Skip to contentSkip to conversation

perf/x86: Add perf text poke events

PATCH Applied Adrian Hunter 6 participants 45 messages May 12, 2020 – Jul 10, 2020

Subsystems (5)
x86 perf events Tracing ftrace +1 more subsystems
lore
Share & tools
lore

Adrian Hunter

author reviewer
#0 lore raw

v7 cover perf/x86: Add perf text poke events

Hi

Here are patches to add a text poke event to record changes to kernel text (i.e. self-modifying code) in order to support tracers like Intel PT decoding through jump labels, kprobes and ftrace trampolines.

The first 8 patches make the kernel changes and the subsequent patches are tools changes.

The next 4 patches add support for updating perf tools' data cache with the changed bytes.

The next patch is an Intel PT specific tools change.

The final 2 patches add perf script --show-text-poke-events option

Patches also here:

git://git.infradead.org/users/ahunter/linux-perf.git text_poke

Changes in V7

perf: Add perf text poke event
perf/x86: Add support for perf text poke event for text_poke_bp_batch() callers
kprobes: Add symbols for kprobe insn pages
kprobes: Add perf ksymbol events for kprobe insn pages
perf/x86: Add perf text poke events for kprobes
ftrace: Add symbols for ftrace trampolines
ftrace: Add perf ksymbol events for ftrace trampolines
ftrace: Add perf text poke events for ftrace trampolines

Added Peter's Ack
Improved commit message for text_poke events for ftrace trampolines

perf kcore_copy: Fix module map when there are no modules loaded perf evlist: Disable 'immediate' events last
perf tools: Add support for PERF_RECORD_TEXT_POKE perf tools: Add support for PERF_RECORD_KSYMBOL_TYPE_OOL perf intel-pt: Add support for text poke events
perf script: Add option --show-text-poke-events
perf script: Show text poke address symbol

Re-based on Arnaldo's perf/core branch

Changes in V6

perf: Add perf text poke event

Adjustments due to re-base on top of cgroup event patches

perf/x86: Add perf text poke events for kprobes

Expand commit message
Add Masami's Ack

perf tools: Add support for PERF_RECORD_TEXT_POKE

Adjustments due to re-base on top of cgroup event patches Improvements to perf_event__fprintf_text_poke()

perf script: Add option --show-text-poke-events
perf script: Show text poke address symbol

New patches

Changes in V5

perf/x86: Add perf text poke events for kprobes

Simplify optimized kprobes events (Peter)

Changes in V4

kprobes: Add symbols for kprobe insn pages

Change "module name" from kprobe to __builtin__kprobes Added comment about "module name" use

ftrace: Add symbols for ftrace trampolines

Change "module name" from ftrace to __builtin__ftrace Move calls of ftrace_add_trampoline_to_kallsyms() and ftrace_remove_trampoline_from_kallsyms() into kernel/trace/ftrace.c
Added comment about "module name" use

ftrace: Add perf ksymbol events for ftrace trampolines

Move changes into kernel/trace/ftrace.c

ftrace: Add perf text poke events for ftrace trampolines

Move changes into kernel/trace/ftrace.c

Changes in V3:

perf: Add perf text poke event

To prevent warning, cast pointer to (unsigned long) not (u64)

kprobes: Add symbols for kprobe insn pages

Expand commit message
Remove un-needed declarations of kprobe_cache_get_kallsym() and arch_kprobe_get_kallsym() when !CONFIG_KPROBES

ftrace: Add symbols for ftrace trampolines

Expand commit message
Make ftrace_get_trampoline_kallsym() static

Changes in V2:

perf: Add perf text poke event

Separate out x86 changes
The text poke event now has old len and new len Revised commit message

perf/x86: Add support for perf text poke event for text_poke_bp_batch() callers

New patch containing x86 changes from original first patch

kprobes: Add symbols for kprobe insn pages
kprobes: Add perf ksymbol events for kprobe insn pages perf/x86: Add perf text poke events for kprobes
ftrace: Add symbols for ftrace trampolines
ftrace: Add perf ksymbol events for ftrace trampolines
ftrace: Add perf text poke events for ftrace trampolines perf kcore_copy: Fix module map when there are no modules loaded perf evlist: Disable 'immediate' events last

New patches

perf tools: Add support for PERF_RECORD_TEXT_POKE

The text poke event now has old len and new len Also select ksymbol events with text poke events

perf tools: Add support for PERF_RECORD_KSYMBOL_TYPE_OOL

New patch

perf intel-pt: Add support for text poke events

The text poke event now has old len and new len Allow for the address not having a map yet

Changes since RFC:

Dropped 'flags' from the new event. The consensus seemed to be that text pokes should employ a scheme similar to x86's INT3 method instead.

dropped tools patches already applied.

Example:

For jump labels, the kernel needs
CONFIG_JUMP_LABEL=y
and also an easy to flip jump label is in sysctl_schedstats() which needs
CONFIG_SCHEDSTATS=y
CONFIG_PROC_SYSCTL=y
CONFIG_SCHED_DEBUG=y

Also note the 'sudo perf record' is put into the background which, as written, needs sudo credential caching (otherwise the background task will stop awaiting the sudo password), hence the 'sudo echo' to start.

Before:

  $ sudo echo
  $ sudo perf record -o perf.data.before --kcore -a -e intel_pt//k -m,64M &
  [1] 1640
  $ cat /proc/sys/kernel/sched_schedstats
  0
  $ sudo bash -c 'echo 1 > /proc/sys/kernel/sched_schedstats'
  $ cat /proc/sys/kernel/sched_schedstats
  1
  $ sudo bash -c 'echo 0 > /proc/sys/kernel/sched_schedstats'
  $ cat /proc/sys/kernel/sched_schedstats
  0
  $ sudo kill 1640
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 16.635 MB perf.data.before ]
  $ perf script -i perf.data.before --itrace=e >/dev/null
  Warning:
  1946 instruction trace errors

After:

  $ sudo echo
  $ sudo perf record -o perf.data.after --kcore -a -e intel_pt//k -m,64M &
  [1] 1882
  $ cat /proc/sys/kernel/sched_schedstats
  0
  $ sudo bash -c 'echo 1 > /proc/sys/kernel/sched_schedstats'
  $ cat /proc/sys/kernel/sched_schedstats
  1
  $ sudo bash -c 'echo 0 > /proc/sys/kernel/sched_schedstats'
  $ cat /proc/sys/kernel/sched_schedstats
  0
  $ sudo kill 1882
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 10.893 MB perf.data.after ]
  $ perf script -i perf.data.after --itrace=e
  $

Adrian Hunter (15):
perf: Add perf text poke event
perf/x86: Add support for perf text poke event for text_poke_bp_batch() callers
kprobes: Add symbols for kprobe insn pages
kprobes: Add perf ksymbol events for kprobe insn pages
perf/x86: Add perf text poke events for kprobes
ftrace: Add symbols for ftrace trampolines
ftrace: Add perf ksymbol events for ftrace trampolines
ftrace: Add perf text poke events for ftrace trampolines
perf kcore_copy: Fix module map when there are no modules loaded perf evlist: Disable 'immediate' events last
perf tools: Add support for PERF_RECORD_TEXT_POKE
perf tools: Add support for PERF_RECORD_KSYMBOL_TYPE_OOL
perf intel-pt: Add support for text poke events
perf script: Add option --show-text-poke-events
perf script: Show text poke address symbol

 arch/x86/include/asm/kprobes.h            |   2 +
 arch/x86/kernel/alternative.c             |  37 ++++++++++-
 arch/x86/kernel/kprobes/core.c            |  15 ++++-
 arch/x86/kernel/kprobes/opt.c             |  38 +++++++++--
 include/linux/ftrace.h                    |  12 ++--
 include/linux/kprobes.h                   |  15 +++++
 include/linux/perf_event.h                |   8 +++
 include/uapi/linux/perf_event.h           |  26 +++++++-
 kernel/events/core.c                      |  90 +++++++++++++++++++++++++-
 kernel/kallsyms.c                         |  42 +++++++++++--
 kernel/kprobes.c                          |  57 +++++++++++++++++
 kernel/trace/ftrace.c                     | 101 +++++++++++++++++++++++++++++-
 tools/include/uapi/linux/perf_event.h     |  26 +++++++-
 tools/lib/perf/include/perf/event.h       |   9 +++
 tools/perf/Documentation/perf-script.txt  |   4 ++
 tools/perf/arch/x86/util/intel-pt.c       |   4 ++
 tools/perf/builtin-record.c               |  45 +++++++++++++
 tools/perf/builtin-script.c               |  23 ++++++-
 tools/perf/tests/perf-record.c            |   4 +-
 tools/perf/util/dso.c                     |   3 +
 tools/perf/util/dso.h                     |   1 +
 tools/perf/util/event.c                   |  62 +++++++++++++++++-
 tools/perf/util/event.h                   |   9 ++-
 tools/perf/util/evlist.c                  |  31 ++++++---
 tools/perf/util/evsel.c                   |   7 ++-
 tools/perf/util/intel-pt.c                |  77 ++++++++++++++++++++++-
 tools/perf/util/machine.c                 |  49 +++++++++++++++
 tools/perf/util/machine.h                 |   3 +
 tools/perf/util/map.c                     |   5 ++
 tools/perf/util/map.h                     |   3 +-
 tools/perf/util/perf_api_probe.c          |  10 +++
 tools/perf/util/perf_api_probe.h          |   1 +
 tools/perf/util/perf_event_attr_fprintf.c |   1 +
 tools/perf/util/record.h                  |   1 +
 tools/perf/util/session.c                 |  23 +++++++
 tools/perf/util/symbol-elf.c              |   7 +++
 tools/perf/util/symbol.c                  |   1 +
 tools/perf/util/tool.h                    |   3 +-
 38 files changed, 815 insertions(+), 40 deletions(-)

Regards
Adrian

author reviewer
#1 lore raw

PATCH v7 1/15 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.

---
 include/linux/perf_event.h      |  8 +++
 include/uapi/linux/perf_event.h | 21 +++++++-
 kernel/events/core.c            | 90 ++++++++++++++++++++++++++++++++-
 3 files changed, 117 insertions(+), 2 deletions(-)
include/linux/perf_event.h +8 -0
index 87e21681759c..038f9678f030 100644
@@ -1232,6 +1232,9 @@ extern void perf_event_exec(void);
 extern void perf_event_comm(struct task_struct *tsk, bool exec);
 extern void perf_event_namespaces(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
+extern void perf_event_text_poke(const void *addr,
+				 const void *old_bytes, size_t old_len,
+				 const void *new_bytes, size_t new_len);
 
 /* Callchains */
 DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
@@ -1482,6 +1485,11 @@ static inline void perf_event_exec(void)				{ }
 static inline void perf_event_comm(struct task_struct *tsk, bool exec)	{ }
 static inline void perf_event_namespaces(struct task_struct *tsk)	{ }
 static inline void perf_event_fork(struct task_struct *tsk)		{ }
+static inline void perf_event_text_poke(const void *addr,
+					const void *old_bytes,
+					size_t old_len,
+					const void *new_bytes,
+					size_t new_len)			{ }
 static inline void perf_event_init(void)				{ }
 static inline int  perf_swevent_get_recursion_context(void)		{ return -1; }
 static inline void perf_swevent_put_recursion_context(int rctx)		{ }
include/uapi/linux/perf_event.h +20 -1
index 7b2d6fc9e6ed..e5bee6c17b86 100644
@@ -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 */
 };
 
kernel/events/core.c +89 -1

120 lines not on this page · raw message

Signature · 1 line
2.17.1
merge bot Applied
#2 lore raw

[tip: perf/core] perf: Add perf text poke event

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     e17d43b93e544f5016c0251d2074c15568d5d963
Gitweb:        https://git.kernel.org/tip/e17d43b93e544f5016c0251d2074c15568d5d963
Author:        Adrian Hunter <[email protected]>
AuthorDate:    Tue, 12 May 2020 15:19:08 +03:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Mon, 15 Jun 2020 14:09:48 +02:00

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.

---
 include/linux/perf_event.h      |  8 +++-
 include/uapi/linux/perf_event.h | 21 ++++++-
 kernel/events/core.c            | 90 +++++++++++++++++++++++++++++++-
 3 files changed, 117 insertions(+), 2 deletions(-)
include/linux/perf_event.h +8 -0
index b4bb320..46fe5cf 100644
@@ -1232,6 +1232,9 @@ extern void perf_event_exec(void);
 extern void perf_event_comm(struct task_struct *tsk, bool exec);
 extern void perf_event_namespaces(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
+extern void perf_event_text_poke(const void *addr,
+				 const void *old_bytes, size_t old_len,
+				 const void *new_bytes, size_t new_len);
 
 /* Callchains */
 DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
@@ -1479,6 +1482,11 @@ static inline void perf_event_exec(void)				{ }
 static inline void perf_event_comm(struct task_struct *tsk, bool exec)	{ }
 static inline void perf_event_namespaces(struct task_struct *tsk)	{ }
 static inline void perf_event_fork(struct task_struct *tsk)		{ }
+static inline void perf_event_text_poke(const void *addr,
+					const void *old_bytes,
+					size_t old_len,
+					const void *new_bytes,
+					size_t new_len)			{ }
 static inline void perf_event_init(void)				{ }
 static inline int  perf_swevent_get_recursion_context(void)		{ return -1; }
 static inline void perf_swevent_put_recursion_context(int rctx)		{ }
include/uapi/linux/perf_event.h +20 -1
index 7b2d6fc..e5bee6c 100644
@@ -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 */
 };
 
kernel/events/core.c +89 -1

120 lines not on this page · raw message

author reviewer
#3 lore raw

PATCH v7 2/15 perf/x86: Add support for perf text poke event for text_poke_bp_batch() callers

In reply to Adrian Hunter

Add support for perf text poke event for text_poke_bp_batch() callers. That includes jump labels. See comments for more details.

---
 arch/x86/kernel/alternative.c | 37 ++++++++++++++++++++++++++++++++++-
 1 file changed, 36 insertions(+), 1 deletion(-)
arch/x86/kernel/alternative.c +36 -1
index 7867dfb3963e..6082289879c1 100644
@@ -3,6 +3,7 @@
 
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/perf_event.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/stringify.h>
@@ -947,6 +948,7 @@ struct text_poke_loc {
 	s32 rel32;
 	u8 opcode;
 	const u8 text[POKE_MAX_OPCODE_SIZE];
+	u8 old;
 };
 
 struct bp_patching_desc {
@@ -1115,8 +1117,10 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	/*
 	 * First step: add a int3 trap to the address that will be patched.
 	 */
-	for (i = 0; i < nr_entries; i++)
+	for (i = 0; i < nr_entries; i++) {
+		tp[i].old = *(u8 *)text_poke_addr(&tp[i]);
 		text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE);
+	}
 
 	text_poke_sync();
 
@@ -1124,14 +1128,45 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	 * Second step: update all but the first byte of the patched range.
 	 */
 	for (do_sync = 0, i = 0; i < nr_entries; i++) {
+		u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, };
 		int len = text_opcode_size(tp[i].opcode);
 
 		if (len - INT3_INSN_SIZE > 0) {
+			memcpy(old + INT3_INSN_SIZE,
+			       text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
+			       len - INT3_INSN_SIZE);
 			text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
 				  (const char *)tp[i].text + INT3_INSN_SIZE,
 				  len - INT3_INSN_SIZE);
 			do_sync++;
 		}
+
+		/*
+		 * Emit a perf event to record the text poke, primarily to
+		 * support Intel PT decoding which must walk the executable code
+		 * to reconstruct the trace. The flow up to here is:
+		 *   - write INT3 byte
+		 *   - IPI-SYNC
+		 *   - write instruction tail
+		 * At this point the actual control flow will be through the
+		 * INT3 and handler and not hit the old or new instruction.
+		 * Intel PT outputs FUP/TIP packets for the INT3, so the flow
+		 * can still be decoded. Subsequently:
+		 *   - emit RECORD_TEXT_POKE with the new instruction
+		 *   - IPI-SYNC
+		 *   - write first byte
+		 *   - IPI-SYNC
+		 * So before the text poke event timestamp, the decoder will see
+		 * either the old instruction flow or FUP/TIP of INT3. After the
+		 * text poke event timestamp, the decoder will see either the
+		 * new instruction flow or FUP/TIP of INT3. Thus decoders can
+		 * use the timestamp as the point at which to modify the
+		 * executable code.
+		 * The old instruction is recorded so that the event can be
+		 * processed forwards or backwards.
+		 */
+		perf_event_text_poke(text_poke_addr(&tp[i]), old, len,
+				     tp[i].text, len);
 	}
 
 	if (do_sync) {
Signature · 1 line
2.17.1
merge bot Applied
#4 lore raw

[tip: perf/core] perf/x86: Add support for perf text poke event for text_poke_bp_batch() callers

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     d769811ca93303deb1d8729d20cceaca7051a6f1
Gitweb:        https://git.kernel.org/tip/d769811ca93303deb1d8729d20cceaca7051a6f1
Author:        Adrian Hunter <[email protected]>
AuthorDate:    Tue, 12 May 2020 15:19:09 +03:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Mon, 15 Jun 2020 14:09:48 +02:00

perf/x86: Add support for perf text poke event for text_poke_bp_batch() callers

Add support for perf text poke event for text_poke_bp_batch() callers. That includes jump labels. See comments for more details.

---
 arch/x86/kernel/alternative.c | 37 +++++++++++++++++++++++++++++++++-
 1 file changed, 36 insertions(+), 1 deletion(-)
arch/x86/kernel/alternative.c +36 -1
index 8fd39ff..f94c9f3 100644
@@ -3,6 +3,7 @@
 
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/perf_event.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/stringify.h>
@@ -1001,6 +1002,7 @@ struct text_poke_loc {
 	s32 rel32;
 	u8 opcode;
 	const u8 text[POKE_MAX_OPCODE_SIZE];
+	u8 old;
 };
 
 struct bp_patching_desc {
@@ -1168,8 +1170,10 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	/*
 	 * First step: add a int3 trap to the address that will be patched.
 	 */
-	for (i = 0; i < nr_entries; i++)
+	for (i = 0; i < nr_entries; i++) {
+		tp[i].old = *(u8 *)text_poke_addr(&tp[i]);
 		text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE);
+	}
 
 	text_poke_sync();
 
@@ -1177,14 +1181,45 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	 * Second step: update all but the first byte of the patched range.
 	 */
 	for (do_sync = 0, i = 0; i < nr_entries; i++) {
+		u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, };
 		int len = text_opcode_size(tp[i].opcode);
 
 		if (len - INT3_INSN_SIZE > 0) {
+			memcpy(old + INT3_INSN_SIZE,
+			       text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
+			       len - INT3_INSN_SIZE);
 			text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
 				  (const char *)tp[i].text + INT3_INSN_SIZE,
 				  len - INT3_INSN_SIZE);
 			do_sync++;
 		}
+
+		/*
+		 * Emit a perf event to record the text poke, primarily to
+		 * support Intel PT decoding which must walk the executable code
+		 * to reconstruct the trace. The flow up to here is:
+		 *   - write INT3 byte
+		 *   - IPI-SYNC
+		 *   - write instruction tail
+		 * At this point the actual control flow will be through the
+		 * INT3 and handler and not hit the old or new instruction.
+		 * Intel PT outputs FUP/TIP packets for the INT3, so the flow
+		 * can still be decoded. Subsequently:
+		 *   - emit RECORD_TEXT_POKE with the new instruction
+		 *   - IPI-SYNC
+		 *   - write first byte
+		 *   - IPI-SYNC
+		 * So before the text poke event timestamp, the decoder will see
+		 * either the old instruction flow or FUP/TIP of INT3. After the
+		 * text poke event timestamp, the decoder will see either the
+		 * new instruction flow or FUP/TIP of INT3. Thus decoders can
+		 * use the timestamp as the point at which to modify the
+		 * executable code.
+		 * The old instruction is recorded so that the event can be
+		 * processed forwards or backwards.
+		 */
+		perf_event_text_poke(text_poke_addr(&tp[i]), old, len,
+				     tp[i].text, len);
 	}
 
 	if (do_sync) {
author reviewer
#5 lore raw

PATCH v7 3/15 kprobes: Add symbols for kprobe insn pages

In reply to Adrian Hunter

Symbols are needed for tools to describe instruction addresses. Pages allocated for kprobe's purposes need symbols to be created for them. Add such symbols to be visible via /proc/kallsyms.

