[V2 1/2] tools/perf: Add text_end to "struct dso" to save .text section size

[V2 1/2] tools/perf: Add text_end to "struct dso" to save .text section size

[Athira Rajeev]

Update "struct dso" to include new member "text_end".
This new field will represent the offset for end of text
section for a dso. For elf, this value is derived as:
sh_size (Size of section in byes) + sh_offset (Section file
offst) of the elf header for text.

For bfd, this value is derived as:
1. For PE file,
section->size + ( section->vma - dso->text_offset)
2. Other cases:
section->filepos (file position) + section->size (size of
section)

To resolve the address from a sample, perf looks at the
DSO maps. In case of address from a kernel module, there
were some address found to be not resolved. This was
observed while running perf test for "Object code reading".
Though the ip falls beteen the start address of the loaded
module (perf map->start ) and end address ( perf map->end),
it was unresolved.

Example:

    Reading object code for memory address: 0xc008000007f0142c
    File is: /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko
    On file address is: 0x1114cc
    Objdump command is: objdump -z -d --start-address=0x11142c --stop-address=0x1114ac /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko
    objdump read too few bytes: 128
    test child finished with -1

Here, module is loaded at:
    # cat /proc/modules | grep xfs
    xfs 2228224 3 - Live 0xc008000007d00000

From objdump for xfs module, text section is:
    text 0010f7bc  0000000000000000 0000000000000000 000000a0 2**4

Here the offset for 0xc008000007f0142c ie  0x112074 falls out
.text section which is up to 0x10f7bc.

In this case for module, the address 0xc008000007e11fd4 is pointing
to stub instructions. This address range represents the module stubs
which is allocated on module load and hence is not part of DSO offset.

To identify such  address, which falls out of text
section and within module end, added the new field "text_end" to
"struct dso".

Reported-by: Disha Goel <disgoel@linux.ibm.com>
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
Changelog:
 v1 -> v2:
 Added text_end for bfd also by updating dso__load_bfd_symbols
 as suggested by Adrian.

 tools/perf/util/dso.h        | 1 +
 tools/perf/util/symbol-elf.c | 4 +++-
 tools/perf/util/symbol.c     | 2 ++
 3 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index b41c9782c754..70fe0fe69bef 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -181,6 +181,7 @@ struct dso {
 	u8		 rel;
 	struct build_id	 bid;
 	u64		 text_offset;
+	u64		 text_end;
 	const char	 *short_name;
 	const char	 *long_name;
 	u16		 long_name_len;
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 95e99c332d7e..9e7eeaf616b8 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1514,8 +1514,10 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 	}
 
 	if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr,
-				".text", NULL))
+				".text", NULL)) {
 		dso->text_offset = tshdr.sh_addr - tshdr.sh_offset;
+		dso->text_end = tshdr.sh_offset + tshdr.sh_size;
+	}
 
 	if (runtime_ss->opdsec)
 		opddata = elf_rawdata(runtime_ss->opdsec, NULL);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3f36675b7c8f..f25e4e62cf25 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1733,8 +1733,10 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
 			/* PE symbols can only have 4 bytes, so use .text high bits */
 			dso->text_offset = section->vma - (u32)section->vma;
 			dso->text_offset += (u32)bfd_asymbol_value(symbols[i]);
+			dso->text_end = (section->vma - dso->text_offset) + section->size;
 		} else {
 			dso->text_offset = section->vma - section->filepos;
+			dso->text_end = section->filepos + section->size;
 		}
 	}
 
-- 
2.31.1

[V2 2/2] tools/perf/tests: Fix object code reading to skip address that falls out of text section

[Athira Rajeev]

The testcase "Object code reading" fails in somecases
for "fs_something" sub test as below:

    Reading object code for memory address: 0xc008000007f0142c
    File is: /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko
    On file address is: 0x1114cc
    Objdump command is: objdump -z -d --start-address=0x11142c --stop-address=0x1114ac /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko
    objdump read too few bytes: 128
    test child finished with -1

This can alo be reproduced when running perf record with
workload that exercises fs_something() code. In the test
setup, this is exercising xfs code since root is xfs.

