Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1372498 > unrolled thread

[PATCH 0/2] perf probe fixes for ppc64le

Started by"Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
First post2016-04-06 14:50 +0200
Last post2016-04-11 15:50 +0200
Articles 7 — 3 participants

Back to article view | Back to linux.kernel

Contents

  [PATCH 0/2] perf probe fixes for ppc64le "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com> - 2016-04-06 14:50 +0200
    Re: [PATCH 0/2] perf probe fixes for ppc64le Balbir Singh <bsingharora@gmail.com> - 2016-04-07 10:20 +0200
      Re: [PATCH 0/2] perf probe fixes for ppc64le "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com> - 2016-04-07 11:30 +0200
        Re: [PATCH 0/2] perf probe fixes for ppc64le Balbir Singh <bsingharora@gmail.com> - 2016-04-08 09:00 +0200
          Re: [PATCH 0/2] perf probe fixes for ppc64le "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com> - 2016-04-09 15:50 +0200
            Re: [PATCH 0/2] perf probe fixes for ppc64le Michael Ellerman <mpe@ellerman.id.au> - 2016-04-11 06:50 +0200
              Re: [PATCH 0/2] perf probe fixes for ppc64le "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com> - 2016-04-11 15:50 +0200

#1372498 — [PATCH 0/2] perf probe fixes for ppc64le

From"Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Date2016-04-06 14:50 +0200
Subject[PATCH 0/2] perf probe fixes for ppc64le
Message-ID<rkUUy-3Mo-17@gated-at.bofh.it>
This patchset fixes three issues found with perf probe on ppc64le:
1. 'perf test kallsyms' failure on ppc64le (reported by Michael
Ellerman). This was due to the symbols being fixed up during symbol
table load. This is fixed in patch 2 by delaying symbol fixup until
later.
2. perf probe function offset was being calculated from the local entry
point (LEP), which does not match user expectation when trying to look
at function disassembly output (reported by Ananth N). This is fixed for
kallsyms in patch 1 and for symbol table in patch 2.
3. perf probe failure with kretprobe when using kallsyms. This was
failing as we were specifying an offset. This is fixed in patch 1.

A few examples demonstrating the issues and the fix:

Example for issue (2):
--------------------
    # objdump -d vmlinux | grep -A8 \<_do_fork\>:
    c0000000000b6a00 <_do_fork>:
    c0000000000b6a00:	f7 00 4c 3c 	addis   r2,r12,247
    c0000000000b6a04:	00 86 42 38 	addi    r2,r2,-31232
    c0000000000b6a08:	a6 02 08 7c 	mflr    r0
    c0000000000b6a0c:	d0 ff 41 fb 	std     r26,-48(r1)
    c0000000000b6a10:	26 80 90 7d 	mfocrf  r12,8
    c0000000000b6a14:	d8 ff 61 fb 	std     r27,-40(r1)
    c0000000000b6a18:	e0 ff 81 fb 	std     r28,-32(r1)
    c0000000000b6a1c:	e8 ff a1 fb 	std     r29,-24(r1)
    # perf probe -v _do_fork+4
    probe-definition(0): _do_fork+4 
    symbol:_do_fork file:(null) line:0 offset:4 return:0 lazy:(null)
    0 arguments
    Looking at the vmlinux_path (8 entries long)
    Using /proc/kcore for kernel object code
    Using /proc/kallsyms for symbols
    Opening /sys/kernel/debug/tracing//kprobe_events write=1
    Writing event: p:probe/_do_fork _text+748044
    Added new event:
      probe:_do_fork       (on _do_fork+4)

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

	    perf record -e probe:_do_fork -aR sleep 1

    # printf "%x\n" 748044
    b6a0c
    ^^^^^
This is offset from the LEP. With this, there is also no way to ever
probe between the GEP and the LEP.

With this patchset:
    # perf probe -v _do_fork+4
    probe-definition(0): _do_fork+4 
    symbol:_do_fork file:(null) line:0 offset:4 return:0 lazy:(null)
    0 arguments
    Looking at the vmlinux_path (8 entries long)
    Using /proc/kcore for kernel object code
    Using /proc/kallsyms for symbols
    Opening /sys/kernel/debug/tracing//kprobe_events write=1
    Writing event: p:probe/_do_fork _text+748036
    Added new event:
      probe:_do_fork       (on _do_fork+4)

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

	    perf record -e probe:_do_fork -aR sleep 1

    # perf probe -v _do_fork
    probe-definition(0): _do_fork 
    symbol:_do_fork file:(null) line:0 offset:0 return:0 lazy:(null)
    0 arguments
    Looking at the vmlinux_path (8 entries long)
    Using /proc/kcore for kernel object code
    Using /proc/kallsyms for symbols
    Opening /sys/kernel/debug/tracing//kprobe_events write=1
    Writing event: p:probe/_do_fork _text+748040
    Added new event:
      probe:_do_fork       (on _do_fork)

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

	    perf record -e probe:_do_fork -aR sleep 1

We only offset to the LEP if function entry is specified, otherwise, we
offset from the GEP.

