Testing:
- Built perf
- Executed perf mem record and report

Tested-by: Ricky Ringler <ricky.ringler@proton.me>

Signed-off-by: Ricky Ringler <ricky.ringler@proton.me>
---
 tools/perf/util/sort.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index f3a565b0e230..aa79eb6476dd 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2474,8 +2474,7 @@ struct sort_entry sort_type_offset = {
 
 /* --sort typecln */
 
-/* TODO: use actual value in the system */
-#define TYPE_CACHELINE_SIZE  64
+#define DEFAULT_CACHELINE_SIZE 64
 
 static int64_t
 sort__typecln_sort(struct hist_entry *left, struct hist_entry *right)
@@ -2484,6 +2483,10 @@ sort__typecln_sort(struct hist_entry *left, struct hist_entry *right)
 	struct annotated_data_type *right_type = right->mem_type;
 	int64_t left_cln, right_cln;
 	int64_t ret;
+	int cln_size = cacheline_size();
+
+	if (cln_size == 0)
+		cln_size = DEFAULT_CACHELINE_SIZE;
 
 	if (!left_type) {
 		sort__type_init(left);
@@ -2499,8 +2502,8 @@ sort__typecln_sort(struct hist_entry *left, struct hist_entry *right)
 	if (ret)
 		return ret;
 
-	left_cln = left->mem_type_off / TYPE_CACHELINE_SIZE;
-	right_cln = right->mem_type_off / TYPE_CACHELINE_SIZE;
+	left_cln = left->mem_type_off / cln_size;
+	right_cln = right->mem_type_off / cln_size;
 	return left_cln - right_cln;
 }
 
@@ -2508,9 +2511,13 @@ static int hist_entry__typecln_snprintf(struct hist_entry *he, char *bf,
 				     size_t size, unsigned int width __maybe_unused)
 {
 	struct annotated_data_type *he_type = he->mem_type;
+	int cln_size = cacheline_size();
+
+	if (cln_size == 0)
+		cln_size = DEFAULT_CACHELINE_SIZE;
 
 	return repsep_snprintf(bf, size, "%s: cache-line %d", he_type->self.type_name,
-			       he->mem_type_off / TYPE_CACHELINE_SIZE);
+			       he->mem_type_off / cln_size);
 }
 
 struct sort_entry sort_type_cacheline = {
-- 
2.52.0

On Thu, Jan 29, 2026 at 12:42:27AM +0000, Ricky Ringler wrote:
> Testing:
> - Built perf
> - Executed perf mem record and report
> 
> Tested-by: Ricky Ringler <ricky.ringler@proton.me>
> 
> Signed-off-by: Ricky Ringler <ricky.ringler@proton.me>
> ---
>  tools/perf/util/sort.c | 17 ++++++++++++-----
>  1 file changed, 12 insertions(+), 5 deletions(-)
> 
> diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
> index f3a565b0e230..aa79eb6476dd 100644
> --- a/tools/perf/util/sort.c
> +++ b/tools/perf/util/sort.c
> @@ -2474,8 +2474,7 @@ struct sort_entry sort_type_offset = {
>  
>  /* --sort typecln */
>  
> -/* TODO: use actual value in the system */
> -#define TYPE_CACHELINE_SIZE  64
> +#define DEFAULT_CACHELINE_SIZE 64

I'm applying as this addresses the TODO and for cases where both record
and report/c2c are performed on the same machine it is an improvement,
but we need to actually get this from the perf.data header, because we
can collect in one machine with a cacheline size and then do the
report/c2c on another, with a different cacheline size.

When doing 'perf report --header-only -I' to see cache info we get
thingsl like:

# CPU cache info:
#  L1 Data                 48K [0,16]
#  L1 Instruction          32K [0,16]
#  L1 Data                 48K [1,17]
#  L1 Instruction          32K [1,17]
#  L1 Data                 48K [2,18]
#  L1 Instruction          32K [2,18]
#  L1 Data                 48K [3,19]
#  L1 Instruction          32K [3,19]
#  L1 Data                 48K [4,20]
#  L1 Instruction          32K [4,20]
#  L1 Data                 48K [5,21]
#  L1 Instruction          32K [5,21]
#  L1 Data                 48K [6,22]
#  L1 Instruction          32K [6,22]
#  L1 Data                 48K [7,23]
#  L1 Instruction          32K [7,23]
#  L1 Data                 48K [8,24]
#  L1 Instruction          32K [8,24]
#  L1 Data                 48K [9,25]
#  L1 Instruction          32K [9,25]
#  L1 Data                 48K [10,26]
#  L1 Instruction          32K [10,26]
#  L1 Data                 48K [11,27]
#  L1 Instruction          32K [11,27]
#  L1 Data                 48K [12,28]
#  L1 Instruction          32K [12,28]
#  L1 Data                 48K [13,29]
#  L1 Instruction          32K [13,29]
#  L1 Data                 48K [14,30]
#  L1 Instruction          32K [14,30]
#  L1 Data                 48K [15,31]
#  L1 Instruction          32K [15,31]
#  L2 Unified            1024K [0,16]
#  L2 Unified            1024K [1,17]
#  L2 Unified            1024K [2,18]
#  L2 Unified            1024K [3,19]
:

But not the cacheline size :-\

Please consider adding this header info :-)

Applied.

- Arnaldo
  
>  static int64_t
>  sort__typecln_sort(struct hist_entry *left, struct hist_entry *right)
> @@ -2484,6 +2483,10 @@ sort__typecln_sort(struct hist_entry *left, struct hist_entry *right)
>  	struct annotated_data_type *right_type = right->mem_type;
>  	int64_t left_cln, right_cln;
>  	int64_t ret;
> +	int cln_size = cacheline_size();
> +
> +	if (cln_size == 0)
> +		cln_size = DEFAULT_CACHELINE_SIZE;
>  
>  	if (!left_type) {
>  		sort__type_init(left);
> @@ -2499,8 +2502,8 @@ sort__typecln_sort(struct hist_entry *left, struct hist_entry *right)
>  	if (ret)
>  		return ret;
>  
> -	left_cln = left->mem_type_off / TYPE_CACHELINE_SIZE;
> -	right_cln = right->mem_type_off / TYPE_CACHELINE_SIZE;
> +	left_cln = left->mem_type_off / cln_size;
> +	right_cln = right->mem_type_off / cln_size;
>  	return left_cln - right_cln;
>  }
>  
> @@ -2508,9 +2511,13 @@ static int hist_entry__typecln_snprintf(struct hist_entry *he, char *bf,
>  				     size_t size, unsigned int width __maybe_unused)
>  {
>  	struct annotated_data_type *he_type = he->mem_type;
> +	int cln_size = cacheline_size();
> +
> +	if (cln_size == 0)
> +		cln_size = DEFAULT_CACHELINE_SIZE;
>  
>  	return repsep_snprintf(bf, size, "%s: cache-line %d", he_type->self.type_name,
> -			       he->mem_type_off / TYPE_CACHELINE_SIZE);
> +			       he->mem_type_off / cln_size);
>  }
>  
>  struct sort_entry sort_type_cacheline = {
> -- 
> 2.52.0
>