/**
 ******************************************************************************
 * Xenia : Xbox 360 Emulator Research Project                                 *
 ******************************************************************************
 * Copyright 2022 Ben Vanik. All rights reserved.                             *
 * Released under the BSD license - see LICENSE in the root for more details. *
 ******************************************************************************
 */

#include <algorithm>
#include <map>
#include <set>
#include <vector>

#include "xenia/base/cvar.h"
#include "xenia/base/debugging.h"
#include "xenia/base/logging.h"
#include "xenia/cpu/backend/backend.h"
#include "xenia/cpu/function.h"
#include "xenia/cpu/processor.h"
#include "xenia/emulator.h"
#include "xenia/kernel/kernel_state.h"
#include "xenia/kernel/util/shim_utils.h"
#include "xenia/kernel/xboxkrnl/xboxkrnl_private.h"
#include "xenia/kernel/xthread.h"
#include "xenia/ui/imgui_dialog.h"
#include "xenia/ui/imgui_drawer.h"
#include "xenia/ui/window.h"
#include "xenia/ui/windowed_app_context.h"

DEFINE_bool(
    cache_throw_diag, false,
    "Run the heavy guest-throw diagnostics (LogGuestThrow / cache-manager dump / "
    "catch-frame walk) on every guest C++ throw. OFF by default: in missions the "
    "cache throws constantly and these dumps allocate gigabytes -- they are for "
    "targeted debugging only.",
    "Kernel");

DEFINE_bool(
    eh_dispatch, false,
    "Dispatch guest C++ exceptions (0xE06D7363) to their catch handler instead "
    "of letting the throw fall through. NOTE: disproven as a fix for the Project "
    "Sylpheed cache crash (that throw is uncaught by design -- its stack ends at "
    "the thread-entry Execute boundary); kept as inert infra + diagnostics.",
    "Kernel");

namespace xe {
namespace kernel {
namespace xboxkrnl {

void DbgBreakPoint_entry() { xe::debugging::Break(); }
DECLARE_XBOXKRNL_EXPORT2(DbgBreakPoint, kDebug, kStub, kImportant);

// https://msdn.microsoft.com/en-us/library/xcb2z8hs.aspx
typedef struct {
  xe::be<uint32_t> type;
  xe::be<uint32_t> name_ptr;
  xe::be<uint32_t> thread_id;
  xe::be<uint32_t> flags;
} X_THREADNAME_INFO;
static_assert_size(X_THREADNAME_INFO, 0x10);

void HandleSetThreadName(pointer_t<X_EXCEPTION_RECORD> record) {
  // SetThreadName. FFS.
  // https://msdn.microsoft.com/en-us/library/xcb2z8hs.aspx

  // TODO(benvanik): check record->number_parameters to make sure it's a
  // correct size.
  auto thread_info =
      reinterpret_cast<X_THREADNAME_INFO*>(&record->exception_information[0]);

  assert_true(thread_info->type == 0x1000);

  if (!thread_info->name_ptr) {
    XELOGD("SetThreadName called with null name_ptr");
    return;
  }

  // 4D5307D6 (and its demo) has a bug where it ends up passing freed memory for
  // the name, so at the point of SetThreadName it's filled with junk.

  // TODO(gibbed): cvar for thread name encoding for conversion, some games use
  // SJIS and there's no way to automatically know this.
  auto name = std::string(
      kernel_memory()->TranslateVirtual<const char*>(thread_info->name_ptr));
  std::replace_if(
      name.begin(), name.end(), [](auto c) { return c < 32 || c > 127; }, '?');

  object_ref<XThread> thread;
  if (thread_info->thread_id == -1) {
    // Current thread.
    thread = retain_object(XThread::GetCurrentThread());
  } else {
    // Lookup thread by ID.
    thread = kernel_state()->GetThreadByID(thread_info->thread_id);
  }

  if (thread) {
    XELOGD("SetThreadName({}, {})", thread->thread_id(), name);
    thread->set_name(name);
  }