    # perf record ./a.out
    # perf report -v |grep "xfs.ko"
      0.76% a.out /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko  0xc008000007de5efc B [k] xlog_cil_commit
      0.74% a.out  /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko  0xc008000007d5ae18 B [k] xfs_btree_key_offset
      0.74% a.out  /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko  0xc008000007e11fd4 B [k] 0x0000000000112074

Here addr "0xc008000007e11fd4" is not resolved. since this is a
kernel module, its offset is from the DSO. Xfs module is loaded
at 0xc008000007d00000

   # cat /proc/modules | grep xfs
    xfs 2228224 3 - Live 0xc008000007d00000

And size is 0x220000. So its loaded between  0xc008000007d00000
and 0xc008000007f20000. From objdump, text section is:
    text 0010f7bc  0000000000000000 0000000000000000 000000a0 2**4

Hence perf captured ip maps to 0x112074 which is:
( ip - start of module ) + a0

This offset 0x112074 falls out .text section which is up to 0x10f7bc
In this case for module, the address 0xc008000007e11fd4 is pointing
to stub instructions. This address range represents the module stubs
which is allocated on module load and hence is not part of DSO offset.

To address this issue in "object code reading", skip the sample if
address falls out of text section and is within the module end.
Use the "text_end" member of "struct dso" to do this check.

To address this issue in "perf report", exploring an option of
having stubs range as part of the /proc/kallsyms, so that perf
report can resolve addresses in stubs range

However this patch uses text_end to skip the stub range for
Object code reading testcase.

Reported-by: Disha Goel <disgoel@linux.ibm.com>
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
Changelog:
 v1 -> v2:
 Updated comment to add description on which arch has stub and
 reason for skipping as suggested by Adrian

 tools/perf/tests/code-reading.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index ed3815163d1b..3cf6c2d42416 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -269,6 +269,18 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 	if (addr + len > map__end(al.map))
 		len = map__end(al.map) - addr;
 
+	/*
+	 * Some architectures (ex: powerpc) have stubs (trampolines) in kernel
+	 * modules to manage long jumps. Check if the ip offset falls in stubs
+	 * sections for kernel modules. And skip module address after text end
+	 */
+	if (strstr(dso->long_name, ".ko")) {
+		if (al.addr > dso->text_end) {
+			pr_debug("skipping the module address %#"PRIx64" after text end\n", al.addr);
+			goto out;
+		}
+	}
+
 	/* Read the object code using perf */
 	ret_len = dso__data_read_offset(dso, maps__machine(thread__maps(thread)),
 					al.addr, buf1, len);
-- 
2.31.1

Re: [V2 2/2] tools/perf/tests: Fix object code reading to skip address that falls out of text section

[Athira Rajeev]