Note: kprobe insn pages are not used if ftrace is configured. To see the effect of this patch, the kernel must be configured with:

# CONFIG_FUNCTION_TRACER is not set
CONFIG_KPROBES=y

and for optimised kprobes:

CONFIG_OPTPROBES=y

Example on x86:

	# perf probe __schedule
	Added new event:
	  probe:__schedule     (on __schedule)
	# cat /proc/kallsyms | grep '\[__builtin__kprobes\]'
	ffffffffc00d4000 t kprobe_insn_page     [__builtin__kprobes]
	ffffffffc00d6000 t kprobe_optinsn_page  [__builtin__kprobes]

Note: This patch adds "__builtin__kprobes" as a module name in /proc/kallsyms for symbols for pages allocated for kprobes' purposes, even though "__builtin__kprobes" is not a module.

---
 include/linux/kprobes.h | 15 ++++++++++++++
 kernel/kallsyms.c       | 37 +++++++++++++++++++++++++++++----
 kernel/kprobes.c        | 45 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 93 insertions(+), 4 deletions(-)
include/linux/kprobes.h +15 -0
index 04bdaf01112c..62d682f47b5e 100644
@@ -242,6 +242,7 @@ struct kprobe_insn_cache {
 	struct mutex mutex;
 	void *(*alloc)(void);	/* allocate insn page */
 	void (*free)(void *);	/* free insn page */
+	const char *sym;	/* symbol for insn pages */
 	struct list_head pages; /* list of kprobe_insn_page */
 	size_t insn_size;	/* size of instruction slot */
 	int nr_garbage;
@@ -272,6 +273,8 @@ static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
 {									\
 	return __is_insn_slot_addr(&kprobe_##__name##_slots, addr);	\
 }
+#define KPROBE_INSN_PAGE_SYM		"kprobe_insn_page"
+#define KPROBE_OPTINSN_PAGE_SYM		"kprobe_optinsn_page"
 #else /* __ARCH_WANT_KPROBES_INSN_SLOT */
 #define DEFINE_INSN_CACHE_OPS(__name)					\
 static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
@@ -373,6 +376,13 @@ void dump_kprobe(struct kprobe *kp);
 void *alloc_insn_page(void);
 void free_insn_page(void *page);
 
+int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		       char *sym);
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym);
+
+int arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
+			    char *type, char *sym);
 #else /* !CONFIG_KPROBES: */
 
 static inline int kprobes_built_in(void)
@@ -435,6 +445,11 @@ static inline bool within_kprobe_blacklist(unsigned long addr)
 {
 	return true;
 }
+static inline int kprobe_get_kallsym(unsigned int symnum, unsigned long *value,
+				     char *type, char *sym)
+{
+	return -ERANGE;
+}
 #endif /* CONFIG_KPROBES */
 static inline int disable_kretprobe(struct kretprobe *rp)
 {
kernel/kallsyms.c +33 -4
index 16c8c605f4b0..c6cc293c0e67 100644
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/filter.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 #include <linux/compiler.h>
 
 /*
@@ -437,6 +438,7 @@ struct kallsym_iter {
 	loff_t pos_arch_end;
 	loff_t pos_mod_end;
 	loff_t pos_ftrace_mod_end;
+	loff_t pos_bpf_end;
 	unsigned long value;
 	unsigned int nameoff; /* If iterating in core kernel symbols. */
 	char type;
@@ -496,11 +498,33 @@ static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 
 static int get_ksymbol_bpf(struct kallsym_iter *iter)
 {
+	int ret;
+
 	strlcpy(iter->module_name, "bpf", MODULE_NAME_LEN);
 	iter->exported = 0;
-	return bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
-			       &iter->value, &iter->type,
-			       iter->name) < 0 ? 0 : 1;
+	ret = bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
+			      &iter->value, &iter->type,
+			      iter->name);
+	if (ret < 0) {
+		iter->pos_bpf_end = iter->pos;
+		return 0;
+	}
+
+	return 1;
+}
+
+/*
+ * This uses "__builtin__kprobes" as a module name for symbols for pages
+ * allocated for kprobes' purposes, even though "__builtin__kprobes" is not a
+ * module.
+ */
+static int get_ksymbol_kprobe(struct kallsym_iter *iter)
+{
+	strlcpy(iter->module_name, "__builtin__kprobes", MODULE_NAME_LEN);
+	iter->exported = 0;
+	return kprobe_get_kallsym(iter->pos - iter->pos_bpf_end,
+				  &iter->value, &iter->type,
+				  iter->name) < 0 ? 0 : 1;
 }
 
 /* Returns space to next name. */
@@ -527,6 +551,7 @@ static void reset_iter(struct kallsym_iter *iter, loff_t new_pos)
 		iter->pos_arch_end = 0;
 		iter->pos_mod_end = 0;
 		iter->pos_ftrace_mod_end = 0;
+		iter->pos_bpf_end = 0;
 	}
 }
 
@@ -551,7 +576,11 @@ static int update_iter_mod(struct kallsym_iter *iter, loff_t pos)
 	    get_ksymbol_ftrace_mod(iter))
 		return 1;
 
-	return get_ksymbol_bpf(iter);
+	if ((!iter->pos_bpf_end || iter->pos_bpf_end > pos) &&
+	    get_ksymbol_bpf(iter))
+		return 1;
+
+	return get_ksymbol_kprobe(iter);
 }
 
 /* Returns false if pos at or past end of file. */
kernel/kprobes.c +45 -0

63 lines not on this page · raw message

Signature · 1 line
2.17.1
maintainer
#6 lore raw

Re: [PATCH V7 03/15] kprobes: Add symbols for kprobe insn pages

Quoted 14 lines · Adrian Hunter
kernel/kprobes.c +10 -0
@@ -2179,6 +2181,49 @@ int kprobe_add_area_blacklist(unsigned long start, unsigned long end)
 	return 0;
 }
 
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym)
+{
+	struct kprobe_insn_page *kip;
+	int ret = -ERANGE;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(kip, &c->pages, list) {
+		if ((*symnum)--)
+			continue;

kernel/kprobes.c int kprobe_add_area_blacklist(unsigned long start, unsigned long end) · line 2203

Quoted 10 lines
kernel/kprobes.c +10 -0
+		strlcpy(sym, c->sym, KSYM_NAME_LEN);
+		*type = 't';
+		*value = (unsigned long)kip->insns;
+		ret = 0;
+		break;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}

This fails on sparc64-defconfig.

In file included from ../include/linux/kprobes.h:19:0,

                 from ../kernel/kprobes.c:21:

../kernel/kprobes.c: In function 'kprobe_cache_get_kallsym':
../include/linux/rculist.h:382:49: error: dereferencing pointer to incomplete type 'struct kprobe_insn_page'

Please provide a new patch.

maintainer
#7 lore raw

Re: [PATCH V7 03/15] kprobes: Add symbols for kprobe insn pages

Quoted 28 lines · On Wed, 27 May 2020 19:43:45 +0200 Peter Zijlstra <[email protected]> wrote:
Quoted 14 lines · Adrian Hunter
kernel/kprobes.c +10 -0
@@ -2179,6 +2181,49 @@ int kprobe_add_area_blacklist(unsigned long start, unsigned long end)
 	return 0;
 }
 
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym)
+{
+	struct kprobe_insn_page *kip;
+	int ret = -ERANGE;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(kip, &c->pages, list) {
+		if ((*symnum)--)
+			continue;

kernel/kprobes.c int kprobe_add_area_blacklist(unsigned long start, unsigned long end) · line 2203

Quoted 10 lines
kernel/kprobes.c +10 -0
+		strlcpy(sym, c->sym, KSYM_NAME_LEN);
+		*type = 't';
+		*value = (unsigned long)kip->insns;
+		ret = 0;
+		break;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}

This fails on sparc64-defconfig.

Quoted 6 lines

In file included from ../include/linux/kprobes.h:19:0,

                 from ../kernel/kprobes.c:21:

../kernel/kprobes.c: In function 'kprobe_cache_get_kallsym':
../include/linux/rculist.h:382:49: error: dereferencing pointer to incomplete type 'struct kprobe_insn_page'

Please provide a new patch.

Ah, yes. Since some archs doesn't require special out-of-line trampoline, we need to check __ARCH_WANT_KPROBES_INSN_SLOT, and if not, kprobe_cache_get_kallsym() has do nothing and return -ERANGE.

Thank you,

Signature · 1 line
Masami Hiramatsu <[email protected]>
author reviewer
#8 lore raw

Re: [PATCH V7 03/15] kprobes: Add symbols for kprobe insn pages

In reply to Peter Zijlstra
Quoted 28 lines · Peter Zijlstra
Quoted 14 lines · Adrian Hunter
kernel/kprobes.c +10 -0
@@ -2179,6 +2181,49 @@ int kprobe_add_area_blacklist(unsigned long start, unsigned long end)
 	return 0;
 }
 
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym)
+{
+	struct kprobe_insn_page *kip;
+	int ret = -ERANGE;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(kip, &c->pages, list) {
+		if ((*symnum)--)
+			continue;

kernel/kprobes.c int kprobe_add_area_blacklist(unsigned long start, unsigned long end) · line 2203

Quoted 10 lines
kernel/kprobes.c +10 -0
+		strlcpy(sym, c->sym, KSYM_NAME_LEN);
+		*type = 't';
+		*value = (unsigned long)kip->insns;
+		ret = 0;
+		break;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}

This fails on sparc64-defconfig.

Quoted 7 lines

In file included from ../include/linux/kprobes.h:19:0,

                 from ../kernel/kprobes.c:21:

../kernel/kprobes.c: In function 'kprobe_cache_get_kallsym':
../include/linux/rculist.h:382:49: error: dereferencing pointer to incomplete type 'struct kprobe_insn_page'

Please provide a new patch.

Yes, sorry about that.

author reviewer
#9 lore raw

PATCH v8 3/15 kprobes: Add symbols for kprobe insn pages

In reply to Peter Zijlstra

Symbols are needed for tools to describe instruction addresses. Pages allocated for kprobe's purposes need symbols to be created for them. Add such symbols to be visible via /proc/kallsyms.

Note: kprobe insn pages are not used if ftrace is configured. To see the effect of this patch, the kernel must be configured with:

# CONFIG_FUNCTION_TRACER is not set
CONFIG_KPROBES=y

and for optimised kprobes:

CONFIG_OPTPROBES=y

Example on x86:

	# perf probe __schedule
	Added new event:
	  probe:__schedule     (on __schedule)
	# cat /proc/kallsyms | grep '\[__builtin__kprobes\]'
	ffffffffc00d4000 t kprobe_insn_page     [__builtin__kprobes]
	ffffffffc00d6000 t kprobe_optinsn_page  [__builtin__kprobes]

Note: This patch adds "__builtin__kprobes" as a module name in /proc/kallsyms for symbols for pages allocated for kprobes' purposes, even though "__builtin__kprobes" is not a module.

---

Changes in V8:

Move kprobe_cache_get_kallsym() under __ARCH_WANT_KPROBES_INSN_SLOT

 include/linux/kprobes.h | 15 ++++++++++++++
 kernel/kallsyms.c       | 37 +++++++++++++++++++++++++++++----
 kernel/kprobes.c        | 45 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 93 insertions(+), 4 deletions(-)
include/linux/kprobes.h +15 -0
index 04bdaf01112c..39878bc9bcb0 100644
@@ -242,6 +242,7 @@ struct kprobe_insn_cache {
 	struct mutex mutex;
 	void *(*alloc)(void);	/* allocate insn page */
 	void (*free)(void *);	/* free insn page */
+	const char *sym;	/* symbol for insn pages */
 	struct list_head pages; /* list of kprobe_insn_page */
 	size_t insn_size;	/* size of instruction slot */
 	int nr_garbage;
@@ -272,6 +273,10 @@ static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
 {									\
 	return __is_insn_slot_addr(&kprobe_##__name##_slots, addr);	\
 }
+#define KPROBE_INSN_PAGE_SYM		"kprobe_insn_page"
+#define KPROBE_OPTINSN_PAGE_SYM		"kprobe_optinsn_page"
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym);
 #else /* __ARCH_WANT_KPROBES_INSN_SLOT */
 #define DEFINE_INSN_CACHE_OPS(__name)					\
 static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
@@ -373,6 +378,11 @@ void dump_kprobe(struct kprobe *kp);
 void *alloc_insn_page(void);
 void free_insn_page(void *page);
 
+int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		       char *sym);
+
+int arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
+			    char *type, char *sym);
 #else /* !CONFIG_KPROBES: */
 
 static inline int kprobes_built_in(void)
@@ -435,6 +445,11 @@ static inline bool within_kprobe_blacklist(unsigned long addr)
 {
 	return true;
 }
+static inline int kprobe_get_kallsym(unsigned int symnum, unsigned long *value,
+				     char *type, char *sym)
+{
+	return -ERANGE;
+}
 #endif /* CONFIG_KPROBES */
 static inline int disable_kretprobe(struct kretprobe *rp)
 {
kernel/kallsyms.c +33 -4
index 16c8c605f4b0..c6cc293c0e67 100644
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/filter.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 #include <linux/compiler.h>
 
 /*
@@ -437,6 +438,7 @@ struct kallsym_iter {
 	loff_t pos_arch_end;
 	loff_t pos_mod_end;
 	loff_t pos_ftrace_mod_end;
+	loff_t pos_bpf_end;
 	unsigned long value;
 	unsigned int nameoff; /* If iterating in core kernel symbols. */
 	char type;
@@ -496,11 +498,33 @@ static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 
 static int get_ksymbol_bpf(struct kallsym_iter *iter)
 {
+	int ret;
+
 	strlcpy(iter->module_name, "bpf", MODULE_NAME_LEN);
 	iter->exported = 0;
-	return bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
-			       &iter->value, &iter->type,
-			       iter->name) < 0 ? 0 : 1;
+	ret = bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
+			      &iter->value, &iter->type,
+			      iter->name);
+	if (ret < 0) {
+		iter->pos_bpf_end = iter->pos;
+		return 0;
+	}
+
+	return 1;
+}
+
+/*
+ * This uses "__builtin__kprobes" as a module name for symbols for pages
+ * allocated for kprobes' purposes, even though "__builtin__kprobes" is not a
+ * module.
+ */
+static int get_ksymbol_kprobe(struct kallsym_iter *iter)
+{
+	strlcpy(iter->module_name, "__builtin__kprobes", MODULE_NAME_LEN);
+	iter->exported = 0;
+	return kprobe_get_kallsym(iter->pos - iter->pos_bpf_end,
+				  &iter->value, &iter->type,
+				  iter->name) < 0 ? 0 : 1;
 }
 
 /* Returns space to next name. */
@@ -527,6 +551,7 @@ static void reset_iter(struct kallsym_iter *iter, loff_t new_pos)
 		iter->pos_arch_end = 0;
 		iter->pos_mod_end = 0;
 		iter->pos_ftrace_mod_end = 0;
+		iter->pos_bpf_end = 0;
 	}
 }
 
@@ -551,7 +576,11 @@ static int update_iter_mod(struct kallsym_iter *iter, loff_t pos)
 	    get_ksymbol_ftrace_mod(iter))
 		return 1;
 
-	return get_ksymbol_bpf(iter);
+	if ((!iter->pos_bpf_end || iter->pos_bpf_end > pos) &&
+	    get_ksymbol_bpf(iter))
+		return 1;
+
+	return get_ksymbol_kprobe(iter);
 }
 
 /* Returns false if pos at or past end of file. */
kernel/kprobes.c +45 -0

69 lines not on this page · raw message

Signature · 1 line
2.17.1
merge bot Applied
#10 lore raw

[tip: perf/core] kprobes: Add symbols for kprobe insn pages

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     d002b8bc6dbc20e9043e279196cff8795dba05fe
Gitweb:        https://git.kernel.org/tip/d002b8bc6dbc20e9043e279196cff8795dba05fe
Author:        Adrian Hunter <[email protected]>
AuthorDate:    Thu, 28 May 2020 11:00:58 +03:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Mon, 15 Jun 2020 14:09:48 +02:00

kprobes: Add symbols for kprobe insn pages

Symbols are needed for tools to describe instruction addresses. Pages allocated for kprobe's purposes need symbols to be created for them. Add such symbols to be visible via /proc/kallsyms.

Note: kprobe insn pages are not used if ftrace is configured. To see the effect of this patch, the kernel must be configured with:

# CONFIG_FUNCTION_TRACER is not set
CONFIG_KPROBES=y

and for optimised kprobes:

CONFIG_OPTPROBES=y

Example on x86:

	# perf probe __schedule
	Added new event:
	  probe:__schedule     (on __schedule)
	# cat /proc/kallsyms | grep '\[__builtin__kprobes\]'
	ffffffffc00d4000 t kprobe_insn_page     [__builtin__kprobes]
	ffffffffc00d6000 t kprobe_optinsn_page  [__builtin__kprobes]

Note: This patch adds "__builtin__kprobes" as a module name in /proc/kallsyms for symbols for pages allocated for kprobes' purposes, even though "__builtin__kprobes" is not a module.

