perf annotate-data: Add a cache for global variable types

They are often searched by many different places.  Let's add a cache
for them to reduce the duplicate DWARF access.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240319055115.4063940-23-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index 633fe125fcd87979b6110ac81a15c70b205175d2..969e2f82079cdec535d1a26be7c14a5632ce2ddb 100644 (file)
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -433,6 +433,91 @@ static struct type_state_stack *findnew_stack_state(struct type_state *state,
        return stack;
 }
 
+/* Maintain a cache for quick global variable lookup */
+struct global_var_entry {
+       struct rb_node node;
+       char *name;
+       u64 start;
+       u64 end;
+       u64 die_offset;
+};
+
+static int global_var_cmp(const void *_key, const struct rb_node *node)
+{
+       const u64 addr = (uintptr_t)_key;
+       struct global_var_entry *gvar;
+
+       gvar = rb_entry(node, struct global_var_entry, node);
+
+       if (gvar->start <= addr && addr < gvar->end)
+               return 0;
+       return gvar->start > addr ? -1 : 1;
+}
+
+static bool global_var_less(struct rb_node *node_a, const struct rb_node *node_b)
+{
+       struct global_var_entry *gvar_a, *gvar_b;
+
+       gvar_a = rb_entry(node_a, struct global_var_entry, node);
+       gvar_b = rb_entry(node_b, struct global_var_entry, node);
+
+       return gvar_a->start < gvar_b->start;
+}
+
+static struct global_var_entry *global_var__find(struct data_loc_info *dloc, u64 addr)
+{
+       struct dso *dso = map__dso(dloc->ms->map);
+       struct rb_node *node;
+
+       node = rb_find((void *)(uintptr_t)addr, &dso->global_vars, global_var_cmp);
+       if (node == NULL)
+               return NULL;
+
+       return rb_entry(node, struct global_var_entry, node);
+}
+
+static bool global_var__add(struct data_loc_info *dloc, u64 addr,
+                           const char *name, Dwarf_Die *type_die)
+{
+       struct dso *dso = map__dso(dloc->ms->map);
+       struct global_var_entry *gvar;
+       Dwarf_Word size;
+
+       if (dwarf_aggregate_size(type_die, &size) < 0)
+               return false;
+
+       gvar = malloc(sizeof(*gvar));
+       if (gvar == NULL)
+               return false;
+
+       gvar->name = strdup(name);
+       if (gvar->name == NULL) {
+               free(gvar);
+               return false;
+       }
+
+       gvar->start = addr;
+       gvar->end = addr + size;
+       gvar->die_offset = dwarf_dieoffset(type_die);
+
+       rb_add(&gvar->node, &dso->global_vars, global_var_less);
+       return true;
+}
+
+void global_var_type__tree_delete(struct rb_root *root)
+{
+       struct global_var_entry *gvar;
+
+       while (!RB_EMPTY_ROOT(root)) {
+               struct rb_node *node = rb_first(root);
+
+               rb_erase(node, root);
+               gvar = rb_entry(node, struct global_var_entry, node);
+               free(gvar->name);
+               free(gvar);
+       }
+}
+
 static bool get_global_var_info(struct data_loc_info *dloc, u64 addr,
                                const char **var_name, int *var_offset)
 {
@@ -467,14 +552,25 @@ static bool get_global_var_type(Dwarf_Die *cu_die, struct data_loc_info *dloc,
        u64 pc;
        int offset;
        bool is_pointer = false;
-       const char *var_name;
+       const char *var_name = NULL;
+       struct global_var_entry *gvar;
        Dwarf_Die var_die;
 