  // TODO(benvanik): unwinding required here?
}

typedef struct {
  xe::be<int32_t> mdisp;
  xe::be<int32_t> pdisp;
  xe::be<int32_t> vdisp;
} x_PMD;

typedef struct {
  xe::be<uint32_t> properties;
  xe::be<uint32_t> type_ptr;
  x_PMD this_displacement;
  xe::be<int32_t> size_or_offset;
  xe::be<uint32_t> copy_function_ptr;
} x_s__CatchableType;

typedef struct {
  xe::be<int32_t> number_catchable_types;
  xe::be<uint32_t> catchable_type_ptrs[1];
} x_s__CatchableTypeArray;

typedef struct {
  xe::be<uint32_t> attributes;
  xe::be<uint32_t> unwind_ptr;
  xe::be<uint32_t> forward_compat_ptr;
  xe::be<uint32_t> catchable_type_array_ptr;
} x_s__ThrowInfo;

// Read a guest C-string, bounded.
static std::string GuestCString(uint32_t guest_ptr, size_t max_len = 128) {
  if (!guest_ptr) {
    return {};
  }
  auto p = kernel_memory()->TranslateVirtual<const char*>(guest_ptr);
  if (!p) {
    return {};
  }
  std::string s;
  for (size_t i = 0; i < max_len && p[i]; ++i) {
    s.push_back(p[i]);
  }
  return s;
}

// Name the thrown C++ type via the MSVC RTTI chain hanging off its vtable:
//   object -> vtable ; vtable[-1] -> CompleteObjectLocator ; COL+0xC ->
//   TypeDescriptor ; TypeDescriptor+8 -> mangled name (".?AVout_of_range@std@@")
static std::string ThrownTypeName(uint32_t thrown_ptr) {
  if (!thrown_ptr) {
    return "<null>";
  }
  auto rd32 = [](uint32_t va) -> uint32_t {
    auto p = kernel_memory()->TranslateVirtual<xe::be<uint32_t>*>(va);
    return p ? static_cast<uint32_t>(*p) : 0;
  };
  const uint32_t vtable = rd32(thrown_ptr);
  if (!vtable) {
    return "<no vtable>";
  }
  const uint32_t col = rd32(vtable - 4);
  if (!col) {
    return "<no RTTI>";
  }
  const uint32_t type_desc = rd32(col + 0x0C);
  if (!type_desc) {
    return "<no type descriptor>";
  }
  return GuestCString(type_desc + 8);
}

// Diagnostics for the swallowed-throw crash: xenia does NOT dispatch guest C++
// exceptions (see below), so a throw returns and the game crashes in the
// unreachable code after it. By then the crash dump's registers are already
// clobbered. Capture the guest state HERE, while the throwing call frame is
// still intact -- the thrown type, the registers (the failing lookup's key and
// loop state live in these), and the guest call stack.
// Dump the asset-cache-manager LRU state at the moment it throws out_of_range,
// so we can see WHICH access-order deque hash-pair is missing from the entry
// map (the desync that crashes in sub_8245A098). r25 survives the throw and
// holds the cache-manager global (guest VA 0x828F4838). Layout (from RE):
//   OBJ+0x30 = std::list<Entry> (map is rebuilt from this, keyed by hash-pair)
//   OBJ+0x48 = std::deque<hashpair(8B)>: +0x4C block-map ptr, +0x50 map_size,
//              +0x54 start off, +0x58 element count. Element i (8-byte, 2/block):
//              bi=((start+i)/2); if bi>=map_size bi-=map_size; addr=blockmap[bi]+(i&1)*8
static void DumpCacheManagerOnThrow(const ppc_context_t& ctx) {
  const uint32_t OBJ = 0x828F4838u;
  if (static_cast<uint32_t>(ctx->r[25]) != OBJ) {
    return;  // not the cache-manager map::at that threw
  }
  auto rd = [](uint32_t va) -> uint32_t {
    auto p = kernel_memory()->TranslateVirtual<xe::be<uint32_t>*>(va);
    return p ? static_cast<uint32_t>(*p) : 0;
  };
  const uint32_t deque_count = rd(OBJ + 0x58);
  const uint32_t list_count = rd(OBJ + 0x38);
  const uint32_t blockmap = rd(OBJ + 0x4C);
  const uint32_t map_size = rd(OBJ + 0x50);
  const uint32_t start = rd(OBJ + 0x54);
  XELOGE(
      "CACHE-DUMP deque_count={} list_count={} blockmap={:08X} map_size={} "
      "start={}",
      deque_count, list_count, blockmap, map_size, start);
  // Raw header words -- resolve the real container layout without guessing.
  auto rawrow = [&](const char* tag, uint32_t base, int words) {
    std::string s;
    for (int i = 0; i < words; ++i)
      s += fmt::format(" +{:X}={:08X}", i * 4, rd(base + i * 4));
    XELOGE("CACHE-RAW {} @{:08X}:{}", tag, base, s);
  };
  rawrow("mgr+0x28", OBJ + 0x28, 16);  // map(+0x30) + deque(+0x48) headers
  // deque hash-pairs (access order)
  std::string dq;
  const uint32_t n = deque_count > 512 ? 512 : deque_count;  // sanity cap
  for (uint32_t i = 0; i < n; ++i) {
    uint32_t bi = (start + i) / 2;
    if (map_size && bi >= map_size) {
      bi -= map_size;
    }
    const uint32_t block = rd(blockmap + bi * 4);
    const uint32_t addr = block + (i & 1) * 8;
    dq += fmt::format(" [{}]{:08X}:{:08X}", i, rd(addr), rd(addr + 4));
  }
  XELOGE("CACHE-DUMP deque hashpairs:{}", dq);

