Files
hakmem/core/tiny_debug_ring.c
Moe Charm (CI) ccf604778c Front-Direct implementation: SS→FC direct refill + SLL complete bypass
## Summary

Implemented Front-Direct architecture with complete SLL bypass:
- Direct SuperSlab → FastCache refill (1-hop, bypasses SLL)
- SLL-free allocation/free paths when Front-Direct enabled
- Legacy path sealing (SLL inline opt-in, SFC cascade ENV-only)

## New Modules

- core/refill/ss_refill_fc.h (236 lines): Standard SS→FC refill entry point
  - Remote drain → Freelist → Carve priority
  - Header restoration for C1-C6 (NOT C0/C7)
  - ENV: HAKMEM_TINY_P0_DRAIN_THRESH, HAKMEM_TINY_P0_NO_DRAIN

- core/front/fast_cache.h: FastCache (L1) type definition
- core/front/quick_slot.h: QuickSlot (L0) type definition

## Allocation Path (core/tiny_alloc_fast.inc.h)

- Added s_front_direct_alloc TLS flag (lazy ENV check)
- SLL pop guarded by: g_tls_sll_enable && !s_front_direct_alloc
- Refill dispatch:
  - Front-Direct: ss_refill_fc_fill() → fastcache_pop() (1-hop)
  - Legacy: sll_refill_batch_from_ss() → SLL → FC (2-hop, A/B only)
- SLL inline pop sealed (requires HAKMEM_TINY_INLINE_SLL=1 opt-in)

## Free Path (core/hakmem_tiny_free.inc, core/hakmem_tiny_fastcache.inc.h)

- FC priority: Try fastcache_push() first (same-thread free)
- tiny_fast_push() bypass: Returns 0 when s_front_direct_free || !g_tls_sll_enable
- Fallback: Magazine/slow path (safe, bypasses SLL)

## Legacy Sealing

- SFC cascade: Default OFF (ENV-only via HAKMEM_TINY_SFC_CASCADE=1)
- Deleted: core/hakmem_tiny_free.inc.bak, core/pool_refill_legacy.c.bak
- Documentation: ss_refill_fc_fill() promoted as CANONICAL refill entry

## ENV Controls

- HAKMEM_TINY_FRONT_DIRECT=1: Enable Front-Direct (SS→FC direct)
- HAKMEM_TINY_P0_DIRECT_FC_ALL=1: Same as above (alt name)
- HAKMEM_TINY_REFILL_BATCH=1: Enable batch refill (also enables Front-Direct)
- HAKMEM_TINY_SFC_CASCADE=1: Enable SFC cascade (default OFF)
- HAKMEM_TINY_INLINE_SLL=1: Enable inline SLL pop (default OFF, requires AGGRESSIVE_INLINE)

## Benchmarks (Front-Direct Enabled)

```bash
ENV: HAKMEM_BENCH_FAST_FRONT=1 HAKMEM_TINY_FRONT_DIRECT=1
     HAKMEM_TINY_REFILL_BATCH=1 HAKMEM_TINY_P0_DIRECT_FC_ALL=1
     HAKMEM_TINY_REFILL_COUNT_HOT=256 HAKMEM_TINY_REFILL_COUNT_MID=96
     HAKMEM_TINY_BUMP_CHUNK=256

bench_random_mixed (16-1040B random, 200K iter):
  256 slots: 1.44M ops/s (STABLE, 0 SEGV)
  128 slots: 1.44M ops/s (STABLE, 0 SEGV)

bench_fixed_size (fixed size, 200K iter):
  256B: 4.06M ops/s (has debug logs, expected >10M without logs)
  128B: Similar (debug logs affect)
```

## Verification

- TRACE_RING test (10K iter): **0 SLL events** detected 
- Complete SLL bypass confirmed when Front-Direct=1
- Stable execution: 200K iterations × multiple sizes, 0 SEGV

## Next Steps

- Disable debug logs in hak_alloc_api.inc.h (call_num 14250-14280 range)
- Re-benchmark with clean Release build (target: 10-15M ops/s)
- 128/256B shortcut path optimization (FC hit rate improvement)

