Received-SPF: pass (google.com: domain of linux-kernel+bounces-69505-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
From: Namhyung Kim <namhyung@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>,
	Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>,
	LKML <linux-kernel@vger.kernel.org>,
	linux-perf-users@vger.kernel.org,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Stephane Eranian <eranian@google.com>,
	Masami Hiramatsu <mhiramat@kernel.org>,
	linux-toolchains@vger.kernel.org,
	linux-trace-devel@vger.kernel.org
Subject: [PATCH 12/14] perf annotate-data: Handle this-cpu variables in kernel
Date: Fri, 16 Feb 2024 15:54:21 -0800
Message-ID: <20240216235423.2343167-13-namhyung@kernel.org>
In-Reply-To: <20240216235423.2343167-1-namhyung@kernel.org>
References: <20240216235423.2343167-1-namhyung@kernel.org>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

On x86, the kernel gets the current task using the current macro like
below:

  #define current  get_current()

  static __always_inline struct task_struct *get_current(void)
  {
      return this_cpu_read_stable(pcpu_hot.current_task);
  }

So it returns the current_task field of struct pcpu_hot which is the
first member.  On my build, it's located at 0x32940.

  $ nm vmlinux | grep pcpu_hot
  0000000000032940 D pcpu_hot

And the current macro generates the instructions like below:

  mov  %gs:0x32940, %rcx

So the %gs segment register points to the beginning of the per-cpu
region of this cpu and it points the variable with a constant.

Let's update the instruction location info to have a segment register
and handle %gs in kernel to look up a global variable.  The new
get_percpu_var_info() helper is to get information about the variable.
Pretend it as a global variable by changing the register number to
DWARF_REG_PC.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/annotate.c | 31 +++++++++++++++++++++++++++++++
 tools/perf/util/annotate.h |  4 ++++
 2 files changed, 35 insertions(+)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 86ac44c476bf..5f3136f57c62 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -3810,6 +3810,27 @@ void get_global_var_info(struct thread *thread, struct map_symbol *ms, u64 ip,
 	addr_location__exit(&al);
 }
 
+void get_percpu_var_info(struct thread *thread, struct map_symbol *ms,
+			 u8 cpumode, u64 var_addr, const char **var_name,
+			 int *poffset)
+{
+	struct addr_location al;
+	struct symbol *var;
+	u64 map_addr;
+
+	/* Kernel symbols might be relocated */
+	map_addr = var_addr + map__reloc(ms->map);
+
+	addr_location__init(&al);
+	var = thread__find_symbol_fb(thread, cpumode, map_addr, &al);
+	if (var) {
+		*var_name = var->name;
+		/* Calculate type offset from the start of variable */
+		*poffset = map_addr - map__unmap_ip(al.map, var->start);
+	}
+	addr_location__exit(&al);
+}
+
 /**
  * hist_entry__get_data_type - find data type for given hist entry
  * @he: hist entry
@@ -3906,6 +3927,16 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 					    &dloc.type_offset);
 		}
 
+		/* This CPU access in kernel - pretend PC-relative addressing */
+		if (op_loc->reg1 < 0 && map__dso(ms->map)->kernel &&
+		    arch__is(arch, "x86") && op_loc->segment == INSN_SEG_X86_GS) {
+			dloc.var_addr = op_loc->offset;
+			get_percpu_var_info(he->thread, ms, he->cpumode,
+					    dloc.var_addr, &dloc.var_name,
+					    &dloc.type_offset);
+			op_loc->reg1 = DWARF_REG_PC;
+		}
+
 		mem_type = find_data_type(&dloc);
 		if (mem_type)
 			istat->good++;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 2bd654620de3..490134d19c9d 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -513,6 +513,10 @@ void get_global_var_info(struct thread *thread, struct map_symbol *ms, u64 ip,
 			 struct disasm_line *dl, u8 cpumode, u64 *var_addr,
 			 const char **var_name, int *poffset);
 
+void get_percpu_var_info(struct thread *thread, struct map_symbol *ms,
+			 u8 cpumode, u64 var_addr, const char **var_name,
+			 int *poffset);
+
 /**
  * struct annotated_basic_block - Basic block of instructions
  * @list: List node
-- 
2.44.0.rc0.258.g7320e95886-goog