Example for issue (3):
---------------------
Before patch:
    # perf probe -v _do_fork:%return
    probe-definition(0): _do_fork:%return 
    symbol:_do_fork file:(null) line:0 offset:0 return:1 lazy:(null)
    0 arguments
    Looking at the vmlinux_path (8 entries long)
    Using /proc/kcore for kernel object code
    Using /proc/kallsyms for symbols
    Opening /sys/kernel/debug/tracing//kprobe_events write=1
    Writing event: r:probe/_do_fork _do_fork+8
    Failed to write event: Invalid argument
      Error: Failed to add events. Reason: Invalid argument (Code: -22)

After patch:
    # perf probe _do_fork:%return
    Added new event:
      probe:_do_fork       (on _do_fork%return)

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

	    perf record -e probe:_do_fork -aR sleep 1

Cc: Mark Wielaard <mjw@redhat.com>
Cc: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>

Naveen N. Rao (2):
  perf/powerpc: Fix kprobe and kretprobe handling with kallsyms
  tools/perf: Fix kallsyms perf test on ppc64le

 tools/perf/arch/powerpc/util/sym-handling.c | 41 ++++++++++++++++++++---------
 tools/perf/util/probe-event.c               |  5 ++--
 tools/perf/util/probe-event.h               |  3 ++-
 tools/perf/util/symbol-elf.c                |  7 ++---
 tools/perf/util/symbol.h                    |  3 ++-
 5 files changed, 40 insertions(+), 19 deletions(-)

-- 
2.7.4

[toc] | [next] | [standalone]

#1373137

FromBalbir Singh <bsingharora@gmail.com>
Date2016-04-07 10:20 +0200
Message-ID<rldku-Vt-11@gated-at.bofh.it>
In reply to#1372498
On 06/04/16 22:32, Naveen N. Rao wrote:
> This patchset fixes three issues found with perf probe on ppc64le:
> 1. 'perf test kallsyms' failure on ppc64le (reported by Michael
> Ellerman). This was due to the symbols being fixed up during symbol
> table load. This is fixed in patch 2 by delaying symbol fixup until
> later.
> 2. perf probe function offset was being calculated from the local entry
> point (LEP), which does not match user expectation when trying to look
> at function disassembly output (reported by Ananth N). This is fixed for
> kallsyms in patch 1 and for symbol table in patch 2.

I think the bit where the offset is w.r.t LEP when using a name, but w.r.t
GEP when using function+offset can be confusing. Do we really need probe
points between GEP and LEP? All the GEP does is setup r2. The use case
could be more generic, but please clarify.

> 3. perf probe failure with kretprobe when using kallsyms. This was
> failing as we were specifying an offset. This is fixed in patch 1.
> 

Balbir Singh.

[toc] | [prev] | [next] | [standalone]

#1373196

From"Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Date2016-04-07 11:30 +0200
Message-ID<rleqe-1G9-3@gated-at.bofh.it>
In reply to#1373137
On 2016/04/07 06:19PM, Balbir Singh wrote:
> 
> On 06/04/16 22:32, Naveen N. Rao wrote:
> > This patchset fixes three issues found with perf probe on ppc64le:
> > 1. 'perf test kallsyms' failure on ppc64le (reported by Michael
> > Ellerman). This was due to the symbols being fixed up during symbol
> > table load. This is fixed in patch 2 by delaying symbol fixup until
> > later.
> > 2. perf probe function offset was being calculated from the local entry
> > point (LEP), which does not match user expectation when trying to look
> > at function disassembly output (reported by Ananth N). This is fixed for
> > kallsyms in patch 1 and for symbol table in patch 2.
> 
> I think the bit where the offset is w.r.t LEP when using a name, but w.r.t
> GEP when using function+offset can be confusing.

Thanks for your review!