---
 include/linux/kprobes.h | 15 +++++++++++++-
 kernel/kallsyms.c       | 37 +++++++++++++++++++++++++++++----
 kernel/kprobes.c        | 45 ++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 93 insertions(+), 4 deletions(-)
include/linux/kprobes.h +15 -0
index 594265b..13fc58a 100644
@@ -242,6 +242,7 @@ struct kprobe_insn_cache {
 	struct mutex mutex;
 	void *(*alloc)(void);	/* allocate insn page */
 	void (*free)(void *);	/* free insn page */
+	const char *sym;	/* symbol for insn pages */
 	struct list_head pages; /* list of kprobe_insn_page */
 	size_t insn_size;	/* size of instruction slot */
 	int nr_garbage;
@@ -272,6 +273,10 @@ static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
 {									\
 	return __is_insn_slot_addr(&kprobe_##__name##_slots, addr);	\
 }
+#define KPROBE_INSN_PAGE_SYM		"kprobe_insn_page"
+#define KPROBE_OPTINSN_PAGE_SYM		"kprobe_optinsn_page"
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym);
 #else /* __ARCH_WANT_KPROBES_INSN_SLOT */
 #define DEFINE_INSN_CACHE_OPS(__name)					\
 static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
@@ -373,6 +378,11 @@ void dump_kprobe(struct kprobe *kp);
 void *alloc_insn_page(void);
 void free_insn_page(void *page);
 
+int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		       char *sym);
+
+int arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
+			    char *type, char *sym);
 #else /* !CONFIG_KPROBES: */
 
 static inline int kprobes_built_in(void)
@@ -435,6 +445,11 @@ static inline bool within_kprobe_blacklist(unsigned long addr)
 {
 	return true;
 }
+static inline int kprobe_get_kallsym(unsigned int symnum, unsigned long *value,
+				     char *type, char *sym)
+{
+	return -ERANGE;
+}
 #endif /* CONFIG_KPROBES */
 static inline int disable_kretprobe(struct kretprobe *rp)
 {
kernel/kallsyms.c +33 -4
index 16c8c60..c6cc293 100644
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/filter.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 #include <linux/compiler.h>
 
 /*
@@ -437,6 +438,7 @@ struct kallsym_iter {
 	loff_t pos_arch_end;
 	loff_t pos_mod_end;
 	loff_t pos_ftrace_mod_end;
+	loff_t pos_bpf_end;
 	unsigned long value;
 	unsigned int nameoff; /* If iterating in core kernel symbols. */
 	char type;
@@ -496,11 +498,33 @@ static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 
 static int get_ksymbol_bpf(struct kallsym_iter *iter)
 {
+	int ret;
+
 	strlcpy(iter->module_name, "bpf", MODULE_NAME_LEN);
 	iter->exported = 0;
-	return bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
-			       &iter->value, &iter->type,
-			       iter->name) < 0 ? 0 : 1;
+	ret = bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
+			      &iter->value, &iter->type,
+			      iter->name);
+	if (ret < 0) {
+		iter->pos_bpf_end = iter->pos;
+		return 0;
+	}
+
+	return 1;
+}
+
+/*
+ * This uses "__builtin__kprobes" as a module name for symbols for pages
+ * allocated for kprobes' purposes, even though "__builtin__kprobes" is not a
+ * module.
+ */
+static int get_ksymbol_kprobe(struct kallsym_iter *iter)
+{
+	strlcpy(iter->module_name, "__builtin__kprobes", MODULE_NAME_LEN);
+	iter->exported = 0;
+	return kprobe_get_kallsym(iter->pos - iter->pos_bpf_end,
+				  &iter->value, &iter->type,
+				  iter->name) < 0 ? 0 : 1;
 }
 
 /* Returns space to next name. */
@@ -527,6 +551,7 @@ static void reset_iter(struct kallsym_iter *iter, loff_t new_pos)
 		iter->pos_arch_end = 0;
 		iter->pos_mod_end = 0;
 		iter->pos_ftrace_mod_end = 0;
+		iter->pos_bpf_end = 0;
 	}
 }
 
@@ -551,7 +576,11 @@ static int update_iter_mod(struct kallsym_iter *iter, loff_t pos)
 	    get_ksymbol_ftrace_mod(iter))
 		return 1;
 
-	return get_ksymbol_bpf(iter);
+	if ((!iter->pos_bpf_end || iter->pos_bpf_end > pos) &&
+	    get_ksymbol_bpf(iter))
+		return 1;
+
+	return get_ksymbol_kprobe(iter);
 }
 
 /* Returns false if pos at or past end of file. */
kernel/kprobes.c +45 -0

69 lines not on this page · raw message

maintainer Acked-by on v7 3/15
#11 lore raw

Re: [PATCH V7 03/15] kprobes: Add symbols for kprobe insn pages

In reply to Adrian Hunter
Quoted 6 lines · On Tue, 12 May 2020 15:19:10 +0300 Adrian Hunter <[email protected]>…

Symbols are needed for tools to describe instruction addresses. Pages allocated for kprobe's purposes need symbols to be created for them. Add such symbols to be visible via /proc/kallsyms.

Note: kprobe insn pages are not used if ftrace is configured. To see the effect of this patch, the kernel must be configured with:

Note, if you put a probe inside the function body, kprobe_insn_pages is used even if ftrace is configured.
(Ftrace is used only for the function entry)

Quoted 17 lines

# CONFIG_FUNCTION_TRACER is not set
CONFIG_KPROBES=y

and for optimised kprobes:

CONFIG_OPTPROBES=y

Example on x86:

	# perf probe __schedule
	Added new event:
	  probe:__schedule     (on __schedule)
	# cat /proc/kallsyms | grep '\[__builtin__kprobes\]'
	ffffffffc00d4000 t kprobe_insn_page     [__builtin__kprobes]
	ffffffffc00d6000 t kprobe_optinsn_page  [__builtin__kprobes]
Quoted 3 lines

Note: This patch adds "__builtin__kprobes" as a module name in /proc/kallsyms for symbols for pages allocated for kprobes' purposes, even though "__builtin__kprobes" is not a module.

Anyway, except for the Peter's sparc64 issue, the code is good to me.

Thank you,

Quoted 207 lines
---
 include/linux/kprobes.h | 15 ++++++++++++++
 kernel/kallsyms.c       | 37 +++++++++++++++++++++++++++++----
 kernel/kprobes.c        | 45 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 93 insertions(+), 4 deletions(-)
include/linux/kprobes.h +15 -0
index 04bdaf01112c..62d682f47b5e 100644
@@ -242,6 +242,7 @@ struct kprobe_insn_cache {
 	struct mutex mutex;
 	void *(*alloc)(void);	/* allocate insn page */
 	void (*free)(void *);	/* free insn page */
+	const char *sym;	/* symbol for insn pages */
 	struct list_head pages; /* list of kprobe_insn_page */
 	size_t insn_size;	/* size of instruction slot */
 	int nr_garbage;
@@ -272,6 +273,8 @@ static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
 {									\
 	return __is_insn_slot_addr(&kprobe_##__name##_slots, addr);	\
 }
+#define KPROBE_INSN_PAGE_SYM		"kprobe_insn_page"
+#define KPROBE_OPTINSN_PAGE_SYM		"kprobe_optinsn_page"
 #else /* __ARCH_WANT_KPROBES_INSN_SLOT */
 #define DEFINE_INSN_CACHE_OPS(__name)					\
 static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
@@ -373,6 +376,13 @@ void dump_kprobe(struct kprobe *kp);
 void *alloc_insn_page(void);
 void free_insn_page(void *page);
 
+int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		       char *sym);
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym);
+
+int arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
+			    char *type, char *sym);
 #else /* !CONFIG_KPROBES: */
 
 static inline int kprobes_built_in(void)
@@ -435,6 +445,11 @@ static inline bool within_kprobe_blacklist(unsigned long addr)
 {
 	return true;
 }
+static inline int kprobe_get_kallsym(unsigned int symnum, unsigned long *value,
+				     char *type, char *sym)
+{
+	return -ERANGE;
+}
 #endif /* CONFIG_KPROBES */
 static inline int disable_kretprobe(struct kretprobe *rp)
 {
kernel/kallsyms.c +33 -4
index 16c8c605f4b0..c6cc293c0e67 100644
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/filter.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 #include <linux/compiler.h>
 
 /*
@@ -437,6 +438,7 @@ struct kallsym_iter {
 	loff_t pos_arch_end;
 	loff_t pos_mod_end;
 	loff_t pos_ftrace_mod_end;
+	loff_t pos_bpf_end;
 	unsigned long value;
 	unsigned int nameoff; /* If iterating in core kernel symbols. */
 	char type;
@@ -496,11 +498,33 @@ static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 
 static int get_ksymbol_bpf(struct kallsym_iter *iter)
 {
+	int ret;
+
 	strlcpy(iter->module_name, "bpf", MODULE_NAME_LEN);
 	iter->exported = 0;
-	return bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
-			       &iter->value, &iter->type,
-			       iter->name) < 0 ? 0 : 1;
+	ret = bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
+			      &iter->value, &iter->type,
+			      iter->name);
+	if (ret < 0) {
+		iter->pos_bpf_end = iter->pos;
+		return 0;
+	}
+
+	return 1;
+}
+
+/*
+ * This uses "__builtin__kprobes" as a module name for symbols for pages
+ * allocated for kprobes' purposes, even though "__builtin__kprobes" is not a
+ * module.
+ */
+static int get_ksymbol_kprobe(struct kallsym_iter *iter)
+{
+	strlcpy(iter->module_name, "__builtin__kprobes", MODULE_NAME_LEN);
+	iter->exported = 0;
+	return kprobe_get_kallsym(iter->pos - iter->pos_bpf_end,
+				  &iter->value, &iter->type,
+				  iter->name) < 0 ? 0 : 1;
 }
 
 /* Returns space to next name. */
@@ -527,6 +551,7 @@ static void reset_iter(struct kallsym_iter *iter, loff_t new_pos)
 		iter->pos_arch_end = 0;
 		iter->pos_mod_end = 0;
 		iter->pos_ftrace_mod_end = 0;
+		iter->pos_bpf_end = 0;
 	}
 }
 
@@ -551,7 +576,11 @@ static int update_iter_mod(struct kallsym_iter *iter, loff_t pos)
 	    get_ksymbol_ftrace_mod(iter))
 		return 1;
 
-	return get_ksymbol_bpf(iter);
+	if ((!iter->pos_bpf_end || iter->pos_bpf_end > pos) &&
+	    get_ksymbol_bpf(iter))
+		return 1;
+
+	return get_ksymbol_kprobe(iter);
 }
 
 /* Returns false if pos at or past end of file. */
kernel/kprobes.c +45 -0
index 2625c241ac00..229d1b596690 100644
@@ -118,6 +118,7 @@ struct kprobe_insn_cache kprobe_insn_slots = {
 	.mutex = __MUTEX_INITIALIZER(kprobe_insn_slots.mutex),
 	.alloc = alloc_insn_page,
 	.free = free_insn_page,
+	.sym = KPROBE_INSN_PAGE_SYM,
 	.pages = LIST_HEAD_INIT(kprobe_insn_slots.pages),
 	.insn_size = MAX_INSN_SIZE,
 	.nr_garbage = 0,
@@ -296,6 +297,7 @@ struct kprobe_insn_cache kprobe_optinsn_slots = {
 	.mutex = __MUTEX_INITIALIZER(kprobe_optinsn_slots.mutex),
 	.alloc = alloc_insn_page,
 	.free = free_insn_page,
+	.sym = KPROBE_OPTINSN_PAGE_SYM,
 	.pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages),
 	/* .insn_size is initialized later */
 	.nr_garbage = 0,
@@ -2179,6 +2181,49 @@ int kprobe_add_area_blacklist(unsigned long start, unsigned long end)
 	return 0;
 }
 
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym)
+{
+	struct kprobe_insn_page *kip;
+	int ret = -ERANGE;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(kip, &c->pages, list) {
+		if ((*symnum)--)
+			continue;
+		strlcpy(sym, c->sym, KSYM_NAME_LEN);
+		*type = 't';
+		*value = (unsigned long)kip->insns;
+		ret = 0;
+		break;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+int __weak arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
+				   char *type, char *sym)
+{
+	return -ERANGE;
+}
+
+int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		       char *sym)
+{
+#ifdef __ARCH_WANT_KPROBES_INSN_SLOT
+	if (!kprobe_cache_get_kallsym(&kprobe_insn_slots, &symnum, value, type, sym))
+		return 0;
+#ifdef CONFIG_OPTPROBES
+	if (!kprobe_cache_get_kallsym(&kprobe_optinsn_slots, &symnum, value, type, sym))
+		return 0;
+#endif
+#endif
+	if (!arch_kprobe_get_kallsym(&symnum, value, type, sym))
+		return 0;
+	return -ERANGE;
+}
+
 int __init __weak arch_populate_kprobe_blacklist(void)
 {
 	return 0;
Signature · 1 line
2.17.1
Signature · 1 line
Masami Hiramatsu <[email protected]>
author reviewer
#12 lore raw

PATCH v7 4/15 kprobes: Add perf ksymbol events for kprobe insn pages

In reply to Adrian Hunter

Symbols are needed for tools to describe instruction addresses. Pages allocated for kprobe's purposes need symbols to be created for them. Add such symbols to be visible via perf ksymbol events.

---
 include/uapi/linux/perf_event.h |  5 +++++
 kernel/kprobes.c                | 12 ++++++++++++
 2 files changed, 17 insertions(+)
include/uapi/linux/perf_event.h +5 -0
index e5bee6c17b86..e1a4179144a1 100644
@@ -1049,6 +1049,11 @@ enum perf_event_type {
 enum perf_record_ksymbol_type {
 	PERF_RECORD_KSYMBOL_TYPE_UNKNOWN	= 0,
 	PERF_RECORD_KSYMBOL_TYPE_BPF		= 1,
+	/*
+	 * Out of line code such as kprobe-replaced instructions or optimized
+	 * kprobes.
+	 */
+	PERF_RECORD_KSYMBOL_TYPE_OOL		= 2,
 	PERF_RECORD_KSYMBOL_TYPE_MAX		/* non-ABI */
 };
 
kernel/kprobes.c +12 -0
index 229d1b596690..f880eb2189c0 100644
@@ -35,6 +35,7 @@
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <linux/jump_label.h>
+#include <linux/perf_event.h>
 
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
@@ -184,6 +185,10 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
 	kip->cache = c;
 	list_add_rcu(&kip->list, &c->pages);
 	slot = kip->insns;
+
+	/* Record the perf ksymbol register event after adding the page */
+	perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (u64)kip->insns,
+			   PAGE_SIZE, false, c->sym);
 out:
 	mutex_unlock(&c->mutex);
 	return slot;
@@ -202,6 +207,13 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
 		 * next time somebody inserts a probe.
 		 */
 		if (!list_is_singular(&kip->list)) {
+			/*
+			 * Record perf ksymbol unregister event before removing
+			 * the page.
+			 */
+			perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+					   (u64)kip->insns, PAGE_SIZE, true,
+					   kip->cache->sym);
 			list_del_rcu(&kip->list);
 			synchronize_rcu();
 			kip->cache->free(kip->insns);
Signature · 1 line
2.17.1
maintainer
#13 lore raw

Re: [PATCH V7 04/15] kprobes: Add perf ksymbol events for kprobe insn pages

Quoted 4 lines · Adrian Hunter
kernel/kprobes.c +0 -0
@@ -202,6 +207,13 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
 		 * next time somebody inserts a probe.
 		 */
 		if (!list_is_singular(&kip->list)) {

kernel/kprobes.c static int collect_one_slot(struct kprobe_insn_page *kip, int idx) · line 219

Quoted 10 lines
kernel/kprobes.c +7 -0
+			/*
+			 * Record perf ksymbol unregister event before removing
+			 * the page.
+			 */
+			perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+					   (u64)kip->insns, PAGE_SIZE, true,
+					   kip->cache->sym);
 			list_del_rcu(&kip->list);
 			synchronize_rcu();
 			kip->cache->free(kip->insns);

My manual build script haz complaints:

i386-defconfig ../kernel/kprobes.c: In function ‘__get_insn_slot’:
../kernel/kprobes.c:190:51: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast] perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (u64)kip->insns,
^
../kernel/kprobes.c: In function ‘collect_one_slot’:
../kernel/kprobes.c:215:9: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast] (u64)kip->insns, PAGE_SIZE, true,
^
FAIL

Now, there's a ton of such warnings elsewhere in the tree, but still I feel we should perhaps strive for a clean build.

maintainer
#14 lore raw

Re: [PATCH V7 04/15] kprobes: Add perf ksymbol events for kprobe insn pages

Quoted 29 lines · Peter Zijlstra
Quoted 4 lines · Adrian Hunter
kernel/kprobes.c +0 -0
@@ -202,6 +207,13 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
 		 * next time somebody inserts a probe.
 		 */
 		if (!list_is_singular(&kip->list)) {

kernel/kprobes.c static int collect_one_slot(struct kprobe_insn_page *kip, int idx) · line 219

Quoted 10 lines
kernel/kprobes.c +7 -0
+			/*
+			 * Record perf ksymbol unregister event before removing
+			 * the page.
+			 */
+			perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+					   (u64)kip->insns, PAGE_SIZE, true,
+					   kip->cache->sym);
 			list_del_rcu(&kip->list);
 			synchronize_rcu();
 			kip->cache->free(kip->insns);

My manual build script haz complaints:

i386-defconfig ../kernel/kprobes.c: In function ‘__get_insn_slot’:
../kernel/kprobes.c:190:51: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast] perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (u64)kip->insns,
^
../kernel/kprobes.c: In function ‘collect_one_slot’:
../kernel/kprobes.c:215:9: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast] (u64)kip->insns, PAGE_SIZE, true,
^
FAIL

Quoted 2 lines

Now, there's a ton of such warnings elsewhere in the tree, but still I feel we should perhaps strive for a clean build.

Fixed those for you. On to cross-builds... :/

author reviewer
#15 lore raw

Re: [PATCH V7 04/15] kprobes: Add perf ksymbol events for kprobe insn pages

Quoted 30 lines · Peter Zijlstra
Quoted 29 lines · Peter Zijlstra
Quoted 4 lines · Adrian Hunter
kernel/kprobes.c +0 -0
@@ -202,6 +207,13 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
 		 * next time somebody inserts a probe.
 		 */
 		if (!list_is_singular(&kip->list)) {

kernel/kprobes.c static int collect_one_slot(struct kprobe_insn_page *kip, int idx) · line 219

Quoted 10 lines
kernel/kprobes.c +7 -0
+			/*
+			 * Record perf ksymbol unregister event before removing
+			 * the page.
+			 */
+			perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+					   (u64)kip->insns, PAGE_SIZE, true,
+					   kip->cache->sym);
 			list_del_rcu(&kip->list);
 			synchronize_rcu();
 			kip->cache->free(kip->insns);

My manual build script haz complaints:

i386-defconfig ../kernel/kprobes.c: In function ‘__get_insn_slot’:
../kernel/kprobes.c:190:51: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast] perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (u64)kip->insns,
^
../kernel/kprobes.c: In function ‘collect_one_slot’:
../kernel/kprobes.c:215:9: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast] (u64)kip->insns, PAGE_SIZE, true,
^
FAIL

Quoted 5 lines
Quoted 2 lines

Now, there's a ton of such warnings elsewhere in the tree, but still I feel we should perhaps strive for a clean build.

Fixed those for you. On to cross-builds... :/

Thank you!

merge bot Applied
#16 lore raw

[tip: perf/core] kprobes: Add perf ksymbol events for kprobe insn pages

In reply to Adrian Hunter
The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     69e49088692899d25dedfa22f00dfb9761e86ed7
Gitweb:        https://git.kernel.org/tip/69e49088692899d25dedfa22f00dfb9761e86ed7
Author:        Adrian Hunter <[email protected]>
AuthorDate:    Tue, 12 May 2020 15:19:11 +03:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Mon, 15 Jun 2020 14:09:49 +02:00

kprobes: Add perf ksymbol events for kprobe insn pages

Symbols are needed for tools to describe instruction addresses. Pages allocated for kprobe's purposes need symbols to be created for them. Add such symbols to be visible via perf ksymbol events.