> On 14-Sep-2023, at 5:47 PM, Disha Goel <disgoel@linux.ibm.com> wrote:
> 
> On 07/09/23 10:15 pm, Athira Rajeev wrote:
>> The testcase "Object code reading" fails in somecases
>> for "fs_something" sub test as below:
>> 
>> Reading object code for memory address: 0xc008000007f0142c
>> File is: /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko
>> On file address is: 0x1114cc
>> Objdump command is: objdump -z -d --start-address=0x11142c --stop-address=0x1114ac /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko
>> objdump read too few bytes: 128
>> test child finished with -1
>> 
>> This can alo be reproduced when running perf record with
>> workload that exercises fs_something() code. In the test
>> setup, this is exercising xfs code since root is xfs.
>> 
>> # perf record ./a.out
>> # perf report -v |grep "xfs.ko"
>> 0.76% a.out /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko 0xc008000007de5efc B [k] xlog_cil_commit
>> 0.74% a.out /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko 0xc008000007d5ae18 B [k] xfs_btree_key_offset
>> 0.74% a.out /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko 0xc008000007e11fd4 B [k] 0x0000000000112074
>> 
>> Here addr "0xc008000007e11fd4" is not resolved. since this is a
>> kernel module, its offset is from the DSO. Xfs module is loaded
>> at 0xc008000007d00000
>> 
>> # cat /proc/modules | grep xfs
>> xfs 2228224 3 - Live 0xc008000007d00000
>> 
>> And size is 0x220000. So its loaded between ߦ0xc008000007d00000
>> and 0xc008000007f20000. From objdump, text section is:
>> text 0010f7bc 0000000000000000 0000000000000000 000000a0 2**4
>> 
>> Hence perf captured ip maps to 0x112074 which is:
>> ( ip - start of module ) + a0
>> 
>> This offset 0x112074 falls out .text section which is up to 0x10f7bc
>> In this case for module, the address 0xc008000007e11fd4 is pointing
>> to stub instructions. This address range represents the module stubs
>> which is allocated on module load and hence is not part of DSO offset.
>> 
>> To address this issue in "object code reading", skip the sample if
>> address falls out of text section and is within the module end.
>> Use the "text_end" member of "struct dso" to do this check.
>> 
>> To address this issue in "perf report", exploring an option of
>> having stubs range as part of the /proc/kallsyms, so that perf
>> report can resolve addresses in stubs range
>> 
>> However this patch uses text_end to skip the stub range for
>> Object code reading testcase.
>> 
>> Reported-by: Disha Goel <disgoel@linux.ibm.com>
>> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
>> ---
>> Changelog:
>> v1 -> v2:
>> Updated comment to add description on which arch has stub and
>> reason for skipping as suggested by Adrian

Thanks for testing Disha.

Hi Adrian,

Can you please review and share feedback on this version.

Thanks
Athira

> With this patch applied perf Object code reading test works correctly.
> 
> 26: Object code reading : Ok
> 
> Tested-by: Disha Goel <disgoel@linux.ibm.com>
> 
>> tools/perf/tests/code-reading.c | 12 ++++++++++++
>> 1 file changed, 12 insertions(+)
>> 
>> diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
>> index ed3815163d1b..3cf6c2d42416 100644
>> --- a/tools/perf/tests/code-reading.c
>> +++ b/tools/perf/tests/code-reading.c
>> @@ -269,6 +269,18 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
>> if (addr + len > map__end(al.map))
>> len = map__end(al.map) - addr;
>> 
>> + /*
>> + * Some architectures (ex: powerpc) have stubs (trampolines) in kernel
>> + * modules to manage long jumps. Check if the ip offset falls in stubs
>> + * sections for kernel modules. And skip module address after text end
>> + */
>> + if (strstr(dso->long_name, ".ko")) {
>> + if (al.addr > dso->text_end) {
>> + pr_debug("skipping the module address %#"PRIx64" after text end\n", al.addr);
>> + goto out;
>> + }
>> + }
>> +
>> /* Read the object code using perf */
>> ret_len = dso__data_read_offset(dso, maps__machine(thread__maps(thread)),
>> al.addr, buf1, len);
>> 

Re: [V2 1/2] tools/perf: Add text_end to "struct dso" to save .text section size

[Adrian Hunter]

On 7/09/23 19:45, Athira Rajeev wrote:
> Update "struct dso" to include new member "text_end".
> This new field will represent the offset for end of text
> section for a dso. For elf, this value is derived as:
> sh_size (Size of section in byes) + sh_offset (Section file
> offst) of the elf header for text.
> 
> For bfd, this value is derived as:
> 1. For PE file,
> section->size + ( section->vma - dso->text_offset)
> 2. Other cases:
> section->filepos (file position) + section->size (size of
> section)
> 
> To resolve the address from a sample, perf looks at the
> DSO maps. In case of address from a kernel module, there
> were some address found to be not resolved. This was
> observed while running perf test for "Object code reading".
> Though the ip falls beteen the start address of the loaded
> module (perf map->start ) and end address ( perf map->end),
> it was unresolved.
> 
> Example:
> 
>     Reading object code for memory address: 0xc008000007f0142c
>     File is: /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko
>     On file address is: 0x1114cc
>     Objdump command is: objdump -z -d --start-address=0x11142c --stop-address=0x1114ac /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko
>     objdump read too few bytes: 128
>     test child finished with -1
> 
> Here, module is loaded at:
>     # cat /proc/modules | grep xfs
>     xfs 2228224 3 - Live 0xc008000007d00000
> 
> From objdump for xfs module, text section is:
>     text 0010f7bc  0000000000000000 0000000000000000 000000a0 2**4
> 
> Here the offset for 0xc008000007f0142c ie  0x112074 falls out
> .text section which is up to 0x10f7bc.
> 
> In this case for module, the address 0xc008000007e11fd4 is pointing
> to stub instructions. This address range represents the module stubs
> which is allocated on module load and hence is not part of DSO offset.
> 
> To identify such  address, which falls out of text
> section and within module end, added the new field "text_end" to
> "struct dso".
> 
> Reported-by: Disha Goel <disgoel@linux.ibm.com>
> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>

Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>

> ---
> Changelog:
>  v1 -> v2:
>  Added text_end for bfd also by updating dso__load_bfd_symbols
>  as suggested by Adrian.
> 
>  tools/perf/util/dso.h        | 1 +
>  tools/perf/util/symbol-elf.c | 4 +++-
>  tools/perf/util/symbol.c     | 2 ++
>  3 files changed, 6 insertions(+), 1 deletion(-)
> 
> diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
> index b41c9782c754..70fe0fe69bef 100644
> --- a/tools/perf/util/dso.h
> +++ b/tools/perf/util/dso.h
> @@ -181,6 +181,7 @@ struct dso {
>  	u8		 rel;
>  	struct build_id	 bid;
>  	u64		 text_offset;
> +	u64		 text_end;
>  	const char	 *short_name;
>  	const char	 *long_name;
>  	u16		 long_name_len;
> diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
> index 95e99c332d7e..9e7eeaf616b8 100644
> --- a/tools/perf/util/symbol-elf.c
> +++ b/tools/perf/util/symbol-elf.c
> @@ -1514,8 +1514,10 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
>  	}
>  
>  	if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr,
> -				".text", NULL))
> +				".text", NULL)) {
>  		dso->text_offset = tshdr.sh_addr - tshdr.sh_offset;
> +		dso->text_end = tshdr.sh_offset + tshdr.sh_size;
> +	}
>  
>  	if (runtime_ss->opdsec)
>  		opddata = elf_rawdata(runtime_ss->opdsec, NULL);
> diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
> index 3f36675b7c8f..f25e4e62cf25 100644
> --- a/tools/perf/util/symbol.c
> +++ b/tools/perf/util/symbol.c
> @@ -1733,8 +1733,10 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
>  			/* PE symbols can only have 4 bytes, so use .text high bits */
>  			dso->text_offset = section->vma - (u32)section->vma;
>  			dso->text_offset += (u32)bfd_asymbol_value(symbols[i]);
> +			dso->text_end = (section->vma - dso->text_offset) + section->size;
>  		} else {
>  			dso->text_offset = section->vma - section->filepos;
> +			dso->text_end = section->filepos + section->size;
>  		}
>  	}
>  

Re: [V2 2/2] tools/perf/tests: Fix object code reading to skip address that falls out of text section

[Adrian Hunter]

