[36/48] perf annotate-data: Introduce struct data_loc_info

  The find_data_type() needs many information to describe the location of
the data.  Add the new struct data_loc_info to pass those information at
once.

No functional changes intended.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/annotate-data.c | 83 +++++++++++++++++----------------
 tools/perf/util/annotate-data.h | 38 ++++++++++++---
 tools/perf/util/annotate.c      | 30 ++++++------
 3 files changed, 91 insertions(+), 60 deletions(-)
  

> On 12-Oct-2023, at 9:20 AM, Namhyung Kim <namhyung@kernel.org> wrote:
> 
> The find_data_type() needs many information to describe the location of
> the data.  Add the new struct data_loc_info to pass those information at
> once.
> 
> No functional changes intended.
> 
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
> tools/perf/util/annotate-data.c | 83 +++++++++++++++++----------------
> tools/perf/util/annotate-data.h | 38 ++++++++++++---
> tools/perf/util/annotate.c      | 30 ++++++------
> 3 files changed, 91 insertions(+), 60 deletions(-)
> 
> diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
> index 39bbd56b2160..90793cbb6aa0 100644
> --- a/tools/perf/util/annotate-data.c
> +++ b/tools/perf/util/annotate-data.c
> @@ -256,21 +256,28 @@ static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset,
> }
> 
> /* The result will be saved in @type_die */
> -static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
> -      const char *var_name, struct annotated_op_loc *loc,
> -      Dwarf_Die *type_die)
> +static int find_data_type_die(struct data_loc_info *dloc, Dwarf_Die *type_die)
> {
> + struct annotated_op_loc *loc = dloc->op;
> Dwarf_Die cu_die, var_die;
> Dwarf_Die *scopes = NULL;
> int reg, offset;
> int ret = -1;
> int i, nr_scopes;
> int fbreg = -1;
> - bool is_fbreg = false;
> int fb_offset = 0;
> + bool is_fbreg = false;
> + u64 pc;
> +
> + /*
> + * IP is a relative instruction address from the start of the map, as
> + * it can be randomized/relocated, it needs to translate to PC which is
> + * a file address for DWARF processing.
> + */
> + pc = map__rip_2objdump(dloc->ms->map, dloc->ip);
> 
> /* Get a compile_unit for this address */
> - if (!find_cu_die(di, pc, &cu_die)) {
> + if (!find_cu_die(dloc->di, pc, &cu_die)) {
> pr_debug("cannot find CU for address %lx\n", pc);
> ann_data_stat.no_cuinfo++;
> return -1;
> @@ -280,18 +287,19 @@ static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
> offset = loc->offset;
> 
> if (reg == DWARF_REG_PC) {
> - if (die_find_variable_by_addr(&cu_die, pc, addr, &var_die, &offset)) {
> + if (die_find_variable_by_addr(&cu_die, pc, dloc->var_addr,
> +      &var_die, &offset)) {
> ret = check_variable(&var_die, type_die, offset,
>     /*is_pointer=*/false);
> - loc->offset = offset;
> + dloc->type_offset = offset;
> goto out;
> }
> 
> - if (var_name && die_find_variable_at(&cu_die, var_name, pc,
> -     &var_die)) {
> - ret = check_variable(&var_die, type_die, 0,
> + if (dloc->var_name &&
> +    die_find_variable_at(&cu_die, dloc->var_name, pc, &var_die)) {
> + ret = check_variable(&var_die, type_die, dloc->type_offset,
>     /*is_pointer=*/false);