---
 include/uapi/linux/perf_event.h |  5 +++++
 kernel/kprobes.c                | 12 ++++++++++++
 2 files changed, 17 insertions(+)
include/uapi/linux/perf_event.h +5 -0
index e5bee6c..e1a4179 100644
@@ -1049,6 +1049,11 @@ enum perf_event_type {
 enum perf_record_ksymbol_type {
 	PERF_RECORD_KSYMBOL_TYPE_UNKNOWN	= 0,
 	PERF_RECORD_KSYMBOL_TYPE_BPF		= 1,
+	/*
+	 * Out of line code such as kprobe-replaced instructions or optimized
+	 * kprobes.
+	 */
+	PERF_RECORD_KSYMBOL_TYPE_OOL		= 2,
 	PERF_RECORD_KSYMBOL_TYPE_MAX		/* non-ABI */
 };
 
kernel/kprobes.c +12 -0
index 058c0be..2b58740 100644
@@ -35,6 +35,7 @@
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <linux/jump_label.h>
+#include <linux/perf_event.h>
 
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
@@ -184,6 +185,10 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
 	kip->cache = c;
 	list_add_rcu(&kip->list, &c->pages);
 	slot = kip->insns;
+
+	/* Record the perf ksymbol register event after adding the page */
+	perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (unsigned long)kip->insns,
+			   PAGE_SIZE, false, c->sym);
 out:
 	mutex_unlock(&c->mutex);
 	return slot;
@@ -202,6 +207,13 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
 		 * next time somebody inserts a probe.
 		 */
 		if (!list_is_singular(&kip->list)) {
+			/*
+			 * Record perf ksymbol unregister event before removing
+			 * the page.
+			 */
+			perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+					   (unsigned long)kip->insns, PAGE_SIZE, true,
+					   kip->cache->sym);
 			list_del_rcu(&kip->list);
 			synchronize_rcu();
 			kip->cache->free(kip->insns);
author reviewer
#17 lore raw

PATCH v7 5/15 perf/x86: Add perf text poke events for kprobes

In reply to Adrian Hunter

Add perf text poke events for kprobes. That includes:

- the replaced instruction(s) which are executed out-of-line i.e. arch_copy_kprobe() and arch_remove_kprobe()

- the INT3 that activates the kprobe
i.e. arch_arm_kprobe() and arch_disarm_kprobe()

- optimised kprobe function
i.e. arch_prepare_optimized_kprobe() and
__arch_remove_optimized_kprobe()

- optimised kprobe
i.e. arch_optimize_kprobes() and arch_unoptimize_kprobe()

Resulting in 8 possible text_poke events:

0: NULL -> probe.ainsn.insn (if ainsn.boostable && !kp.post_handler)
arch_copy_kprobe()

1: old0 -> INT3 arch_arm_kprobe()

// boosted kprobe active

2: NULL -> optprobe_trampoline arch_prepare_optimized_kprobe()

3: INT3,old1,old2,old3,old4 -> JMP32 arch_optimize_kprobes()

// optprobe active

4: JMP32 -> INT3,old1,old2,old3,old4

// optprobe disabled and kprobe active (this sometimes goes back to 3)
arch_unoptimize_kprobe()

5: optprobe_trampoline -> NULL arch_remove_optimized_kprobe()

// boosted kprobe active

6: INT3 -> old0 arch_disarm_kprobe()

7: probe.ainsn.insn -> NULL (if ainsn.boostable && !kp.post_handler)
arch_remove_kprobe()

---
 arch/x86/include/asm/kprobes.h |  2 ++
 arch/x86/kernel/kprobes/core.c | 15 +++++++++++++-
 arch/x86/kernel/kprobes/opt.c  | 38 +++++++++++++++++++++++++++++-----
 3 files changed, 49 insertions(+), 6 deletions(-)
arch/x86/include/asm/kprobes.h +2 -0
index 073eb7ad2f56..143bc9abe99c 100644
@@ -66,6 +66,8 @@ struct arch_specific_insn {
 	 */
 	bool boostable;
 	bool if_modifier;
+	/* Number of bytes of text poked */
+	int tp_len;
 };
 
 struct arch_optimized_insn {
arch/x86/kernel/kprobes/core.c +14 -1
index 4d7022a740ab..6d8b58c84cbc 100644
@@ -33,6 +33,7 @@
 #include <linux/hardirq.h>
 #include <linux/preempt.h>
 #include <linux/sched/debug.h>
+#include <linux/perf_event.h>
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
@@ -471,6 +472,9 @@ static int arch_copy_kprobe(struct kprobe *p)
 	/* Also, displacement change doesn't affect the first byte */
 	p->opcode = buf[0];
 
+	p->ainsn.tp_len = len;
+	perf_event_text_poke(p->ainsn.insn, NULL, 0, buf, len);
+
 	/* OK, write back the instruction(s) into ROX insn buffer */
 	text_poke(p->ainsn.insn, buf, len);
 
@@ -502,12 +506,18 @@ int arch_prepare_kprobe(struct kprobe *p)
 
 void arch_arm_kprobe(struct kprobe *p)
 {
-	text_poke(p->addr, ((unsigned char []){INT3_INSN_OPCODE}), 1);
+	u8 int3 = INT3_INSN_OPCODE;
+
+	text_poke(p->addr, &int3, 1);
 	text_poke_sync();
+	perf_event_text_poke(p->addr, &p->opcode, 1, &int3, 1);
 }
 
 void arch_disarm_kprobe(struct kprobe *p)
 {
+	u8 int3 = INT3_INSN_OPCODE;
+
+	perf_event_text_poke(p->addr, &int3, 1, &p->opcode, 1);
 	text_poke(p->addr, &p->opcode, 1);
 	text_poke_sync();
 }
@@ -515,6 +525,9 @@ void arch_disarm_kprobe(struct kprobe *p)
 void arch_remove_kprobe(struct kprobe *p)
 {
 	if (p->ainsn.insn) {
+		/* Record the perf event before freeing the slot */
+		perf_event_text_poke(p->ainsn.insn, p->ainsn.insn,
+				     p->ainsn.tp_len, NULL, 0);
 		free_insn_slot(p->ainsn.insn, p->ainsn.boostable);
 		p->ainsn.insn = NULL;
 	}
arch/x86/kernel/kprobes/opt.c +33 -5
index ea13f6888284..f86be31d37cc 100644
@@ -6,6 +6,7 @@
  * Copyright (C) Hitachi Ltd., 2012
  */
 #include <linux/kprobes.h>
+#include <linux/perf_event.h>
 #include <linux/ptrace.h>
 #include <linux/string.h>
 #include <linux/slab.h>
@@ -354,8 +355,15 @@ int arch_within_optimized_kprobe(struct optimized_kprobe *op,
 static
 void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
 {
-	if (op->optinsn.insn) {
-		free_optinsn_slot(op->optinsn.insn, dirty);
+	u8 *slot = op->optinsn.insn;
+	if (slot) {
+		int len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE;
+
+		/* Record the perf event before freeing the slot */
+		if (dirty)
+			perf_event_text_poke(slot, slot, len, NULL, 0);
+
+		free_optinsn_slot(slot, dirty);
 		op->optinsn.insn = NULL;
 		op->optinsn.size = 0;
 	}
@@ -426,8 +434,15 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
 			   (u8 *)op->kp.addr + op->optinsn.size);
 	len += JMP32_INSN_SIZE;
 
+	/*
+	 * Note	len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE is also
+	 * used in __arch_remove_optimized_kprobe().
+	 */
+
 	/* We have to use text_poke() for instruction buffer because it is RO */
+	perf_event_text_poke(slot, NULL, 0, buf, len);
 	text_poke(slot, buf, len);
+
 	ret = 0;
 out:
 	kfree(buf);
@@ -479,10 +494,23 @@ void arch_optimize_kprobes(struct list_head *oplist)
  */
 void arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
-	arch_arm_kprobe(&op->kp);
-	text_poke(op->kp.addr + INT3_INSN_SIZE,
-		  op->optinsn.copied_insn, DISP32_SIZE);
+	u8 new[JMP32_INSN_SIZE] = { INT3_INSN_OPCODE, };
+	u8 old[JMP32_INSN_SIZE];
+	u8 *addr = op->kp.addr;
+
+	memcpy(old, op->kp.addr, JMP32_INSN_SIZE);
+	memcpy(new + INT3_INSN_SIZE,
+	       op->optinsn.copied_insn,
+	       JMP32_INSN_SIZE - INT3_INSN_SIZE);
+
+	text_poke(addr, new, INT3_INSN_SIZE);
 	text_poke_sync();
+	text_poke(addr + INT3_INSN_SIZE,
+		  new + INT3_INSN_SIZE,
+		  JMP32_INSN_SIZE - INT3_INSN_SIZE);
+	text_poke_sync();
+
+	perf_event_text_poke(op->kp.addr, old, JMP32_INSN_SIZE, new, JMP32_INSN_SIZE);
 }
 
 /*
Signature · 1 line
2.17.1
merge bot Applied
#18 lore raw

[tip: perf/core] perf/x86: Add perf text poke events for kprobes

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     3e46bb40af8c12947c093efb8af56e0e921cd39b
Gitweb:        https://git.kernel.org/tip/3e46bb40af8c12947c093efb8af56e0e921cd39b
Author:        Adrian Hunter <[email protected]>
AuthorDate:    Tue, 12 May 2020 15:19:12 +03:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Mon, 15 Jun 2020 14:09:49 +02:00

perf/x86: Add perf text poke events for kprobes

Add perf text poke events for kprobes. That includes:

- the replaced instruction(s) which are executed out-of-line i.e. arch_copy_kprobe() and arch_remove_kprobe()

- the INT3 that activates the kprobe
i.e. arch_arm_kprobe() and arch_disarm_kprobe()

- optimised kprobe function
i.e. arch_prepare_optimized_kprobe() and
__arch_remove_optimized_kprobe()

- optimised kprobe
i.e. arch_optimize_kprobes() and arch_unoptimize_kprobe()

Resulting in 8 possible text_poke events:

0: NULL -> probe.ainsn.insn (if ainsn.boostable && !kp.post_handler)
arch_copy_kprobe()

1: old0 -> INT3 arch_arm_kprobe()

// boosted kprobe active

2: NULL -> optprobe_trampoline arch_prepare_optimized_kprobe()

3: INT3,old1,old2,old3,old4 -> JMP32 arch_optimize_kprobes()

// optprobe active

4: JMP32 -> INT3,old1,old2,old3,old4

// optprobe disabled and kprobe active (this sometimes goes back to 3)
arch_unoptimize_kprobe()

5: optprobe_trampoline -> NULL arch_remove_optimized_kprobe()

// boosted kprobe active

6: INT3 -> old0 arch_disarm_kprobe()

7: probe.ainsn.insn -> NULL (if ainsn.boostable && !kp.post_handler)
arch_remove_kprobe()

---
 arch/x86/include/asm/kprobes.h |  2 ++-
 arch/x86/kernel/kprobes/core.c | 15 ++++++++++++-
 arch/x86/kernel/kprobes/opt.c  | 38 ++++++++++++++++++++++++++++-----
 3 files changed, 49 insertions(+), 6 deletions(-)
arch/x86/include/asm/kprobes.h +2 -0
index 073eb7a..143bc9a 100644
@@ -66,6 +66,8 @@ struct arch_specific_insn {
 	 */
 	bool boostable;
 	bool if_modifier;
+	/* Number of bytes of text poked */
+	int tp_len;
 };
 
 struct arch_optimized_insn {
arch/x86/kernel/kprobes/core.c +14 -1
index 3bafe1b..bcc53c0 100644
@@ -33,6 +33,7 @@
 #include <linux/hardirq.h>
 #include <linux/preempt.h>
 #include <linux/sched/debug.h>
+#include <linux/perf_event.h>
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
@@ -471,6 +472,9 @@ static int arch_copy_kprobe(struct kprobe *p)
 	/* Also, displacement change doesn't affect the first byte */
 	p->opcode = buf[0];
 
+	p->ainsn.tp_len = len;
+	perf_event_text_poke(p->ainsn.insn, NULL, 0, buf, len);
+
 	/* OK, write back the instruction(s) into ROX insn buffer */
 	text_poke(p->ainsn.insn, buf, len);
 
@@ -502,12 +506,18 @@ int arch_prepare_kprobe(struct kprobe *p)
 
 void arch_arm_kprobe(struct kprobe *p)
 {
-	text_poke(p->addr, ((unsigned char []){INT3_INSN_OPCODE}), 1);
+	u8 int3 = INT3_INSN_OPCODE;
+
+	text_poke(p->addr, &int3, 1);
 	text_poke_sync();
+	perf_event_text_poke(p->addr, &p->opcode, 1, &int3, 1);
 }
 
 void arch_disarm_kprobe(struct kprobe *p)
 {
+	u8 int3 = INT3_INSN_OPCODE;
+
+	perf_event_text_poke(p->addr, &int3, 1, &p->opcode, 1);
 	text_poke(p->addr, &p->opcode, 1);
 	text_poke_sync();
 }
@@ -515,6 +525,9 @@ void arch_disarm_kprobe(struct kprobe *p)
 void arch_remove_kprobe(struct kprobe *p)
 {
 	if (p->ainsn.insn) {
+		/* Record the perf event before freeing the slot */
+		perf_event_text_poke(p->ainsn.insn, p->ainsn.insn,
+				     p->ainsn.tp_len, NULL, 0);
 		free_insn_slot(p->ainsn.insn, p->ainsn.boostable);
 		p->ainsn.insn = NULL;
 	}
arch/x86/kernel/kprobes/opt.c +33 -5
index 321c199..3239b6a 100644
@@ -6,6 +6,7 @@
  * Copyright (C) Hitachi Ltd., 2012
  */
 #include <linux/kprobes.h>
+#include <linux/perf_event.h>
 #include <linux/ptrace.h>
 #include <linux/string.h>
 #include <linux/slab.h>
@@ -352,8 +353,15 @@ int arch_within_optimized_kprobe(struct optimized_kprobe *op,
 static
 void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
 {
-	if (op->optinsn.insn) {
-		free_optinsn_slot(op->optinsn.insn, dirty);
+	u8 *slot = op->optinsn.insn;
+	if (slot) {
+		int len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE;
+
+		/* Record the perf event before freeing the slot */
+		if (dirty)
+			perf_event_text_poke(slot, slot, len, NULL, 0);
+
+		free_optinsn_slot(slot, dirty);
 		op->optinsn.insn = NULL;
 		op->optinsn.size = 0;
 	}
@@ -424,8 +432,15 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
 			   (u8 *)op->kp.addr + op->optinsn.size);
 	len += JMP32_INSN_SIZE;
 
+	/*
+	 * Note	len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE is also
+	 * used in __arch_remove_optimized_kprobe().
+	 */
+
 	/* We have to use text_poke() for instruction buffer because it is RO */
+	perf_event_text_poke(slot, NULL, 0, buf, len);
 	text_poke(slot, buf, len);
+
 	ret = 0;
 out:
 	kfree(buf);
@@ -477,10 +492,23 @@ void arch_optimize_kprobes(struct list_head *oplist)
  */
 void arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
-	arch_arm_kprobe(&op->kp);
-	text_poke(op->kp.addr + INT3_INSN_SIZE,
-		  op->optinsn.copied_insn, DISP32_SIZE);
+	u8 new[JMP32_INSN_SIZE] = { INT3_INSN_OPCODE, };
+	u8 old[JMP32_INSN_SIZE];
+	u8 *addr = op->kp.addr;
+
+	memcpy(old, op->kp.addr, JMP32_INSN_SIZE);
+	memcpy(new + INT3_INSN_SIZE,
+	       op->optinsn.copied_insn,
+	       JMP32_INSN_SIZE - INT3_INSN_SIZE);
+
+	text_poke(addr, new, INT3_INSN_SIZE);
 	text_poke_sync();
+	text_poke(addr + INT3_INSN_SIZE,
+		  new + INT3_INSN_SIZE,
+		  JMP32_INSN_SIZE - INT3_INSN_SIZE);
+	text_poke_sync();
+
+	perf_event_text_poke(op->kp.addr, old, JMP32_INSN_SIZE, new, JMP32_INSN_SIZE);
 }
 
 /*
author reviewer
#19 lore raw

PATCH v7 6/15 ftrace: Add symbols for ftrace trampolines

In reply to Adrian Hunter

Symbols are needed for tools to describe instruction addresses. Pages allocated for ftrace's purposes need symbols to be created for them. Add such symbols to be visible via /proc/kallsyms.

Example on x86 with CONFIG_DYNAMIC_FTRACE=y

	# echo function > /sys/kernel/debug/tracing/current_tracer
	# cat /proc/kallsyms | grep '\[__builtin__ftrace\]'
	ffffffffc0238000 t ftrace_trampoline    [__builtin__ftrace]

Note: This patch adds "__builtin__ftrace" as a module name in /proc/kallsyms for symbols for pages allocated for ftrace's purposes, even though "__builtin__ftrace" is not a module.

---
 include/linux/ftrace.h | 12 ++++---
 kernel/kallsyms.c      |  5 +++
 kernel/trace/ftrace.c  | 77 ++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 88 insertions(+), 6 deletions(-)
include/linux/ftrace.h +8 -4
index db95244a62d4..ea726ad1fa83 100644
@@ -58,9 +58,6 @@ struct ftrace_direct_func;
 const char *
 ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
 		   unsigned long *off, char **modname, char *sym);
-int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
-			   char *type, char *name,
-			   char *module_name, int *exported);
 #else
 static inline const char *
 ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
@@ -68,6 +65,13 @@ ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
 {
 	return NULL;
 }
+#endif
+
+#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
+int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
+			   char *type, char *name,
+			   char *module_name, int *exported);
+#else
 static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 					 char *type, char *name,
 					 char *module_name, int *exported)
@@ -76,7 +80,6 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val
 }
 #endif
 
-
 #ifdef CONFIG_FUNCTION_TRACER
 
 extern int ftrace_enabled;
@@ -207,6 +210,7 @@ struct ftrace_ops {
 	struct ftrace_ops_hash		old_hash;
 	unsigned long			trampoline;
 	unsigned long			trampoline_size;
+	struct list_head		list;
 #endif
 };
 
kernel/kallsyms.c +5 -0
index c6cc293c0e67..834bfdc43235 100644
@@ -482,6 +482,11 @@ static int get_ksymbol_mod(struct kallsym_iter *iter)
 	return 1;
 }
 
+/*
+ * ftrace_mod_get_kallsym() may also get symbols for pages allocated for ftrace
+ * purposes. In that case "__builtin__ftrace" is used as a module name, even
+ * though "__builtin__ftrace" is not a module.
+ */
 static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 {
 	int ret = ftrace_mod_get_kallsym(iter->pos - iter->pos_mod_end,
kernel/trace/ftrace.c +75 -2

121 lines not on this page · raw message

Signature · 1 line
2.17.1
merge bot Applied
#20 lore raw

[tip: perf/core] ftrace: Add symbols for ftrace trampolines

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     fc0ea795f53c8d7040fa42471f74fe51d78d0834
Gitweb:        https://git.kernel.org/tip/fc0ea795f53c8d7040fa42471f74fe51d78d0834
Author:        Adrian Hunter <[email protected]>
AuthorDate:    Tue, 12 May 2020 15:19:13 +03:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Mon, 15 Jun 2020 14:09:49 +02:00

ftrace: Add symbols for ftrace trampolines

Symbols are needed for tools to describe instruction addresses. Pages allocated for ftrace's purposes need symbols to be created for them. Add such symbols to be visible via /proc/kallsyms.

