_dcookie(struct path *path)
* 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;
@@ -235,13 +240,14 @@ 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 +269,20 @@ static unsigned long lookup_dcookie(struct mm_struct * mm, unsigned long addr, o
return cookie;
}
+static void increment_tail(struct oprofile_cpu_buffer *b)
+{
+ unsigned long new_tail = b->tail_pos + 1;
+
+ rmb(); /* be sure fifo pointers are synchromized */
+
+ if (new_tail < b->buffer_size)
+ b->tail_pos = new_tail;
+ else
+ b->tail_pos = 0;
+}
static unsigned long last_cookie = INVALID_COOKIE;
-
+
static void add_cpu_switch(int i)
{
add_event_entry(ESCAPE_CODE);
@@ -278,16 +295,16 @@ 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 +313,7 @@ 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);
@@ -304,13 +321,78 @@ 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);
}
+#ifdef CONFIG_OPROFILE_IBS
+
+#define IBS_FETCH_CODE_SIZE 2
+#define IBS_OP_CODE_SIZE 5
+#define IBS_EIP(offset) \
+ (((struct op_sample *)&cpu_buf->buffer[(offset)])->eip)
+#define IBS_EVENT(offset) \
+ (((struct op_sample *)&cpu_buf->buffer[(offset)])->event)
+
+/*
+ * Add IBS fetch and op entries to event buffer
+ */
+static void add_ibs_begin(struct oprofile_cpu_buffer *cpu_buf, int code,
+ int in_kernel, struct mm_struct *mm)
+{
+ unsigned long rip;
+ int i, count;
+ unsigned long ibs_cookie = 0;
+ off_t offset;
+
+ increment_tail(cpu_buf); /* move to RIP entry */
+
+ rip = IBS_EIP(cpu_buf->tail_pos);
+
+#ifdef __LP64__
+ rip += IBS_EVENT(cpu_buf->tail_pos) << 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(IBS_EIP(cpu_buf->tail_pos));
+ add_event_entry(IBS_EVENT(cpu_buf->tail_pos));
+
+ 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++) {
+ increment_tail(cpu_buf);
+ add_event_entry(IBS_EIP(cpu_buf->tail_pos));
+ add_event_entry(IBS_EVENT(cpu_buf->tail_pos));
+ }
+}
+
+#endif
static void add_sample_entry(unsigned long offset, unsigned long event)
{
@@ -319,13 +401,13 @@ 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;
@@ -341,13 +423,13 @@ 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)
+add_sample(struct mm_struct *mm, struct op_sample *s, int in_kernel)
{
if (in_kernel) {
add_sample_entry(s->eip, s->event);
@@ -359,9 +441,9 @@ add_sample(struct mm_struct * mm, struct op_sample * s, int in_kernel)
}
return 0;
}
-
-static void release_mm(struct mm_struct * mm)
+
+static void release_mm(struct mm_struct *mm)
{
if (!mm)
return;
@@ -370,9 +452,9 @@ 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;
@@ -383,10 +465,10 @@ 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)
+static unsigned long get_slots(struct oprofile_cpu_buffer *b)
{
unsigned long head = b->head_pos;
unsigned long tail = b->tail_pos;
@@ -412,19 +494,6 @@ static unsigned long get_slots(struct oprofile_cpu_buffer * b)
}
-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
* will definitely have no remaining references in any
* CPU buffers at this point, because we use two lists,
@@ -435,8 +504,8 @@ 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);
@@ -493,7 +562,7 @@ void sync_buffer(int cpu)
{
struct oprofile_cpu_buffer *cpu_buf = &per_cpu(cpu_buffer, cpu);
struct mm_struct *mm = NULL;
- struct task_struct * new;
+ struct task_struct *new;
unsigned long cookie = 0;
int in_kernel = 1;
unsigned int i;
@@ -501,7 +570,7 @@ void sync_buffer(int cpu)
unsigned long available;
mutex_lock(&buffer_mutex);
-
+
add_cpu_switch(cpu);
/* Remember, only we can modify tail_pos */
@@ -509,8 +578,8 @@ void sync_buffer(int cpu)
available = get_slots(cpu_buf);
for (i = 0; i < available; ++i) {
- struct op_sample * s = &cpu_buf->buffer[cpu_buf->tail_pos];
-
+ struct op_sample *s = &cpu_buf->buffer[cpu_buf->tail_pos];
+
if (is_code(s->eip)) {
if (s->event <= CPU_IS_KERNEL) {
/* kernel/userspace switch */
@@ -521,8 +590,18 @@ void sync_buffer(int cpu)
} else if (s->event == CPU_TRACE_BEGIN) {
state = sb_bt_start;
add_trace_begin();
+#ifdef CONFIG_OPROFILE_IBS
+ } else if (s->event == IBS_FETCH_BEGIN) {
+ state = sb_bt_start;
+ add_ibs_begin(cpu_buf,
+ IBS_FETCH_CODE, in_kernel, mm);
+ } else if (s->event == IBS_OP_BEGIN) {
+ state = sb_bt_start;
+ add_ibs_begin(cpu_buf,
+ IBS_OP_CODE, in_kernel, mm);
+#endif
} else {
- struct mm_struct * oldmm = mm;
+ struct mm_struct *oldmm = mm;
/* userspace context switch */
new = (struct task_struct *)s->event;
@@ -533,13 +612,11 @@ void sync_buffer(int cpu)
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);
- }
+ } 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);
}
}
diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index 7ba78e6d210..e1bd5a937f6 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -5,6 +5,7 @@
* @remark Read the file COPYING
*
* @author John Levon <levon@movementarian.org>
+ * @author Barry Kasindorf <barry.kasindorf@amd.com>
*
* Each CPU has a local buffer that stores PC value/event
* pairs. We also log context switches when we notice them.
