Files
hakmem/core/box/front_gate_classifier.c
Moe Charm (CI) 03df05ec75 Phase 12: Shared SuperSlab Pool implementation (WIP - runtime crash)
## Summary
Implemented Phase 12 Shared SuperSlab Pool (mimalloc-style) to address
SuperSlab allocation churn (877 SuperSlabs → 100-200 target).

## Implementation (ChatGPT + Claude)
1. **Metadata changes** (superslab_types.h):
   - Added class_idx to TinySlabMeta (per-slab dynamic class)
   - Removed size_class from SuperSlab (no longer per-SuperSlab)
   - Changed owner_tid (16-bit) → owner_tid_low (8-bit)

2. **Shared Pool** (hakmem_shared_pool.{h,c}):
   - Global pool shared by all size classes
   - shared_pool_acquire_slab() - Get free slab for class_idx
   - shared_pool_release_slab() - Return slab when empty
   - Per-class hints for fast path optimization

3. **Integration** (23 files modified):
   - Updated all ss->size_class → meta->class_idx
   - Updated all meta->owner_tid → meta->owner_tid_low
   - superslab_refill() now uses shared pool
   - Free path releases empty slabs back to pool

4. **Build system** (Makefile):
   - Added hakmem_shared_pool.o to OBJS_BASE and TINY_BENCH_OBJS_BASE

## Status: ⚠️ Build OK, Runtime CRASH

**Build**:  SUCCESS
- All 23 files compile without errors
- Only warnings: superslab_allocate type mismatch (legacy code)

**Runtime**:  SEGFAULT
- Crash location: sll_refill_small_from_ss()
- Exit code: 139 (SIGSEGV)
- Test case: ./bench_random_mixed_hakmem 1000 256 42

## Known Issues
1. **SEGFAULT in refill path** - Likely shared_pool_acquire_slab() issue
2. **Legacy superslab_allocate()** still exists (type mismatch warning)
3. **Remaining TODOs** from design doc:
   - SuperSlab physical layout integration
   - slab_handle.h cleanup
   - Remove old per-class head implementation

## Next Steps
1. Debug SEGFAULT (gdb backtrace shows sll_refill_small_from_ss)
2. Fix shared_pool_acquire_slab() or superslab_init_slab()
3. Basic functionality test (1K → 100K iterations)
4. Measure SuperSlab count reduction (877 → 100-200)
5. Performance benchmark (+650-860% expected)

## Files Changed (25 files)
core/box/free_local_box.c
core/box/free_remote_box.c
core/box/front_gate_classifier.c
core/hakmem_super_registry.c
core/hakmem_tiny.c
core/hakmem_tiny_bg_spill.c
core/hakmem_tiny_free.inc
core/hakmem_tiny_lifecycle.inc
core/hakmem_tiny_magazine.c
core/hakmem_tiny_query.c
core/hakmem_tiny_refill.inc.h
core/hakmem_tiny_superslab.c
core/hakmem_tiny_superslab.h
core/hakmem_tiny_tls_ops.h
core/slab_handle.h
core/superslab/superslab_inline.h
core/superslab/superslab_types.h
core/tiny_debug.h
core/tiny_free_fast.inc.h
core/tiny_free_magazine.inc.h
core/tiny_remote.c
core/tiny_superslab_alloc.inc.h
core/tiny_superslab_free.inc.h
Makefile

## New Files (3 files)
PHASE12_SHARED_SUPERSLAB_POOL_DESIGN.md
core/hakmem_shared_pool.c
core/hakmem_shared_pool.h

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: ChatGPT <chatgpt@openai.com>
2025-11-13 16:33:03 +09:00

