Phase E3-FINAL: Fix Box API offset bugs - ALL classes now use correct offsets
## Root Cause Analysis (GPT5) **Physical Layout Constraints**: - Class 0: 8B = [1B header][7B payload] → offset 1 = 9B needed = ❌ IMPOSSIBLE - Class 1-6: >=16B = [1B header][15B+ payload] → offset 1 = ✅ POSSIBLE - Class 7: 1KB → offset 0 (compatibility) **Correct Specification**: - HAKMEM_TINY_HEADER_CLASSIDX != 0: - Class 0, 7: next at offset 0 (overwrites header when on freelist) - Class 1-6: next at offset 1 (after header) - HAKMEM_TINY_HEADER_CLASSIDX == 0: - All classes: next at offset 0 **Previous Bug**: - Attempted "ALL classes offset 1" unification - Class 0 with offset 1 caused immediate SEGV (9B > 8B block size) - Mixed 2-arg/3-arg API caused confusion ## Fixes Applied ### 1. Restored 3-Argument Box API (core/box/tiny_next_ptr_box.h) ```c // Correct signatures void tiny_next_write(int class_idx, void* base, void* next_value) void* tiny_next_read(int class_idx, const void* base) // Correct offset calculation size_t offset = (class_idx == 0 || class_idx == 7) ? 0 : 1; ``` ### 2. Updated 123+ Call Sites Across 34 Files - hakmem_tiny_hot_pop_v4.inc.h (4 locations) - hakmem_tiny_fastcache.inc.h (3 locations) - hakmem_tiny_tls_list.h (12 locations) - superslab_inline.h (5 locations) - tiny_fastcache.h (3 locations) - ptr_trace.h (macro definitions) - tls_sll_box.h (2 locations) - + 27 additional files Pattern: `tiny_next_read(base)` → `tiny_next_read(class_idx, base)` Pattern: `tiny_next_write(base, next)` → `tiny_next_write(class_idx, base, next)` ### 3. Added Sentinel Detection Guards - tiny_fast_push(): Block nodes with sentinel in ptr or ptr->next - tls_list_push(): Block nodes with sentinel in ptr or ptr->next - Defense-in-depth against remote free sentinel leakage ## Verification (GPT5 Report) **Test Command**: `./out/release/bench_random_mixed_hakmem --iterations=70000` **Results**: - ✅ Main loop completed successfully - ✅ Drain phase completed successfully - ✅ NO SEGV (previous crash at iteration 66151 is FIXED) - ℹ️ Final log: "tiny_alloc(1024) failed" is normal fallback to Mid/ACE layers **Analysis**: - Class 0 immediate SEGV: ✅ RESOLVED (correct offset 0 now used) - 66K iteration crash: ✅ RESOLVED (offset consistency fixed) - Box API conflicts: ✅ RESOLVED (unified 3-arg API) ## Technical Details ### Offset Logic Justification ``` Class 0: 8B block → next pointer (8B) fits ONLY at offset 0 Class 1: 16B block → next pointer (8B) fits at offset 1 (after 1B header) Class 2: 32B block → next pointer (8B) fits at offset 1 ... Class 6: 512B block → next pointer (8B) fits at offset 1 Class 7: 1024B block → offset 0 for legacy compatibility ``` ### Files Modified (Summary) - Core API: `box/tiny_next_ptr_box.h` - Hot paths: `hakmem_tiny_hot_pop*.inc.h`, `tiny_fastcache.h` - TLS layers: `hakmem_tiny_tls_list.h`, `hakmem_tiny_tls_ops.h` - SuperSlab: `superslab_inline.h`, `tiny_superslab_*.inc.h` - Refill: `hakmem_tiny_refill.inc.h`, `tiny_refill_opt.h` - Free paths: `tiny_free_magazine.inc.h`, `tiny_superslab_free.inc.h` - Documentation: Multiple Phase E3 reports ## Remaining Work None for Box API offset bugs - all structural issues resolved. Future enhancements (non-critical): - Periodic `grep -R '*(void**)' core/` to detect direct pointer access violations - Enforce Box API usage via static analysis - Document offset rationale in architecture docs 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
@ -5,6 +5,7 @@
|
||||
#include "hakmem_tiny_superslab.h"
|
||||
#include "hakmem_super_registry.h"
|
||||
#include "tiny_remote.h"
|
||||
#include "box/tiny_next_ptr_box.h"
|
||||
#include <stdint.h>
|
||||
|
||||
// Forward declarations for external dependencies
|
||||
@ -61,7 +62,8 @@ static inline int tls_refill_from_tls_slab(int class_idx, TinyTLSList* tls, uint
|