@@ -209,7 +210,7 @@ static int log_sample(struct oprofile_cpu_buffer * cpu_buf, unsigned long pc,
return 1;
}
-static int oprofile_begin_trace(struct oprofile_cpu_buffer * cpu_buf)
+static int oprofile_begin_trace(struct oprofile_cpu_buffer *cpu_buf)
{
if (nr_available_slots(cpu_buf) < 4) {
cpu_buf->sample_lost_overflow++;
@@ -254,6 +255,75 @@ void oprofile_add_sample(struct pt_regs * const regs, unsigned long event)
oprofile_add_ext_sample(pc, regs, event, is_kernel);
}
+#ifdef CONFIG_OPROFILE_IBS
+
+#define MAX_IBS_SAMPLE_SIZE 14
+static int log_ibs_sample(struct oprofile_cpu_buffer *cpu_buf,
+ unsigned long pc, int is_kernel, unsigned int *ibs, int ibs_code)
+{
+ struct task_struct *task;
+
+ cpu_buf->sample_received++;
+
+ if (nr_available_slots(cpu_buf) < MAX_IBS_SAMPLE_SIZE) {
+ cpu_buf->sample_lost_overflow++;
+ return 0;
+ }
+
+ is_kernel = !!is_kernel;
+
+ /* notice a switch from user->kernel or vice versa */
+ if (cpu_buf->last_is_kernel != is_kernel) {
+ cpu_buf->last_is_kernel = is_kernel;
+ add_code(cpu_buf, is_kernel);
+ }
+
+ /* notice a task switch */
+ if (!is_kernel) {
+ task = current;
+
+ if (cpu_buf->last_task != task) {
+ cpu_buf->last_task = task;
+ add_code(cpu_buf, (unsigned long)task);
+ }
+ }
+
+ add_code(cpu_buf, ibs_code);
+ add_sample(cpu_buf, ibs[0], ibs[1]);
+ add_sample(cpu_buf, ibs[2], ibs[3]);
+ add_sample(cpu_buf, ibs[4], ibs[5]);
+
+ if (ibs_code == IBS_OP_BEGIN) {
+ add_sample(cpu_buf, ibs[6], ibs[7]);
+ add_sample(cpu_buf, ibs[8], ibs[9]);
+ add_sample(cpu_buf, ibs[10], ibs[11]);
+ }
+
+ return 1;
+}
+
+void oprofile_add_ibs_sample(struct pt_regs *const regs,
+ unsigned int * const ibs_sample, u8 code)
+{
+ int is_kernel = !user_mode(regs);
+ unsigned long pc = profile_pc(regs);
+
+ struct oprofile_cpu_buffer *cpu_buf =
+ &per_cpu(cpu_buffer, smp_processor_id());
+
+ if (!backtrace_depth) {
+ log_ibs_sample(cpu_buf, pc, is_kernel, ibs_sample, code);
+ return;
+ }
+
+ /* if log_sample() fails we can't backtrace since we lost the source
+ * of this event */
+ if (log_ibs_sample(cpu_buf, pc, is_kernel, ibs_sample, code))
+ oprofile_ops.backtrace(regs, backtrace_depth);
+}
+
+#endif
+
void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
{
struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
@@ -296,7 +366,7 @@ static void wq_sync_buffer(struct work_struct *work)
struct oprofile_cpu_buffer * b =
container_of(work, struct oprofile_cpu_buffer, work.work);
if (b->cpu != smp_processor_id()) {
- printk("WQ on CPU%d, prefer CPU%d\n",
+ printk(KERN_DEBUG "WQ on CPU%d, prefer CPU%d\n",
smp_processor_id(), b->cpu);
}
sync_buffer(b->cpu);
diff --git a/drivers/oprofile/cpu_buffer.h b/drivers/oprofile/cpu_buffer.h
index c3e366b5226..9c44d004da6 100644
--- a/drivers/oprofile/cpu_buffer.h
+++ b/drivers/oprofile/cpu_buffer.h
@@ -55,5 +55,7 @@ void cpu_buffer_reset(struct oprofile_cpu_buffer * cpu_buf);
/* transient events for the CPU buffer -> event buffer */
#define CPU_IS_KERNEL 1
#define CPU_TRACE_BEGIN 2
+#define IBS_FETCH_BEGIN 3
+#define IBS_OP_BEGIN 4
#endif /* OPROFILE_CPU_BUFFER_H */
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-20 18:39:16 +0000