  // Walk the entry map at OBJ+0x30 (MSVC _Tree, CONFIRMED by live raw dump:
  // _Left@+0, _Parent@+4, _Right@+8, keyLo@+12, keyHi@+16, _Isnil@+25). Map
  // object header is at OBJ+0x30; head=[OBJ+0x34]; root=head._Parent=[head+4].
  // This is the map sub_8245A098 queries per deque entry.
  std::set<uint64_t> map_keys;
  const uint32_t head = rd(OBJ + 0x34);
  const uint32_t root = head ? rd(head + 4) : 0;
  std::vector<uint32_t> stack;
  if (root && (rd(root + 25) & 0xFF) == 0) {
    stack.push_back(root);
  }
  // Hard guards: a corrupted map (cyclic/garbage node pointers -- common at the
  // moment it throws) would otherwise balloon this walk to gigabytes.
  uint32_t visits = 0;
  while (!stack.empty() && map_keys.size() < 4096 && ++visits < 100000 &&
         stack.size() < 100000) {
    const uint32_t nd = stack.back();
    stack.pop_back();
    const uint64_t key = (static_cast<uint64_t>(rd(nd + 12)) << 32) | rd(nd + 16);
    map_keys.insert(key);
    const uint32_t l = rd(nd + 0), r = rd(nd + 8);
    if (l && (rd(l + 25) & 0xFF) == 0) stack.push_back(l);
    if (r && (rd(r + 25) & 0xFF) == 0) stack.push_back(r);
  }
  // For each deque key, flag whether it exists in the persistent map. The
  // orphan(s) = deque keys absent from the map == the cause of the map::at miss.
  std::string orphans;
  uint32_t orphan_count = 0;
  for (uint32_t i = 0; i < n; ++i) {
    uint32_t bi = (start + i) / 2;
    if (map_size && bi >= map_size) bi -= map_size;
    const uint32_t block = rd(blockmap + bi * 4);
    const uint32_t addr = block + (i & 1) * 8;
    const uint64_t key =
        (static_cast<uint64_t>(rd(addr)) << 32) | rd(addr + 4);
    if (!map_keys.count(key)) {
      orphans += fmt::format(" [{}]{:08X}:{:08X}", i, rd(addr), rd(addr + 4));
      ++orphan_count;
    }
  }
  XELOGE("CACHE-DUMP map_keys={} deque_orphans={} (deque keys NOT in map):{}",
         static_cast<uint32_t>(map_keys.size()), orphan_count, orphans);