+       gvar = global_var__find(dloc, var_addr);
+       if (gvar) {
+               if (!dwarf_offdie(dloc->di->dbg, gvar->die_offset, type_die))
+                       return false;
+
+               *var_offset = var_addr - gvar->start;
+               return true;
+       }
+
        /* Try to get the variable by address first */
        if (die_find_variable_by_addr(cu_die, var_addr, &var_die, &offset) &&
            check_variable(&var_die, type_die, offset, is_pointer) == 0) {
+               var_name = dwarf_diename(&var_die);
                *var_offset = offset;
-               return true;
+               goto ok;
        }
 
        if (!get_global_var_info(dloc, var_addr, &var_name, var_offset))
@@ -485,9 +581,14 @@ static bool get_global_var_type(Dwarf_Die *cu_die, struct data_loc_info *dloc,
        /* Try to get the name of global variable */
        if (die_find_variable_at(cu_die, var_name, pc, &var_die) &&
            check_variable(&var_die, type_die, *var_offset, is_pointer) == 0)
-               return true;
+               goto ok;
 
        return false;
+
+ok:
+       /* The address should point to the start of the variable */
+       global_var__add(dloc, var_addr - *var_offset, var_name, type_die);
+       return true;
 }
 
 /**

diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
index 1b5a152163b5950bca54278274d6f337bd623f1c..fe1e53d6e8c7f17d8ea0d1c0dae9d97507392829 100644 (file)
--- a/tools/perf/util/annotate-data.h
+++ b/tools/perf/util/annotate-data.h
@@ -153,6 +153,9 @@ int annotated_data_type__update_samples(struct annotated_data_type *adt,
 /* Release all data type information in the tree */
 void annotated_data_type__tree_delete(struct rb_root *root);
 
+/* Release all global variable information in the tree */
+void global_var_type__tree_delete(struct rb_root *root);
+
 #else /* HAVE_DWARF_SUPPORT */
 
 static inline struct annotated_data_type *
@@ -175,6 +178,10 @@ static inline void annotated_data_type__tree_delete(struct rb_root *root __maybe
 {
 }
 
+static inline void global_var_type__tree_delete(struct rb_root *root __maybe_unused)
+{
+}
+
 #endif /* HAVE_DWARF_SUPPORT */
 
 #endif /* _PERF_ANNOTATE_DATA_H */

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 22fd5fa806ed8f589ca1209710288c0e44ac19a2..6e2a7198b382acaf960cb3c252a51589e45bbb36 100644 (file)
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1329,6 +1329,7 @@ struct dso *dso__new_id(const char *name, struct dso_id *id)
                dso->inlined_nodes = RB_ROOT_CACHED;
                dso->srclines = RB_ROOT_CACHED;
                dso->data_types = RB_ROOT;
+               dso->global_vars = RB_ROOT;
                dso->data.fd = -1;
                dso->data.status = DSO_DATA_STATUS_UNKNOWN;
                dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
@@ -1373,6 +1374,7 @@ void dso__delete(struct dso *dso)
        dso->symbol_names_len = 0;
        zfree(&dso->symbol_names);
        annotated_data_type__tree_delete(&dso->data_types);
+       global_var_type__tree_delete(&dso->global_vars);
 
        if (dso->short_name_allocated) {
                zfree((char **)&dso->short_name);

diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index ce9f3849a773cc49c17b9835a675f895667843eb..2cdcd1e2ef8b93742fd20258b93fee9086b95f5e 100644 (file)
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -154,7 +154,8 @@ struct dso {
        size_t           symbol_names_len;
        struct rb_root_cached inlined_nodes;
        struct rb_root_cached srclines;
-       struct rb_root  data_types;
+       struct rb_root   data_types;
+       struct rb_root   global_vars;
 
        struct {
                u64             addr;
@@ -411,4 +412,7 @@ int dso__strerror_load(struct dso *dso, char *buf, size_t buflen);
 
 void reset_fd_limit(void);
 
+u64 dso__find_global_type(struct dso *dso, u64 addr);
+u64 dso__findnew_global_type(struct dso *dso, u64 addr, u64 offset);
+
 #endif /* __PERF_DSO */