The rationale for this is actually from the end-user perspective. The 
two use cases we are considering are:
1. User just wants to probe at function entry point:
	# perf probe _do_fork

In this case, the user most definitely needs the local entry point, 
without which the probe won't be hit. So, for this case, we 
automatically insert the probe at the LEP.

[We really only want to alter perf probe behavior in this case only, but 
we were incorrectly changing the behavior of perf with the below 
scenario as well.]

2. User wants to probe at a specific location. In this case, the user 
most likely starts by looking at the function disassembly. For instance:
	# objdump -S -d vmlinux.bak | grep -A100 \<_do_fork\>:
	c0000000000b6a00 <_do_fork>:
		      unsigned long stack_start,
		      unsigned long stack_size,
		      int __user *parent_tidptr,
		      int __user *child_tidptr,
		      unsigned long tls)
	{
	c0000000000b6a00:	f7 00 4c 3c 	addis   r2,r12,247
	c0000000000b6a04:	00 86 42 38 	addi    r2,r2,-31232
	c0000000000b6a08:	a6 02 08 7c 	mflr    r0
	c0000000000b6a0c:	d0 ff 41 fb 	std     r26,-48(r1)
	c0000000000b6a10:	26 80 90 7d 	mfocrf  r12,8
	...<snip>...
		if (!(clone_flags & CLONE_UNTRACED)) {
	c0000000000b6a54:	e3 4f c7 7b 	rldicl. r7,r30,41,63
	c0000000000b6a58:	2c 00 82 40 	bne     c0000000000b6a84 <_do_fork+0x84>
			if (clone_flags & CLONE_VFORK)
	c0000000000b6a5c:	e3 97 c8 7b 	rldicl. r8,r30,50,63
	c0000000000b6a60:	a0 01 82 41 	beq     c0000000000b6c00 <_do_fork+0x200>
	c0000000000b6a64:	20 00 20 39 	li      r9,32
				trace = PTRACE_EVENT_VFORK;
	c0000000000b6a68:	02 00 80 3b 	li      r28,2
	c0000000000b6a6c:	10 02 4d e9 	ld      r10,528(r13)

If the user wants to probe at _do_fork+0x54, he'd do:
	# perf probe _do_fork+0x54

With the earlier approach, we would insert the probe at _do_fork+0x5c 
(0x54 from the LEP) instead, which is incorrect.

In reality, user would probably just use debuginfo:
	# perf probe -L _do_fork
	<_do_fork@/root/linus/kernel/fork.c:0>
	      0  long _do_fork(unsigned long clone_flags,
			      unsigned long stack_start,
			      unsigned long stack_size,
			      int __user *parent_tidptr,
			      int __user *child_tidptr,
			      unsigned long tls)
	      6  {
			struct task_struct *p;
	      8         int trace = 0;
			long nr;
		 
			/*
			 * Determine whether and which event to report to ptracer.  When
			 * called from kernel_thread or CLONE_UNTRACED is explicitly
			 * requested, no event is reported; otherwise, report if the event
			 * for the type of forking is enabled.
			 */
	     17         if (!(clone_flags & CLONE_UNTRACED)) {
	     18                 if (clone_flags & CLONE_VFORK)
	     19                         trace = PTRACE_EVENT_VFORK;
	     20                 else if ((clone_flags & CSIGNAL) != SIGCHLD)
	     21                         trace = PTRACE_EVENT_CLONE;

	# perf probe _do_fork:17

In this case, perf chooses the right address based on DWARF. The current 
patchset matches the behavior of perf without debuginfo with this.

> Do we really need probe
> points between GEP and LEP? All the GEP does is setup r2. The use case
> could be more generic, but please clarify.

There could be scenarios where having a probe point between GEP and LEP 
is useful - for instance, if we are only interested in calls to an 
in-kernel function from an external module. However, this is a secondary 
consideration and the more important consideration was to be consistent 
with userspace tooling (readelf/objdump) while choosing the address to 
probe.