239 lines
7.5 KiB
C

// front_gate_classifier.c - Box FG: Pointer Classification Implementation
// CRITICAL: Box FG requires header-based classification
// Ensure HEADER_MAGIC and HEADER_CLASS_MASK are available
#ifndef HAKMEM_TINY_HEADER_CLASSIDX
#define HAKMEM_TINY_HEADER_CLASSIDX 1
#endif
#include <stdio.h> // For fprintf in debug
#include <stdlib.h> // For abort in debug
#include "front_gate_classifier.h"
#include "../tiny_region_id.h" // Must come before hakmem_tiny_superslab.h for HEADER_MAGIC
#include "../hakmem_tiny_superslab.h"
#include "../superslab/superslab_inline.h" // For ss_slabs_capacity
#include "../hakmem_build_flags.h"
#include "../hakmem_internal.h" // AllocHeader, HAKMEM_MAGIC, HEADER_SIZE, hak_is_memory_readable
#include "../hakmem_tiny_config.h" // For TINY_NUM_CLASSES, SLAB_SIZE
#include "../hakmem_super_registry.h" // For hak_super_lookup (Box REG)
#ifdef HAKMEM_POOL_TLS_PHASE1
#include "../pool_tls_registry.h" // Safer pool pointer lookup (no header deref)
#endif
// ========== Debug Stats ==========
#if !HAKMEM_BUILD_RELEASE
__thread uint64_t g_classify_header_hit = 0;
__thread uint64_t g_classify_headerless_hit = 0;
__thread uint64_t g_classify_pool_hit = 0;
__thread uint64_t g_classify_unknown_hit = 0;
void front_gate_print_stats(void) {
uint64_t total = g_classify_header_hit + g_classify_headerless_hit +
g_classify_pool_hit + g_classify_unknown_hit;
if (total == 0) return;
fprintf(stderr, "\n========== Front Gate Classification Stats ==========\n");
fprintf(stderr, "Header (C0-C6): %lu (%.2f%%)\n",
g_classify_header_hit, 100.0 * g_classify_header_hit / total);
fprintf(stderr, "Headerless (C7): %lu (%.2f%%)\n",
g_classify_headerless_hit, 100.0 * g_classify_headerless_hit / total);
fprintf(stderr, "Pool TLS: %lu (%.2f%%)\n",
g_classify_pool_hit, 100.0 * g_classify_pool_hit / total);
fprintf(stderr, "Unknown: %lu (%.2f%%)\n",
g_classify_unknown_hit, 100.0 * g_classify_unknown_hit / total);
fprintf(stderr, "Total: %lu\n", total);
fprintf(stderr, "======================================================\n");
}
static void __attribute__((destructor)) front_gate_stats_destructor(void) {
front_gate_print_stats();
}
#endif
// ========== Safe Header Probe ==========
// Try to read 1-byte header at ptr-1 (safe conditions only)
// Returns: class_idx (0-7) on success, -1 on failure
//
// Safety conditions:
// 1. Same page: (ptr & 0xFFF) >= 1 → header won't cross page boundary
// 2. Valid magic: (header & 0xF0) == HEADER_MAGIC (0xa0)
// 3. Valid class: class_idx in range [0, 7]
//
// Performance: 2-3 cycles (L1 cache hit)
static inline int safe_header_probe(void* ptr) {
// Reject obviously invalid/sentinel-sized pointers (defense-in-depth)
if ((uintptr_t)ptr < 4096) {
return -1;
}
// Safety check: header must be in same page as ptr
uintptr_t offset_in_page = (uintptr_t)ptr & 0xFFF;
if (offset_in_page == 0) {
// ptr is page-aligned → header would be on previous page (unsafe)
return -1;
}
// Safe to read header (same page guaranteed)
uint8_t* header_ptr = (uint8_t*)ptr - 1;
uint8_t header = *header_ptr;
// Validate magic
if ((header & 0xF0) != HEADER_MAGIC) {
return -1; // Not a Tiny header
}
// Extract class index
int class_idx = header & HEADER_CLASS_MASK;
// Phase E1-CORRECT: Validate class range (all classes 0-7 valid)
if (class_idx < 0 || class_idx >= TINY_NUM_CLASSES) {
return -1; // Invalid class
}
return class_idx;
}
// ========== Registry Lookup ==========