Example on x86 with CONFIG_DYNAMIC_FTRACE=y

	# echo function > /sys/kernel/debug/tracing/current_tracer
	# cat /proc/kallsyms | grep '\[__builtin__ftrace\]'
	ffffffffc0238000 t ftrace_trampoline    [__builtin__ftrace]

Note: This patch adds "__builtin__ftrace" as a module name in /proc/kallsyms for symbols for pages allocated for ftrace's purposes, even though "__builtin__ftrace" is not a module.

---
 include/linux/ftrace.h | 12 ++++--
 kernel/kallsyms.c      |  5 +++-
 kernel/trace/ftrace.c  | 77 +++++++++++++++++++++++++++++++++++++++--
 3 files changed, 88 insertions(+), 6 deletions(-)
include/linux/ftrace.h +8 -4
index e339dac..ce2c06f 100644
@@ -58,9 +58,6 @@ struct ftrace_direct_func;
 const char *
 ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
 		   unsigned long *off, char **modname, char *sym);
-int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
-			   char *type, char *name,
-			   char *module_name, int *exported);
 #else
 static inline const char *
 ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
@@ -68,6 +65,13 @@ ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
 {
 	return NULL;
 }
+#endif
+
+#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
+int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
+			   char *type, char *name,
+			   char *module_name, int *exported);
+#else
 static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 					 char *type, char *name,
 					 char *module_name, int *exported)
@@ -76,7 +80,6 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val
 }
 #endif
 
-
 #ifdef CONFIG_FUNCTION_TRACER
 
 extern int ftrace_enabled;
@@ -207,6 +210,7 @@ struct ftrace_ops {
 	struct ftrace_ops_hash		old_hash;
 	unsigned long			trampoline;
 	unsigned long			trampoline_size;
+	struct list_head		list;
 #endif
 };
 
kernel/kallsyms.c +5 -0
index c6cc293..834bfdc 100644
@@ -482,6 +482,11 @@ static int get_ksymbol_mod(struct kallsym_iter *iter)
 	return 1;
 }
 
+/*
+ * ftrace_mod_get_kallsym() may also get symbols for pages allocated for ftrace
+ * purposes. In that case "__builtin__ftrace" is used as a module name, even
+ * though "__builtin__ftrace" is not a module.
+ */
 static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 {
 	int ret = ftrace_mod_get_kallsym(iter->pos - iter->pos_mod_end,
kernel/trace/ftrace.c +75 -2

121 lines not on this page · raw message

author reviewer
#21 lore raw

PATCH v7 7/15 ftrace: Add perf ksymbol events for ftrace trampolines

In reply to Adrian Hunter

Symbols are needed for tools to describe instruction addresses. Pages allocated for ftrace's purposes need symbols to be created for them. Add such symbols to be visible via perf ksymbol events.

---
 include/uapi/linux/perf_event.h |  2 +-
 kernel/trace/ftrace.c           | 14 ++++++++++++--
 2 files changed, 13 insertions(+), 3 deletions(-)
include/uapi/linux/perf_event.h +1 -1
index e1a4179144a1..52ca2093831c 100644
@@ -1051,7 +1051,7 @@ enum perf_record_ksymbol_type {
 	PERF_RECORD_KSYMBOL_TYPE_BPF		= 1,
 	/*
 	 * Out of line code such as kprobe-replaced instructions or optimized
-	 * kprobes.
+	 * kprobes or ftrace trampolines.
 	 */
 	PERF_RECORD_KSYMBOL_TYPE_OOL		= 2,
 	PERF_RECORD_KSYMBOL_TYPE_MAX		/* non-ABI */
kernel/trace/ftrace.c +12 -2
index 9b0baeb4f0bb..1103a8fcf142 100644
@@ -2801,8 +2801,13 @@ static void ftrace_remove_trampoline_from_kallsyms(struct ftrace_ops *ops)
 static void ftrace_trampoline_free(struct ftrace_ops *ops)
 {
 	if (ops && (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP) &&
-	    ops->trampoline)
+	    ops->trampoline) {
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+				   ops->trampoline, ops->trampoline_size,
+				   true, FTRACE_TRAMPOLINE_SYM);
+		/* Remove from kallsyms after the perf events */
 		ftrace_remove_trampoline_from_kallsyms(ops);
+	}
 
 	arch_ftrace_trampoline_free(ops);
 }
@@ -6815,8 +6820,13 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops)
 
 	arch_ftrace_update_trampoline(ops);
 	if (ops->trampoline && ops->trampoline != trampoline &&
-	    (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
+	    (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) {
+		/* Add to kallsyms before the perf events */
 		ftrace_add_trampoline_to_kallsyms(ops);
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+				   ops->trampoline, ops->trampoline_size, false,
+				   FTRACE_TRAMPOLINE_SYM);
+	}
 }
 
 void ftrace_init_trace_array(struct trace_array *tr)
Signature · 1 line
2.17.1
merge bot Applied
#22 lore raw

[tip: perf/core] ftrace: Add perf ksymbol events for ftrace trampolines

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     dd9ddf466ad7a5d2e247925d81ebb0b878bf3b76
Gitweb:        https://git.kernel.org/tip/dd9ddf466ad7a5d2e247925d81ebb0b878bf3b76
Author:        Adrian Hunter <[email protected]>
AuthorDate:    Tue, 12 May 2020 15:19:14 +03:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Mon, 15 Jun 2020 14:09:49 +02:00

ftrace: Add perf ksymbol events for ftrace trampolines

Symbols are needed for tools to describe instruction addresses. Pages allocated for ftrace's purposes need symbols to be created for them. Add such symbols to be visible via perf ksymbol events.

---
 include/uapi/linux/perf_event.h |  2 +-
 kernel/trace/ftrace.c           | 14 ++++++++++++--
 2 files changed, 13 insertions(+), 3 deletions(-)
include/uapi/linux/perf_event.h +1 -1
index e1a4179..52ca209 100644
@@ -1051,7 +1051,7 @@ enum perf_record_ksymbol_type {
 	PERF_RECORD_KSYMBOL_TYPE_BPF		= 1,
 	/*
 	 * Out of line code such as kprobe-replaced instructions or optimized
-	 * kprobes.
+	 * kprobes or ftrace trampolines.
 	 */
 	PERF_RECORD_KSYMBOL_TYPE_OOL		= 2,
 	PERF_RECORD_KSYMBOL_TYPE_MAX		/* non-ABI */
kernel/trace/ftrace.c +12 -2
index 31675b2..2baaf77 100644
@@ -2790,8 +2790,13 @@ static void ftrace_remove_trampoline_from_kallsyms(struct ftrace_ops *ops)
 static void ftrace_trampoline_free(struct ftrace_ops *ops)
 {
 	if (ops && (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP) &&
-	    ops->trampoline)
+	    ops->trampoline) {
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+				   ops->trampoline, ops->trampoline_size,
+				   true, FTRACE_TRAMPOLINE_SYM);
+		/* Remove from kallsyms after the perf events */
 		ftrace_remove_trampoline_from_kallsyms(ops);
+	}
 
 	arch_ftrace_trampoline_free(ops);
 }
@@ -6805,8 +6810,13 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops)
 
 	arch_ftrace_update_trampoline(ops);
 	if (ops->trampoline && ops->trampoline != trampoline &&
-	    (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
+	    (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) {
+		/* Add to kallsyms before the perf events */
 		ftrace_add_trampoline_to_kallsyms(ops);
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+				   ops->trampoline, ops->trampoline_size, false,
+				   FTRACE_TRAMPOLINE_SYM);
+	}
 }
 
 void ftrace_init_trace_array(struct trace_array *tr)
author reviewer
#23 lore raw

PATCH v7 8/15 ftrace: Add perf text poke events for ftrace trampolines

In reply to Adrian Hunter

Add perf text poke events for ftrace trampolines when created and when freed.

There can be 3 text_poke events for ftrace trampolines:

1. NULL -> trampoline
By ftrace_update_trampoline() when !ops->trampoline Trampoline created

2. [e.g. on x86] CALL rel32 -> CALL rel32
By arch_ftrace_update_trampoline() when ops->trampoline and

                        ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP

[e.g. on x86] via text_poke_bp() which generates text poke events Trampoline-called function target updated

3. trampoline -> NULL
By ftrace_trampoline_free() when ops->trampoline and

                 ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP

Trampoline freed

---
 kernel/trace/ftrace.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)
kernel/trace/ftrace.c +14 -0
index 1103a8fcf142..abdf8f415a6e 100644
@@ -2802,6 +2802,13 @@ static void ftrace_trampoline_free(struct ftrace_ops *ops)
 {
 	if (ops && (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP) &&
 	    ops->trampoline) {
+		/*
+		 * Record the text poke event before the ksymbol unregister
+		 * event.
+		 */
+		perf_event_text_poke((void *)ops->trampoline,
+				     (void *)ops->trampoline,
+				     ops->trampoline_size, NULL, 0);
 		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
 				   ops->trampoline, ops->trampoline_size,
 				   true, FTRACE_TRAMPOLINE_SYM);
@@ -6826,6 +6833,13 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops)
 		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
 				   ops->trampoline, ops->trampoline_size, false,
 				   FTRACE_TRAMPOLINE_SYM);
+		/*
+		 * Record the perf text poke event after the ksymbol register
+		 * event.
+		 */
+		perf_event_text_poke((void *)ops->trampoline, NULL, 0,
+				     (void *)ops->trampoline,
+				     ops->trampoline_size);
 	}
 }
 
Signature · 1 line
2.17.1
merge bot Applied
#24 lore raw

[tip: perf/core] ftrace: Add perf text poke events for ftrace trampolines

The following commit has been merged into the perf/core branch of tip:

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     548e1f6c76e1eb80ba29edd4286b9b9f2c37f5bf
Gitweb:        https://git.kernel.org/tip/548e1f6c76e1eb80ba29edd4286b9b9f2c37f5bf
Author:        Adrian Hunter <[email protected]>
AuthorDate:    Tue, 12 May 2020 15:19:15 +03:00
Committer:     Peter Zijlstra <[email protected]>
CommitterDate: Mon, 15 Jun 2020 14:09:50 +02:00

ftrace: Add perf text poke events for ftrace trampolines

Add perf text poke events for ftrace trampolines when created and when freed.

There can be 3 text_poke events for ftrace trampolines:

1. NULL -> trampoline
By ftrace_update_trampoline() when !ops->trampoline Trampoline created

2. [e.g. on x86] CALL rel32 -> CALL rel32
By arch_ftrace_update_trampoline() when ops->trampoline and

                        ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP

[e.g. on x86] via text_poke_bp() which generates text poke events Trampoline-called function target updated

3. trampoline -> NULL
By ftrace_trampoline_free() when ops->trampoline and

                 ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP

Trampoline freed

---
 kernel/trace/ftrace.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)
kernel/trace/ftrace.c +14 -0
index 2baaf77..d6bba73 100644
@@ -2791,6 +2791,13 @@ static void ftrace_trampoline_free(struct ftrace_ops *ops)
 {
 	if (ops && (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP) &&
 	    ops->trampoline) {
+		/*
+		 * Record the text poke event before the ksymbol unregister
+		 * event.
+		 */
+		perf_event_text_poke((void *)ops->trampoline,
+				     (void *)ops->trampoline,
+				     ops->trampoline_size, NULL, 0);
 		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
 				   ops->trampoline, ops->trampoline_size,
 				   true, FTRACE_TRAMPOLINE_SYM);
@@ -6816,6 +6823,13 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops)
 		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
 				   ops->trampoline, ops->trampoline_size, false,
 				   FTRACE_TRAMPOLINE_SYM);
+		/*
+		 * Record the perf text poke event after the ksymbol register
+		 * event.
+		 */
+		perf_event_text_poke((void *)ops->trampoline, NULL, 0,
+				     (void *)ops->trampoline,
+				     ops->trampoline_size);
 	}
 }
 
author reviewer
#25 lore raw

PATCH v7 9/15 perf kcore_copy: Fix module map when there are no modules loaded

In reply to Adrian Hunter

In the absence of any modules, no "modules" map is created, but there are other executable pages to map, due to eBPF JIT, kprobe or ftrace. Map them by recognizing that the first "module" symbol is not necessarily from a module, and adjust the map accordingly.

---
 tools/perf/util/symbol-elf.c | 7 +++++++
 1 file changed, 7 insertions(+)
tools/perf/util/symbol-elf.c +7 -0
index be5b493f8284..5e43054bffea 100644
@@ -1458,6 +1458,7 @@ struct kcore_copy_info {
 	u64 first_symbol;
 	u64 last_symbol;
 	u64 first_module;
+	u64 first_module_symbol;
 	u64 last_module_symbol;
 	size_t phnum;
 	struct list_head phdrs;
@@ -1534,6 +1535,8 @@ static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
 		return 0;
 
 	if (strchr(name, '[')) {
+		if (!kci->first_module_symbol || start < kci->first_module_symbol)
+			kci->first_module_symbol = start;
 		if (start > kci->last_module_symbol)
 			kci->last_module_symbol = start;
 		return 0;
@@ -1731,6 +1734,10 @@ static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
 		kci->etext += page_size;
 	}
 
+	if (kci->first_module_symbol &&
+	    (!kci->first_module || kci->first_module_symbol < kci->first_module))
+		kci->first_module = kci->first_module_symbol;
+
 	kci->first_module = round_down(kci->first_module, page_size);
 
 	if (kci->last_module_symbol) {
Signature · 1 line
2.17.1
maintainer Applied
#26 lore raw

Re: [PATCH V7 09/15] perf kcore_copy: Fix module map when there are no modules loaded

Em Tue, May 12, 2020 at 03:19:16PM +0300, Adrian Hunter escreveu:

Quoted 4 lines

In the absence of any modules, no "modules" map is created, but there are other executable pages to map, due to eBPF JIT, kprobe or ftrace. Map them by recognizing that the first "module" symbol is not necessarily from a module, and adjust the map accordingly.

Applied,

- Arnaldo

Quoted 40 lines
---
 tools/perf/util/symbol-elf.c | 7 +++++++
 1 file changed, 7 insertions(+)
tools/perf/util/symbol-elf.c +7 -0
index be5b493f8284..5e43054bffea 100644
@@ -1458,6 +1458,7 @@ struct kcore_copy_info {
 	u64 first_symbol;
 	u64 last_symbol;
 	u64 first_module;
+	u64 first_module_symbol;
 	u64 last_module_symbol;
 	size_t phnum;
 	struct list_head phdrs;
@@ -1534,6 +1535,8 @@ static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
 		return 0;
 
 	if (strchr(name, '[')) {
+		if (!kci->first_module_symbol || start < kci->first_module_symbol)
+			kci->first_module_symbol = start;
 		if (start > kci->last_module_symbol)
 			kci->last_module_symbol = start;
 		return 0;
@@ -1731,6 +1734,10 @@ static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
 		kci->etext += page_size;
 	}
 
+	if (kci->first_module_symbol &&
+	    (!kci->first_module || kci->first_module_symbol < kci->first_module))
+		kci->first_module = kci->first_module_symbol;
+
 	kci->first_module = round_down(kci->first_module, page_size);
 
 	if (kci->last_module_symbol) {
Signature · 1 line
2.17.1
Signature · 1 line
- Arnaldo
author reviewer
#27 lore raw

PATCH v7 10/15 perf evlist: Disable 'immediate' events last

In reply to Adrian Hunter

Events marked as 'immediate' are started before other events to ensure that there is context at the start of the main tracing events. The same is true at the end of tracing, so disable 'immediate' events after other events.

---
 tools/perf/util/evlist.c | 31 +++++++++++++++++++++----------
 1 file changed, 21 insertions(+), 10 deletions(-)
tools/perf/util/evlist.c +21 -10
index 2a9de6491700..173b4f0e0e6e 100644
@@ -380,22 +380,33 @@ void evlist__disable(struct evlist *evlist)
 {
 	struct evsel *pos;
 	struct affinity affinity;
-	int cpu, i;
+	int cpu, i, imm = 0;
+	bool has_imm = false;
 
 	if (affinity__setup(&affinity) < 0)
 		return;
 
-	evlist__for_each_cpu(evlist, i, cpu) {
-		affinity__set(&affinity, cpu);
-
-		evlist__for_each_entry(evlist, pos) {
-			if (evsel__cpu_iter_skip(pos, cpu))
-				continue;
-			if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd)
-				continue;
-			evsel__disable_cpu(pos, pos->cpu_iter - 1);
+	/* Disable 'immediate' events last */
+	for (imm = 0; imm <= 1; imm++) {
+		evlist__for_each_cpu(evlist, i, cpu) {
+			affinity__set(&affinity, cpu);
+
+			evlist__for_each_entry(evlist, pos) {
+				if (evsel__cpu_iter_skip(pos, cpu))
+					continue;
+				if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd)
+					continue;
+				if (pos->immediate)
+					has_imm = true;
+				if (pos->immediate != imm)
+					continue;
+				evsel__disable_cpu(pos, pos->cpu_iter - 1);
+			}
 		}
+		if (!has_imm)
+			break;
 	}
+
 	affinity__cleanup(&affinity);
 	evlist__for_each_entry(evlist, pos) {
 		if (!evsel__is_group_leader(pos) || !pos->core.fd)
Signature · 1 line
2.17.1
maintainer Applied
#28 lore raw

Re: [PATCH V7 10/15] perf evlist: Disable 'immediate' events last

Em Tue, May 12, 2020 at 03:19:17PM +0300, Adrian Hunter escreveu:

Quoted 4 lines

Events marked as 'immediate' are started before other events to ensure that there is context at the start of the main tracing events. The same is true at the end of tracing, so disable 'immediate' events after other events.

Applied, thanks,

- Arnaldo

Quoted 56 lines
---
 tools/perf/util/evlist.c | 31 +++++++++++++++++++++----------
 1 file changed, 21 insertions(+), 10 deletions(-)
tools/perf/util/evlist.c +21 -10
index 2a9de6491700..173b4f0e0e6e 100644
@@ -380,22 +380,33 @@ void evlist__disable(struct evlist *evlist)
 {
 	struct evsel *pos;
 	struct affinity affinity;
-	int cpu, i;
+	int cpu, i, imm = 0;
+	bool has_imm = false;
 
 	if (affinity__setup(&affinity) < 0)
 		return;
 
-	evlist__for_each_cpu(evlist, i, cpu) {
-		affinity__set(&affinity, cpu);
-
-		evlist__for_each_entry(evlist, pos) {
-			if (evsel__cpu_iter_skip(pos, cpu))
-				continue;
-			if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd)
-				continue;
-			evsel__disable_cpu(pos, pos->cpu_iter - 1);
+	/* Disable 'immediate' events last */
+	for (imm = 0; imm <= 1; imm++) {
+		evlist__for_each_cpu(evlist, i, cpu) {
+			affinity__set(&affinity, cpu);
+
+			evlist__for_each_entry(evlist, pos) {
+				if (evsel__cpu_iter_skip(pos, cpu))
+					continue;
+				if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd)
+					continue;
+				if (pos->immediate)
+					has_imm = true;
+				if (pos->immediate != imm)
+					continue;
+				evsel__disable_cpu(pos, pos->cpu_iter - 1);
+			}
 		}
+		if (!has_imm)
+			break;
 	}
+
 	affinity__cleanup(&affinity);
 	evlist__for_each_entry(evlist, pos) {
 		if (!evsel__is_group_leader(pos) || !pos->core.fd)
Signature · 1 line
2.17.1
Signature · 1 line
- Arnaldo
author reviewer
#29 lore raw

PATCH v7 11/15 perf tools: Add support for PERF_RECORD_TEXT_POKE

In reply to Adrian Hunter

Add processing for PERF_RECORD_TEXT_POKE events. When a text poke event is processed, then the kernel dso data cache is updated with the poked bytes.

