Files
hakmem/core/hakmem_tiny_fastcache.inc.h
Moe Charm (CI) 72b38bc994 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>
2025-11-13 06:50:20 +09:00

202 lines
7.4 KiB
C

// hakmem_tiny_fastcache.inc.h
// Phase 2D-1: Hot-path inline functions - Fast cache and quick slot operations
//
// This file contains fast cache and quick slot inline functions.
// These functions are extracted from hakmem_tiny.c to improve maintainability and
// reduce the main file size by approximately 53 lines.
//
// Functions handle:
// - tiny_fast_pop/push: Fast TLS cache operations (lines 377-404)
// - fastcache_pop/push: Frontend fast cache (lines 873-888)
// - quick_pop: Quick slot pop operation (line 892-896)
#ifndef HAKMEM_TINY_FASTCACHE_INC_H
#define HAKMEM_TINY_FASTCACHE_INC_H
#include "hakmem_tiny.h"
#include <stdint.h>
#include <stdlib.h>
#include <stdio.h>
#include <stdatomic.h>
#include "tiny_remote.h" // For TINY_REMOTE_SENTINEL detection
#include "box/tiny_next_ptr_box.h" // For tiny_next_read(class_idx, )
// External TLS variables
extern int g_fast_enable;
extern uint16_t g_fast_cap[TINY_NUM_CLASSES];
extern __thread void* g_fast_head[TINY_NUM_CLASSES];
extern __thread uint16_t g_fast_count[TINY_NUM_CLASSES];
// Fast cache capacity
#define TINY_FASTCACHE_CAP 128
// Quick slot capacity
#define QUICK_CAP 6
// External variable declarations
// Note: TinyFastCache and TinyQuickSlot types must be defined before including this file
extern int g_fastcache_enable;
extern __thread TinyFastCache g_fast_cache[TINY_NUM_CLASSES];
extern int g_quick_enable;
extern __thread TinyQuickSlot g_tls_quick[TINY_NUM_CLASSES];
extern unsigned long long g_free_via_fastcache[];
extern unsigned long long g_fast_push_hits[];
extern unsigned long long g_fast_push_full[];
extern unsigned long long g_fast_push_disabled[];
extern unsigned long long g_fast_push_zero_cap[];
static int g_fast_debug_mode = -1;
static int g_fast_debug_limit = 8;
static _Atomic int g_fast_debug_seen[TINY_NUM_CLASSES];
static inline void tiny_fast_debug_log(int class_idx, const char* event, uint16_t count, uint16_t cap) {
if (__builtin_expect(g_fast_debug_mode == -1, 0)) {
const char* e = getenv("HAKMEM_TINY_FAST_DEBUG");
g_fast_debug_mode = (e && atoi(e) != 0) ? 1 : 0;
const char* limit_env = getenv("HAKMEM_TINY_FAST_DEBUG_MAX");
if (limit_env && *limit_env) {
int v = atoi(limit_env);
if (v > 0) g_fast_debug_limit = v;
}
}
if (!g_fast_debug_mode) return;
int limit = g_fast_debug_limit;
if (limit <= 0) limit = 8;
int seen = atomic_fetch_add_explicit(&g_fast_debug_seen[class_idx], 1, memory_order_relaxed);
if (seen < limit) {
fprintf(stderr, "[FASTDBG] class=%d event=%s count=%u cap=%u\n",
class_idx, event, (unsigned)count, (unsigned)cap);
}
}
// Tracepoint macros (no-op if not defined)
#ifndef HAK_TP1
#define HAK_TP1(name, idx) do { (void)(idx); } while(0)
#endif
// Basic fast cache operations
static inline __attribute__((always_inline)) void* tiny_fast_pop(int class_idx) {
if (!g_fast_enable) return NULL;
uint16_t cap = g_fast_cap[class_idx];
if (cap == 0) return NULL;
void* head = g_fast_head[class_idx];
if (!head) return NULL;
// Phase 7: header-aware next pointer (C0-C6: base+1, C7: base)
#if HAKMEM_TINY_HEADER_CLASSIDX
// Phase E1-CORRECT: ALL classes have 1-byte header, next ptr at offset 1
const size_t next_offset = 1;
#else
const size_t next_offset = 0;
#endif
// Phase E1-CORRECT: Use Box API for next pointer read (ALL classes: base+1)
#include "box/tiny_next_ptr_box.h"
void* next = tiny_next_read(class_idx, head);
g_fast_head[class_idx] = next;
uint16_t count = g_fast_count[class_idx];
if (count > 0) {
g_fast_count[class_idx] = (uint16_t)(count - 1);
} else {
g_fast_count[class_idx] = 0;
}
// Phase E1-CORRECT: All classes return user pointer (base+1)
return (void*)((uint8_t*)head + 1);
}
static inline __attribute__((always_inline)) int tiny_fast_push(int class_idx, void* ptr) {
// ✅ CRITICAL FIX: Prevent sentinel-poisoned nodes from entering fast cache
// Remote free operations can write SENTINEL to node->next, which eventually
// propagates through freelist → TLS list → fast cache. If we push such a node,
// the next pop will try to dereference the sentinel → SEGV!
