Larson double-free investigation: Enhanced diagnostics + Remove buggy drain pushback
**Problem**: Larson benchmark crashes with TLS_SLL_DUP (double-free), 100% crash rate in debug
**Root Cause**: TLS drain pushback code (commit c2f104618) created duplicates by
pushing pointers back to TLS SLL while they were still in the linked list chain.
**Diagnostic Enhancements** (ChatGPT + Claude collaboration):
1. **Callsite Tracking**: Track file:line for each TLS SLL push (debug only)
- Arrays: g_tls_sll_push_file[], g_tls_sll_push_line[]
- Macro: tls_sll_push() auto-records __FILE__, __LINE__
2. **Enhanced Duplicate Detection**:
- Scan depth: 64 → 256 nodes (deep duplicate detection)
- Error message shows BOTH current and previous push locations
- Calls ptr_trace_dump_now() for detailed analysis
3. **Evidence Captured**:
- Both duplicate pushes from same line (221)
- Pointer at position 11 in TLS SLL (count=18, scanned=11)
- Confirms pointer allocated without being popped from TLS SLL
**Fix**:
- **core/box/tls_sll_drain_box.h**: Remove pushback code entirely
- Old: Push back to TLS SLL on validation failure → duplicates!
- New: Skip pointer (accept rare leak) to avoid duplicates
- Rationale: SuperSlab lookup failures are transient/rare
**Status**: Fix implemented, ready for testing
**Updated**:
- LARSON_DOUBLE_FREE_INVESTIGATION.md: Root cause confirmed
This commit is contained in:
@ -52,6 +52,12 @@ extern __thread uint64_t g_tls_canary_after_sll;
|
||||
extern __thread const char* g_tls_sll_last_writer[TINY_NUM_CLASSES];
|
||||
extern int g_tls_sll_class_mask; // bit i=1 → SLL allowed for class i
|
||||
|
||||
#if !HAKMEM_BUILD_RELEASE
|
||||
// Global callsite record (debug only; zero overhead in release)
|
||||
static const char* g_tls_sll_push_file[TINY_NUM_CLASSES] = {0};
|
||||
static int g_tls_sll_push_line[TINY_NUM_CLASSES] = {0};
|
||||
#endif
|
||||
|
||||
// ========== Debug guard ==========
|
||||
|
||||
#if !HAKMEM_BUILD_RELEASE
|
||||
@ -669,12 +675,51 @@ static inline uint32_t tls_sll_splice(int class_idx,
|
||||
|
||||
// ========== Macro Wrappers ==========
|
||||
//
|
||||
// Box Theory: Callers use tls_sll_push/pop() macros which auto-insert __func__.
|
||||
// No changes required to 20+ call sites.
|
||||
// Box Theory: Callers use tls_sll_push/pop() macros which auto-insert callsite info (debug only).
|
||||
// No changes required to call sites.
|
||||
|
||||
#if !HAKMEM_BUILD_RELEASE
|
||||
static inline bool tls_sll_push_guarded(int class_idx, void* ptr, uint32_t capacity,
|
||||
const char* where, const char* file, int line) {
|
||||
// Enhanced duplicate guard (scan up to 256 nodes for deep duplicates)
|
||||
uint32_t scanned = 0;
|
||||
void* cur = g_tls_sll[class_idx].head;
|
||||
const uint32_t limit = (g_tls_sll[class_idx].count < 256) ? g_tls_sll[class_idx].count : 256;
|
||||
|
||||
while (cur && scanned < limit) {
|
||||
if (cur == ptr) {
|
||||
// Enhanced error message with both old and new callsite info
|
||||
const char* last_file = g_tls_sll_push_file[class_idx] ? g_tls_sll_push_file[class_idx] : "(null)";
|
||||
fprintf(stderr,
|
||||
"[TLS_SLL_DUP] cls=%d ptr=%p head=%p count=%u scanned=%u\n"
|
||||
" Current push: where=%s at %s:%d\n"
|
||||
" Previous push: %s:%d\n",
|
||||
class_idx, ptr, g_tls_sll[class_idx].head, g_tls_sll[class_idx].count, scanned,
|
||||
where, file, line,
|
||||
last_file, g_tls_sll_push_line[class_idx]);
|
||||
|
||||
// Dump pointer trace for detailed analysis
|
||||
ptr_trace_dump_now("tls_sll_dup");
|
||||
abort();
|
||||
}
|
||||
void* next = NULL;
|
||||
PTR_NEXT_READ("tls_sll_dupcheck", class_idx, cur, 0, next);
|
||||
cur = next;
|
||||
scanned++;
|
||||
}
|
||||
|
||||
// Call impl (duplicate check in impl will be skipped since we already checked above and would abort)
|
||||
// Note: impl has its own duplicate check, but we'll never reach it because we abort above
|
||||
bool ok = tls_sll_push_impl(class_idx, ptr, capacity, where);
|
||||
if (ok) {
|
||||
g_tls_sll_push_file[class_idx] = file;
|
||||
g_tls_sll_push_line[class_idx] = line;
|
||||
}
|
||||
return ok;
|
||||
}
|
||||
|
||||
# define tls_sll_push(cls, ptr, cap) \
|
||||
tls_sll_push_impl((cls), (ptr), (cap), __func__)
|
||||
tls_sll_push_guarded((cls), (ptr), (cap), __func__, __FILE__, __LINE__)
|
||||
# define tls_sll_pop(cls, out) \
|
||||
tls_sll_pop_impl((cls), (out), __func__)
|
||||
#else
|
||||
|
||||
Reference in New Issue
Block a user