- Naveen

[toc] | [prev] | [next] | [standalone]

#1374023

FromBalbir Singh <bsingharora@gmail.com>
Date2016-04-08 09:00 +0200
Message-ID<rlyyC-8iG-23@gated-at.bofh.it>
In reply to#1373196
On Thu, 2016-04-07 at 14:56 +0530, Naveen N. Rao wrote:
> On 2016/04/07 06:19PM, Balbir Singh wrote:
> > 
> > 
> > On 06/04/16 22:32, Naveen N. Rao wrote:
> > > 
> > > This patchset fixes three issues found with perf probe on ppc64le:
> > > 1. 'perf test kallsyms' failure on ppc64le (reported by Michael
> > > Ellerman). This was due to the symbols being fixed up during symbol
> > > table load. This is fixed in patch 2 by delaying symbol fixup until
> > > later.
> > > 2. perf probe function offset was being calculated from the local entry
> > > point (LEP), which does not match user expectation when trying to look
> > > at function disassembly output (reported by Ananth N). This is fixed for
> > > kallsyms in patch 1 and for symbol table in patch 2.
> > I think the bit where the offset is w.r.t LEP when using a name, but w.r.t
> > GEP when using function+offset can be confusing.
> Thanks for your review!
> 
> The rationale for this is actually from the end-user perspective. The 
> two use cases we are considering are:
> 1. User just wants to probe at function entry point:
> 	# perf probe _do_fork
> 
> In this case, the user most definitely needs the local entry point, 
> without which the probe won't be hit. So, for this case, we 
> automatically insert the probe at the LEP.
> 
> [We really only want to alter perf probe behavior in this case only, but 
> we were incorrectly changing the behavior of perf with the below 
> scenario as well.]
> 
> 2. User wants to probe at a specific location. In this case, the user 
> most likely starts by looking at the function disassembly. For instance:
> 	# objdump -S -d vmlinux.bak | grep -A100 \<_do_fork\>:
> 	c0000000000b6a00 <_do_fork>:
> 		      unsigned long stack_start,
> 		      unsigned long stack_size,
> 		      int __user *parent_tidptr,
> 		      int __user *child_tidptr,
> 		      unsigned long tls)
> 	{
> 	c0000000000b6a00:	f7 00 4c 3c 	addis   r2,r12,247
> 	c0000000000b6a04:	00 86 42 38 	addi    r2,r2,-31232
> 	c0000000000b6a08:	a6 02 08 7c 	mflr    r0
> 	c0000000000b6a0c:	d0 ff 41 fb 	std     r26,-48(r1)
> 	c0000000000b6a10:	26 80 90 7d 	mfocrf  r12,8
> 	...<snip>...
> 		if (!(clone_flags & CLONE_UNTRACED)) {
> 	c0000000000b6a54:	e3 4f c7 7b 	rldicl. r7,r30,41,63
> 	c0000000000b6a58:	2c 00 82 40 	bne     c0000000000b6a84 <_do_fork+0x84>
> 			if (clone_flags & CLONE_VFORK)
> 	c0000000000b6a5c:	e3 97 c8 7b 	rldicl. r8,r30,50,63
> 	c0000000000b6a60:	a0 01 82 41 	beq     c0000000000b6c00 <_do_fork+0x200>
> 	c0000000000b6a64:	20 00 20 39 	li      r9,32
> 				trace = PTRACE_EVENT_VFORK;
> 	c0000000000b6a68:	02 00 80 3b 	li      r28,2
> 	c0000000000b6a6c:	10 02 4d e9 	ld      r10,528(r13)
> 
> If the user wants to probe at _do_fork+0x54, he'd do:
> 	# perf probe _do_fork+0x54
> 
> With the earlier approach, we would insert the probe at _do_fork+0x5c 
> (0x54 from the LEP) instead, which is incorrect.
> 
> In reality, user would probably just use debuginfo:
> 	# perf probe -L _do_fork
> 	<_do_fork@/root/linus/kernel/fork.c:0>
> 	      0  long _do_fork(unsigned long clone_flags,
> 			      unsigned long stack_start,
> 			      unsigned long stack_size,
> 			      int __user *parent_tidptr,
> 			      int __user *child_tidptr,
> 			      unsigned long tls)
> 	      6  {
> 			struct task_struct *p;
> 	      8         int trace = 0;
> 			long nr;
> 		 
> 			/*
> 			 * Determine whether and which event to report to ptracer.  When
> 			 * called from kernel_thread or CLONE_UNTRACED is explicitly
> 			 * requested, no event is reported; otherwise, report if the event
> 			 * for the type of forking is enabled.
> 			 */
> 	     17         if (!(clone_flags & CLONE_UNTRACED)) {
> 	     18                 if (clone_flags & CLONE_VFORK)
> 	     19                         trace = PTRACE_EVENT_VFORK;
> 	     20                 else if ((clone_flags & CSIGNAL) != SIGCHLD)
> 	     21                         trace = PTRACE_EVENT_CLONE;
> 
> 	# perf probe _do_fork:17
> 
> In this case, perf chooses the right address based on DWARF. The current 
> patchset matches the behavior of perf without debuginfo with this.