> - /* loc->offset will be updated by the caller */
> + /* dloc->type_offset was updated by the caller */
> goto out;
> }
> }
> @@ -308,10 +316,11 @@ static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
>    dwarf_formblock(&attr, &block) == 0 && block.length == 1) {
> switch (*block.data) {
> case DW_OP_reg0 ... DW_OP_reg31:
> - fbreg = *block.data - DW_OP_reg0;
> + fbreg = dloc->fbreg = *block.data - DW_OP_reg0;
> break;
> case DW_OP_call_frame_cfa:
> - if (die_get_cfa(di->dbg, pc, &fbreg,
> + dloc->fb_cfa = true;
> + if (die_get_cfa(dloc->di->dbg, pc, &fbreg,
> &fb_offset) < 0)
> fbreg = -1;
> break;
> @@ -329,7 +338,7 @@ static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
> /* Search from the inner-most scope to the outer */
> for (i = nr_scopes - 1; i >= 0; i--) {
> if (reg == DWARF_REG_PC) {
> - if (!die_find_variable_by_addr(&scopes[i], pc, addr,
> + if (!die_find_variable_by_addr(&scopes[i], pc, dloc->var_addr,
>       &var_die, &offset))
> continue;
> } else {
> @@ -342,7 +351,7 @@ static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
> /* Found a variable, see if it's correct */
> ret = check_variable(&var_die, type_die, offset,
>     reg != DWARF_REG_PC && !is_fbreg);
> - loc->offset = offset;
> + dloc->type_offset = offset;
> goto out;
> }
> 
> @@ -361,50 +370,46 @@ static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
> 
> /**
>  * find_data_type - Return a data type at the location
> - * @ms: map and symbol at the location
> - * @ip: instruction address of the memory access
> - * @loc: instruction operand location
> - * @addr: data address of the memory access
> - * @var_name: global variable name
> + * @dloc: data location
>  *
>  * This functions searches the debug information of the binary to get the data
> - * type it accesses.  The exact location is expressed by (@ip, reg, offset)
> - * for pointer variables or (@ip, @addr) for global variables.  Note that global
> - * variables might update the @loc->offset after finding the start of the variable.
> - * If it cannot find a global variable by address, it tried to fine a declaration
> - * of the variable using @var_name.  In that case, @loc->offset won't be updated.
> + * type it accesses.  The exact location is expressed by (ip, reg, offset)
> + * for pointer variables or (ip, addr) for global variables.  Note that global
> + * variables might update the @dloc->type_offset after finding the start of the
> + * variable.  If it cannot find a global variable by address, it tried to find
> + * a declaration of the variable using var_name.  In that case, @dloc->offset
> + * won't be updated.
>  *
>  * It return %NULL if not found.
>  */
> -struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
> -   struct annotated_op_loc *loc, u64 addr,
> -   const char *var_name)
> +struct annotated_data_type *find_data_type(struct data_loc_info *dloc)
> {
> struct annotated_data_type *result = NULL;
> - struct dso *dso = ms->map->dso;
> - struct debuginfo *di;
> + struct dso *dso = dloc->ms->map->dso;
> Dwarf_Die type_die;
> - u64 pc;
> 
> - di = debuginfo__new(dso->long_name);
> - if (di == NULL) {
> + dloc->di = debuginfo__new(dso->long_name);
