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:
@ -10,7 +10,7 @@
|
||||
#include <stdint.h>
|
||||
#include "hakmem_build_flags.h"
|
||||
#include "tiny_remote.h" // for TINY_REMOTE_SENTINEL (defense-in-depth)
|
||||
#include "tiny_nextptr.h"
|
||||
#include "box/tiny_next_ptr_box.h" // Phase E1-CORRECT: unified next pointer API
|
||||
#include "tiny_region_id.h" // For HEADER_MAGIC, HEADER_CLASS_MASK (Fix #7)
|
||||
|
||||
// External TLS variables (defined in hakmem_tiny.c)
|
||||
@ -52,16 +52,14 @@ extern __thread uint32_t g_tls_sll_count[TINY_NUM_CLASSES];
|
||||
if (g_tls_sll_count[(class_idx)] > 0) g_tls_sll_count[(class_idx)]--; \
|
||||
(ptr_out) = NULL; \
|
||||
} else { \
|
||||
/* Safe load of header-aware next (avoid UB on unaligned) */ \
|
||||
void* _next = tiny_next_load(_head, (class_idx)); \
|
||||
/* Phase E1-CORRECT: Use Box API for next pointer read */ \
|
||||
void* _next = tiny_next_read(class_idx, _head); \
|
||||
g_tls_sll_head[(class_idx)] = _next; \
|
||||
if (g_tls_sll_count[(class_idx)] > 0) { \
|
||||
g_tls_sll_count[(class_idx)]--; \
|
||||
} \
|
||||
(ptr_out) = _head; \
|
||||
if (__builtin_expect((class_idx) == 7, 0)) { \
|
||||
*(void**)(ptr_out) = NULL; \
|
||||
} \
|
||||
/* Phase E1-CORRECT: All classes return user pointer (base+1) */ \
|
||||
(ptr_out) = (void*)((uint8_t*)_head + 1); \
|
||||
} \
|
||||
} else { \
|
||||
(ptr_out) = NULL; \
|
||||
@ -85,21 +83,19 @@ extern __thread uint32_t g_tls_sll_count[TINY_NUM_CLASSES];
|
||||
// mov %rsi, g_tls_sll_head(%rdi)
|
||||
//
|
||||
#if HAKMEM_TINY_HEADER_CLASSIDX
|
||||
// ✅ FIX #7: Restore header on FREE (header-mode enabled)
|
||||
// Phase E1-CORRECT: Restore header on FREE for ALL classes (including C7)
|
||||
// ROOT CAUSE: User may have overwritten byte 0 (header). tls_sll_splice() checks
|
||||
// byte 0 for HEADER_MAGIC. Without restoration, it finds 0x00 → uses wrong offset → SEGV.
|
||||
// COST: 1 byte write (~1-2 cycles per free, negligible).
|
||||
#define TINY_ALLOC_FAST_PUSH_INLINE(class_idx, ptr) do { \
|
||||
if ((class_idx) != 7) { \
|
||||
*(uint8_t*)(ptr) = HEADER_MAGIC | ((class_idx) & HEADER_CLASS_MASK); \
|
||||
} \
|
||||
tiny_next_store((ptr), (class_idx), g_tls_sll_head[(class_idx)]); \
|
||||
*(uint8_t*)(ptr) = HEADER_MAGIC | ((class_idx) & HEADER_CLASS_MASK); \
|
||||
tiny_next_write(class_idx, (ptr), g_tls_sll_head[(class_idx)]); \
|
||||
g_tls_sll_head[(class_idx)] = (ptr); \
|
||||
g_tls_sll_count[(class_idx)]++; \
|
||||
} while(0)
|
||||
#else
|
||||
#define TINY_ALLOC_FAST_PUSH_INLINE(class_idx, ptr) do { \
|
||||
tiny_next_store((ptr), (class_idx), g_tls_sll_head[(class_idx)]); \
|
||||
tiny_next_write(class_idx, (ptr), g_tls_sll_head[(class_idx)]); \
|
||||
g_tls_sll_head[(class_idx)] = (ptr); \
|
||||
g_tls_sll_count[(class_idx)]++; \
|
||||
} while(0)
|
||||
|
||||
Reference in New Issue
Block a user