I agree what I worry is that perf probe _do_fork sets a breakpoint after
perf probe _do_fork+0x4. I am not sure if there is an easy solution to
the problem. 

Balbir

[toc] | [prev] | [next] | [standalone]

#1374631

From"Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Date2016-04-09 15:50 +0200
Message-ID<rm1qV-5Qu-3@gated-at.bofh.it>
In reply to#1374023
On 2016/04/08 04:57PM, Balbir Singh wrote:
> On Thu, 2016-04-07 at 14:56 +0530, Naveen N. Rao wrote:
> > On 2016/04/07 06:19PM, Balbir Singh wrote:
> > > 
> > > 
> > > On 06/04/16 22:32, Naveen N. Rao wrote:
> > > > 
> > > > This patchset fixes three issues found with perf probe on ppc64le:
> > > > 1. 'perf test kallsyms' failure on ppc64le (reported by Michael
> > > > Ellerman). This was due to the symbols being fixed up during symbol
> > > > table load. This is fixed in patch 2 by delaying symbol fixup until
> > > > later.
> > > > 2. perf probe function offset was being calculated from the local entry
> > > > point (LEP), which does not match user expectation when trying to look
> > > > at function disassembly output (reported by Ananth N). This is fixed for
> > > > kallsyms in patch 1 and for symbol table in patch 2.
> > > I think the bit where the offset is w.r.t LEP when using a name, but w.r.t
> > > GEP when using function+offset can be confusing.
> > Thanks for your review!
> > 
> > The rationale for this is actually from the end-user perspective. The 
> > two use cases we are considering are:
> > 1. User just wants to probe at function entry point:
> > 	# perf probe _do_fork
> > 
> > In this case, the user most definitely needs the local entry point, 
> > without which the probe won't be hit. So, for this case, we 
> > automatically insert the probe at the LEP.
> > 
> > [We really only want to alter perf probe behavior in this case only, but 
> > we were incorrectly changing the behavior of perf with the below 
> > scenario as well.]
> > 
> > 2. User wants to probe at a specific location. In this case, the user 
> > most likely starts by looking at the function disassembly. For instance:
> > 	# objdump -S -d vmlinux.bak | grep -A100 \<_do_fork\>:
> > 	c0000000000b6a00 <_do_fork>:
> > 		      unsigned long stack_start,
> > 		      unsigned long stack_size,
> > 		      int __user *parent_tidptr,
> > 		      int __user *child_tidptr,
> > 		      unsigned long tls)
> > 	{
> > 	c0000000000b6a00:	f7 00 4c 3c 	addis   r2,r12,247
> > 	c0000000000b6a04:	00 86 42 38 	addi    r2,r2,-31232
> > 	c0000000000b6a08:	a6 02 08 7c 	mflr    r0
> > 	c0000000000b6a0c:	d0 ff 41 fb 	std     r26,-48(r1)
> > 	c0000000000b6a10:	26 80 90 7d 	mfocrf  r12,8
> > 	...<snip>...
> > 		if (!(clone_flags & CLONE_UNTRACED)) {
> > 	c0000000000b6a54:	e3 4f c7 7b 	rldicl. r7,r30,41,63
> > 	c0000000000b6a58:	2c 00 82 40 	bne     c0000000000b6a84 <_do_fork+0x84>
> > 			if (clone_flags & CLONE_VFORK)
> > 	c0000000000b6a5c:	e3 97 c8 7b 	rldicl. r8,r30,50,63
> > 	c0000000000b6a60:	a0 01 82 41 	beq     c0000000000b6c00 <_do_fork+0x200>
> > 	c0000000000b6a64:	20 00 20 39 	li      r9,32
> > 				trace = PTRACE_EVENT_VFORK;
> > 	c0000000000b6a68:	02 00 80 3b 	li      r28,2
> > 	c0000000000b6a6c:	10 02 4d e9 	ld      r10,528(r13)
> > 
> > If the user wants to probe at _do_fork+0x54, he'd do:
> > 	# perf probe _do_fork+0x54
> > 
> > With the earlier approach, we would insert the probe at _do_fork+0x5c 
> > (0x54 from the LEP) instead, which is incorrect.
> > 
> > In reality, user would probably just use debuginfo:
> > 	# perf probe -L _do_fork
> > 	<_do_fork@/root/linus/kernel/fork.c:0>
> > 	      0  long _do_fork(unsigned long clone_flags,
> > 			      unsigned long stack_start,
> > 			      unsigned long stack_size,
> > 			      int __user *parent_tidptr,
> > 			      int __user *child_tidptr,
> > 			      unsigned long tls)
> > 	      6  {
> > 			struct task_struct *p;
> > 	      8         int trace = 0;
> > 			long nr;
> > 		 
> > 			/*
> > 			 * Determine whether and which event to report to ptracer.  When
> > 			 * called from kernel_thread or CLONE_UNTRACED is explicitly
> > 			 * requested, no event is reported; otherwise, report if the event
> > 			 * for the type of forking is enabled.
> > 			 */
> > 	     17         if (!(clone_flags & CLONE_UNTRACED)) {
> > 	     18                 if (clone_flags & CLONE_VFORK)
> > 	     19                         trace = PTRACE_EVENT_VFORK;
> > 	     20                 else if ((clone_flags & CSIGNAL) != SIGCHLD)
> > 	     21                         trace = PTRACE_EVENT_CLONE;
> > 
> > 	# perf probe _do_fork:17
> > 
> > In this case, perf chooses the right address based on DWARF. The current 
> > patchset matches the behavior of perf without debuginfo with this.
> 
> 
> I agree what I worry is that perf probe _do_fork sets a breakpoint after
> perf probe _do_fork+0x4. I am not sure if there is an easy solution to
> the problem. 