Co-Authored-By: ChatGPT <chatgpt@openai.com>
Suggested-By: ultrathink
2025-11-14 05:41:49 +09:00

238 lines
8.8 KiB
C

#include "tiny_debug_ring.h"
#include "hakmem_build_flags.h"
#include "hakmem_tiny.h"
#include <signal.h>
#include <stdatomic.h>
#include <unistd.h>
#include <stdlib.h>
#include <sys/types.h>
#include <ucontext.h>
#if HAKMEM_BUILD_RELEASE && !HAKMEM_DEBUG_VERBOSE
// In release builds without verbose debug, provide no-op stubs.
// These are needed for LTO builds where inline stubs may not be visible.
void tiny_debug_ring_init(void) {
// No-op in release builds
}
void tiny_debug_ring_record(uint16_t event, uint16_t class_idx, void* ptr, uintptr_t aux) {
(void)event;
(void)class_idx;
(void)ptr;
(void)aux;
// No-op in release builds
}
#else
#define TINY_RING_IGNORE(expr) do { ssize_t _tw_ret = (expr); (void)_tw_ret; } while(0)
#define TINY_RING_CAP 4096u
typedef struct {
uintptr_t ptr;
uintptr_t aux;
uint16_t event;
uint16_t class_idx;
} TinyRingEntry;
static TinyRingEntry g_tiny_ring[TINY_RING_CAP];
static _Atomic uint32_t g_tiny_ring_head = 0;
static int g_tiny_ring_enabled = 0;
typedef struct {
const char* name;
size_t len;
} TinyRingName;
static TinyRingName tiny_ring_event_name(uint16_t event) {
switch (event) {
case TINY_RING_EVENT_ALLOC_ENTER: return (TinyRingName){"alloc_enter", 11};
case TINY_RING_EVENT_ALLOC_SUCCESS: return (TinyRingName){"alloc_ok", 8};
case TINY_RING_EVENT_ALLOC_NULL: return (TinyRingName){"alloc_null", 10};
case TINY_RING_EVENT_ALLOC_REFILL_START: return (TinyRingName){"refill_start", 12};
case TINY_RING_EVENT_ALLOC_REFILL_NULL: return (TinyRingName){"refill_null", 11};
case TINY_RING_EVENT_ALLOC_BIND: return (TinyRingName){"bind", 4};
case TINY_RING_EVENT_FREE_ENTER: return (TinyRingName){"free_enter", 10};
case TINY_RING_EVENT_FREE_FAST: return (TinyRingName){"free_fast", 8};
case TINY_RING_EVENT_FREE_REMOTE: return (TinyRingName){"free_remote", 11};
case TINY_RING_EVENT_FREE_LOCAL: return (TinyRingName){"free_local", 10};
case TINY_RING_EVENT_FREE_RETURN_MAG: return (TinyRingName){"free_mag", 7};
case TINY_RING_EVENT_SUPERSLAB_ADOPT: return (TinyRingName){"ss_adopt", 8};
case TINY_RING_EVENT_SUPERSLAB_ALLOC: return (TinyRingName){"ss_alloc", 8};
case TINY_RING_EVENT_SUPERSLAB_PUBLISH: return (TinyRingName){"ss_publish", 10};
case TINY_RING_EVENT_SUPERSLAB_ADOPT_FAIL: return (TinyRingName){"ss_adopt_fail", 13};
case TINY_RING_EVENT_REMOTE_PUSH: return (TinyRingName){"remote_push", 11};
case TINY_RING_EVENT_REMOTE_INVALID: return (TinyRingName){"remote_invalid", 14};
case TINY_RING_EVENT_REMOTE_DRAIN: return (TinyRingName){"remote_drain", 12};
case TINY_RING_EVENT_OWNER_ACQUIRE: return (TinyRingName){"owner_acq", 9};