// Lookup pointer in SuperSlab registry (fallback when header probe fails)
// Returns: classification result with SuperSlab + class_idx + slab_idx
//
// Performance: 50-100 cycles (hash lookup + validation)
static inline ptr_classification_t registry_lookup(void* ptr) {
ptr_classification_t result = {
.kind = PTR_KIND_UNKNOWN,
.class_idx = -1,
.ss = NULL,
.slab_idx = -1
};
// Query SuperSlab registry
struct SuperSlab* ss = hak_super_lookup(ptr);
if (!ss || ss->magic != SUPERSLAB_MAGIC) {
// Not in Tiny registry
return result;
}
// Found SuperSlab - determine slab index from ptr-1 (block base)
result.ss = ss;
uintptr_t ptr_addr = (uintptr_t)ptr;
uintptr_t ss_addr = (uintptr_t)ss;
if (ptr_addr <= ss_addr) {
result.kind = PTR_KIND_UNKNOWN;
return result;
}
// Use block base for slab index to be consistent with free paths
uintptr_t base_addr = ptr_addr - 1;
size_t offset = base_addr - ss_addr;
int slab_idx = (int)(offset / SLAB_SIZE);
if (slab_idx < 0 || slab_idx >= ss_slabs_capacity(ss)) {
result.kind = PTR_KIND_UNKNOWN;
return result;
}
result.slab_idx = slab_idx;
TinySlabMeta* meta = &ss->slabs[slab_idx];
int cls = (meta->class_idx < TINY_NUM_CLASSES) ? (int)meta->class_idx : -1;
result.class_idx = cls;
if (cls == 7) {
// 1KB headerless tiny
result.kind = PTR_KIND_TINY_HEADERLESS;
} else if (cls >= 0) {
// Other tiny classes with 1-byte header
result.kind = PTR_KIND_TINY_HEADER;
} else {
result.kind = PTR_KIND_UNKNOWN;
}
return result;
}
// ========== Pool TLS Probe ==========
#ifdef HAKMEM_POOL_TLS_PHASE1
// Registry-based Pool TLS probe (no memory deref)
static inline int is_pool_tls_reg(void* ptr) {
pid_t tid = 0; int cls = -1;
return pool_reg_lookup(ptr, &tid, &cls);
}
#endif
// ========== Front Gate Entry Point ==========
ptr_classification_t classify_ptr(void* ptr) {
ptr_classification_t result = {
.kind = PTR_KIND_UNKNOWN,
.class_idx = -1,
.ss = NULL,
.slab_idx = -1
};
if (!ptr) return result;
// Early guard: reject non-canonical tiny integers to avoid ptr-1 probe crashes
if ((uintptr_t)ptr < 4096) {
result.kind = PTR_KIND_UNKNOWN;
return result;
}
// Step 1: Check Pool TLS via registry (no pointer deref)
#ifdef HAKMEM_POOL_TLS_PHASE1
if (is_pool_tls_reg(ptr)) {
result.kind = PTR_KIND_POOL_TLS;
#if !HAKMEM_BUILD_RELEASE
g_classify_pool_hit++;
#endif
return result;
}
#endif
// Step 2: Registry lookup for Tiny (header or headerless)
result = registry_lookup(ptr);
if (result.kind == PTR_KIND_TINY_HEADERLESS) {
#if !HAKMEM_BUILD_RELEASE
g_classify_headerless_hit++;
#endif
return result;
}
if (result.kind == PTR_KIND_TINY_HEADER) {
#if !HAKMEM_BUILD_RELEASE
g_classify_header_hit++;
#endif
return result;
}
// Step 3: Try AllocHeader (HAKMEM header) for Mid/Large/Mmap
do {
if (!ptr) break;
// Quick page-safety check: avoid crossing page for header read
uintptr_t off = (uintptr_t)ptr & 0xFFFu;
int safe_same_page = (off >= HEADER_SIZE);
void* raw = (char*)ptr - HEADER_SIZE;
if (!safe_same_page) {
if (!hak_is_memory_readable(raw)) break;
}
AllocHeader* hdr = (AllocHeader*)raw;
if (hdr->magic == HAKMEM_MAGIC) {
result.kind = PTR_KIND_MID_LARGE; // HAKMEM-owned (non-Tiny)
#if !HAKMEM_BUILD_RELEASE
g_classify_unknown_hit++; // reuse for stats without adding a new counter
#endif
return result;
}
} while (0);
// Step 4: Not recognized → UNKNOWN (route to libc or slow path)
result.kind = PTR_KIND_UNKNOWN;
#if !HAKMEM_BUILD_RELEASE
g_classify_unknown_hit++;
#endif
return result;
}