This commit implements the first phase of Tiny Pool redesign based on
ChatGPT architecture review. The goal is to eliminate Header/Next pointer
conflicts by moving class_idx lookup out-of-band (to SuperSlab metadata).
## P0.1: C0(8B) class upgraded to 16B
- Size table changed: {16,32,64,128,256,512,1024,2048} (8 classes)
- LUT updated: 1..16 → class 0, 17..32 → class 1, etc.
- tiny_next_off: C0 now uses offset 1 (header preserved)
- Eliminates edge cases for 8B allocations
## P0.3: Slab reuse guard Box (tls_slab_reuse_guard_box.h)
- New Box for draining TLS SLL before slab reuse
- ENV gate: HAKMEM_TINY_SLAB_REUSE_GUARD=1
- Prevents stale pointers when slabs are recycled
- Follows Box theory: single responsibility, minimal API
## P1.1: SuperSlab class_map addition
- Added uint8_t class_map[SLABS_PER_SUPERSLAB_MAX] to SuperSlab
- Maps slab_idx → class_idx for out-of-band lookup
- Initialized to 255 (UNASSIGNED) on SuperSlab creation
- Set correctly on slab initialization in all backends
## P1.2: Free fast path uses class_map
- ENV gate: HAKMEM_TINY_USE_CLASS_MAP=1
- Free path can now get class_idx from class_map instead of Header
- Falls back to Header read if class_map returns invalid value
- Fixed Legacy Backend dynamic slab initialization bug
## Documentation added
- HAKMEM_ARCHITECTURE_OVERVIEW.md: 4-layer architecture analysis
- TLS_SLL_ARCHITECTURE_INVESTIGATION.md: Root cause analysis
- PTR_LIFECYCLE_TRACE_AND_ROOT_CAUSE_ANALYSIS.md: Pointer tracking
- TINY_REDESIGN_CHECKLIST.md: Implementation roadmap (P0-P3)
## Test results
- Baseline: 70% success rate (30% crash - pre-existing issue)
- class_map enabled: 70% success rate (same as baseline)
- Performance: ~30.5M ops/s (unchanged)
## Next steps (P1.3, P2, P3)
- P1.3: Add meta->active for accurate TLS/freelist sync
- P2: TLS SLL redesign with Box-based counting
- P3: Complete Header out-of-band migration
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
106 lines
3.9 KiB
C
106 lines
3.9 KiB
C
// tiny_nextptr.h - Authoritative next-pointer offset/load/store for tiny boxes
|
|
//
|
|
// Finalized Phase E1-CORRECT spec (物理制約込み):
|
|
// P0.1: C7 uses offset 0 (overwrites header), C0-C6 use offset 1 (header preserved)
|
|
//
|
|
// HAKMEM_TINY_HEADER_CLASSIDX != 0 のとき:
|
|
//
|
|
// Class 0:
|
|
// [1B header][15B payload] (total 16B)
|
|
// → headerは保持し、next は header直後 base+1 に格納
|
|
// → next_off = 1
|
|
//
|
|
// Class 1〜6:
|
|
// [1B header][payload >= 8B]
|
|
// → headerは保持し、next は header直後 base+1 に格納
|
|
// → next_off = 1
|
|
//
|
|
// Class 7:
|
|
// [1B header][payload 2047B]
|
|
// → headerは上書きし、next は base+0 に格納(最大サイズなので許容)
|
|
// → next_off = 0
|
|
//
|
|
// HAKMEM_TINY_HEADER_CLASSIDX == 0 のとき:
|
|
//
|
|
// 全クラス headerなし → next_off = 0
|
|
//
|
|
// このヘッダは上記仕様を唯一の真実として提供する。
|
|
// すべての tiny freelist / TLS / fast-cache / refill / SLL で
|
|
// tiny_next_off/tiny_next_load/tiny_next_store を経由すること。
|
|
// 直接の *(void**) アクセスやローカルな offset 分岐は使用禁止。
|
|
|
|
#ifndef TINY_NEXTPTR_H
|
|
#define TINY_NEXTPTR_H
|
|
|
|
#include <stdint.h>
|
|
#include <string.h>
|
|
#include "hakmem_build_flags.h"
|
|
#include "tiny_region_id.h" // HEADER_MAGIC/HEADER_CLASS_MASK for header repair/logging
|
|
#include "hakmem_super_registry.h" // hak_super_lookup
|
|
#include "superslab/superslab_inline.h" // slab_index_for
|
|
#include <stdio.h>
|
|
#include <stdatomic.h>
|
|
#include <dlfcn.h>
|
|
#include <execinfo.h> // backtrace for rare misalign diagnostics
|
|
|
|
// Compute freelist next-pointer offset within a block for the given class.