  // --- SNAPSHOT vs LIVE: prove the TOCTOU race. The flush (sub_8245A098) locks,
  // copies OBJ+0x30 into a temp map at [flush_r31+104], UNLOCKS (0x8245a150),
  // then iterates the live deque doing map::at on the FROZEN snapshot. A
  // concurrent LOCKED add (8245ABD8/8245AD00) pushes a deque + map entry during
  // the unlocked window -> that key is in the LIVE map but NOT the snapshot ->
  // map::at throws. Find the flush frame (its live PC is in the map::at loop);
  // its snapshot map object is at frame_sp+104 (== r26 at the throw).
  uint32_t flush_sp = 0;
  {
    uint32_t sp = static_cast<uint32_t>(ctx->r[1]);
    for (int depth = 0; depth < 128 && sp; ++depth) {
      auto f = kernel_memory()->TranslateVirtual(sp);
      if (!f) break;
      uint32_t nsp = xe::load_and_swap<uint32_t>(f);
      if (nsp <= sp || nsp - sp > 0x1000000) break;
      auto lp = kernel_memory()->TranslateVirtual(nsp - 8);
      uint32_t pc = lp ? xe::load_and_swap<uint32_t>(lp) : 0;
      if (pc >= 0x8245A154u && pc <= 0x8245A1D0u) {  // flush deque/map::at loop
        flush_sp = nsp;
        break;
      }
      sp = nsp;
    }
  }
  if (!flush_sp) {
    XELOGE("CACHE-DUMP flush frame not found on stack (snapshot compare skipped)");
    return;
  }
  rawrow("snapshot@r31+104", flush_sp + 96, 16);  // raw temp-map header region
  const uint32_t snap = flush_sp + 104;  // temp map object [r31+104]
  std::set<uint64_t> snap_keys;
  const uint32_t shead = rd(snap + 4);
  const uint32_t sroot = shead ? rd(shead + 4) : 0;
  std::vector<uint32_t> st;
  if (sroot && (rd(sroot + 25) & 0xFF) == 0) st.push_back(sroot);
  uint32_t svisits = 0;
  while (!st.empty() && snap_keys.size() < 4096 && ++svisits < 100000 &&
         st.size() < 100000) {
    const uint32_t nd = st.back();
    st.pop_back();
    snap_keys.insert((static_cast<uint64_t>(rd(nd + 12)) << 32) | rd(nd + 16));
    const uint32_t l = rd(nd + 0), r = rd(nd + 8);
    if (l && (rd(l + 25) & 0xFF) == 0) st.push_back(l);
    if (r && (rd(r + 25) & 0xFF) == 0) st.push_back(r);
  }
  std::string miss;
  uint32_t miss_count = 0;
  for (uint32_t i = 0; i < n; ++i) {
    uint32_t bi = (start + i) / 2;
    if (map_size && bi >= map_size) bi -= map_size;
    const uint32_t addr = rd(blockmap + bi * 4) + (i & 1) * 8;
    const uint64_t key = (static_cast<uint64_t>(rd(addr)) << 32) | rd(addr + 4);
    if (!snap_keys.count(key)) {
      miss += fmt::format(" [{}]{:08X}:{:08X}(in_live_map={})", i,
                          static_cast<uint32_t>(key >> 32),
                          static_cast<uint32_t>(key), map_keys.count(key) ? 1 : 0);
      ++miss_count;
    }
  }
  XELOGE(
      "CACHE-DUMP flush_sp={:08X} snapshot_keys={} deque_NOT_in_snapshot={} "
      "(these are what map::at throws on; in_live_map=1 => added during the "
      "flush's UNLOCKED window = the TOCTOU race):{}",
      flush_sp, static_cast<uint32_t>(snap_keys.size()), miss_count, miss);
}

// ---------------------------------------------------------------------------
// Fix-A analysis half (read-only): determine which guest stack frame WOULD catch
// the current C++ throw and where it would resume, by parsing the guest's MSVC
// C++ EH tables. Zero behaviour change -- logs WOULD-CATCH so the frame-finding
// can be validated against a live crash before the control-transfer half is
// wired in. Layout (all BE u32 unless noted):
//   FuncInfo (magic 0x19930522): +12 nTryBlocks, +16 pTryBlockMap,
//     +20 nIPMap, +24 pIP2StateMap
//   IP2StateMapEntry(8B): +0 Ip(VA), +4 State(int)
//   TryBlockMapEntry(20B): +0 tryLow, +4 tryHigh, +8 catchHigh, +12 nCatches,
//     +16 pHandlerArray
//   HandlerType(16B): +4 pType(TypeDescriptor; 0=catch(...)), +8 dispCatchObj,
//     +12 addressOfHandler(funclet)
//   CatchableTypeArray: +0 count, +4 CatchableType*[]; CatchableType: +4 type_ptr
namespace {