On 7/09/23 19:45, Athira Rajeev wrote:
> The testcase "Object code reading" fails in somecases
> for "fs_something" sub test as below:
> 
>     Reading object code for memory address: 0xc008000007f0142c
>     File is: /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko
>     On file address is: 0x1114cc
>     Objdump command is: objdump -z -d --start-address=0x11142c --stop-address=0x1114ac /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko
>     objdump read too few bytes: 128
>     test child finished with -1
> 
> This can alo be reproduced when running perf record with
> workload that exercises fs_something() code. In the test
> setup, this is exercising xfs code since root is xfs.
> 
>     # perf record ./a.out
>     # perf report -v |grep "xfs.ko"
>       0.76% a.out /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko  0xc008000007de5efc B [k] xlog_cil_commit
>       0.74% a.out  /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko  0xc008000007d5ae18 B [k] xfs_btree_key_offset
>       0.74% a.out  /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko  0xc008000007e11fd4 B [k] 0x0000000000112074
> 
> Here addr "0xc008000007e11fd4" is not resolved. since this is a
> kernel module, its offset is from the DSO. Xfs module is loaded
> at 0xc008000007d00000
> 
>    # cat /proc/modules | grep xfs
>     xfs 2228224 3 - Live 0xc008000007d00000
> 
> And size is 0x220000. So its loaded between  0xc008000007d00000
> and 0xc008000007f20000. From objdump, text section is:
>     text 0010f7bc  0000000000000000 0000000000000000 000000a0 2**4
> 
> Hence perf captured ip maps to 0x112074 which is:
> ( ip - start of module ) + a0
> 
> This offset 0x112074 falls out .text section which is up to 0x10f7bc
> In this case for module, the address 0xc008000007e11fd4 is pointing
> to stub instructions. This address range represents the module stubs
> which is allocated on module load and hence is not part of DSO offset.
> 
> To address this issue in "object code reading", skip the sample if
> address falls out of text section and is within the module end.
> Use the "text_end" member of "struct dso" to do this check.
> 
> To address this issue in "perf report", exploring an option of
> having stubs range as part of the /proc/kallsyms, so that perf
> report can resolve addresses in stubs range
> 
> However this patch uses text_end to skip the stub range for
> Object code reading testcase.
> 
> Reported-by: Disha Goel <disgoel@linux.ibm.com>
> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
> ---
> Changelog:
>  v1 -> v2:
>  Updated comment to add description on which arch has stub and
>  reason for skipping as suggested by Adrian
> 
>  tools/perf/tests/code-reading.c | 12 ++++++++++++
>  1 file changed, 12 insertions(+)
> 
> diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
> index ed3815163d1b..3cf6c2d42416 100644
> --- a/tools/perf/tests/code-reading.c
> +++ b/tools/perf/tests/code-reading.c
> @@ -269,6 +269,18 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
>  	if (addr + len > map__end(al.map))
>  		len = map__end(al.map) - addr;
>  
> +	/*
> +	 * Some architectures (ex: powerpc) have stubs (trampolines) in kernel
> +	 * modules to manage long jumps. Check if the ip offset falls in stubs
> +	 * sections for kernel modules. And skip module address after text end
> +	 */
> +	if (strstr(dso->long_name, ".ko")) {

Sorry for slow reply

!strtailcmp() is slightly better here

> +		if (al.addr > dso->text_end) {

We normally avoid nesting if-statements e.g.

	if (!strtailcmp(dso->long_name, ".ko") && al.addr > dso->text_end)

Make those changes and you can add:

Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>


> +			pr_debug("skipping the module address %#"PRIx64" after text end\n", al.addr);
> +			goto out;
> +		}
> +	}
> +
>  	/* Read the object code using perf */
>  	ret_len = dso__data_read_offset(dso, maps__machine(thread__maps(thread)),
>  					al.addr, buf1, len);

Re: [V2 1/2] tools/perf: Add text_end to "struct dso" to save .text section size

[Athira Rajeev]

