OProfile: Rework oprofile_add_ibs_sample() function

[safe/jmp/linux-2.6] / drivers / oprofile / cpu_buffer.c

diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index c93d3d2..d6c6827 100644 (file)
--- 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.
@@ -27,7 +28,7 @@
 #include "buffer_sync.h"
 #include "oprof.h"
 
-struct oprofile_cpu_buffer cpu_buffer[NR_CPUS] __cacheline_aligned;
+DEFINE_PER_CPU(struct oprofile_cpu_buffer, cpu_buffer);
 
 static void wq_sync_buffer(struct work_struct *work);
 
@@ -38,8 +39,10 @@ void free_cpu_buffers(void)
 {
        int i;
  
-       for_each_online_cpu(i)
-               vfree(cpu_buffer[i].buffer);
+       for_each_online_cpu(i) {
+               vfree(per_cpu(cpu_buffer, i).buffer);
+               per_cpu(cpu_buffer, i).buffer = NULL;
+       }
 }
 
 int alloc_cpu_buffers(void)
@@ -49,7 +52,7 @@ int alloc_cpu_buffers(void)
        unsigned long buffer_size = fs_cpu_buffer_size;
  
        for_each_online_cpu(i) {
-               struct oprofile_cpu_buffer * b = &cpu_buffer[i];
+               struct oprofile_cpu_buffer *b = &per_cpu(cpu_buffer, i);
  
                b->buffer = vmalloc_node(sizeof(struct op_sample) * buffer_size,
                        cpu_to_node(i));
@@ -83,7 +86,7 @@ void start_cpu_work(void)
        work_enabled = 1;
 
        for_each_online_cpu(i) {
-               struct oprofile_cpu_buffer * b = &cpu_buffer[i];
+               struct oprofile_cpu_buffer *b = &per_cpu(cpu_buffer, i);
 
                /*
                 * Spread the work by 1 jiffy per cpu so they dont all
@@ -100,7 +103,7 @@ void end_cpu_work(void)
        work_enabled = 0;
 
        for_each_online_cpu(i) {
-               struct oprofile_cpu_buffer * b = &cpu_buffer[i];
+               struct oprofile_cpu_buffer *b = &per_cpu(cpu_buffer, i);
 
                cancel_delayed_work(&b->work);
        }
@@ -207,7 +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++;
@@ -227,7 +230,7 @@ static void oprofile_end_trace(struct oprofile_cpu_buffer * cpu_buf)
 void oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
                                unsigned long event, int is_kernel)
 {
-       struct oprofile_cpu_buffer * cpu_buf = &cpu_buffer[smp_processor_id()];
+       struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
 
        if (!backtrace_depth) {
                log_sample(cpu_buf, pc, is_kernel, event);
@@ -252,15 +255,66 @@ 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
+
+void oprofile_add_ibs_sample(struct pt_regs *const regs,
+                            unsigned int * const ibs_sample, int ibs_code)
+{
+       int is_kernel = !user_mode(regs);
+       struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
+       struct task_struct *task;
+
+       cpu_buf->sample_received++;
+
+       if (nr_available_slots(cpu_buf) < MAX_IBS_SAMPLE_SIZE) {
+               /* we can't backtrace since we lost the source of this event */
+               cpu_buf->sample_lost_overflow++;
+               return;
+       }
+
+       /* 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_sample[0], ibs_sample[1]);
+       add_sample(cpu_buf, ibs_sample[2], ibs_sample[3]);
+       add_sample(cpu_buf, ibs_sample[4], ibs_sample[5]);
+
+       if (ibs_code == IBS_OP_BEGIN) {
+               add_sample(cpu_buf, ibs_sample[6], ibs_sample[7]);
+               add_sample(cpu_buf, ibs_sample[8], ibs_sample[9]);
+               add_sample(cpu_buf, ibs_sample[10], ibs_sample[11]);
+       }
+
+       if (backtrace_depth)
+               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 = &cpu_buffer[smp_processor_id()];
+       struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
        log_sample(cpu_buf, pc, is_kernel, event);
 }
 
 void oprofile_add_trace(unsigned long pc)
 {
-       struct oprofile_cpu_buffer * cpu_buf = &cpu_buffer[smp_processor_id()];
+       struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
 
        if (!cpu_buf->tracing)
                return;
@@ -294,7 +348,7 @@ 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);