||||
size_t block_stride = tiny_stride_for_class(class_idx);
|
||||
// Header-aware TLS list next offset for chains we build here
|
||||
#if HAKMEM_TINY_HEADER_CLASSIDX
|
||||
const size_t next_off_tls = (class_idx == 7) ? 0 : 1;
|
||||
// Phase E1-CORRECT: ALL classes have 1-byte header, next ptr at offset 1
|
||||
const size_t next_off_tls = 1;
|
||||
#else
|
||||
const size_t next_off_tls = 0;
|
||||
#endif
|
||||
@ -80,8 +82,9 @@ static inline int tls_refill_from_tls_slab(int class_idx, TinyTLSList* tls, uint
|
||||
uint32_t need = want - total;
|
||||
while (local < need && meta->freelist) {
|
||||
void* node = meta->freelist;
|
||||
meta->freelist = *(void**)node; // freelist is base-linked
|
||||
*(void**)((uint8_t*)node + next_off_tls) = local_head;
|
||||
// BUG FIX: Use Box API to read next pointer at correct offset
|
||||
meta->freelist = tiny_next_read(class_idx, node); // freelist is base-linked
|
||||
tiny_next_write(class_idx, node, local_head);
|
||||
local_head = node;
|
||||
if (!local_tail) local_tail = node;
|
||||
local++;
|
||||
@ -93,7 +96,7 @@ static inline int tls_refill_from_tls_slab(int class_idx, TinyTLSList* tls, uint
|
||||
accum_head = local_head;
|
||||
accum_tail = local_tail;
|
||||
} else {
|
||||
*(void**)((uint8_t*)local_tail + next_off_tls) = accum_head;
|
||||
tiny_next_write(class_idx, local_tail, accum_head);
|
||||
accum_head = local_head;
|
||||
}
|
||||
total += local;
|
||||
@ -127,7 +130,7 @@ static inline int tls_refill_from_tls_slab(int class_idx, TinyTLSList* tls, uint
|
||||
uint8_t* cursor = base_cursor;
|
||||
for (uint32_t i = 1; i < need; ++i) {
|
||||
uint8_t* next = cursor + block_stride;
|
||||
*(void**)(cursor + next_off_tls) = (void*)next;
|
||||
tiny_next_write(class_idx, (void*)cursor, (void*)next);
|
||||
cursor = next;
|
||||
}
|
||||
void* local_tail = (void*)cursor;
|
||||
@ -138,7 +141,7 @@ static inline int tls_refill_from_tls_slab(int class_idx, TinyTLSList* tls, uint
|
||||
accum_head = local_head;
|
||||
accum_tail = local_tail;
|
||||
} else {
|
||||
*(void**)((uint8_t*)local_tail + next_off_tls) = accum_head;
|
||||
tiny_next_write(class_idx, local_tail, accum_head);
|
||||
accum_head = local_head;
|
||||
}
|
||||
total += need;
|
||||
@ -182,13 +185,8 @@ static inline void tls_list_spill_excess(int class_idx, TinyTLSList* tls) {
|
||||
|
||||
uint32_t self_tid = tiny_self_u32();
|
||||
void* node = head;
|
||||
#if HAKMEM_TINY_HEADER_CLASSIDX
|
||||
const size_t next_off_tls = (class_idx == 7) ? 0 : 1;
|
||||
#else
|
||||
const size_t next_off_tls = 0;
|
||||
#endif
|
||||
while (node) {
|
||||
void* next = *(void**)((uint8_t*)node + next_off_tls);
|
||||
void* next = tiny_next_read(class_idx, node);
|
||||
int handled = 0;
|
||||
|
||||
// Phase 1: Try SuperSlab first (registry-based lookup, no false positives)
|
||||
@ -202,7 +200,8 @@ static inline void tls_list_spill_excess(int class_idx, TinyTLSList* tls) {
|
||||
handled = 1;
|
||||
} else {
|
||||
void* prev = meta->freelist;
|
||||
*(void**)((uint8_t*)node + 0) = prev; // freelist within slab uses base link
|
||||
// BUG FIX: Use Box API to write next pointer at correct offset
|
||||
tiny_next_write(class_idx, node, prev); // freelist within slab uses base link
|
||||
meta->freelist = node;
|
||||
tiny_failfast_log("tls_spill_ss", ss->size_class, ss, meta, node, prev);
|
||||
if (meta->used > 0) meta->used--;
|
||||
@ -248,7 +247,7 @@ static inline void tls_list_spill_excess(int class_idx, TinyTLSList* tls) {
|
||||
}
|
||||
#endif
|
||||
if (!handled) {
|
||||
*(void**)((uint8_t*)node + next_off_tls) = requeue_head;
|
||||
tiny_next_write(class_idx, node, requeue_head);
|
||||
if (!requeue_head) requeue_tail = node;
|
||||
requeue_head = node;
|
||||
requeue_count++;
|
||||
|
||||
Reference in New Issue
Block a user