> On 14-Sep-2023, at 11:49 PM, Adrian Hunter <adrian.hunter@intel.com> wrote:
> 
> On 7/09/23 19:45, Athira Rajeev wrote:
>> Update "struct dso" to include new member "text_end".
>> This new field will represent the offset for end of text
>> section for a dso. For elf, this value is derived as:
>> sh_size (Size of section in byes) + sh_offset (Section file
>> offst) of the elf header for text.
>> 
>> For bfd, this value is derived as:
>> 1. For PE file,
>> section->size + ( section->vma - dso->text_offset)
>> 2. Other cases:
>> section->filepos (file position) + section->size (size of
>> section)
>> 
>> To resolve the address from a sample, perf looks at the
>> DSO maps. In case of address from a kernel module, there
>> were some address found to be not resolved. This was
>> observed while running perf test for "Object code reading".
>> Though the ip falls beteen the start address of the loaded
>> module (perf map->start ) and end address ( perf map->end),
>> it was unresolved.
>> 
>> Example:
>> 
>>    Reading object code for memory address: 0xc008000007f0142c
>>    File is: /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko
>>    On file address is: 0x1114cc
>>    Objdump command is: objdump -z -d --start-address=0x11142c --stop-address=0x1114ac /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko
>>    objdump read too few bytes: 128
>>    test child finished with -1
>> 
>> Here, module is loaded at:
>>    # cat /proc/modules | grep xfs
>>    xfs 2228224 3 - Live 0xc008000007d00000
>> 
>> From objdump for xfs module, text section is:
>>    text 0010f7bc  0000000000000000 0000000000000000 000000a0 2**4
>> 
>> Here the offset for 0xc008000007f0142c ie  0x112074 falls out
>> .text section which is up to 0x10f7bc.
>> 
>> In this case for module, the address 0xc008000007e11fd4 is pointing
>> to stub instructions. This address range represents the module stubs
>> which is allocated on module load and hence is not part of DSO offset.
>> 
>> To identify such  address, which falls out of text
>> section and within module end, added the new field "text_end" to
>> "struct dso".
>> 
>> Reported-by: Disha Goel <disgoel@linux.ibm.com>
>> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
> 
> Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>

Hi Adrian

Thanks for the review

> 
>> ---
>> Changelog:
>> v1 -> v2:
>> Added text_end for bfd also by updating dso__load_bfd_symbols
>> as suggested by Adrian.
>> 
>> tools/perf/util/dso.h        | 1 +
>> tools/perf/util/symbol-elf.c | 4 +++-
>> tools/perf/util/symbol.c     | 2 ++
>> 3 files changed, 6 insertions(+), 1 deletion(-)
>> 
>> diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
>> index b41c9782c754..70fe0fe69bef 100644
>> --- a/tools/perf/util/dso.h
>> +++ b/tools/perf/util/dso.h
>> @@ -181,6 +181,7 @@ struct dso {
>> u8  rel;
>> struct build_id  bid;
>> u64  text_offset;
>> + u64  text_end;
>> const char  *short_name;
>> const char  *long_name;
>> u16  long_name_len;
>> diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
>> index 95e99c332d7e..9e7eeaf616b8 100644
>> --- a/tools/perf/util/symbol-elf.c
>> +++ b/tools/perf/util/symbol-elf.c
>> @@ -1514,8 +1514,10 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
>> }
>> 
>> if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr,
>> - ".text", NULL))
>> + ".text", NULL)) {
>> dso->text_offset = tshdr.sh_addr - tshdr.sh_offset;
>> + dso->text_end = tshdr.sh_offset + tshdr.sh_size;
>> + }
>> 
>> if (runtime_ss->opdsec)
>> opddata = elf_rawdata(runtime_ss->opdsec, NULL);
>> diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
>> index 3f36675b7c8f..f25e4e62cf25 100644
>> --- a/tools/perf/util/symbol.c
>> +++ b/tools/perf/util/symbol.c
>> @@ -1733,8 +1733,10 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
>> /* PE symbols can only have 4 bytes, so use .text high bits */
>> dso->text_offset = section->vma - (u32)section->vma;
>> dso->text_offset += (u32)bfd_asymbol_value(symbols[i]);
>> + dso->text_end = (section->vma - dso->text_offset) + section->size;
>> } else {
>> dso->text_offset = section->vma - section->filepos;
>> + dso->text_end = section->filepos + section->size;
>> }
>> }

Re: [V2 2/2] tools/perf/tests: Fix object code reading to skip address that falls out of text section

[Athira Rajeev]

