summaryrefslogtreecommitdiff
path: root/include/uapi/linux/perf_event.h
diff options
context:
space:
mode:
authorAdrian Hunter <adrian.hunter@intel.com>2020-05-12 15:19:08 +0300
committerPeter Zijlstra <peterz@infradead.org>2020-06-15 15:09:48 +0300
commite17d43b93e544f5016c0251d2074c15568d5d963 (patch)
treeed92a3866abba36346c47c163d45c78fbad1beeb /include/uapi/linux/perf_event.h
parentbb85429a9bf2e7d370b8e1afd72f933a88f0629f (diff)
downloadlinux-e17d43b93e544f5016c0251d2074c15568d5d963.tar.xz
perf: Add perf text poke event
Record (single instruction) changes to the kernel text (i.e. self-modifying code) in order to support tracers like Intel PT and ARM CoreSight. A copy of the running kernel code is needed as a reference point (e.g. from /proc/kcore). The text poke event records the old bytes and the new bytes so that the event can be processed forwards or backwards. The basic problem is recording the modified instruction in an unambiguous manner given SMP instruction cache (in)coherence. That is, when modifying an instruction concurrently any solution with one or multiple timestamps is not sufficient: CPU0 CPU1 0 1 write insn A 2 execute insn A 3 sync-I$ 4 Due to I$, CPU1 might execute either the old or new A. No matter where we record tracepoints on CPU0, one simply cannot tell what CPU1 will have observed, except that at 0 it must be the old one and at 4 it must be the new one. To solve this, take inspiration from x86 text poking, which has to solve this exact problem due to variable length instruction encoding and I-fetch windows. 1) overwrite the instruction with a breakpoint and sync I$ This guarantees that that code flow will never hit the target instruction anymore, on any CPU (or rather, it will cause an exception). 2) issue the TEXT_POKE event 3) overwrite the breakpoint with the new instruction and sync I$ Now we know that any execution after the TEXT_POKE event will either observe the breakpoint (and hit the exception) or the new instruction. So by guarding the TEXT_POKE event with an exception on either side; we can now tell, without doubt, which instruction another CPU will have observed. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20200512121922.8997-2-adrian.hunter@intel.com
Diffstat (limited to 'include/uapi/linux/perf_event.h')
-rw-r--r--include/uapi/linux/perf_event.h21
1 files changed, 20 insertions, 1 deletions
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 7b2d6fc9e6ed..e5bee6c17b86 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -383,7 +383,8 @@ struct perf_event_attr {
bpf_event : 1, /* include bpf events */
aux_output : 1, /* generate AUX records instead of events */
cgroup : 1, /* include cgroup events */
- __reserved_1 : 31;
+ text_poke : 1, /* include text poke events */
+ __reserved_1 : 30;
union {
__u32 wakeup_events; /* wakeup every n events */
@@ -1024,6 +1025,24 @@ enum perf_event_type {
*/
PERF_RECORD_CGROUP = 19,
+ /*
+ * Records changes to kernel text i.e. self-modified code. 'old_len' is
+ * the number of old bytes, 'new_len' is the number of new bytes. Either
+ * 'old_len' or 'new_len' may be zero to indicate, for example, the
+ * addition or removal of a trampoline. 'bytes' contains the old bytes
+ * followed immediately by the new bytes.
+ *
+ * struct {
+ * struct perf_event_header header;
+ * u64 addr;
+ * u16 old_len;
+ * u16 new_len;
+ * u8 bytes[];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_TEXT_POKE = 20,
+
PERF_RECORD_MAX, /* non-ABI */
};