case TINY_RING_EVENT_OWNER_RELEASE: return (TinyRingName){"owner_rel", 9};
case TINY_RING_EVENT_FRONT_BYPASS: return (TinyRingName){"front_bypass", 12};
case TINY_RING_EVENT_MAILBOX_PUBLISH: return (TinyRingName){"mailbox_publish", 15};
case TINY_RING_EVENT_MAILBOX_FETCH: return (TinyRingName){"mailbox_fetch", 13};
case TINY_RING_EVENT_MAILBOX_FETCH_NULL: return (TinyRingName){"mailbox_fetch_null", 18};
case TINY_RING_EVENT_ROUTE: return (TinyRingName){"route", 5};
case TINY_RING_EVENT_TLS_SLL_REJECT: return (TinyRingName){"tls_sll_reject", 14};
case TINY_RING_EVENT_TLS_SLL_SENTINEL: return (TinyRingName){"tls_sll_sentinel", 16};
case TINY_RING_EVENT_TLS_SLL_HDR_CORRUPT: return (TinyRingName){"tls_sll_hdr_corrupt", 20};
default: return (TinyRingName){"unknown", 7};
}
}
static void tiny_ring_write_dec(int fd, uint64_t value) {
char buf[32];
int pos = 31;
if (value == 0) {
buf[pos--] = '0';
} else {
while (value > 0 && pos >= 0) {
buf[pos--] = (char)('0' + (value % 10));
value /= 10;
}
}
int len = 31 - pos;
TINY_RING_IGNORE(write(fd, buf + pos + 1, len));
}
static void tiny_ring_write_hex(int fd, uintptr_t value) {
static const char* hex = "0123456789abcdef";
char buf[2 + sizeof(uintptr_t) * 2 + 1];
buf[0] = '0';
buf[1] = 'x';
for (int i = (int)(sizeof(uintptr_t) * 2) - 1; i >= 0; --i) {
buf[2 + i] = hex[value & 0xFu];
value >>= 4;
}
buf[2 + sizeof(uintptr_t) * 2] = '\0';
TINY_RING_IGNORE(write(fd, buf, 2 + sizeof(uintptr_t) * 2));
}
static void tiny_debug_ring_dump(int fd, uintptr_t fault_addr) {
const char hdr[] = "\n[Tiny Debug Ring Dump]\n";
TINY_RING_IGNORE(write(fd, hdr, sizeof(hdr) - 1));
const char addr_prefix[] = "fault_addr=";
TINY_RING_IGNORE(write(fd, addr_prefix, sizeof(addr_prefix) - 1));
tiny_ring_write_hex(fd, fault_addr);
TINY_RING_IGNORE(write(fd, "\n", 1));
uint32_t head = atomic_load_explicit(&g_tiny_ring_head, memory_order_relaxed);
uint32_t count = head < TINY_RING_CAP ? head : TINY_RING_CAP;
for (uint32_t i = 0; i < count; i++) {
uint32_t idx = (head - count + i) & (TINY_RING_CAP - 1u);
TinyRingEntry ent = g_tiny_ring[idx];
TINY_RING_IGNORE(write(fd, "[", 1));
tiny_ring_write_dec(fd, idx);
const char mid[] = "] event=";
TINY_RING_IGNORE(write(fd, mid, sizeof(mid) - 1));
TinyRingName name = tiny_ring_event_name(ent.event);
TINY_RING_IGNORE(write(fd, name.name, name.len));
const char cls[] = " class=";
TINY_RING_IGNORE(write(fd, cls, sizeof(cls) - 1));
tiny_ring_write_dec(fd, ent.class_idx);
const char ptr_prefix[] = " ptr=";
TINY_RING_IGNORE(write(fd, ptr_prefix, sizeof(ptr_prefix) - 1));
tiny_ring_write_hex(fd, ent.ptr);
const char aux_prefix[] = " aux=";
TINY_RING_IGNORE(write(fd, aux_prefix, sizeof(aux_prefix) - 1));
tiny_ring_write_hex(fd, ent.aux);