> + if (dloc->di == NULL) {
> pr_debug("cannot get the debug info\n");
> return NULL;
> }
> 
> /*
> - * IP is a relative instruction address from the start of the map, as
> - * it can be randomized/relocated, it needs to translate to PC which is
> - * a file address for DWARF processing.
> + * The type offset is the same as instruction offset by default.
> + * But when finding a global variable, the offset won't be valid.
> */
> - pc = map__rip_2objdump(ms->map, ip);
> - if (find_data_type_die(di, pc, addr, var_name, loc, &type_die) < 0)
> + if (dloc->var_name == NULL)
> + dloc->type_offset = dloc->op->offset;
> +
> + dloc->fbreg = -1;
> +
> + if (find_data_type_die(dloc, &type_die) < 0)
> goto out;
> 
> result = dso__findnew_data_type(dso, &type_die);
> 
> out:
> - debuginfo__delete(di);
> + debuginfo__delete(dloc->di);
> return result;
> }
> 
> diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
> index 1b0db8e8c40e..ad6493ea2c8e 100644
> --- a/tools/perf/util/annotate-data.h
> +++ b/tools/perf/util/annotate-data.h
> @@ -8,6 +8,7 @@
> #include <linux/types.h>
> 
> struct annotated_op_loc;
> +struct debuginfo;
> struct evsel;
> struct map_symbol;
> 
> @@ -72,6 +73,35 @@ struct annotated_data_type {
> extern struct annotated_data_type unknown_type;
> extern struct annotated_data_type stackop_type;
> 
> +/**
> + * struct data_loc_info - Data location information
> + * @ms: Map and Symbol info
> + * @ip: Instruction address
> + * @var_addr: Data address (for global variables)
> + * @var_name: Variable name (for global variables)
> + * @op: Instruction operand location (regs and offset)
> + * @di: Debug info
> + * @fbreg: Frame base register
> + * @fb_cfa: Whether the frame needs to check CFA
> + * @type_offset: Final offset in the type
> + */
> +struct data_loc_info {
> + /* These are input field, should be filled by caller */
> + struct map_symbol *ms;
> + u64 ip;
> + u64 var_addr;
> + const char *var_name;
> + struct annotated_op_loc *op;
> +
> + /* These are used internally */
> + struct debuginfo *di;
> + int fbreg;
> + bool fb_cfa;
> +
> + /* This is for the result */
> + int type_offset;
> +};
> +
> /**
>  * struct annotated_data_stat - Debug statistics
>  * @total: Total number of entry
> @@ -106,9 +136,7 @@ extern struct annotated_data_stat ann_data_stat;
> #ifdef HAVE_DWARF_SUPPORT
> 
> /* Returns data type at the location (ip, reg, offset) */
> -struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
> -   struct annotated_op_loc *loc, u64 addr,
> -   const char *var_name);
> +struct annotated_data_type *find_data_type(struct data_loc_info *dloc);
> 
> /* Update type access histogram at the given offset */
> int annotated_data_type__update_samples(struct annotated_data_type *adt,
> @@ -121,9 +149,7 @@ void annotated_data_type__tree_delete(struct rb_root *root);
> #else /* HAVE_DWARF_SUPPORT */
> 
> static inline struct annotated_data_type *
> -find_data_type(struct map_symbol *ms __maybe_unused, u64 ip __maybe_unused,
> -       struct annotated_op_loc *loc __maybe_unused,
> -       u64 addr __maybe_unused, const char *var_name __maybe_unused)
> +find_data_type(struct data_loc_info *dloc __maybe_unused)
> {
> return NULL;
> }

