Global variables are accessed using PC-relative address so it needs to
be handled separately. The PC-rel addressing is detected by using
DWARF_REG_PC. On x86, %rip register would be used.
The address can be calculated using the ip and offset in the
instruction. But it should start from the next instruction so add
calculate_pcrel_addr() to do it properly.
But global variables defined in a different file would only have a
declaration which doesn't include a location list. So it first tries
to get the type info using the address, and then looks up the variable
declarations using name. The name of global variables should be get
from the symbol table. The declaration would have the type info.
So extend find_var_type() to take both address and name for global
variables.
The stat is now looks like:
Annotate data type stats:
total 294, ok 153 (52.0%), bad 141 (48.0%)
-----------------------------------------------------------
30 : no_sym
32 : no_mem_ops
61 : no_var
10 : no_typeinfo
8 : bad_offset
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20240117062657.985479-7-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
/* The result will be saved in @type_die */
static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
- struct annotated_op_loc *loc, Dwarf_Die *type_die)
+ const char *var_name, struct annotated_op_loc *loc,
+ Dwarf_Die *type_die)
{
Dwarf_Die cu_die, var_die;
Dwarf_Die *scopes = NULL;
reg = loc->reg1;
offset = loc->offset;
- if (reg == DWARF_REG_PC &&
- die_find_variable_by_addr(&cu_die, pc, addr, &var_die, &offset)) {
- ret = check_variable(&var_die, type_die, offset,
- /*is_pointer=*/false);
- goto out;
+ if (reg == DWARF_REG_PC) {
+ if (die_find_variable_by_addr(&cu_die, pc, addr, &var_die, &offset)) {
+ ret = check_variable(&var_die, type_die, offset,
+ /*is_pointer=*/false);
+ loc->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,
+ /*is_pointer=*/false);
+ /* loc->offset will be updated by the caller */
+ goto out;
+ }
}
/* Get a list of nested scopes - i.e. (inlined) functions and blocks. */
/* Found a variable, see if it's correct */
ret = check_variable(&var_die, type_die, offset,
reg != DWARF_REG_PC);
+ loc->offset = offset;
goto out;
}
* @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
*
* 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).
+ * 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.
+ *
* It return %NULL if not found.
*/
struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
- struct annotated_op_loc *loc)
+ struct annotated_op_loc *loc, u64 addr,
+ const char *var_name)
{
struct annotated_data_type *result = NULL;
struct dso *dso = map__dso(ms->map);
* a file address for DWARF processing.
*/
pc = map__rip_2objdump(ms->map, ip);
- if (find_data_type_die(di, pc, 0, loc, &type_die) < 0)
+ if (find_data_type_die(di, pc, addr, var_name, loc, &type_die) < 0)
goto out;
result = dso__findnew_data_type(dso, &type_die);
/* 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);
+ struct annotated_op_loc *loc, u64 addr,
+ const char *var_name);
/* Update type access histogram at the given offset */
int annotated_data_type__update_samples(struct annotated_data_type *adt,
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)
+ struct annotated_op_loc *loc __maybe_unused,
+ u64 addr __maybe_unused, const char *var_name __maybe_unused)
{
return NULL;
}
#include "util/sharded_mutex.h"
#include "arch/common.h"
#include "namespaces.h"
+#include "thread.h"
#include <regex.h>
#include <linux/bitops.h>
#include <linux/kernel.h>
return false;
}
+u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset,
+ struct disasm_line *dl)
+{
+ struct annotation *notes;
+ struct disasm_line *next;
+ u64 addr;
+
+ notes = symbol__annotation(ms->sym);
+ /*
+ * PC-relative addressing starts from the next instruction address
+ * But the IP is for the current instruction. Since disasm_line
+ * doesn't have the instruction size, calculate it using the next
+ * disasm_line. If it's the last one, we can use symbol's end
+ * address directly.
+ */
+ if (&dl->al.node == notes->src->source.prev)
+ addr = ms->sym->end + offset;
+ else {
+ next = list_next_entry(dl, al.node);
+ addr = ip + (next->al.offset - dl->al.offset) + offset;
+ }
+ return map__rip_2objdump(ms->map, addr);
+}
+
/**
* hist_entry__get_data_type - find data type for given hist entry
* @he: hist entry
struct annotated_op_loc *op_loc;
struct annotated_data_type *mem_type;
struct annotated_item_stat *istat;
- u64 ip = he->ip;
+ u64 ip = he->ip, addr = 0;
+ const char *var_name = NULL;
+ int var_offset;
int i;
ann_data_stat.total++;
/* Recalculate IP because of LOCK prefix or insn fusion */
ip = ms->sym->start + dl->al.offset;
- mem_type = find_data_type(ms, ip, op_loc);
+ 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);
+ /* Kernel symbols might be relocated */
+ map_addr = 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;
+ /* Calculate type offset from the start of variable */
+ var_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);
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,
};
extern struct list_head ann_insn_stat;
+/* Calculate PC-relative address */
+u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset,
+ struct disasm_line *dl);
+
#endif /* __PERF_ANNOTATE_H */
projects / linux.git / commitdiff