I suppose this boils down to the quirkiness of ABIv2. Though, in 
reality, I don't think most users will notice. As I stated above, users 
will most likely start with the disassembly or debuginfo and this patch 
ensures there are actually no surprises there.

- Naveen

[toc] | [prev] | [next] | [standalone]

#1375489

FromMichael Ellerman <mpe@ellerman.id.au>
Date2016-04-11 06:50 +0200
Message-ID<rmBXs-8ud-3@gated-at.bofh.it>
In reply to#1374631
On Sat, 2016-04-09 at 19:12 +0530, Naveen N. Rao wrote:
> 
> I suppose this boils down to the quirkiness of ABIv2. Though, in 
> reality, I don't think most users will notice. As I stated above, users 
> will most likely start with the disassembly or debuginfo and this patch 
> ensures there are actually no surprises there.

Yeah it's unfortunate that we have to handle these two cases differently.

But I think you've chosen the right trade off.

When we are just given the name we *must not* use the global entry point,
otherwise the probes will often not hit - because most calls go to the local
entry point and skip the global entry point entirely.

When we're given a name and offset, it's less confusing if we use the global
entry point as the base for the offset calculation.

So for the concept:

Acked-by: Michael Ellerman <mpe@ellerman.id.au>

I don't really know this part of the perf code enough to give you an ack for the
actual changes, I'll leave that to the perf maintainers.

cheers

[toc] | [prev] | [next] | [standalone]

#1375899

From"Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Date2016-04-11 15:50 +0200
Message-ID<rmKo1-6L0-7@gated-at.bofh.it>
In reply to#1375489
On 2016/04/11 02:41PM, Michael Ellerman wrote:
> On Sat, 2016-04-09 at 19:12 +0530, Naveen N. Rao wrote:
> > 
> > I suppose this boils down to the quirkiness of ABIv2. Though, in 
> > reality, I don't think most users will notice. As I stated above, users 
> > will most likely start with the disassembly or debuginfo and this patch 
> > ensures there are actually no surprises there.
> 
> Yeah it's unfortunate that we have to handle these two cases differently.
> 
> But I think you've chosen the right trade off.
> 
> When we are just given the name we *must not* use the global entry point,
> otherwise the probes will often not hit - because most calls go to the local
> entry point and skip the global entry point entirely.
> 
> When we're given a name and offset, it's less confusing if we use the global
> entry point as the base for the offset calculation.
> 
> So for the concept:
> 
> Acked-by: Michael Ellerman <mpe@ellerman.id.au>

Thanks, Michael. That helps.

> 
> I don't really know this part of the perf code enough to give you an ack for the
> actual changes, I'll leave that to the perf maintainers.

Sure.

Arnaldo,
I will send a v2 soon with a bit more testing to make sure this covers 
all scenarios properly (I am also trying to see if we can address 
debuginfo-based probing properly).

- Naveen

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web