if (__builtin_expect((uintptr_t)ptr == TINY_REMOTE_SENTINEL, 0)) {
static __thread int sentinel_ptr_logged = 0;
if (sentinel_ptr_logged < 5) {
fprintf(stderr, "[FAST_PUSH_SENTINEL] cls=%d ptr=%p BLOCKED (ptr is sentinel)!\n",
class_idx, ptr);
sentinel_ptr_logged++;
}
return 0; // Reject push
}
// ✅ CRITICAL FIX #2: Also check if node's NEXT pointer is sentinel (defense-in-depth)
// This catches nodes that have sentinel in their next field (from remote free)
void* next_check = tiny_next_read(class_idx, ptr);
if (__builtin_expect((uintptr_t)next_check == TINY_REMOTE_SENTINEL, 0)) {
static __thread int sentinel_next_logged = 0;
if (sentinel_next_logged < 5) {
fprintf(stderr, "[FAST_PUSH_NEXT_SENTINEL] cls=%d ptr=%p next=%p BLOCKED (next is sentinel)!\n",
class_idx, ptr, next_check);
sentinel_next_logged++;
}
return 0; // Reject push
}
if (!g_fast_enable) {
g_fast_push_disabled[class_idx]++;
tiny_fast_debug_log(class_idx, "disabled", 0, 0);
return 0;
}
uint16_t cap = g_fast_cap[class_idx];
if (cap == 0) {
g_fast_push_zero_cap[class_idx]++;
tiny_fast_debug_log(class_idx, "zero_cap", g_fast_count[class_idx], cap);
return 0;
}
uint16_t count = g_fast_count[class_idx];
if (count >= cap) {
g_fast_push_full[class_idx]++;
tiny_fast_debug_log(class_idx, "full", count, cap);
return 0;
}
// Phase 7: header-aware next pointer (C0-C6: base+1, C7: base)
#if HAKMEM_TINY_HEADER_CLASSIDX
// Phase E1-CORRECT: ALL classes have 1-byte header, next ptr at offset 1
const size_t next_offset2 = 1;
#else
const size_t next_offset2 = 0;
#endif
// Phase E1-CORRECT: Use Box API for next pointer write (ALL classes: base+1)
#include "box/tiny_next_ptr_box.h"
tiny_next_write(class_idx, ptr, g_fast_head[class_idx]);
g_fast_head[class_idx] = ptr;
g_fast_count[class_idx] = (uint16_t)(count + 1);
g_fast_push_hits[class_idx]++;
tiny_fast_debug_log(class_idx, "hit", (uint16_t)(count + 1), cap);
return 1;
}
// Frontend fast cache operations
static inline void* fastcache_pop(int class_idx) {
TinyFastCache* fc = &g_fast_cache[class_idx];
if (__builtin_expect(fc->top > 0, 1)) {
void* base = fc->items[--fc->top];
// ✅ FIX #16: Return BASE pointer (not USER)
// FastCache stores base pointers. Caller will apply HAK_RET_ALLOC
// which does BASE → USER conversion via tiny_region_id_write_header
return base;
}
return NULL;
}
static inline int fastcache_push(int class_idx, void* ptr) {
TinyFastCache* fc = &g_fast_cache[class_idx];
if (__builtin_expect(fc->top < TINY_FASTCACHE_CAP, 1)) {
fc->items[fc->top++] = ptr;
g_free_via_fastcache[class_idx]++;
return 1;
}
return 0;
}
// Quick slot pop operation
static inline void* quick_pop(int class_idx) {
TinyQuickSlot* qs = &g_tls_quick[class_idx];
if (__builtin_expect(qs->top > 0, 1)) {
void* p = qs->items[--qs->top];
HAK_TP1(quick_pop, class_idx);
return p;
}
return NULL;
}
#endif // HAKMEM_TINY_FASTCACHE_INC_H