[PATCH] perf header: Set proper symbol name for vdso when build-id event found

[PATCH] perf header: Set proper symbol name for vdso when build-id event found

[Like Xu]

From: Like Xu <likexu@tencent.com>

If using perf-record to sample a cpu-cycles:P event on a hypervisor process
when '--kcore' is not enabled, user may find some surprise in perf-report:

# perf report -i perf.data -v:
# Overhead Command   Shared Object            	Symbol
    99.71%  vcpu0    arch/x86/kvm/kvm-intel.ko  0xffffffffa10d1e30 B [k] 0x0000000000034ed0

build id event received for vmlinux: d12116149f511f7dbd0b21c45d38d3d2ec09b87f [20]
build id event received for kvm-intel.ko: a8fc0213abbafd97b10ce58ce84bec8519f9abce [20]
build id event received for [vdso]: 4d56e381df8d2c051f6bc1ef69c0118c59d5c49f [20]

# perf report:
# Overhead  Command  Shared Object     Symbol
# ........  .......  ................  .......................................
#
    99.71%  vcpu0    [kvm_intel]       [k] 0x0000000000034ed0
     0.10%  vcpu0    [kernel.vmlinux]  [k] __lock_acquire.isra.29

Users may be curious as to how 0x34ed0 was generated and wondered if this
RIP came from the guest application but perf-script-D does not point to any
samples of this address.

Based on perf/tool implementation, this is actually an offset pointing to
the vdso object (in this case it is the assembly __vmx_vcpu_run defined
in arch/x86/kvm/vmx/vmenter.S). The pattern is not reproduced on perf-tool
of some distributions, and git-bisect quickly identified the possible root
cause, which leds to this straightforward fix and after this change:

# perf report -i perf.data -v:
# Overhead Command   Shared Object            	Symbol
    99.71%  vcpu0    arch/x86/kvm/kvm-intel.ko  0x34ed0            B [k] __vmx_vcpu_run

# perf report:
# Overhead  Command  Shared Object     Symbol
# ........  .......  ................  .......................................
#
    99.71%  vcpu0    [kvm_intel]       [k] __vmx_vcpu_run

The fix also gets commit 1deec1bd96cc ("perf header: Set proper module name
when build-id event found") lit again.

Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Fixes: b2fe96a350de ("perf tools: Fix module symbol processing")
Signed-off-by: Like Xu <likexu@tencent.com>
---
 tools/perf/util/header.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index e86b9439ffee..a33d589511ff 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2305,8 +2305,8 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev,
 
 			if (!kmod_path__parse_name(&m, filename) && m.kmod)
 				dso__set_module_info(dso, &m, machine);
-
-			dso->kernel = dso_space;
+			else
+				dso->kernel = dso_space;
 			free(m.name);
 		}
 
-- 
2.43.0

Re: [PATCH] perf header: Set proper symbol name for vdso when build-id event found

[Adrian Hunter]

On 1/12/23 13:15, Like Xu wrote:
> From: Like Xu <likexu@tencent.com>
> 
> If using perf-record to sample a cpu-cycles:P event on a hypervisor process
> when '--kcore' is not enabled, user may find some surprise in perf-report:
> 
> # perf report -i perf.data -v:
> # Overhead Command   Shared Object            	Symbol
>     99.71%  vcpu0    arch/x86/kvm/kvm-intel.ko  0xffffffffa10d1e30 B [k] 0x0000000000034ed0
> 
> build id event received for vmlinux: d12116149f511f7dbd0b21c45d38d3d2ec09b87f [20]
> build id event received for kvm-intel.ko: a8fc0213abbafd97b10ce58ce84bec8519f9abce [20]
> build id event received for [vdso]: 4d56e381df8d2c051f6bc1ef69c0118c59d5c49f [20]
> 
> # perf report:
> # Overhead  Command  Shared Object     Symbol
> # ........  .......  ................  .......................................
> #
>     99.71%  vcpu0    [kvm_intel]       [k] 0x0000000000034ed0
>      0.10%  vcpu0    [kernel.vmlinux]  [k] __lock_acquire.isra.29
> 
> Users may be curious as to how 0x34ed0 was generated and wondered if this
> RIP came from the guest application but perf-script-D does not point to any
> samples of this address.
> 
> Based on perf/tool implementation, this is actually an offset pointing to
> the vdso object (in this case it is the assembly __vmx_vcpu_run defined
> in arch/x86/kvm/vmx/vmenter.S). The pattern is not reproduced on perf-tool
> of some distributions, and git-bisect quickly identified the possible root
> cause, which leds to this straightforward fix and after this change:
> 
> # perf report -i perf.data -v:
> # Overhead Command   Shared Object            	Symbol
>     99.71%  vcpu0    arch/x86/kvm/kvm-intel.ko  0x34ed0            B [k] __vmx_vcpu_run
> 
> # perf report:
> # Overhead  Command  Shared Object     Symbol
> # ........  .......  ................  .......................................
> #
>     99.71%  vcpu0    [kvm_intel]       [k] __vmx_vcpu_run
> 
> The fix also gets commit 1deec1bd96cc ("perf header: Set proper module name
> when build-id event found") lit again.
> 
> Cc: Jiri Olsa <jolsa@kernel.org>
> Cc: Namhyung Kim <namhyung@kernel.org>
> Cc: Ian Rogers <irogers@google.com>
> Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
> Fixes: b2fe96a350de ("perf tools: Fix module symbol processing")
> Signed-off-by: Like Xu <likexu@tencent.com>
> ---
>  tools/perf/util/header.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
> index e86b9439ffee..a33d589511ff 100644
> --- a/tools/perf/util/header.c
> +++ b/tools/perf/util/header.c
> @@ -2305,8 +2305,8 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev,
>  
>  			if (!kmod_path__parse_name(&m, filename) && m.kmod)
>  				dso__set_module_info(dso, &m, machine);
> -
> -			dso->kernel = dso_space;
> +			else
> +				dso->kernel = dso_space;

