fabi/xenia-rs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

M1: parse .pdata RUNTIME_FUNCTION; cross-validate function boundaries

Browse Source 
Adds an authoritative function-boundary source from the linker:
- New `xenia_xex::pdata` parses .pdata 8-byte entries (BeginAddress + packed
  prolog/length/flags). Bit layout per Microsoft PE32 PowerPC spec: prolog in
  bits 0..7, function_length in bits 8..29, flags in 30..31.
- `func::analyze_with_pdata` unions pdata BeginAddresses into the candidate
  set, attaches `pdata_validated`/`pdata_length` to each `FuncInfo`, and trims
  any function whose `end` overlaps the next start (catches mis-merge where
  one row spanned two prologues — the audit-031 sub_824D23B0/sub_824D29F0
  case).
- DB: extends `functions` with `pdata_validated BOOLEAN`, `pdata_length BIGINT`;
  new table `pdata_entries`; index on pdata_validated.
- New `crates/xenia-analysis/SCHEMA.md` documents M1 layer + forward work.

Validation on Sylpheed: 25481 functions (was 12156) / 23073 pdata_validated /
0 orphans / 0 mis-merges. Audit-031 mis-merge resolved: sub_824D29F0 now has
its own row with `pdata_length=280` (70 dwords); sub_824D23B0 now correctly
ends at 0x824D2878 (`pdata_length=1224` matches prologue walk).

Tests 605→610. New 5-test pdata unit suite covers bit layout + sentinel +
out-of-range filtering + real-world layout round-trip.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-05-08 19:44:02 +02:00
parent e061e21851
commit 70120465a3
7 changed files with 503 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
crates/xenia-analysis/src/db.rs
View File

@@ -314,13 +314,23 @@ impl DbWriter {
) -> anyhow::Result<()> {
self.conn.execute_batch("
CREATE TABLE functions (
address BIGINT PRIMARY KEY, -- absolute VA of entry point
name VARCHAR NOT NULL, -- symbol name, or sub_XXXXXXXX if unresolved
end_address BIGINT NOT NULL, -- VA of last instruction + 4 (exclusive end)
frame_size BIGINT NOT NULL, -- stack frame size in bytes (from prologue)
saved_gprs BIGINT NOT NULL, -- bitmask of GPRs saved in prologue (bit N = rN)
is_leaf BOOLEAN NOT NULL, -- true if the function has no outgoing calls
is_saverestore BOOLEAN NOT NULL -- true if __savegprlr_* / __restgprlr_* stub
address BIGINT PRIMARY KEY, -- absolute VA of entry point
name VARCHAR NOT NULL, -- symbol name, or sub_XXXXXXXX if unresolved
end_address BIGINT NOT NULL, -- VA of last instruction + 4 (exclusive end)
frame_size BIGINT NOT NULL, -- stack frame size in bytes (from prologue)
saved_gprs BIGINT NOT NULL, -- bitmask of GPRs saved in prologue (bit N = rN)
is_leaf BOOLEAN NOT NULL, -- true if the function has no outgoing calls
is_saverestore BOOLEAN NOT NULL, -- true if __savegprlr_* / __restgprlr_* stub
pdata_validated BOOLEAN NOT NULL, -- true if .pdata RUNTIME_FUNCTION exists at this VA
pdata_length BIGINT -- length in bytes per .pdata; NULL if no pdata entry
);
CREATE TABLE pdata_entries (
begin_address BIGINT PRIMARY KEY, -- absolute VA of function start (RUNTIME_FUNCTION.BeginAddress)
end_address BIGINT NOT NULL, -- begin_address + function_length (exclusive)
function_length BIGINT NOT NULL, -- function size in bytes
prolog_length BIGINT NOT NULL, -- prolog size in bytes
flags BIGINT NOT NULL -- raw 2-bit flags (bit 1=32-bit-code, bit 0=exception)
);
CREATE TABLE labels (
@@ -341,11 +351,13 @@ impl DbWriter {
")?;
insert_functions(&self.conn, func_analysis, labels)?;
insert_pdata_entries(&self.conn, &func_analysis.pdata_entries)?;
insert_labels(&self.conn, labels)?;
insert_xrefs_streaming(&self.conn, xrefs, pe, info.image_base, func_analysis, labels)?;
let indices = [
("idx_functions_name", "CREATE INDEX idx_functions_name ON functions(name)"),
("idx_functions_pdata_validated", "CREATE INDEX idx_functions_pdata_validated ON functions(pdata_validated)"),
("idx_labels_kind", "CREATE INDEX idx_labels_kind ON labels(kind)"),
("idx_labels_name", "CREATE INDEX idx_labels_name ON labels(name)"),
("idx_xrefs_target", "CREATE INDEX idx_xrefs_target ON xrefs(target)"),
@@ -680,8 +692,10 @@ fn insert_functions(
labels: &HashMap<u32, String>,
) -> anyhow::Result<()> {
let mut stmt = conn.prepare(
"INSERT INTO functions (address, name, end_address, frame_size, saved_gprs, is_leaf, is_saverestore)
VALUES (?, ?, ?, ?, ?, ?, ?)"
"INSERT INTO functions
(address, name, end_address, frame_size, saved_gprs, is_leaf, is_saverestore,
pdata_validated, pdata_length)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)"
)?;
for (&addr, fi) in &func_analysis.functions {
let name = labels.get(&addr)
@@ -695,6 +709,33 @@ fn insert_functions(
fi.saved_gprs as i64,
fi.is_leaf,
fi.is_saverestore,
fi.pdata_validated,
fi.pdata_length.map(|n| n as i64),
])?;
}
Ok(())
}
fn insert_pdata_entries(
conn: &Connection,
entries: &[xenia_xex::pdata::PdataEntry],
) -> anyhow::Result<()> {
if entries.is_empty() {
return Ok(());
}
let mut stmt = conn.prepare(
"INSERT INTO pdata_entries
(begin_address, end_address, function_length, prolog_length, flags)
VALUES (?, ?, ?, ?, ?)
ON CONFLICT DO NOTHING"
)?;
for e in entries {
stmt.execute(params![
e.begin_address as i64,
e.end_address() as i64,
e.function_length as i64,
e.prolog_length as i64,
e.flags as i64,
])?;
}
Ok(())