From dec07fe5d4fd29aed2faf17f56140cd402175d72 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 24 Oct 2023 15:23:13 -0700
Subject: perf callchain: Minor layout changes to callchain_list

Avoid 6 byte hole for padding. Place more frequently used fields
first in an attempt to use just 1 cacheline in the common case.

Before:
```
struct callchain_list {
        u64                        ip;                   /*     0     8 */
        struct map_symbol          ms;                   /*     8    24 */
        struct {
                _Bool              unfolded;             /*    32     1 */
                _Bool              has_children;         /*    33     1 */
        };                                               /*    32     2 */

        /* XXX 6 bytes hole, try to pack */

        u64                        branch_count;         /*    40     8 */
        u64                        from_count;           /*    48     8 */
        u64                        predicted_count;      /*    56     8 */
        /* --- cacheline 1 boundary (64 bytes) --- */
        u64                        abort_count;          /*    64     8 */
        u64                        cycles_count;         /*    72     8 */
        u64                        iter_count;           /*    80     8 */
        u64                        iter_cycles;          /*    88     8 */
        struct branch_type_stat *  brtype_stat;          /*    96     8 */
        const char  *              srcline;              /*   104     8 */
        struct list_head           list;                 /*   112    16 */

        /* size: 128, cachelines: 2, members: 13 */
        /* sum members: 122, holes: 1, sum holes: 6 */
};
```

After:
```
struct callchain_list {
        struct list_head           list;                 /*     0    16 */
        u64                        ip;                   /*    16     8 */
        struct map_symbol          ms;                   /*    24    24 */
        const char  *              srcline;              /*    48     8 */
        u64                        branch_count;         /*    56     8 */
        /* --- cacheline 1 boundary (64 bytes) --- */
        u64                        from_count;           /*    64     8 */
        u64                        cycles_count;         /*    72     8 */
        u64                        iter_count;           /*    80     8 */
        u64                        iter_cycles;          /*    88     8 */
        struct branch_type_stat *  brtype_stat;          /*    96     8 */
        u64                        predicted_count;      /*   104     8 */
        u64                        abort_count;          /*   112     8 */
        struct {
                _Bool              unfolded;             /*   120     1 */
                _Bool              has_children;         /*   121     1 */
        };                                               /*   120     2 */

        /* size: 128, cachelines: 2, members: 13 */
        /* padding: 6 */
};
```

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Nick Terrell <terrelln@fb.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: liuwenyu <liuwenyu7@huawei.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Song Liu <song@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Yanteng Si <siyanteng@loongson.cn>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20231024222353.3024098-11-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/callchain.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 86e8a9e81456..d5c66345ae31 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -116,22 +116,22 @@ extern struct callchain_param callchain_param;
 extern struct callchain_param callchain_param_default;
 
 struct callchain_list {
+	struct list_head	list;
 	u64			ip;
 	struct map_symbol	ms;
-	struct /* for TUI */ {
-		bool		unfolded;
-		bool		has_children;
-	};
+	const char		*srcline;
 	u64			branch_count;
 	u64			from_count;
-	u64			predicted_count;
-	u64			abort_count;
 	u64			cycles_count;
 	u64			iter_count;
 	u64			iter_cycles;
 	struct branch_type_stat *brtype_stat;
-	const char		*srcline;
-	struct list_head	list;
+	u64			predicted_count;
+	u64			abort_count;
+	struct /* for TUI */ {
+		bool		unfolded;
+		bool		has_children;
+	};
 };
 
 /*
-- 
cgit v1.2.3