---
 tools/include/uapi/linux/perf_event.h     | 21 +++++++++-
 tools/lib/perf/include/perf/event.h       |  9 +++++
 tools/perf/builtin-record.c               | 45 ++++++++++++++++++++++
 tools/perf/util/event.c                   | 47 +++++++++++++++++++++++
 tools/perf/util/event.h                   |  5 +++
 tools/perf/util/evsel.c                   |  7 +++-
 tools/perf/util/machine.c                 | 43 +++++++++++++++++++++
 tools/perf/util/machine.h                 |  3 ++
 tools/perf/util/perf_api_probe.c          | 10 +++++
 tools/perf/util/perf_api_probe.h          |  1 +
 tools/perf/util/perf_event_attr_fprintf.c |  1 +
 tools/perf/util/record.h                  |  1 +
 tools/perf/util/session.c                 | 23 +++++++++++
 tools/perf/util/tool.h                    |  3 +-
 14 files changed, 216 insertions(+), 3 deletions(-)
tools/include/uapi/linux/perf_event.h +20 -1
index 7b2d6fc9e6ed..e5bee6c17b86 100644
@@ -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 */
 };
 
tools/lib/perf/include/perf/event.h +9 -0
index 69b44d2cc0f5..842028858d66 100644
@@ -111,6 +111,14 @@ struct perf_record_cgroup {
 	char			 path[PATH_MAX];
 };
 
+struct perf_record_text_poke_event {
+	struct perf_event_header header;
+	__u64			addr;
+	__u16			old_len;
+	__u16			new_len;
+	__u8			bytes[];
+};
+
 struct perf_record_sample {
 	struct perf_event_header header;
 	__u64			 array[];
@@ -367,6 +375,7 @@ union perf_event {
 	struct perf_record_sample		sample;
 	struct perf_record_bpf_event		bpf;
 	struct perf_record_ksymbol		ksymbol;
+	struct perf_record_text_poke_event	text_poke;
 	struct perf_record_header_attr		attr;
 	struct perf_record_event_update		event_update;
 	struct perf_record_header_event_type	event_type;
tools/perf/builtin-record.c +45 -0

57 lines not on this page · raw message

tools/perf/util/event.c +47 -0

77 lines not on this page · raw message

tools/perf/util/event.h +5 -0
index b8289f160f07..dbbba6dea51d 100644
@@ -351,6 +351,10 @@ int perf_event__process_bpf(struct perf_tool *tool,
 			    union perf_event *event,
 			    struct perf_sample *sample,
 			    struct machine *machine);
+int perf_event__process_text_poke(struct perf_tool *tool,
+				  union perf_event *event,
+				  struct perf_sample *sample,
+				  struct machine *machine);
 int perf_event__process(struct perf_tool *tool,
 			union perf_event *event,
 			struct perf_sample *sample,
@@ -385,6 +389,7 @@ size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_cgroup(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_text_poke(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 int kallsyms__get_function_start(const char *kallsyms_filename,
tools/perf/util/evsel.c +6 -1
index 28683b0eb738..f2edcb2ff68b 100644
@@ -1069,7 +1069,12 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 	attr->mmap  = track;
 	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
-	attr->ksymbol = track && !perf_missing_features.ksymbol;
+	/*
+	 * ksymbol is tracked separately with text poke because it needs to be
+	 * system wide and enabled immediately.
+	 */
+	if (!opts->text_poke)
+		attr->ksymbol = track && !perf_missing_features.ksymbol;
 	attr->bpf_event = track && !opts->no_bpf_event && !perf_missing_features.bpf;
 
 	if (opts->record_namespaces)
tools/perf/util/machine.c +43 -0

55 lines not on this page · raw message

tools/perf/util/machine.h +3 -0
index fa1be9ea00fa..062c36a8433c 100644
@@ -138,6 +138,9 @@ int machine__process_mmap2_event(struct machine *machine, union perf_event *even
 int machine__process_ksymbol(struct machine *machine,
 			     union perf_event *event,
 			     struct perf_sample *sample);
+int machine__process_text_poke(struct machine *machine,
+			       union perf_event *event,
+			       struct perf_sample *sample);
 int machine__process_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
 
tools/perf/util/perf_api_probe.c +10 -0
index 1337965673d7..3840d02f0f7b 100644
@@ -93,6 +93,11 @@ static void perf_probe_context_switch(struct evsel *evsel)
 	evsel->core.attr.context_switch = 1;
 }
 
+static void perf_probe_text_poke(struct evsel *evsel)
+{
+	evsel->core.attr.text_poke = 1;
+}
+
 bool perf_can_sample_identifier(void)
 {
 	return perf_probe_api(perf_probe_sample_identifier);
@@ -108,6 +113,11 @@ bool perf_can_record_switch_events(void)
 	return perf_probe_api(perf_probe_context_switch);
 }
 
+bool perf_can_record_text_poke_events(void)
+{
+	return perf_probe_api(perf_probe_text_poke);
+}
+
 bool perf_can_record_cpu_wide(void)
 {
 	struct perf_event_attr attr = {
tools/perf/util/perf_api_probe.h +1 -0
index 706c3c6426e2..d5506a983a94 100644
@@ -9,6 +9,7 @@ bool perf_can_aux_sample(void);
 bool perf_can_comm_exec(void);
 bool perf_can_record_cpu_wide(void);
 bool perf_can_record_switch_events(void);
+bool perf_can_record_text_poke_events(void);
 bool perf_can_sample_identifier(void);
 
 #endif // __PERF_API_PROBE_H
tools/perf/util/perf_event_attr_fprintf.c +1 -0
index b94fa07f5d32..e67a227c0ce7 100644
@@ -147,6 +147,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(aux_watermark, p_unsigned);
 	PRINT_ATTRf(sample_max_stack, p_unsigned);
 	PRINT_ATTRf(aux_sample_size, p_unsigned);
+	PRINT_ATTRf(text_poke, p_unsigned);
 
 	return ret;
 }
tools/perf/util/record.h +1 -0
index 923565c3b155..dce6332f5071 100644
@@ -47,6 +47,7 @@ struct record_opts {
 	bool	      sample_id;
 	bool	      no_bpf_event;
 	bool	      kcore;
+	bool	      text_poke;
 	unsigned int  freq;
 	unsigned int  mmap_pages;
 	unsigned int  auxtrace_mmap_pages;
tools/perf/util/session.c +23 -0
index b860f9f1b09e..652dd58a649f 100644
@@ -491,6 +491,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->ksymbol = perf_event__process_ksymbol;
 	if (tool->bpf == NULL)
 		tool->bpf = perf_event__process_bpf;
+	if (tool->text_poke == NULL)
+		tool->text_poke = perf_event__process_text_poke;
 	if (tool->read == NULL)
 		tool->read = process_event_sample_stub;
 	if (tool->throttle == NULL)
@@ -660,6 +662,24 @@ static void perf_event__switch_swap(union perf_event *event, bool sample_id_all)
 		swap_sample_id_all(event, &event->context_switch + 1);
 }
 
+static void perf_event__text_poke_swap(union perf_event *event, bool sample_id_all)
+{
+	event->text_poke.addr    = bswap_64(event->text_poke.addr);
+	event->text_poke.old_len = bswap_16(event->text_poke.old_len);
+	event->text_poke.new_len = bswap_16(event->text_poke.new_len);
+
+	if (sample_id_all) {
+		size_t len = sizeof(event->text_poke.old_len) +
+			     sizeof(event->text_poke.new_len) +
+			     event->text_poke.old_len +
+			     event->text_poke.new_len;
+		void *data = &event->text_poke.old_len;
+
+		data += PERF_ALIGN(len, sizeof(u64));
+		swap_sample_id_all(event, data);
+	}
+}
+
 static void perf_event__throttle_swap(union perf_event *event,
 				      bool sample_id_all)
 {
@@ -933,6 +953,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_SWITCH]		  = perf_event__switch_swap,
 	[PERF_RECORD_SWITCH_CPU_WIDE]	  = perf_event__switch_swap,
 	[PERF_RECORD_NAMESPACES]	  = perf_event__namespaces_swap,
+	[PERF_RECORD_TEXT_POKE]		  = perf_event__text_poke_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
@@ -1475,6 +1496,8 @@ static int machines__deliver_event(struct machines *machines,
 		return tool->ksymbol(tool, event, sample, machine);
 	case PERF_RECORD_BPF_EVENT:
 		return tool->bpf(tool, event, sample, machine);
+	case PERF_RECORD_TEXT_POKE:
+		return tool->text_poke(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;
tools/perf/util/tool.h +2 -1
index 3fb67bd31e4a..bbbc0dcd461f 100644
@@ -57,7 +57,8 @@ struct perf_tool {
 			throttle,
 			unthrottle,
 			ksymbol,
-			bpf;
+			bpf,
+			text_poke;
 
 	event_attr_op	attr;
 	event_attr_op	event_update;
Signature · 1 line
2.17.1
author reviewer
#30 lore raw

PATCH v7 12/15 perf tools: Add support for PERF_RECORD_KSYMBOL_TYPE_OOL

In reply to Adrian Hunter

PERF_RECORD_KSYMBOL_TYPE_OOL marks an executable page. Create a map backed only by memory, which will be populated as necessary by text poke events.

---
 tools/include/uapi/linux/perf_event.h | 5 +++++
 tools/perf/util/dso.c                 | 3 +++
 tools/perf/util/dso.h                 | 1 +
 tools/perf/util/machine.c             | 6 ++++++
 tools/perf/util/map.c                 | 5 +++++
 tools/perf/util/map.h                 | 3 ++-
 tools/perf/util/symbol.c              | 1 +
 7 files changed, 23 insertions(+), 1 deletion(-)
tools/include/uapi/linux/perf_event.h +5 -0
index e5bee6c17b86..52ca2093831c 100644
@@ -1049,6 +1049,11 @@ enum perf_event_type {
 enum perf_record_ksymbol_type {
 	PERF_RECORD_KSYMBOL_TYPE_UNKNOWN	= 0,
 	PERF_RECORD_KSYMBOL_TYPE_BPF		= 1,
+	/*
+	 * Out of line code such as kprobe-replaced instructions or optimized
+	 * kprobes or ftrace trampolines.
+	 */
+	PERF_RECORD_KSYMBOL_TYPE_OOL		= 2,
 	PERF_RECORD_KSYMBOL_TYPE_MAX		/* non-ABI */
 };
 
tools/perf/util/dso.c +3 -0
index f338990e0fe6..e68e1375e3c0 100644
@@ -192,6 +192,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	case DSO_BINARY_TYPE__JAVA_JIT:
 	case DSO_BINARY_TYPE__BPF_PROG_INFO:
 	case DSO_BINARY_TYPE__BPF_IMAGE:
+	case DSO_BINARY_TYPE__OOL:
 	case DSO_BINARY_TYPE__NOT_FOUND:
 		ret = -1;
 		break;
@@ -882,6 +883,8 @@ static struct dso_cache *dso_cache__populate(struct dso *dso,
 
 	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
 		*ret = bpf_read(dso, cache_offset, cache->data);
+	else if (dso->binary_type == DSO_BINARY_TYPE__OOL)
+		*ret = DSO__DATA_CACHE_SIZE;
 	else
 		*ret = file_read(dso, machine, cache_offset, cache->data);
 
tools/perf/util/dso.h +1 -0
index 9553a1fd9e8a..42b3a278ac59 100644
@@ -41,6 +41,7 @@ enum dso_binary_type {
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
 	DSO_BINARY_TYPE__BPF_PROG_INFO,
 	DSO_BINARY_TYPE__BPF_IMAGE,
+	DSO_BINARY_TYPE__OOL,
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
 
tools/perf/util/machine.c +6 -0
index c7282c01ee53..9120d7dc274f 100644
@@ -762,6 +762,12 @@ static int machine__process_ksymbol_register(struct machine *machine,
 			return -ENOMEM;
 		}
 
+		if (event->ksymbol.ksym_type == PERF_RECORD_KSYMBOL_TYPE_OOL) {
+			map->dso->binary_type = DSO_BINARY_TYPE__OOL;
+			map->dso->data.file_size = event->ksymbol.len;
+			dso__set_loaded(map->dso);
+		}
+
 		map->start = event->ksymbol.addr;
 		map->end = map->start + event->ksymbol.len;
 		maps__insert(&machine->kmaps, map);
tools/perf/util/map.c +5 -0
index 53d96611e6a6..f9dc8c5493ea 100644
@@ -267,6 +267,11 @@ bool __map__is_bpf_prog(const struct map *map)
 	return name && (strstr(name, "bpf_prog_") == name);
 }
 
+bool __map__is_ool(const struct map *map)
+{
+	return map->dso && map->dso->binary_type == DSO_BINARY_TYPE__OOL;
+}
+
 bool map__has_symbols(const struct map *map)
 {
 	return dso__has_symbols(map->dso);
tools/perf/util/map.h +2 -1
index 067036e8970c..9e312ae2d656 100644
@@ -147,11 +147,12 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name,
 bool __map__is_kernel(const struct map *map);
 bool __map__is_extra_kernel_map(const struct map *map);
 bool __map__is_bpf_prog(const struct map *map);
+bool __map__is_ool(const struct map *map);
 
 static inline bool __map__is_kmodule(const struct map *map)
 {
 	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) &&
-	       !__map__is_bpf_prog(map);
+	       !__map__is_bpf_prog(map) && !__map__is_ool(map);
 }
 
 bool map__has_symbols(const struct map *map);
tools/perf/util/symbol.c +1 -0
index 381da6b39f89..7725c83996f4 100644
@@ -1559,6 +1559,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 
 	case DSO_BINARY_TYPE__BPF_PROG_INFO:
 	case DSO_BINARY_TYPE__BPF_IMAGE:
+	case DSO_BINARY_TYPE__OOL:
 	case DSO_BINARY_TYPE__NOT_FOUND:
 	default:
 		return false;
Signature · 1 line
2.17.1
author reviewer
#31 lore raw

PATCH v7 13/15 perf intel-pt: Add support for text poke events

In reply to Adrian Hunter

Select text poke events when available and the kernel is being traced. Process text poke events to invalidate entries in Intel PT's instruction cache.

Example:

The example requires kernel config:
CONFIG_PROC_SYSCTL=y
CONFIG_SCHED_DEBUG=y
CONFIG_SCHEDSTATS=y

Before:

    # perf record -o perf.data.before --kcore -a -e intel_pt//k -m,64M &
    # cat /proc/sys/kernel/sched_schedstats
    0
    # echo 1 > /proc/sys/kernel/sched_schedstats
    # cat /proc/sys/kernel/sched_schedstats
    1
    # echo 0 > /proc/sys/kernel/sched_schedstats
    # cat /proc/sys/kernel/sched_schedstats
    0
    # kill %1
    [ perf record: Woken up 1 times to write data ]
    [ perf record: Captured and wrote 3.341 MB perf.data.before ]
    [1]+  Terminated                 perf record -o perf.data.before --kcore -a -e intel_pt//k -m,64M
    # perf script -i perf.data.before --itrace=e >/dev/null
    Warning:
    474 instruction trace errors

After:

    # perf record -o perf.data.after --kcore -a -e intel_pt//k -m,64M &
    # cat /proc/sys/kernel/sched_schedstats
    0
    # echo 1 > /proc/sys/kernel/sched_schedstats
    # cat /proc/sys/kernel/sched_schedstats
    1
    # echo 0 > /proc/sys/kernel/sched_schedstats
    # cat /proc/sys/kernel/sched_schedstats
    0
    # kill %1
    [ perf record: Woken up 1 times to write data ]
    [ perf record: Captured and wrote 2.646 MB perf.data.after ]
    [1]+  Terminated                 perf record -o perf.data.after --kcore -a -e intel_pt//k -m,64M
    # perf script -i perf.data.after --itrace=e >/dev/null

Example:

The example requires kernel config:
# CONFIG_FUNCTION_TRACER is not set

Before:

    # perf record --kcore -m,64M -o t1 -a -e intel_pt//k &
    # perf probe __schedule
    Added new event:
      probe:__schedule     (on __schedule)

You can now use it in all perf tools, such as:

perf record -e probe:__schedule -aR sleep 1

# perf record -e probe:__schedule -aR sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.026 MB perf.data (68 samples) ] # perf probe -d probe:__schedule
Removed event: probe:__schedule
# kill %1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 41.268 MB t1 ]
[1]+ Terminated perf record --kcore -m,64M -o t1 -a -e intel_pt//k
# perf script -i t1 --itrace=e >/dev/null
Warning:
207 instruction trace errors

After:

    # perf record --kcore -m,64M -o t1 -a -e intel_pt//k &
    # perf probe __schedule
    Added new event:
      probe:__schedule     (on __schedule)
    You can now use it in all perf tools, such as:

        perf record -e probe:__schedule -aR sleep 1

    # perf record -e probe:__schedule -aR sleep 1
    [ perf record: Woken up 1 times to write data ]
    [ perf record: Captured and wrote 0.028 MB perf.data (107 samples) ]
    # perf probe -d probe:__schedule
    Removed event: probe:__schedule
    # kill %1
    [ perf record: Woken up 1 times to write data ]
    [ perf record: Captured and wrote 39.978 MB t1 ]
    [1]+  Terminated                 perf record --kcore -m,64M -o t1 -a -e intel_pt//k
    # perf script -i t1 --itrace=e >/dev/null
    # perf script -i t1 --no-itrace -D | grep 'POKE\|KSYMBOL'
    6 565303693547 0x291f18 [0x50]: PERF_RECORD_KSYMBOL addr ffffffffc027a000 len 4096 type 2 flags 0x0 name kprobe_insn_page
    6 565303697010 0x291f68 [0x40]: PERF_RECORD_TEXT_POKE addr 0xffffffffc027a000 old len 0 new len 6
    6 565303838278 0x291fa8 [0x50]: PERF_RECORD_KSYMBOL addr ffffffffc027c000 len 4096 type 2 flags 0x0 name kprobe_optinsn_page
    6 565303848286 0x291ff8 [0xa0]: PERF_RECORD_TEXT_POKE addr 0xffffffffc027c000 old len 0 new len 106
    6 565369336743 0x292af8 [0x40]: PERF_RECORD_TEXT_POKE addr 0xffffffff88ab8890 old len 5 new len 5
    7 566434327704 0x217c208 [0x40]: PERF_RECORD_TEXT_POKE addr 0xffffffff88ab8890 old len 5 new len 5
    6 566456313475 0x293198 [0xa0]: PERF_RECORD_TEXT_POKE addr 0xffffffffc027c000 old len 106 new len 0
    6 566456314935 0x293238 [0x40]: PERF_RECORD_TEXT_POKE addr 0xffffffffc027a000 old len 6 new len 0

