| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20171112234014.2983360-4-songliubraving@fb.com>
Date: Sun, 12 Nov 2017 15:40:09 -0800
From: Song Liu <songliubraving@...com>
To: <peterz@...radead.org>, <rostedt@...dmis.org>, <mingo@...hat.com>,
<davem@...emloft.net>, <netdev@...r.kernel.org>, <ast@...nel.org>,
<daniel@...earbox.net>
CC: <kernel-team@...com>, Song Liu <songliubraving@...com>
Subject: [RFC] perf_event_open.2: add new type PERF_TYPE_PROBE
A new type PERF_TYPE_PROBE is being added to perf_event_attr. This
patch adds information about this type.
Note: the following two flags are also added to the man page. They
are from perf_event.h in latest kernel repo. However, they are not
related to PERF_TYPE_PROBE. Therefore, their usage are not included
in this patch.
write_backward : 1
namespaces : 1
Signed-off-by: Song Liu <songliubraving@...com>
---
man2/perf_event_open.2 | 82 ++++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 80 insertions(+), 2 deletions(-)
diff --git a/man2/perf_event_open.2 b/man2/perf_event_open.2
index 03dc748..a37b78b 100644
--- a/man2/perf_event_open.2
+++ b/man2/perf_event_open.2
@@ -205,7 +205,12 @@ for the event being created.
struct perf_event_attr {
__u32 type; /* Type of event */
__u32 size; /* Size of attribute structure */
- __u64 config; /* Type-specific configuration */
+
+ /* Type-specific configuration */
+ union {
+ __u64 config;
+ __u64 probe_desc; /* ptr to struct probe_desc */
+ };
union {
__u64 sample_period; /* Period of sampling */
@@ -244,8 +249,13 @@ struct perf_event_attr {
due to exec */
use_clockid : 1, /* use clockid for time fields */
context_switch : 1, /* context switch data */
+ write_backward : 1, /* Write ring buffer from end to beginning */
+ namespaces : 1, /* include namespaces data */
- __reserved_1 : 37;
+ /* For PERF_TYPE_PROBE */
+ is_uprobe : 1, /* 0 for kprobe, 1 for uprobe */
+ is_return : 1, /* 0 for [k,u]probe, 1 for [k,u]retprobe */
+ __reserved_1 : 33;
union {
__u32 wakeup_events; /* wakeup every n events */
@@ -336,6 +346,13 @@ field.
For instance,
.I /sys/bus/event_source/devices/cpu/type
contains the value for the core CPU PMU, which is usually 4.
+.TP
+.BR PERF_TYPE_PROBE " (since Linux 4.TBD)"
+This indicates a kprobe or uprobe should be created and
+attached to the file descriptor.
+See fields
+.IR probe_desc ", " is_uprobe ", and " is_return
+for more details.
.RE
.TP
.I "size"
@@ -627,6 +644,67 @@ then leave
.I config
set to zero.
Its parameters are set in other places.
+.PP
+If
+.I type
+is
+.BR PERF_TYPE_PROBE ,
+.I probe_desc
+is used instead of
+.IR config .
+.RE
+.TP
+.I probe_desc
+The
+.I probe_desc
+field is used with
+.I type
+of
+.BR PERF_TYPE_PROBE ,
+to save a pointer to struct probe_desc:
+.PP
+.in +8n
+.EX
+struct probe_desc {
+ union {
+ __aligned_u64 func;
+ __aligned_u64 path;
+ };
+ union {
+ __aligned_u64 addr;
+ __u64 offset;
+ };
+};
+.EE
+Different fields of struct probe_desc are used to describe kprobes
+and uprobes. For kprobes: use
+.I func
+and
+.IR offset ,
+or use
+.I addr
+and leave
+.I func
+as NULL. For uprobe: use
+.I path
+and
+.IR offset .
+.RE
+.TP
+.IR is_uprobe ", " is_return
+These two bits are used with
+.I type
+of
+.BR PERF_TYPE_PROBE ,
+to specify type of the probe:
+.PP
+.in +8n
+.EX
+is_uprobe == 0, is_return == 0: kprobe
+is_uprobe == 0, is_return == 1: kretprobe
+is_uprobe == 1, is_return == 0: uprobe
+is_uprobe == 1, is_return == 1: uretprobe
+.EE
.RE
.TP
.IR sample_period ", " sample_freq
--
2.9.5
Powered by blists - more mailing lists