This is undoing some of b2fe96a350de ("perf tools: Fix module
symbol processing") without explanation.

Symbols in the .noinstr.text section don't seem to be
being resolved, so that could be the issue.  perf synthesizes
an MMAP record from /proc/modules, which works for .text
but perhaps not for .noinstr.text

>  			free(m.name);
>  		}
>  

Re: [PATCH] perf header: Set proper symbol name for vdso when build-id event found

[Like Xu]

On 14/12/2023 3:26 am, Adrian Hunter wrote:
> On 1/12/23 13:15, Like Xu wrote:
>> From: Like Xu <likexu@tencent.com>
>>
>> If using perf-record to sample a cpu-cycles:P event on a hypervisor process
>> when '--kcore' is not enabled, user may find some surprise in perf-report:
>>
>> # perf report -i perf.data -v:
>> # Overhead Command   Shared Object            	Symbol
>>      99.71%  vcpu0    arch/x86/kvm/kvm-intel.ko  0xffffffffa10d1e30 B [k] 0x0000000000034ed0
>>
>> build id event received for vmlinux: d12116149f511f7dbd0b21c45d38d3d2ec09b87f [20]
>> build id event received for kvm-intel.ko: a8fc0213abbafd97b10ce58ce84bec8519f9abce [20]
>> build id event received for [vdso]: 4d56e381df8d2c051f6bc1ef69c0118c59d5c49f [20]
>>
>> # perf report:
>> # Overhead  Command  Shared Object     Symbol
>> # ........  .......  ................  .......................................
>> #
>>      99.71%  vcpu0    [kvm_intel]       [k] 0x0000000000034ed0
>>       0.10%  vcpu0    [kernel.vmlinux]  [k] __lock_acquire.isra.29
>>
>> Users may be curious as to how 0x34ed0 was generated and wondered if this
>> RIP came from the guest application but perf-script-D does not point to any
>> samples of this address.
>>
>> Based on perf/tool implementation, this is actually an offset pointing to
>> the vdso object (in this case it is the assembly __vmx_vcpu_run defined
>> in arch/x86/kvm/vmx/vmenter.S). The pattern is not reproduced on perf-tool
>> of some distributions, and git-bisect quickly identified the possible root
>> cause, which leds to this straightforward fix and after this change:
>>
>> # perf report -i perf.data -v:
>> # Overhead Command   Shared Object            	Symbol
>>      99.71%  vcpu0    arch/x86/kvm/kvm-intel.ko  0x34ed0            B [k] __vmx_vcpu_run
>>
>> # perf report:
>> # Overhead  Command  Shared Object     Symbol
>> # ........  .......  ................  .......................................
>> #
>>      99.71%  vcpu0    [kvm_intel]       [k] __vmx_vcpu_run
>>
>> The fix also gets commit 1deec1bd96cc ("perf header: Set proper module name
>> when build-id event found") lit again.
>>
>> Cc: Jiri Olsa <jolsa@kernel.org>
>> Cc: Namhyung Kim <namhyung@kernel.org>
>> Cc: Ian Rogers <irogers@google.com>
>> Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
>> Fixes: b2fe96a350de ("perf tools: Fix module symbol processing")
>> Signed-off-by: Like Xu <likexu@tencent.com>
>> ---
>>   tools/perf/util/header.c | 4 ++--
>>   1 file changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
>> index e86b9439ffee..a33d589511ff 100644
>> --- a/tools/perf/util/header.c
>> +++ b/tools/perf/util/header.c
>> @@ -2305,8 +2305,8 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev,
>>   
>>   			if (!kmod_path__parse_name(&m, filename) && m.kmod)
>>   				dso__set_module_info(dso, &m, machine);
>> -
>> -			dso->kernel = dso_space;
>> +			else
>> +				dso->kernel = dso_space;
> 
> This is undoing some of b2fe96a350de ("perf tools: Fix module
> symbol processing") without explanation.