Example:

The example requires kernel config:
CONFIG_FUNCTION_TRACER=y

Before:

    # perf record --kcore -m,64M -o t1 -a -e intel_pt//k &
    # perf probe __kmalloc
    Added new event:
      probe:__kmalloc      (on __kmalloc)

You can now use it in all perf tools, such as:

perf record -e probe:__kmalloc -aR sleep 1

# perf record -e probe:__kmalloc -aR sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.022 MB perf.data (6 samples) ] # perf probe -d probe:__kmalloc
Removed event: probe:__kmalloc
# kill %1
[ perf record: Woken up 2 times to write data ]
[ perf record: Captured and wrote 43.850 MB t1 ]
[1]+ Terminated perf record --kcore -m,64M -o t1 -a -e intel_pt//k
# perf script -i t1 --itrace=e >/dev/null
Warning:
8 instruction trace errors

After:

    # perf record --kcore -m,64M -o t1 -a -e intel_pt//k &
    # perf probe __kmalloc
    Added new event:
      probe:__kmalloc      (on __kmalloc)
    You can now use it in all perf tools, such as:

            perf record -e probe:__kmalloc -aR sleep 1

    # perf record -e probe:__kmalloc -aR sleep 1
    [ perf record: Woken up 1 times to write data ]
    [ perf record: Captured and wrote 0.037 MB perf.data (206 samples) ]
    # perf probe -d probe:__kmalloc
    Removed event: probe:__kmalloc
    # kill %1
    [ perf record: Woken up 1 times to write data ]
    [ perf record: Captured and wrote 41.442 MB t1 ]
    [1]+  Terminated                 perf record --kcore -m,64M -o t1 -a -e intel_pt//k
    # perf script -i t1 --itrace=e >/dev/null
    # perf script -i t1 --no-itrace -D | grep 'POKE\|KSYMBOL'
    5 312216133258 0x8bafe0 [0x50]: PERF_RECORD_KSYMBOL addr ffffffffc0360000 len 415 type 2 flags 0x0 name ftrace_trampoline
    5 312216133494 0x8bb030 [0x1d8]: PERF_RECORD_TEXT_POKE addr 0xffffffffc0360000 old len 0 new len 415
    5 312216229563 0x8bb208 [0x40]: PERF_RECORD_TEXT_POKE addr 0xffffffffac6016f5 old len 5 new len 5
    5 312216239063 0x8bb248 [0x40]: PERF_RECORD_TEXT_POKE addr 0xffffffffac601803 old len 5 new len 5
    5 312216727230 0x8bb288 [0x40]: PERF_RECORD_TEXT_POKE addr 0xffffffffabbea190 old len 5 new len 5
    5 312216739322 0x8bb2c8 [0x40]: PERF_RECORD_TEXT_POKE addr 0xffffffffac6016f5 old len 5 new len 5
    5 312216748321 0x8bb308 [0x40]: PERF_RECORD_TEXT_POKE addr 0xffffffffac601803 old len 5 new len 5
    7 313287163462 0x2817430 [0x40]: PERF_RECORD_TEXT_POKE addr 0xffffffffac6016f5 old len 5 new len 5
    7 313287174890 0x2817470 [0x40]: PERF_RECORD_TEXT_POKE addr 0xffffffffac601803 old len 5 new len 5
    7 313287818979 0x28174b0 [0x40]: PERF_RECORD_TEXT_POKE addr 0xffffffffabbea190 old len 5 new len 5
    7 313287829357 0x28174f0 [0x40]: PERF_RECORD_TEXT_POKE addr 0xffffffffac6016f5 old len 5 new len 5
    7 313287841246 0x2817530 [0x40]: PERF_RECORD_TEXT_POKE addr 0xffffffffac601803 old len 5 new len 5
---
 tools/perf/arch/x86/util/intel-pt.c |  4 ++
 tools/perf/util/intel-pt.c          | 75 +++++++++++++++++++++++++++++
 2 files changed, 79 insertions(+)
tools/perf/arch/x86/util/intel-pt.c +4 -0
index fd9e22d1e366..fdb917fcf511 100644
@@ -827,6 +827,10 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		}
 	}
 
+	if (have_timing_info && !intel_pt_evsel->core.attr.exclude_kernel &&
+	    perf_can_record_text_poke_events() && perf_can_record_cpu_wide())
+		opts->text_poke = true;
+
 	if (intel_pt_evsel) {
 		/*
 		 * To obtain the auxtrace buffer file descriptor, the auxtrace
tools/perf/util/intel-pt.c +75 -0

93 lines not on this page · raw message

Signature · 1 line
2.17.1
author reviewer
#32 lore raw

PATCH v7 14/15 perf script: Add option --show-text-poke-events

In reply to Adrian Hunter

Consistent with other new events, add an option to perf script to display text poke events and ksymbol events. Both text poke events and ksymbol events are displayed because some text pokes (e.g. ftrace trampolines) have corresponding ksymbol events.

---
 tools/perf/Documentation/perf-script.txt |  4 ++++
 tools/perf/builtin-script.c              | 19 +++++++++++++++++++
 2 files changed, 23 insertions(+)
tools/perf/Documentation/perf-script.txt +4 -0
index 372dfd110e6d..4f712fb8f175 100644
@@ -322,6 +322,10 @@ OPTIONS
 --show-cgroup-events
 	Display cgroup events i.e. events of type PERF_RECORD_CGROUP.
 
+--show-text-poke-events
+	Display text poke events i.e. events of type PERF_RECORD_TEXT_POKE and
+	PERF_RECORD_KSYMBOL.
+
 --demangle::
 	Demangle symbol names to human readable form. It's enabled by default,
 	disable with --no-demangle.
tools/perf/builtin-script.c +19 -0
index ecc8bd4c5e57..35ed8f69ed6a 100644
@@ -1678,6 +1678,7 @@ struct perf_script {
 	bool			show_round_events;
 	bool			show_bpf_events;
 	bool			show_cgroup_events;
+	bool			show_text_poke_events;
 	bool			allocated;
 	bool			per_event_dump;
 	bool			stitch_lbr;
@@ -2321,6 +2322,18 @@ process_bpf_events(struct perf_tool *tool __maybe_unused,
 			   sample->tid);
 }
 
+static int process_text_poke_events(struct perf_tool *tool,
+				    union perf_event *event,
+				    struct perf_sample *sample,
+				    struct machine *machine)
+{
+	if (perf_event__process_text_poke(tool, event, sample, machine) < 0)
+		return -1;
+
+	return print_event(tool, event, sample, machine, sample->pid,
+			   sample->tid);
+}
+
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
@@ -2429,6 +2442,10 @@ static int __cmd_script(struct perf_script *script)
 		script->tool.ksymbol = process_bpf_events;
 		script->tool.bpf     = process_bpf_events;
 	}
+	if (script->show_text_poke_events) {
+		script->tool.ksymbol   = process_bpf_events;
+		script->tool.text_poke = process_text_poke_events;
+	}
 
 	if (perf_script__setup_per_event_dump(script)) {
 		pr_err("Couldn't create the per event dump files\n");
@@ -3460,6 +3477,8 @@ int cmd_script(int argc, const char **argv)
 		    "Show round events (if recorded)"),
 	OPT_BOOLEAN('\0', "show-bpf-events", &script.show_bpf_events,
 		    "Show bpf related events (if recorded)"),
+	OPT_BOOLEAN('\0', "show-text-poke-events", &script.show_text_poke_events,
+		    "Show text poke related events (if recorded)"),
 	OPT_BOOLEAN('\0', "per-event-dump", &script.per_event_dump,
 		    "Dump trace output to files named by the monitored events"),
 	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
Signature · 1 line
2.17.1
author reviewer
#33 lore raw

PATCH v7 15/15 perf script: Show text poke address symbol

In reply to Adrian Hunter

It is generally more useful to show the symbol with an address. In this case, the print function requires the 'machine' which means changing callers to provide it as a parameter. It is optional because most events do not need it and the callers that matter can provide it.

---
 tools/perf/builtin-script.c    |  4 ++--
 tools/perf/tests/perf-record.c |  4 ++--
 tools/perf/util/event.c        | 23 ++++++++++++++++++-----
 tools/perf/util/event.h        |  6 ++++--
 tools/perf/util/intel-pt.c     |  2 +-
 tools/perf/util/machine.c      |  2 +-
 6 files changed, 28 insertions(+), 13 deletions(-)
tools/perf/builtin-script.c +2 -2
index 35ed8f69ed6a..5bdd1a393399 100644
@@ -2170,7 +2170,7 @@ static int print_event_with_time(struct perf_tool *tool,
 					   event->header.type, stdout);
 	}
 
-	perf_event__fprintf(event, stdout);
+	perf_event__fprintf(machine, event, stdout);
 
 	thread__put(thread);
 
@@ -2305,7 +2305,7 @@ process_finished_round_event(struct perf_tool *tool __maybe_unused,
 			     struct ordered_events *oe __maybe_unused)
 
 {
-	perf_event__fprintf(event, stdout);
+	perf_event__fprintf(NULL, event, stdout);
 	return 0;
 }
 
tools/perf/tests/perf-record.c +2 -2
index 83adfd846ccd..ff6febf15269 100644
@@ -185,14 +185,14 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 				err = perf_evlist__parse_sample(evlist, event, &sample);
 				if (err < 0) {
 					if (verbose > 0)
-						perf_event__fprintf(event, stderr);
+						perf_event__fprintf(NULL, event, stderr);
 					pr_debug("Couldn't parse sample\n");
 					goto out_delete_evlist;
 				}
 
 				if (verbose > 0) {
 					pr_info("%" PRIu64" %d ", sample.time, sample.cpu);
-					perf_event__fprintf(event, stderr);
+					perf_event__fprintf(NULL, event, stderr);
 				}
 
 				if (prev_time > sample.time) {
tools/perf/util/event.c +18 -5
index dde2f0147713..4b60cd57ad62 100644
@@ -440,14 +440,26 @@ static int text_poke_printer(enum binary_printer_ops op, unsigned int val,
 	}
 }
 
-size_t perf_event__fprintf_text_poke(union perf_event *event, FILE *fp)
+size_t perf_event__fprintf_text_poke(struct machine *machine,
+				     union perf_event *event, FILE *fp)
 {
 	struct perf_record_text_poke_event *tp = &event->text_poke;
 	size_t ret;
 	bool old;
 
-	ret = fprintf(fp, " %" PRI_lx64 " old len %u new len %u\n",
-		      tp->addr, tp->old_len, tp->new_len);
+	ret = fprintf(fp, " %" PRI_lx64 " ", tp->addr);
+	if (machine) {
+		struct addr_location al;
+
+		al.map = maps__find(&machine->kmaps, tp->addr);
+		if (al.map && map__load(al.map) >= 0) {
+			al.addr = al.map->map_ip(al.map, tp->addr);
+			al.sym = map__find_symbol(al.map, al.addr);
+			if (al.sym)
+				ret += symbol__fprintf_symname_offs(al.sym, &al, fp);
+		}
+	}
+	ret += fprintf(fp, " old len %u new len %u\n", tp->old_len, tp->new_len);
 	old = true;
 	ret += binary__fprintf(tp->bytes, tp->old_len, 16, text_poke_printer,
 			       &old, fp);
@@ -457,7 +469,8 @@ size_t perf_event__fprintf_text_poke(union perf_event *event, FILE *fp)
 	return ret;
 }
 
-size_t perf_event__fprintf(union perf_event *event, FILE *fp)
+size_t perf_event__fprintf(struct machine *machine, union perf_event *event,
+			   FILE *fp)
 {
 	size_t ret = fprintf(fp, "PERF_RECORD_%s",
 			     perf_event__name(event->header.type));
@@ -502,7 +515,7 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 		ret += perf_event__fprintf_bpf(event, fp);
 		break;
 	case PERF_RECORD_TEXT_POKE:
-		ret += perf_event__fprintf_text_poke(event, fp);
+		ret += perf_event__fprintf_text_poke(machine, event, fp);
 		break;
 	default:
 		ret += fprintf(fp, "\n");
tools/perf/util/event.h +4 -2
index dbbba6dea51d..611c8e5ad9d9 100644
@@ -389,8 +389,10 @@ size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_cgroup(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp);
-size_t perf_event__fprintf_text_poke(union perf_event *event, FILE *fp);
-size_t perf_event__fprintf(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_text_poke(struct machine *machine,
+				     union perf_event *event, FILE *fp);
+size_t perf_event__fprintf(struct machine *machine, union perf_event *event,
+			   FILE *fp);
 
 int kallsyms__get_function_start(const char *kallsyms_filename,
 				 const char *symbol_name, u64 *addr);
tools/perf/util/intel-pt.c +1 -1
index e2e199a58222..4c6bb45d8200 100644
@@ -236,7 +236,7 @@ static void intel_pt_log_event(union perf_event *event)
 	if (!intel_pt_enable_logging || !f)
 		return;
 
-	perf_event__fprintf(event, f);
+	perf_event__fprintf(NULL, event, f);
 }
 
 static void intel_pt_dump_sample(struct perf_session *session,
tools/perf/util/machine.c +1 -1
index 9120d7dc274f..5f52b579b3fe 100644
@@ -821,7 +821,7 @@ int machine__process_text_poke(struct machine *machine, union perf_event *event,
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	if (dump_trace)
-		perf_event__fprintf_text_poke(event, stdout);
+		perf_event__fprintf_text_poke(machine, event, stdout);
 
 	if (!event->text_poke.new_len)
 		return 0;
Signature · 1 line
2.17.1
#34 lore raw

Re: [PATCH V7 15/15] perf script: Show text poke address symbol

Em Tue, May 12, 2020 at 03:19:22PM +0300, Adrian Hunter escreveu:

Quoted 20 lines

It is generally more useful to show the symbol with an address. In this case, the print function requires the 'machine' which means changing callers to provide it as a parameter. It is optional because most events do not need it and the callers that matter can provide it.

---
 tools/perf/builtin-script.c    |  4 ++--
 tools/perf/tests/perf-record.c |  4 ++--
 tools/perf/util/event.c        | 23 ++++++++++++++++++-----
 tools/perf/util/event.h        |  6 ++++--
 tools/perf/util/intel-pt.c     |  2 +-
 tools/perf/util/machine.c      |  2 +-
 6 files changed, 28 insertions(+), 13 deletions(-)
tools/perf/builtin-script.c +0 -0
index 35ed8f69ed6a..5bdd1a393399 100644

tools/perf/builtin-script.c static int print_event_with_time(struct perf_tool *tool, · line 2173

Quoted 5 lines
tools/perf/builtin-script.c +1 -1
@@ -2170,7 +2170,7 @@ static int print_event_with_time(struct perf_tool *tool,
 					   event->header.type, stdout);
 	}
 
-	perf_event__fprintf(event, stdout);
+	perf_event__fprintf(machine, event, stdout);

Since this is for a perf event, the first arg should be event, not machine, but I can fixup this when processing these patches, no need to resend.

Quoted 37 lines
tools/perf/builtin-script.c +1 -1
 	thread__put(thread);
 
@@ -2305,7 +2305,7 @@ process_finished_round_event(struct perf_tool *tool __maybe_unused,
 			     struct ordered_events *oe __maybe_unused)
 
 {
-	perf_event__fprintf(event, stdout);
+	perf_event__fprintf(NULL, event, stdout);
 	return 0;
 }
 
tools/perf/tests/perf-record.c +2 -2
index 83adfd846ccd..ff6febf15269 100644
@@ -185,14 +185,14 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 				err = perf_evlist__parse_sample(evlist, event, &sample);
 				if (err < 0) {
 					if (verbose > 0)
-						perf_event__fprintf(event, stderr);
+						perf_event__fprintf(NULL, event, stderr);
 					pr_debug("Couldn't parse sample\n");
 					goto out_delete_evlist;
 				}
 
 				if (verbose > 0) {
 					pr_info("%" PRIu64" %d ", sample.time, sample.cpu);
-					perf_event__fprintf(event, stderr);
+					perf_event__fprintf(NULL, event, stderr);
 				}
 
 				if (prev_time > sample.time) {
tools/perf/util/event.c +0 -0
index dde2f0147713..4b60cd57ad62 100644

tools/perf/util/event.c static int text_poke_printer(enum binary_printer_ops op, unsigned int val, · line 444

Quoted 6 lines
tools/perf/util/event.c +2 -1
@@ -440,14 +440,26 @@ static int text_poke_printer(enum binary_printer_ops op, unsigned int val,
 	}
 }
 
-size_t perf_event__fprintf_text_poke(union perf_event *event, FILE *fp)
+size_t perf_event__fprintf_text_poke(struct machine *machine,
+				     union perf_event *event, FILE *fp)

Ditto

Quoted 88 lines
tools/perf/util/event.c +16 -4
 {
 	struct perf_record_text_poke_event *tp = &event->text_poke;
 	size_t ret;
 	bool old;
 
-	ret = fprintf(fp, " %" PRI_lx64 " old len %u new len %u\n",
-		      tp->addr, tp->old_len, tp->new_len);
+	ret = fprintf(fp, " %" PRI_lx64 " ", tp->addr);
+	if (machine) {
+		struct addr_location al;
+
+		al.map = maps__find(&machine->kmaps, tp->addr);
+		if (al.map && map__load(al.map) >= 0) {
+			al.addr = al.map->map_ip(al.map, tp->addr);
+			al.sym = map__find_symbol(al.map, al.addr);
+			if (al.sym)
+				ret += symbol__fprintf_symname_offs(al.sym, &al, fp);
+		}
+	}
+	ret += fprintf(fp, " old len %u new len %u\n", tp->old_len, tp->new_len);
 	old = true;
 	ret += binary__fprintf(tp->bytes, tp->old_len, 16, text_poke_printer,
 			       &old, fp);
@@ -457,7 +469,8 @@ size_t perf_event__fprintf_text_poke(union perf_event *event, FILE *fp)
 	return ret;
 }
 
-size_t perf_event__fprintf(union perf_event *event, FILE *fp)
+size_t perf_event__fprintf(struct machine *machine, union perf_event *event,
+			   FILE *fp)
 {
 	size_t ret = fprintf(fp, "PERF_RECORD_%s",
 			     perf_event__name(event->header.type));
@@ -502,7 +515,7 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 		ret += perf_event__fprintf_bpf(event, fp);
 		break;
 	case PERF_RECORD_TEXT_POKE:
-		ret += perf_event__fprintf_text_poke(event, fp);
+		ret += perf_event__fprintf_text_poke(machine, event, fp);
 		break;
 	default:
 		ret += fprintf(fp, "\n");
tools/perf/util/event.h +4 -2
index dbbba6dea51d..611c8e5ad9d9 100644
@@ -389,8 +389,10 @@ size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_cgroup(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp);
-size_t perf_event__fprintf_text_poke(union perf_event *event, FILE *fp);
-size_t perf_event__fprintf(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_text_poke(struct machine *machine,
+				     union perf_event *event, FILE *fp);
+size_t perf_event__fprintf(struct machine *machine, union perf_event *event,
+			   FILE *fp);
 
 int kallsyms__get_function_start(const char *kallsyms_filename,
 				 const char *symbol_name, u64 *addr);
tools/perf/util/intel-pt.c +1 -1
index e2e199a58222..4c6bb45d8200 100644
@@ -236,7 +236,7 @@ static void intel_pt_log_event(union perf_event *event)
 	if (!intel_pt_enable_logging || !f)
 		return;
 
-	perf_event__fprintf(event, f);
+	perf_event__fprintf(NULL, event, f);
 }
 
 static void intel_pt_dump_sample(struct perf_session *session,
tools/perf/util/machine.c +1 -1
index 9120d7dc274f..5f52b579b3fe 100644
@@ -821,7 +821,7 @@ int machine__process_text_poke(struct machine *machine, union perf_event *event,
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	if (dump_trace)
-		perf_event__fprintf_text_poke(event, stdout);
+		perf_event__fprintf_text_poke(machine, event, stdout);
 
 	if (!event->text_poke.new_len)
 		return 0;
Signature · 1 line
2.17.1
Signature · 1 line
- Arnaldo
#35 lore raw

Re: [PATCH V7 15/15] perf script: Show text poke address symbol

In reply to Adrian Hunter

Em Tue, May 12, 2020 at 03:19:22PM +0300, Adrian Hunter escreveu:

Quoted 4 lines

It is generally more useful to show the symbol with an address. In this case, the print function requires the 'machine' which means changing callers to provide it as a parameter. It is optional because most events do not need it and the callers that matter can provide it.