> On 14-Sep-2023, at 11:54 PM, Adrian Hunter <adrian.hunter@intel.com> wrote:
> 
> On 7/09/23 19:45, Athira Rajeev wrote:
>> The testcase "Object code reading" fails in somecases
>> for "fs_something" sub test as below:
>> 
>>    Reading object code for memory address: 0xc008000007f0142c
>>    File is: /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko
>>    On file address is: 0x1114cc
>>    Objdump command is: objdump -z -d --start-address=0x11142c --stop-address=0x1114ac /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko
>>    objdump read too few bytes: 128
>>    test child finished with -1
>> 
>> This can alo be reproduced when running perf record with
>> workload that exercises fs_something() code. In the test
>> setup, this is exercising xfs code since root is xfs.
>> 
>>    # perf record ./a.out
>>    # perf report -v |grep "xfs.ko"
>>      0.76% a.out /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko  0xc008000007de5efc B [k] xlog_cil_commit
>>      0.74% a.out  /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko  0xc008000007d5ae18 B [k] xfs_btree_key_offset
>>      0.74% a.out  /lib/modules/6.5.0-rc3+/kernel/fs/xfs/xfs.ko  0xc008000007e11fd4 B [k] 0x0000000000112074
>> 
>> Here addr "0xc008000007e11fd4" is not resolved. since this is a
>> kernel module, its offset is from the DSO. Xfs module is loaded
>> at 0xc008000007d00000
>> 
>>   # cat /proc/modules | grep xfs
>>    xfs 2228224 3 - Live 0xc008000007d00000
>> 
>> And size is 0x220000. So its loaded between  0xc008000007d00000
>> and 0xc008000007f20000. From objdump, text section is:
>>    text 0010f7bc  0000000000000000 0000000000000000 000000a0 2**4
>> 
>> Hence perf captured ip maps to 0x112074 which is:
>> ( ip - start of module ) + a0
>> 
>> This offset 0x112074 falls out .text section which is up to 0x10f7bc
>> In this case for module, the address 0xc008000007e11fd4 is pointing
>> to stub instructions. This address range represents the module stubs
>> which is allocated on module load and hence is not part of DSO offset.
>> 
>> To address this issue in "object code reading", skip the sample if
>> address falls out of text section and is within the module end.
>> Use the "text_end" member of "struct dso" to do this check.
>> 
>> To address this issue in "perf report", exploring an option of
>> having stubs range as part of the /proc/kallsyms, so that perf
>> report can resolve addresses in stubs range
>> 
>> However this patch uses text_end to skip the stub range for
>> Object code reading testcase.
>> 
>> Reported-by: Disha Goel <disgoel@linux.ibm.com>
>> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
>> ---
>> Changelog:
>> v1 -> v2:
>> Updated comment to add description on which arch has stub and
>> reason for skipping as suggested by Adrian
>> 
>> tools/perf/tests/code-reading.c | 12 ++++++++++++
>> 1 file changed, 12 insertions(+)
>> 
>> diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
>> index ed3815163d1b..3cf6c2d42416 100644
>> --- a/tools/perf/tests/code-reading.c
>> +++ b/tools/perf/tests/code-reading.c
>> @@ -269,6 +269,18 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
>> if (addr + len > map__end(al.map))
>> len = map__end(al.map) - addr;
>> 
>> + /*
>> +  * Some architectures (ex: powerpc) have stubs (trampolines) in kernel
>> +  * modules to manage long jumps. Check if the ip offset falls in stubs
>> +  * sections for kernel modules. And skip module address after text end
>> +  */
>> + if (strstr(dso->long_name, ".ko")) {
> 
> Sorry for slow reply
> 
> !strtailcmp() is slightly better here
> 
>> + if (al.addr > dso->text_end) {
> 
> We normally avoid nesting if-statements e.g.
> 
> if (!strtailcmp(dso->long_name, ".ko") && al.addr > dso->text_end)
> 
> Make those changes and you can add:
> 
> Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>

Sure, will post a V3 with this change

Athira
> 
> 
>> + pr_debug("skipping the module address %#"PRIx64" after text end\n", al.addr);
>> + goto out;
>> + }
>> + }
>> +
>> /* Read the object code using perf */
>> ret_len = dso__data_read_offset(dso, maps__machine(thread__maps(thread)),
>> al.addr, buf1, len);