perf annotate-data: Support global variables

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>

1 files changed, 55 insertions, 2 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 655bd9443f5e..107b264fa41e 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -37,6 +37,7 @@
 #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>
@@ -3744,6 +3745,30 @@ static bool is_stack_operation(struct arch *arch, struct disasm_line *dl)
 	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
@@ -3763,7 +3788,9 @@ 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;
+	u64 ip = he->ip, addr = 0;
+	const char *var_name = NULL;
+	int var_offset;
 	int i;
 
 	ann_data_stat.total++;
@@ -3822,12 +3849,38 @@ retry:
 		/* 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,