I'm just inverting the order of the parameters for perf_event__fprintf(), to keep as the first arg the pointer to the type that is the prefix for the function, i.e. instead of:

size_t perf_event__fprintf_text_poke(struct machine *machine,
union perf_event *event, FILE *fp)

I'll make it be:

size_t perf_event__fprintf_text_poke(union perf_event *event,
struct machine *machine,FILE *fp)

Ok?

Thanks,

- Arnaldo

Quoted 152 lines
---
 tools/perf/builtin-script.c    |  4 ++--
 tools/perf/tests/perf-record.c |  4 ++--
 tools/perf/util/event.c        | 23 ++++++++++++++++++-----
 tools/perf/util/event.h        |  6 ++++--
 tools/perf/util/intel-pt.c     |  2 +-
 tools/perf/util/machine.c      |  2 +-
 6 files changed, 28 insertions(+), 13 deletions(-)
tools/perf/builtin-script.c +2 -2
index 35ed8f69ed6a..5bdd1a393399 100644
@@ -2170,7 +2170,7 @@ static int print_event_with_time(struct perf_tool *tool,
 					   event->header.type, stdout);
 	}
 
-	perf_event__fprintf(event, stdout);
+	perf_event__fprintf(machine, event, stdout);
 
 	thread__put(thread);
 
@@ -2305,7 +2305,7 @@ process_finished_round_event(struct perf_tool *tool __maybe_unused,
 			     struct ordered_events *oe __maybe_unused)
 
 {
-	perf_event__fprintf(event, stdout);
+	perf_event__fprintf(NULL, event, stdout);
 	return 0;
 }
 
tools/perf/tests/perf-record.c +2 -2
index 83adfd846ccd..ff6febf15269 100644
@@ -185,14 +185,14 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 				err = perf_evlist__parse_sample(evlist, event, &sample);
 				if (err < 0) {
 					if (verbose > 0)
-						perf_event__fprintf(event, stderr);
+						perf_event__fprintf(NULL, event, stderr);
 					pr_debug("Couldn't parse sample\n");
 					goto out_delete_evlist;
 				}
 
 				if (verbose > 0) {
 					pr_info("%" PRIu64" %d ", sample.time, sample.cpu);
-					perf_event__fprintf(event, stderr);
+					perf_event__fprintf(NULL, event, stderr);
 				}
 
 				if (prev_time > sample.time) {
tools/perf/util/event.c +18 -5
index dde2f0147713..4b60cd57ad62 100644
@@ -440,14 +440,26 @@ static int text_poke_printer(enum binary_printer_ops op, unsigned int val,
 	}
 }
 
-size_t perf_event__fprintf_text_poke(union perf_event *event, FILE *fp)
+size_t perf_event__fprintf_text_poke(struct machine *machine,
+				     union perf_event *event, FILE *fp)
 {
 	struct perf_record_text_poke_event *tp = &event->text_poke;
 	size_t ret;
 	bool old;
 
-	ret = fprintf(fp, " %" PRI_lx64 " old len %u new len %u\n",
-		      tp->addr, tp->old_len, tp->new_len);
+	ret = fprintf(fp, " %" PRI_lx64 " ", tp->addr);
+	if (machine) {
+		struct addr_location al;
+
+		al.map = maps__find(&machine->kmaps, tp->addr);
+		if (al.map && map__load(al.map) >= 0) {
+			al.addr = al.map->map_ip(al.map, tp->addr);
+			al.sym = map__find_symbol(al.map, al.addr);
+			if (al.sym)
+				ret += symbol__fprintf_symname_offs(al.sym, &al, fp);
+		}
+	}
+	ret += fprintf(fp, " old len %u new len %u\n", tp->old_len, tp->new_len);
 	old = true;
 	ret += binary__fprintf(tp->bytes, tp->old_len, 16, text_poke_printer,
 			       &old, fp);
@@ -457,7 +469,8 @@ size_t perf_event__fprintf_text_poke(union perf_event *event, FILE *fp)
 	return ret;
 }
 
-size_t perf_event__fprintf(union perf_event *event, FILE *fp)
+size_t perf_event__fprintf(struct machine *machine, union perf_event *event,
+			   FILE *fp)
 {
 	size_t ret = fprintf(fp, "PERF_RECORD_%s",
 			     perf_event__name(event->header.type));
@@ -502,7 +515,7 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 		ret += perf_event__fprintf_bpf(event, fp);
 		break;
 	case PERF_RECORD_TEXT_POKE:
-		ret += perf_event__fprintf_text_poke(event, fp);
+		ret += perf_event__fprintf_text_poke(machine, event, fp);
 		break;
 	default:
 		ret += fprintf(fp, "\n");
tools/perf/util/event.h +4 -2
index dbbba6dea51d..611c8e5ad9d9 100644
@@ -389,8 +389,10 @@ size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_cgroup(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp);
-size_t perf_event__fprintf_text_poke(union perf_event *event, FILE *fp);
-size_t perf_event__fprintf(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_text_poke(struct machine *machine,
+				     union perf_event *event, FILE *fp);
+size_t perf_event__fprintf(struct machine *machine, union perf_event *event,
+			   FILE *fp);
 
 int kallsyms__get_function_start(const char *kallsyms_filename,
 				 const char *symbol_name, u64 *addr);
tools/perf/util/intel-pt.c +1 -1
index e2e199a58222..4c6bb45d8200 100644
@@ -236,7 +236,7 @@ static void intel_pt_log_event(union perf_event *event)
 	if (!intel_pt_enable_logging || !f)
 		return;
 
-	perf_event__fprintf(event, f);
+	perf_event__fprintf(NULL, event, f);
 }
 
 static void intel_pt_dump_sample(struct perf_session *session,
tools/perf/util/machine.c +1 -1
index 9120d7dc274f..5f52b579b3fe 100644
@@ -821,7 +821,7 @@ int machine__process_text_poke(struct machine *machine, union perf_event *event,
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	if (dump_trace)
-		perf_event__fprintf_text_poke(event, stdout);
+		perf_event__fprintf_text_poke(machine, event, stdout);
 
 	if (!event->text_poke.new_len)
 		return 0;
Signature · 1 line
2.17.1
Signature · 1 line
- Arnaldo
author reviewer
#36 lore raw

Re: [PATCH V7 15/15] perf script: Show text poke address symbol

Quoted 13 lines · Arnaldo Carvalho de Melo

Em Tue, May 12, 2020 at 03:19:22PM +0300, Adrian Hunter escreveu:

Quoted 4 lines

It is generally more useful to show the symbol with an address. In this case, the print function requires the 'machine' which means changing callers to provide it as a parameter. It is optional because most events do not need it and the callers that matter can provide it.

I'm just inverting the order of the parameters for perf_event__fprintf(), to keep as the first arg the pointer to the type that is the prefix for the function, i.e. instead of:

size_t perf_event__fprintf_text_poke(struct machine *machine,
union perf_event *event, FILE *fp)

Quoted 6 lines

I'll make it be:

size_t perf_event__fprintf_text_poke(union perf_event *event,
struct machine *machine,FILE *fp)

Ok?

Yup! Thank you!

author reviewer
#37 lore raw
In reply to Adrian Hunter
Quoted 42 lines · Adrian Hunter

Hi

Here are patches to add a text poke event to record changes to kernel text (i.e. self-modifying code) in order to support tracers like Intel PT decoding through jump labels, kprobes and ftrace trampolines.

The first 8 patches make the kernel changes and the subsequent patches are tools changes.

The next 4 patches add support for updating perf tools' data cache with the changed bytes.

The next patch is an Intel PT specific tools change.

The final 2 patches add perf script --show-text-poke-events option

Patches also here:

git://git.infradead.org/users/ahunter/linux-perf.git text_poke

Changes in V7

perf: Add perf text poke event
perf/x86: Add support for perf text poke event for text_poke_bp_batch() callers
kprobes: Add symbols for kprobe insn pages
kprobes: Add perf ksymbol events for kprobe insn pages
perf/x86: Add perf text poke events for kprobes
ftrace: Add symbols for ftrace trampolines
ftrace: Add perf ksymbol events for ftrace trampolines
ftrace: Add perf text poke events for ftrace trampolines

Added Peter's Ack
Improved commit message for text_poke events for ftrace trampolines

perf kcore_copy: Fix module map when there are no modules loaded perf evlist: Disable 'immediate' events last
perf tools: Add support for PERF_RECORD_TEXT_POKE perf tools: Add support for PERF_RECORD_KSYMBOL_TYPE_OOL perf intel-pt: Add support for text poke events
perf script: Add option --show-text-poke-events
perf script: Show text poke address symbol

Quoted 2 lines

Re-based on Arnaldo's perf/core branch

Arnaldo, any comments on the tools patches?

#38 lore raw

Em Sun, May 17, 2020 at 04:16:50PM +0300, Adrian Hunter escreveu:

Quoted 43 lines · Adrian Hunter
Quoted 42 lines

Hi

Here are patches to add a text poke event to record changes to kernel text (i.e. self-modifying code) in order to support tracers like Intel PT decoding through jump labels, kprobes and ftrace trampolines.

The first 8 patches make the kernel changes and the subsequent patches are tools changes.

The next 4 patches add support for updating perf tools' data cache with the changed bytes.

The next patch is an Intel PT specific tools change.

The final 2 patches add perf script --show-text-poke-events option

Patches also here:

git://git.infradead.org/users/ahunter/linux-perf.git text_poke

Changes in V7

perf: Add perf text poke event
perf/x86: Add support for perf text poke event for text_poke_bp_batch() callers
kprobes: Add symbols for kprobe insn pages
kprobes: Add perf ksymbol events for kprobe insn pages
perf/x86: Add perf text poke events for kprobes
ftrace: Add symbols for ftrace trampolines
ftrace: Add perf ksymbol events for ftrace trampolines
ftrace: Add perf text poke events for ftrace trampolines

Added Peter's Ack
Improved commit message for text_poke events for ftrace trampolines

perf kcore_copy: Fix module map when there are no modules loaded perf evlist: Disable 'immediate' events last
perf tools: Add support for PERF_RECORD_TEXT_POKE perf tools: Add support for PERF_RECORD_KSYMBOL_TYPE_OOL perf intel-pt: Add support for text poke events
perf script: Add option --show-text-poke-events
perf script: Show text poke address symbol

Quoted 4 lines
Quoted 2 lines

Re-based on Arnaldo's perf/core branch

Arnaldo, any comments on the tools patches?

I couldn't get to this yet, sorry, but from a quick look I saw just the ordering of some args to perf_event__ functions, and I can quickly fix it.

PeterZ, from what we discussed for the next merge Window, perhaps we should route the kernel bits via the tip tree while I will push the tooling bits on my 5.8 merge request to Linus, Ok?

- Arnaldo

maintainer
#39 lore raw
Quoted 3 lines · Arnaldo Carvalho de Melo

PeterZ, from what we discussed for the next merge Window, perhaps we should route the kernel bits via the tip tree while I will push the tooling bits on my 5.8 merge request to Linus, Ok?

Sure, I can take the kernel bits. Thanks!

#40 lore raw

Em Wed, May 20, 2020 at 05:56:34PM +0200, Peter Zijlstra escreveu:

Quoted 6 lines · Arnaldo Carvalho de Melo
Quoted 3 lines

PeterZ, from what we discussed for the next merge Window, perhaps we should route the kernel bits via the tip tree while I will push the tooling bits on my 5.8 merge request to Linus, Ok?

Sure, I can take the kernel bits. Thanks!

So, I'm going thru the userpace bits and stopped at the patch copying include/uapi/linux/perf_events.h to tools/include/uapi/linux/perf_events.h to get the text_poke perf_event_attr bit, looked at tip/ and this hasn't landed there yet, any issues with the kernel bits?

I can try to put a separate branch, merge the kernel bits, and do a pull request to Ingo/Thomas to get that going, would that help?

- Arnaldo

maintainer
#41 lore raw
Quoted 6 lines · Arnaldo Carvalho de Melo

Em Wed, May 20, 2020 at 05:56:34PM +0200, Peter Zijlstra escreveu:

Quoted 5 lines · Arnaldo Carvalho de Melo
Quoted 3 lines

PeterZ, from what we discussed for the next merge Window, perhaps we should route the kernel bits via the tip tree while I will push the tooling bits on my 5.8 merge request to Linus, Ok?

Quoted 7 lines
Quoted 1 line

Sure, I can take the kernel bits. Thanks!

So, I'm going thru the userpace bits and stopped at the patch copying include/uapi/linux/perf_events.h to tools/include/uapi/linux/perf_events.h to get the text_poke perf_event_attr bit, looked at tip/ and this hasn't landed there yet, any issues with the kernel bits?

Nah, I was waiting on the 0day robot, but its broken *again* :-(

Let me go move things along manually.

author reviewer
#42 lore raw
Quoted 15 lines · Peter Zijlstra
Quoted 6 lines · Arnaldo Carvalho de Melo

Em Wed, May 20, 2020 at 05:56:34PM +0200, Peter Zijlstra escreveu:

Quoted 5 lines · Arnaldo Carvalho de Melo
Quoted 3 lines

PeterZ, from what we discussed for the next merge Window, perhaps we should route the kernel bits via the tip tree while I will push the tooling bits on my 5.8 merge request to Linus, Ok?

Quoted 7 lines
Quoted 1 line

Sure, I can take the kernel bits. Thanks!

So, I'm going thru the userpace bits and stopped at the patch copying include/uapi/linux/perf_events.h to tools/include/uapi/linux/perf_events.h to get the text_poke perf_event_attr bit, looked at tip/ and this hasn't landed there yet, any issues with the kernel bits?

Quoted 4 lines

Nah, I was waiting on the 0day robot, but its broken *again* :-(

Let me go move things along manually.

Hi

The kernel patches are in tip and the remaining tools patches still apply. Remaining patches 11-15 are:

perf tools: Add support for PERF_RECORD_TEXT_POKE perf tools: Add support for PERF_RECORD_KSYMBOL_TYPE_OOL perf intel-pt: Add support for text poke events perf script: Add option --show-text-poke-events perf script: Show text poke address symbol

Is there anything else I can do for these?

Regards
Adrian

#43 lore raw

Em Wed, Jul 08, 2020 at 02:55:36PM +0300, Adrian Hunter escreveu:

Quoted 23 lines · Peter Zijlstra
Quoted 15 lines · Arnaldo Carvalho de Melo
Quoted 6 lines

Em Wed, May 20, 2020 at 05:56:34PM +0200, Peter Zijlstra escreveu:

Quoted 5 lines · Arnaldo Carvalho de Melo
Quoted 3 lines

PeterZ, from what we discussed for the next merge Window, perhaps we should route the kernel bits via the tip tree while I will push the tooling bits on my 5.8 merge request to Linus, Ok?

Quoted 7 lines
Quoted 1 line

Sure, I can take the kernel bits. Thanks!

So, I'm going thru the userpace bits and stopped at the patch copying include/uapi/linux/perf_events.h to tools/include/uapi/linux/perf_events.h to get the text_poke perf_event_attr bit, looked at tip/ and this hasn't landed there yet, any issues with the kernel bits?

Quoted 4 lines

Nah, I was waiting on the 0day robot, but its broken *again* :-(

Let me go move things along manually.

Hi

Quoted 8 lines

The kernel patches are in tip and the remaining tools patches still apply. Remaining patches 11-15 are:

perf tools: Add support for PERF_RECORD_TEXT_POKE perf tools: Add support for PERF_RECORD_KSYMBOL_TYPE_OOL perf intel-pt: Add support for text poke events perf script: Add option --show-text-poke-events perf script: Show text poke address symbol

Sure, I'll merge those now that the kernel support is in tip, thanks for the reminder,

- Arnaldo

Quoted 4 lines

Is there anything else I can do for these?

Regards
Adrian

Signature · 1 line
- Arnaldo
#44 lore raw

Em Wed, Jul 08, 2020 at 09:34:23AM -0300, Arnaldo Carvalho de Melo escreveu:

Quoted 27 lines

Em Wed, Jul 08, 2020 at 02:55:36PM +0300, Adrian Hunter escreveu:

Quoted 26 lines · Peter Zijlstra
Quoted 15 lines · Arnaldo Carvalho de Melo
Quoted 6 lines

Em Wed, May 20, 2020 at 05:56:34PM +0200, Peter Zijlstra escreveu:

Quoted 5 lines · Arnaldo Carvalho de Melo
Quoted 3 lines

PeterZ, from what we discussed for the next merge Window, perhaps we should route the kernel bits via the tip tree while I will push the tooling bits on my 5.8 merge request to Linus, Ok?

Quoted 7 lines
Quoted 1 line

Sure, I can take the kernel bits. Thanks!

So, I'm going thru the userpace bits and stopped at the patch copying include/uapi/linux/perf_events.h to tools/include/uapi/linux/perf_events.h to get the text_poke perf_event_attr bit, looked at tip/ and this hasn't landed there yet, any issues with the kernel bits?

Quoted 4 lines

Nah, I was waiting on the 0day robot, but its broken *again* :-(

Let me go move things along manually.

Hi

The kernel patches are in tip and the remaining tools patches still apply. Remaining patches 11-15 are:

Quoted 8 lines
Quoted 5 lines

perf tools: Add support for PERF_RECORD_TEXT_POKE perf tools: Add support for PERF_RECORD_KSYMBOL_TYPE_OOL perf intel-pt: Add support for text poke events perf script: Add option --show-text-poke-events perf script: Show text poke address symbol

Sure, I'll merge those now that the kernel support is in tip, thanks for the reminder,

Done, now I need to build a kernel from tip/perf/core and test with the tooling from acme/perf/core, will do later today.

So far what I have is in my repo at the tmp.perf/core branch, if anyone wants to test before I do test it with the kernel with these features and the usual container build tests.

- Arnaldo