Thanks for your comments.
W/ this fix, "perf test -v object" looks OK.

> 
> Symbols in the .noinstr.text section don't seem to be
> being resolved, so that could be the issue.  perf synthesizes
> an MMAP record from /proc/modules, which works for .text
> but perhaps not for .noinstr.text

Not sure if it covers the potentially broken features you mentioned above,
would you be willing to provide a more detailed test command ?

> 
>>   			free(m.name);
>>   		}
>>   
> 

Re: [PATCH] perf header: Set proper symbol name for vdso when build-id event found

[Adrian Hunter]

On 14/12/23 04:48, Like Xu wrote:
> On 14/12/2023 3:26 am, Adrian Hunter wrote:
>> On 1/12/23 13:15, Like Xu wrote:
>>> From: Like Xu <likexu@tencent.com>
>>>
>>> If using perf-record to sample a cpu-cycles:P event on a hypervisor process
>>> when '--kcore' is not enabled, user may find some surprise in perf-report:
>>>
>>> # perf report -i perf.data -v:
>>> # Overhead Command   Shared Object                Symbol
>>>      99.71%  vcpu0    arch/x86/kvm/kvm-intel.ko  0xffffffffa10d1e30 B [k] 0x0000000000034ed0
>>>
>>> build id event received for vmlinux: d12116149f511f7dbd0b21c45d38d3d2ec09b87f [20]
>>> build id event received for kvm-intel.ko: a8fc0213abbafd97b10ce58ce84bec8519f9abce [20]
>>> build id event received for [vdso]: 4d56e381df8d2c051f6bc1ef69c0118c59d5c49f [20]
>>>
>>> # perf report:
>>> # Overhead  Command  Shared Object     Symbol
>>> # ........  .......  ................  .......................................
>>> #
>>>      99.71%  vcpu0    [kvm_intel]       [k] 0x0000000000034ed0
>>>       0.10%  vcpu0    [kernel.vmlinux]  [k] __lock_acquire.isra.29
>>>
>>> Users may be curious as to how 0x34ed0 was generated and wondered if this
>>> RIP came from the guest application but perf-script-D does not point to any
>>> samples of this address.
>>>
>>> Based on perf/tool implementation, this is actually an offset pointing to
>>> the vdso object (in this case it is the assembly __vmx_vcpu_run defined
>>> in arch/x86/kvm/vmx/vmenter.S). The pattern is not reproduced on perf-tool
>>> of some distributions, and git-bisect quickly identified the possible root
>>> cause, which leds to this straightforward fix and after this change:
>>>
>>> # perf report -i perf.data -v:
>>> # Overhead Command   Shared Object                Symbol
>>>      99.71%  vcpu0    arch/x86/kvm/kvm-intel.ko  0x34ed0            B [k] __vmx_vcpu_run
>>>
>>> # perf report:
>>> # Overhead  Command  Shared Object     Symbol
>>> # ........  .......  ................  .......................................
>>> #
>>>      99.71%  vcpu0    [kvm_intel]       [k] __vmx_vcpu_run
>>>
>>> The fix also gets commit 1deec1bd96cc ("perf header: Set proper module name
>>> when build-id event found") lit again.
>>>
>>> Cc: Jiri Olsa <jolsa@kernel.org>
>>> Cc: Namhyung Kim <namhyung@kernel.org>
>>> Cc: Ian Rogers <irogers@google.com>
>>> Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
>>> Fixes: b2fe96a350de ("perf tools: Fix module symbol processing")
>>> Signed-off-by: Like Xu <likexu@tencent.com>
>>> ---
>>>   tools/perf/util/header.c | 4 ++--
>>>   1 file changed, 2 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
>>> index e86b9439ffee..a33d589511ff 100644
>>> --- a/tools/perf/util/header.c
>>> +++ b/tools/perf/util/header.c
>>> @@ -2305,8 +2305,8 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev,
>>>                 if (!kmod_path__parse_name(&m, filename) && m.kmod)
>>>                   dso__set_module_info(dso, &m, machine);
>>> -
>>> -            dso->kernel = dso_space;
>>> +            else
>>> +                dso->kernel = dso_space;
>>
>> This is undoing some of b2fe96a350de ("perf tools: Fix module
>> symbol processing") without explanation.
> 
> Thanks for your comments.
> W/ this fix, "perf test -v object" looks OK.
> 
>>
>> Symbols in the .noinstr.text section don't seem to be
>> being resolved, so that could be the issue.  perf synthesizes
>> an MMAP record from /proc/modules, which works for .text
>> but perhaps not for .noinstr.text
> 
> Not sure if it covers the potentially broken features you mentioned above,
> would you be willing to provide a more detailed test command ?

I sent a patch that might help a bit:

https://lore.kernel.org/linux-perf-users/20240202110130.3553-3-adrian.hunter@intel.com/