struct EhFuncInfo {
  uint32_t funcinfo_va;
  uint32_t func_start;      // xenia function containing this FuncInfo's code
  uint32_t first_ip, last_ip;  // IP2State map coverage (fallback PC match)
  uint32_t p_ip, n_ip;      // IP2State map
  uint32_t p_try, n_try;    // try-block map
};

static std::vector<EhFuncInfo>* g_eh_catch_index = nullptr;

static uint32_t EhRd(uint32_t va) {
  auto p = kernel_memory()->TranslateVirtual<xe::be<uint32_t>*>(va);
  return p ? static_cast<uint32_t>(*p) : 0;
}

// xenia function-start containing pc, or 0. Non-analyzing lookup: every frame on
// a live stack has already executed, so its function is known (no side effects).
static uint32_t EhFuncStart(uint32_t pc) {
  auto* f = kernel_state()->processor()->LookupFunction(pc);
  return f ? f->address() : 0;
}

// Build the catch index once: scan .rdata for FuncInfo(magic) with nTry>=1.
static void EhBuildIndex() {
  if (g_eh_catch_index) return;
  g_eh_catch_index = new std::vector<EhFuncInfo>();
  // .rdata bounds from the PE section table (PESEC): addr 82000600 size 1142488.
  const uint32_t lo = 0x82000600u, hi = 0x82000600u + 1142488u;
  for (uint32_t a = lo; a + 28 < hi; a += 4) {
    if (EhRd(a) != 0x19930522u) continue;
    uint32_t n_try = EhRd(a + 12), p_try = EhRd(a + 16);
    uint32_t n_ip = EhRd(a + 20), p_ip = EhRd(a + 24);
    if (!n_try || !p_try || n_try > 64 || !n_ip || !p_ip) continue;
    uint32_t first_ip = EhRd(p_ip);
    uint32_t last_ip = EhRd(p_ip + (n_ip - 1) * 8);
    uint32_t fn = EhFuncStart(first_ip);  // first IP -> its function
    if (!fn) fn = first_ip;               // fall back to the IP itself
    g_eh_catch_index->push_back(
        {a, fn, first_ip, last_ip, p_ip, n_ip, p_try, n_try});
  }
  XELOGE("EH-INDEX built: {} catch-bearing FuncInfos",
         static_cast<uint32_t>(g_eh_catch_index->size()));
}

// State at pc: State of the IP2State entry with the greatest Ip<=pc; -1 if pc
// precedes the first entry (not inside any protected region).
static int EhStateAt(const EhFuncInfo& fi, uint32_t pc) {
  int state = -1;
  uint32_t best_ip = 0;
  for (uint32_t i = 0; i < fi.n_ip; ++i) {
    uint32_t ip = EhRd(fi.p_ip + i * 8);
    if (ip <= pc && ip >= best_ip) {
      best_ip = ip;
      state = static_cast<int>(EhRd(fi.p_ip + i * 8 + 4));
    }
  }
  return state;
}

}  // namespace

// Sentinel return address ExecuteRaw() gives a guest function (matches
// Processor::ExecuteRaw). We force the catching frame's saved-LR slot to this so
// the catch funclet returns to us regardless of how it restores LR.
static constexpr uint32_t kFuncletReturnSentinel = 0xBCBCBCBCu;

// Fix A. Dispatch the current guest C++ throw to the first stack frame that
// catches it, then resume the guest as if that frame had caught-and-returned.
// Returns true if dispatched -- in which case this does NOT return normally: it
// calls XThread::Reenter, which throws FiberReentryException to unwind every
// intervening host/JIT frame before resuming the guest at the catch frame's
// return site. Returns false (falls through to the old crash path) when no
// handler matches or --eh_dispatch=false.
bool DispatchGuestCatch(pointer_t<X_EXCEPTION_RECORD> record,
                        const ppc_context_t& ctx) {
  EhBuildIndex();

  const uint32_t thrown_obj = record->exception_information[1];