Hi Namhyung,

I have a thought there. For the type and typeoff sort keys to work, we depend on Dwarf support in perf, right ?
If the perf is built without dwarf support ( either due to older elfutils or missing libdw.h ) , find_data_type will return NULL and we will get “unknown” for Data Type and Data Type Offset in the result.

Can we add a pr_debug line in find_data_type (which is in else part for HAVE_DWARF_SUPPORT) so that user can understand if “unknown” is due to missing devel during the build ? Or may be restrict -s type,typeoff if dwarf support is missing ?

Thanks
Athira
> diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
> index fe0074bb98f0..1cf55f903ee4 100644
> --- a/tools/perf/util/annotate.c
> +++ b/tools/perf/util/annotate.c
> @@ -3744,9 +3744,7 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
> struct annotated_op_loc *op_loc;
> struct annotated_data_type *mem_type;
> struct annotated_item_stat *istat;
> - u64 ip = he->ip, addr = 0;
> - const char *var_name = NULL;
> - int var_offset;
> + u64 ip = he->ip;
> int i;
> 
> ann_data_stat.total++;
> @@ -3794,51 +3792,53 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
> }
> 
> for_each_insn_op_loc(&loc, i, op_loc) {
> + struct data_loc_info dloc = {
> + .ms = ms,
> + /* Recalculate IP for LOCK prefix or insn fusion */
> + .ip = ms->sym->start + dl->al.offset,
> + .op = op_loc,
> + };
> +
> if (!op_loc->mem_ref)
> continue;
> 
> /* Recalculate IP because of LOCK prefix or insn fusion */
> ip = ms->sym->start + dl->al.offset;
> 
> - var_offset = op_loc->offset;
> -
> /* PC-relative addressing */
> if (op_loc->reg1 == DWARF_REG_PC) {
> struct addr_location al;
> struct symbol *var;
> u64 map_addr;
> 
> - addr = annotate_calc_pcrel(ms, ip, op_loc->offset, dl);
> + dloc.var_addr = annotate_calc_pcrel(ms, ip, op_loc->offset, dl);
> /* Kernel symbols might be relocated */
> - map_addr = addr + map__reloc(ms->map);
> + map_addr = dloc.var_addr + map__reloc(ms->map);
> 
> addr_location__init(&al);
> var = thread__find_symbol_fb(he->thread, he->cpumode,
>     map_addr, &al);
> if (var) {
> - var_name = var->name;
> + dloc.var_name = var->name;
> /* Calculate type offset from the start of variable */
> - var_offset = map_addr - map__unmap_ip(al.map, var->start);
> + dloc.type_offset = map_addr - map__unmap_ip(al.map, var->start);
> }
> addr_location__exit(&al);
> }
> 
> - mem_type = find_data_type(ms, ip, op_loc, addr, var_name);
> + mem_type = find_data_type(&dloc);
> if (mem_type)
> istat->good++;
> else
> istat->bad++;
> 
> - if (mem_type && var_name)
> - op_loc->offset = var_offset;
> -
> if (symbol_conf.annotate_data_sample) {
> annotated_data_type__update_samples(mem_type, evsel,
> -    op_loc->offset,
> +    dloc.type_offset,
>    he->stat.nr_events,
>    he->stat.period);
> }
> - he->mem_type_off = op_loc->offset;
> + he->mem_type_off = dloc.type_offset;
> return mem_type;
> }
> 
> -- 
> 2.42.0.655.g421f12c284-goog
>
  

Hello,

On Sun, Dec 3, 2023 at 8:22 AM Athira Rajeev
<atrajeev@linux.vnet.ibm.com> wrote:
> Hi Namhyung,
>
> I have a thought there. For the type and typeoff sort keys to work, we depend on Dwarf support in perf, right ?
> If the perf is built without dwarf support ( either due to older elfutils or missing libdw.h ) , find_data_type will return NULL and we will get “unknown” for Data Type and Data Type Offset in the result.

Yes, right.

>
> Can we add a pr_debug line in find_data_type (which is in else part for HAVE_DWARF_SUPPORT) so that user can understand if “unknown” is due to missing devel during the build ? Or may be restrict -s type,typeoff if dwarf support is missing ?

I think it's better to add a warning if DWARF is not supported.
Thanks for your review!

Namhyung
  

> On 05-Dec-2023, at 5:40 AM, Namhyung Kim <namhyung@kernel.org> wrote:
> 
> Hello,
> 
> On Sun, Dec 3, 2023 at 8:22 AM Athira Rajeev
> <atrajeev@linux.vnet.ibm.com> wrote:
>> Hi Namhyung,
>> 
>> I have a thought there. For the type and typeoff sort keys to work, we depend on Dwarf support in perf, right ?
>> If the perf is built without dwarf support ( either due to older elfutils or missing libdw.h ) , find_data_type will return NULL and we will get “unknown” for Data Type and Data Type Offset in the result.
> 
> Yes, right.
> 
>> 
>> Can we add a pr_debug line in find_data_type (which is in else part for HAVE_DWARF_SUPPORT) so that user can understand if “unknown” is due to missing devel during the build ? Or may be restrict -s type,typeoff if dwarf support is missing ?
> 
> I think it's better to add a warning if DWARF is not supported.
> Thanks for your review!

Sure, having a warning if DWARF is not supported will help

Thanks
Athira
> 
> Namhyung