|
|
// P0.1: C7 uses offset 0 (overwrites header), C0-C6 use offset 1 (header preserved)
|
|
static inline __attribute__((always_inline)) size_t tiny_next_off(int class_idx) {
|
|
#if HAKMEM_TINY_HEADER_CLASSIDX
|
|
// C7 (2048B): offset 0 (overwrites header in freelist - largest class can tolerate)
|
|
// C0-C6: offset 1 (header preserved - user data is not disturbed)
|
|
return (class_idx == 7) ? 0u : 1u;
|
|
#else
|
|
(void)class_idx;
|
|
return 0u;
|
|
#endif
|
|
}
|
|
|
|
// Safe load of next pointer from a block base.
|
|
static inline __attribute__((always_inline)) void* tiny_next_load(const void* base, int class_idx) {
|
|
size_t off = tiny_next_off(class_idx);
|
|
|
|
if (off == 0) {
|
|
// Aligned access at base (header無し or C7 freelist時)
|
|
return *(void* const*)base;
|
|
}
|
|
|
|
// off != 0: use memcpy to avoid UB on architectures that forbid unaligned loads.
|
|
// C0-C6: offset 1 (header preserved)
|
|
void* next = NULL;
|
|
const uint8_t* p = (const uint8_t*)base + off;
|
|
memcpy(&next, p, sizeof(void*));
|
|
return next;
|
|
}
|
|
|
|
// Safe store of next pointer into a block base.
|
|
// DESIGN RULE: "Header is written by BOTH Alloc and Free/Drain"
|
|
// - Free/Drain paths: This function restores header for C0-C6 (offset 1), then writes Next pointer
|
|
// - Alloc paths: Write header before returning block to user (HAK_RET_ALLOC)
|
|
// - C7 (offset 0): Header is overwritten by next pointer, so no restoration needed
|
|
// P0.1: C7 uses offset 0 (overwrites header), C0-C6 use offset 1 (header preserved)
|
|
static inline __attribute__((always_inline)) void tiny_next_store(void* base, int class_idx, void* next) {
|
|
size_t off = tiny_next_off(class_idx);
|
|
|
|
#if HAKMEM_TINY_HEADER_CLASSIDX
|
|
// For C0-C6 (offset 1): Restore header before writing next pointer
|
|
// For C7 (offset 0): Header is overwritten, so no restoration needed
|
|
if (off != 0) {
|
|
// Restore header for classes that preserve it (C0-C6)
|
|
*(uint8_t*)base = HEADER_MAGIC | (class_idx & HEADER_CLASS_MASK);
|
|
}
|
|
#endif
|
|
|
|
if (off == 0) {
|
|
// Aligned access at base (overwrites header for C7).
|
|
*(void**)base = next;
|
|
return;
|
|
}
|
|
|
|
// off != 0: use memcpy for portability / UB-avoidance.
|
|
uint8_t* p = (uint8_t*)base + off;
|
|
memcpy(p, &next, sizeof(void*));
|
|
}
|
|
|
|
#endif // TINY_NEXTPTR_H
|