  // Every TypeDescriptor the throw can be caught as -> its base-subobject
  // displacement (x_PMD.mdisp), from the throw's CatchableTypeArray.
  std::map<uint32_t, int32_t> catchable;
  uint32_t cta = EhRd(record->exception_information[2] + 12);
  if (cta) {
    uint32_t n = EhRd(cta);
    for (uint32_t i = 0; i < n && i < 32; ++i) {
      uint32_t ct = EhRd(cta + 4 + i * 4);
      if (ct) catchable[EhRd(ct + 4)] = static_cast<int32_t>(EhRd(ct + 8));
    }
  }

  uint32_t sp = static_cast<uint32_t>(ctx->r[1]);
  for (int depth = 0; depth < 128; ++depth) {
    auto frame = kernel_memory()->TranslateVirtual(sp);
    if (!sp || !frame) {
      XELOGE("EH-WALK stop depth={} sp={:08X} (untranslatable)", depth, sp);
      break;
    }
    uint32_t next_sp = xe::load_and_swap<uint32_t>(frame);
    // The cache flush runs on a fiber/task stack; the back-chain can jump a long
    // way (or to a different stack) when crossing into the dispatcher that has
    // the try/catch. Only require it to go UP; allow large gaps.
    if (next_sp <= sp) {
      XELOGE("EH-WALK stop depth={} sp={:08X} next_sp={:08X} (not ascending)",
             depth, sp, next_sp);
      break;
    }
    if (next_sp - sp > 0x1000000) {
      XELOGE("EH-WALK stop depth={} sp={:08X} next_sp={:08X} (gap>16M)", depth,
             sp, next_sp);
      break;
    }
    auto lrp = kernel_memory()->TranslateVirtual(next_sp - 8);
    uint32_t pc = lrp ? xe::load_and_swap<uint32_t>(lrp) : 0;
    uint32_t frame_sp = next_sp;  // SP_F: the catching frame's running SP
    sp = next_sp;
    uint32_t fn = (pc >= 0x82150000 && pc < 0x8284A000) ? EhFuncStart(pc) : 0;
    XELOGE("EH-WALK depth={} SP_F={:08X} pc={:08X} fn={:08X}", depth, frame_sp,
           pc, fn);
    if (pc < 0x82150000 || pc >= 0x8284A000) continue;

    for (const auto& fi : *g_eh_catch_index) {
      // Match the frame to a catch FuncInfo either by xenia's function-start or
      // (robust to xenia splitting funcs/funclets) by the FuncInfo's IP range.
      bool by_fn = fn && fi.func_start == fn;
      bool by_ip = pc >= fi.first_ip && pc <= fi.last_ip;
      if (!by_fn && !by_ip) continue;
      int state = EhStateAt(fi, pc);
      for (uint32_t t = 0; t < fi.n_try; ++t) {
        uint32_t te = fi.p_try + t * 20;
        int try_low = static_cast<int>(EhRd(te));
        int try_high = static_cast<int>(EhRd(te + 4));
        if (state < try_low || state > try_high) continue;
        uint32_t n_catch = EhRd(te + 12), pH = EhRd(te + 16);
        for (uint32_t c = 0; c < n_catch && c < 32; ++c) {
          uint32_t pType = EhRd(pH + c * 16 + 4);
          auto it = (pType == 0) ? catchable.end() : catchable.find(pType);
          if (pType != 0 && it == catchable.end()) continue;
          int32_t mdisp = (it == catchable.end()) ? 0 : it->second;
          uint32_t dispCatchObj = EhRd(pH + c * 16 + 8);
          uint32_t funclet = EhRd(pH + c * 16 + 12);

          // Establisher frame = SP at F's entry = the back-chain word saved at
          // F's SP by its `stwu`. The funclet rebuilds its frame ptr as
          // r31 = r12 - N, and __save/restgprlr save/restore F's nonvolatiles +
          // return address at [establisher-8].
          uint32_t establisher = EhRd(frame_sp);
          uint32_t f_return = EhRd(establisher - 8);  // F's real return address

