Re: [PATCH V4 10/17] perf tools: Save previous sample for LBR stitching approach

[Arnaldo Carvalho de Melo <arnaldo.melo@gmail.com>]

Em Thu, Mar 19, 2020 at 01:25:10PM -0700, kan.liang@linux.intel.com escreveu:
> From: Kan Liang <kan.liang@linux.intel.com>
> 
> To retrieve the overwritten LBRs from previous sample for LBR stitching
> approach, perf has to save the previous sample.
> 
> Only allocate the struct lbr_stitch once, when LBR stitching approach
> is enabled and kernel supports hw_idx.

Applied + this one on top:

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 59778f5aec2a..a54ca09a1d00 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2297,7 +2297,7 @@ static bool alloc_lbr_stitch(struct thread *thread)
 	if (thread->lbr_stitch)
 		return true;
 
-	thread->lbr_stitch = calloc(1, sizeof(struct lbr_stitch));
+	thread->lbr_stitch = zalloc(sizeof(*thread->lbr_stitch));
 	if (!thread->lbr_stitch)
 		goto err;
 
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index f65a84a25f93..34eb61cee6a4 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -5,6 +5,7 @@
 #include <linux/refcount.h>
 #include <linux/rbtree.h>
 #include <linux/list.h>
+#include <linux/zalloc.h>
 #include <stdio.h>
 #include <unistd.h>
 #include <sys/types.h>
@@ -153,7 +154,7 @@ static inline bool thread__is_filtered(struct thread *thread)
 
 static inline void thread__free_stitch_list(struct thread *thread)
 {
-	free(thread->lbr_stitch);
+	zfree(&thread->lbr_stitch);
 }
 
 #endif	/* __PERF_THREAD_H */
 
> Reviewed-by: Andi Kleen <ak@linux.intel.com>
> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
> ---
>  tools/perf/util/machine.c | 23 +++++++++++++++++++++++
>  tools/perf/util/thread.c  |  1 +
>  tools/perf/util/thread.h  | 11 +++++++++++
>  3 files changed, 35 insertions(+)
> 
> diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
> index f1661dd3ca69..d91e11bfc8ca 100644
> --- a/tools/perf/util/machine.c
> +++ b/tools/perf/util/machine.c
> @@ -2261,6 +2261,21 @@ static int lbr_callchain_add_lbr_ip(struct thread *thread,
>  	return 0;
>  }
>  
> +static bool alloc_lbr_stitch(struct thread *thread)
> +{
> +	if (thread->lbr_stitch)
> +		return true;
> +
> +	thread->lbr_stitch = calloc(1, sizeof(struct lbr_stitch));
> +	if (!thread->lbr_stitch)
> +		goto err;
> +
> +err:
> +	pr_warning("Failed to allocate space for stitched LBRs. Disable LBR stitch\n");
> +	thread->lbr_stitch_enable = false;
> +	return false;
> +}
> +
>  /*
>   * Recolve LBR callstack chain sample
>   * Return:
> @@ -2277,6 +2292,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
>  {
>  	struct ip_callchain *chain = sample->callchain;
>  	int chain_nr = min(max_stack, (int)chain->nr), i;
> +	struct lbr_stitch *lbr_stitch;
>  	u64 branch_from = 0;
>  	int err;
>  
> @@ -2289,6 +2305,13 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
>  	if (i == chain_nr)
>  		return 0;
>  
> +	if (thread->lbr_stitch_enable && !sample->no_hw_idx &&
> +	    alloc_lbr_stitch(thread)) {
> +		lbr_stitch = thread->lbr_stitch;
> +
> +		memcpy(&lbr_stitch->prev_sample, sample, sizeof(*sample));
> +	}
> +
>  	if (callchain_param.order == ORDER_CALLEE) {
>  		/* Add kernel ip */
>  		err = lbr_callchain_add_kernel_ip(thread, cursor, sample,
> diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
> index 1f080db23615..8d0da260c84c 100644
> --- a/tools/perf/util/thread.c
> +++ b/tools/perf/util/thread.c
> @@ -111,6 +111,7 @@ void thread__delete(struct thread *thread)
>  
>  	exit_rwsem(&thread->namespaces_lock);
>  	exit_rwsem(&thread->comm_lock);
> +	thread__free_stitch_list(thread);
>  	free(thread);
>  }
>  
> diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
> index 95294050cff2..f65a84a25f93 100644
> --- a/tools/perf/util/thread.h
> +++ b/tools/perf/util/thread.h
> @@ -13,6 +13,7 @@
>  #include <strlist.h>
>  #include <intlist.h>
>  #include "rwsem.h"
> +#include "event.h"
>  
>  struct addr_location;
>  struct map;
> @@ -20,6 +21,10 @@ struct perf_record_namespaces;
>  struct thread_stack;
>  struct unwind_libunwind_ops;
>  
> +struct lbr_stitch {
> +	struct perf_sample		prev_sample;
> +};
> +
>  struct thread {
>  	union {
>  		struct rb_node	 rb_node;
> @@ -49,6 +54,7 @@ struct thread {
>  
>  	/* LBR call stack stitch */
>  	bool			lbr_stitch_enable;
> +	struct lbr_stitch	*lbr_stitch;
>  };
>  
>  struct machine;
> @@ -145,4 +151,9 @@ static inline bool thread__is_filtered(struct thread *thread)
>  	return false;
>  }
>  
> +static inline void thread__free_stitch_list(struct thread *thread)
> +{
> +	free(thread->lbr_stitch);
> +}
> +
>  #endif	/* __PERF_THREAD_H */
> -- 
> 2.17.1
> 

-- 

- Arnaldo