Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix profiling when python symbols aren't available. #718

Merged
merged 2 commits into from
Nov 1, 2024
Merged

Fix profiling when python symbols aren't available. #718

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
22acdff
Fix profiling when python symbols aren't available.
benfred Oct 31, 2024
0c97a65
Merge branch 'master' into fix_no_symbols
benfred Nov 1, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
96 changes: 72 additions & 24 deletions src/binary_parser.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,8 @@ pub struct BinaryInfo {
pub symbols: HashMap<String, u64>,
pub bss_addr: u64,
pub bss_size: u64,
pub pyruntime_addr: u64,
pub pyruntime_size: u64,
#[allow(dead_code)]
pub addr: u64,
#[allow(dead_code)]
Expand Down Expand Up @@ -65,11 +67,23 @@ pub fn parse_binary(filename: &Path, addr: u64, size: u64) -> Result<BinaryInfo,
}
};

let mut pyruntime_addr = 0;
let mut pyruntime_size = 0;
let mut bss_addr = 0;
let mut bss_size = 0;
for segment in mach.segments.iter() {
for (section, _) in &segment.sections()? {
if section.name()? == "__bss" {
let name = section.name()?;
if name == "PyRuntime" {
if let Some(addr) = section.addr.checked_add(offset) {
if addr.checked_add(section.size).is_some() {
pyruntime_addr = addr;
pyruntime_size = section.size;
}
}
}

if name == "__bss" {
if let Some(addr) = section.addr.checked_add(offset) {
if addr.checked_add(section.size).is_some() {
bss_addr = addr;
Expand All @@ -94,6 +108,8 @@ pub fn parse_binary(filename: &Path, addr: u64, size: u64) -> Result<BinaryInfo,
symbols,
bss_addr,
bss_size,
pyruntime_addr,
pyruntime_size,
addr,
size,
})
Expand Down Expand Up @@ -153,6 +169,21 @@ pub fn parse_binary(filename: &Path, addr: u64, size: u64) -> Result<BinaryInfo,
bss_end = bss_header.sh_addr + bss_header.sh_size;
}

let pyruntime_header = elf.section_headers.iter().find(|header| {
strtab
.get_at(header.sh_name)
.map_or(false, |name| name == ".PyRuntime")
});

let mut pyruntime_addr = 0;
let mut pyruntime_size = 0;
if let Some(header) = pyruntime_header {
if let Some(addr) = header.sh_addr.checked_add(offset) {
pyruntime_addr = addr;
pyruntime_size = header.sh_size;
}
}

for sym in elf.syms.iter() {
// Skip imported symbols
if sym.is_import()
Expand Down Expand Up @@ -194,6 +225,8 @@ pub fn parse_binary(filename: &Path, addr: u64, size: u64) -> Result<BinaryInfo,
symbols,
bss_addr,
bss_size,
pyruntime_addr,
pyruntime_size,
addr,
size,
})
Expand All @@ -207,33 +240,48 @@ pub fn parse_binary(filename: &Path, addr: u64, size: u64) -> Result<BinaryInfo,
}
}

pe.sections
.iter()
.find(|section| section.name.starts_with(b".data"))
.ok_or_else(|| {
format_err!(
"Failed to find .data section in PE binary of {}",
filename.display()
)
})
.map(|data_section| {
let mut bss_addr = 0;
let mut bss_size = 0;
if let Some(addr) = offset.checked_add(data_section.virtual_address as u64) {
if addr.checked_add(data_section.virtual_size as u64).is_some() {
let mut bss_addr = 0;
let mut bss_size = 0;
let mut pyruntime_addr = 0;
let mut pyruntime_size = 0;
let mut found_data = false;
for section in pe.sections.iter() {
if section.name.starts_with(b".data") {
found_data = true;
if let Some(addr) = offset.checked_add(section.virtual_address as u64) {
if addr.checked_add(section.virtual_size as u64).is_some() {
bss_addr = addr;
bss_size = u64::from(data_section.virtual_size);
bss_size = u64::from(section.virtual_size);
}
}

BinaryInfo {
symbols,
bss_addr,
bss_size,
addr,
size,
} else if section.name.starts_with(b"PyRuntim") {
// note that the name is only 8 chars here, so we don't check for
// trailing 'e' in PyRuntime
if let Some(addr) = offset.checked_add(section.virtual_address as u64) {
if addr.checked_add(section.virtual_size as u64).is_some() {
pyruntime_addr = addr;
pyruntime_size = u64::from(section.virtual_size);
}
}
})
}
}

if !found_data {
return Err(format_err!(
"Failed to find .data section in PE binary of {}",
filename.display()
));
}

Ok(BinaryInfo {
symbols,
bss_addr,
bss_size,
pyruntime_size,
pyruntime_addr,
addr,
size,
})
}
_ => Err(format_err!("Unhandled binary type")),
}
Expand Down
15 changes: 15 additions & 0 deletions src/python_process_info.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -451,6 +451,21 @@ fn get_interpreter_address_from_binary<P>(
where
P: ProcessMemory,
{
// First check the pyruntime section it was found
if binary.pyruntime_addr != 0 {
let bss = process.copy(
binary.pyruntime_addr as usize,
binary.pyruntime_size as usize,
)?;
#[allow(clippy::cast_ptr_alignment)]
let addrs = unsafe {
slice::from_raw_parts(bss.as_ptr() as *const usize, bss.len() / size_of::<usize>())
};
if let Ok(addr) = check_interpreter_addresses(addrs, maps, process, version) {
return Ok(addr);
}
}

// We're going to scan the BSS/data section for things, and try to narrowly scan things that
// look like pointers to PyinterpreterState
let bss = process.copy(binary.bss_addr as usize, binary.bss_size as usize)?;
Expand Down
Loading