Techwizz/kernel-fxtec-pro1x
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

x86/oprofile: add IBS support for AMD CPUs, IBS buffer handling routines

Browse source 
This patchset supports the new profiling hardware available in the
latest AMD CPUs in the oProfile driver.

Signed-off-by: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: Robert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Barry Kasindorf 2008-07-22 21:08:54 +02:00 committed by Ingo Molnar
parent ee648bc77f
commit 345c25730d
3 changed files with 140 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

72
drivers/oprofile/buffer_sync.c
View file

@ -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
@ -272,7 +273,7 @@ static void increment_tail(struct oprofile_cpu_buffer *b)
{
unsigned long new_tail = b->tail_pos + 1;
rmb();
rmb(); /* be sure fifo pointers are synchromized */
if (new_tail < b->buffer_size)
b->tail_pos = new_tail;
@ -327,6 +328,67 @@ static void add_trace_begin(void)
add_event_entry(TRACE_BEGIN_CODE);
}
#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));
}
}
static void add_sample_entry(unsigned long offset, unsigned long event)
{
@ -524,6 +586,14 @@ void sync_buffer(int cpu)
} else if (s->event == CPU_TRACE_BEGIN) {
state = sb_bt_start;
add_trace_begin();
} 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);
} else {
struct mm_struct *oldmm = mm;

68
drivers/oprofile/cpu_buffer.c
View file

@ -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.
@ -207,7 +208,7 @@ 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++;
@ -252,6 +253,71 @@ void oprofile_add_sample(struct pt_regs * const regs, unsigned long event)
oprofile_add_ext_sample(pc, regs, event, is_kernel);
}
#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);
}
void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
{
struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);

2
drivers/oprofile/cpu_buffer.h
View file

@ -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 */