TINY_RING_IGNORE(write(fd, "\n", 1));
}
}
static void tiny_debug_ring_sigsegv(int signo, siginfo_t* info, void* uctx) {
uintptr_t ip = 0;
#if defined(__x86_64__)
if (uctx) {
ucontext_t* uc = (ucontext_t*)uctx;
#ifdef REG_RIP
ip = (uintptr_t)uc->uc_mcontext.gregs[REG_RIP];
#else
(void)uc; // REG_RIP not available on this platform
#endif
}
#endif
if (g_tiny_ring_enabled) {
uintptr_t fault = info ? (uintptr_t)info->si_addr : 0;
#if defined(__x86_64__)
#ifdef REG_RIP
if (ip != 0) {
const char rip_prefix[] = "rip=";
TINY_RING_IGNORE(write(STDERR_FILENO, rip_prefix, sizeof(rip_prefix) - 1));
tiny_ring_write_hex(STDERR_FILENO, ip);
TINY_RING_IGNORE(write(STDERR_FILENO, "\n", 1));
}
#endif
#endif
tiny_debug_ring_dump(STDERR_FILENO, fault);
}
const char msg[] = "[Tiny Debug Ring] captured SIGSEGV\n";
TINY_RING_IGNORE(write(STDERR_FILENO, msg, sizeof(msg) - 1));
#if defined(__x86_64__)
#ifdef REG_RIP
if (ip != 0) {
const char rip_prefix[] = "rip=";
TINY_RING_IGNORE(write(STDERR_FILENO, rip_prefix, sizeof(rip_prefix) - 1));
tiny_ring_write_hex(STDERR_FILENO, ip);
TINY_RING_IGNORE(write(STDERR_FILENO, "\n", 1));
}
#endif
#endif
_exit(128 + signo);
}
static void tiny_debug_ring_sigusr(int signo, siginfo_t* info, void* uctx) {
(void)signo;
(void)info;
(void)uctx;
if (g_tiny_ring_enabled) {
tiny_debug_ring_dump(STDERR_FILENO, 0);
const char msg[] = "[Tiny Debug Ring] SIGUSR2 dump\n";
TINY_RING_IGNORE(write(STDERR_FILENO, msg, sizeof(msg) - 1));
}
}
void tiny_debug_ring_init(void) {
if (g_tiny_ring_enabled) return;
const char* env = getenv("HAKMEM_TINY_TRACE_RING");
if (!(env && *env && env[0] != '0')) {
return;
}
g_tiny_ring_enabled = 1;
struct sigaction sa;
sigemptyset(&sa.sa_mask);
sa.sa_flags = SA_SIGINFO | SA_RESETHAND;
sa.sa_sigaction = tiny_debug_ring_sigsegv;
sigaction(SIGSEGV, &sa, NULL);
struct sigaction su;
sigemptyset(&su.sa_mask);
su.sa_flags = SA_SIGINFO | SA_RESTART;
su.sa_sigaction = tiny_debug_ring_sigusr;
sigaction(SIGUSR2, &su, NULL);
}
void tiny_debug_ring_record(uint16_t event, uint16_t class_idx, void* ptr, uintptr_t aux) {
if (!g_tiny_ring_enabled) return;
uint32_t idx = atomic_fetch_add_explicit(&g_tiny_ring_head, 1u, memory_order_relaxed);
TinyRingEntry entry;
entry.ptr = (uintptr_t)ptr;
entry.aux = aux;
entry.event = event;
entry.class_idx = class_idx;
g_tiny_ring[idx & (TINY_RING_CAP - 1u)] = entry;
}
__attribute__((constructor))
static void tiny_debug_ring_ctor(void) {
tiny_debug_ring_init();
}
__attribute__((destructor))
static void tiny_debug_ring_dtor(void) {
const char* e = getenv("HAKMEM_TINY_DUMP_RING_ATEXIT");
if (e && *e && e[0] != '0') {
tiny_debug_ring_dump(STDERR_FILENO, 0);
}
}
#endif // HAKMEM_BUILD_RELEASE && !HAKMEM_DEBUG_VERBOSE