          XELOGE(
              "GUEST-CATCH frame_pc={:08X} fn={:08X} SP_F={:08X} est={:08X} "
              "f_return={:08X} state={} try{}[{}..{}] catch#{} pType={:08X} "
              "obj@est+{:X} funclet={:08X} dispatch={}",
              pc, fn, frame_sp, establisher, f_return, state, t, try_low,
              try_high, c, pType, dispCatchObj, funclet,
              cvars::eh_dispatch ? 1 : 0);

          if (!cvars::eh_dispatch) return false;
          if (!establisher || !f_return) {
            XELOGE("GUEST-CATCH abort: bad establisher/return frame");
            return false;
          }

          auto store32 = [](uint32_t va, uint32_t val) {
            auto p = kernel_memory()->TranslateVirtual<xe::be<uint32_t>*>(va);
            if (p) *p = val;
          };

          // Hand the caught object (adjusted to the caught base) to the catch.
          // catch(...) (dispCatchObj==0) takes no object.
          if (dispCatchObj != 0) {
            store32(establisher + dispCatchObj,
                    thrown_obj + static_cast<uint32_t>(mdisp));
          }
          // Force the funclet to return to us no matter how it restores LR.
          store32(establisher - 8, kFuncletReturnSentinel);

          // Run the game's own catch funclet in F's frame: r12=r1=establisher.
          // It runs the catch body, restores F's inherited nonvolatiles, and
          // returns (r3 = F's return value).
          ctx->r[12] = establisher;
          ctx->r[1] = establisher;
          ctx->processor->ExecuteRaw(ctx->thread_state, funclet);

          // F has effectively caught-and-returned: resume at F's caller with the
          // funclet's return value. Reenter unwinds all the throw's host/JIT
          // frames first. r1 is already the caller SP (establisher).
          ctx->processor->backend()->PrepareForReentry(ctx.value());
          XELOGE("GUEST-CATCH dispatched -> resuming at f_return={:08X} r3={:08X}",
                 f_return, static_cast<uint32_t>(ctx->r[3]));
          XThread::GetCurrentThread()->Reenter(f_return);
          return true;  // not reached
        }
      }
    }
  }
  XELOGE("GUEST-CATCH none (no matching handler frame found)");
  return false;
}

void LogGuestThrow(pointer_t<X_EXCEPTION_RECORD> record,
                   const ppc_context_t& ctx) {
  const uint32_t thrown_ptr = record->exception_information[1];
  XELOGE("GUEST-THROW type={} object={:08X} lr={:08X}",
         ThrownTypeName(thrown_ptr), thrown_ptr,
         static_cast<uint32_t>(ctx->lr));
  DumpCacheManagerOnThrow(ctx);

  std::string regs;
  for (int i = 3; i <= 31; ++i) {
    regs += fmt::format(" r{}={:08X}", i, static_cast<uint32_t>(ctx->r[i]));
  }
  XELOGE("GUEST-THROW regs:{}", regs);

  // Walk the guest stack. Xenon prologues do `mfspr r12,LR; stw r12,-8(r1)`
  // BEFORE `stwu r1,-N(r1)`, so a frame's return address is stored at
  // [caller_sp - 8] = [([sp]) - 8], NOT [sp+4]. Back chain = [sp]. Filter to
  // .text (0x82150000..0x8284A000).
  std::string frames;
  uint32_t sp = static_cast<uint32_t>(ctx->r[1]);
  for (int depth = 0; depth < 64; ++depth) {
    auto frame = kernel_memory()->TranslateVirtual(sp);
    if (!sp || !frame) {
      break;
    }
    const uint32_t next_sp = xe::load_and_swap<uint32_t>(frame);
    if (next_sp <= sp || next_sp - sp > 0x40000) {
      break;
    }
    auto lrp = kernel_memory()->TranslateVirtual(next_sp - 8);
    if (lrp) {
      const uint32_t lr = xe::load_and_swap<uint32_t>(lrp);
      if (lr >= 0x82150000 && lr < 0x8284A000) {
        frames += fmt::format(" {:08X}", lr);
      }
    }
    sp = next_sp;
  }
  XELOGE("GUEST-THROW guest stack:{}", frames);
}

void HandleCppException(pointer_t<X_EXCEPTION_RECORD> record) {
  // C++ exception.
  // https://blogs.msdn.com/b/oldnewthing/archive/2010/07/30/10044061.aspx
  // http://www.drdobbs.com/visual-c-exception-handling-instrumentat/184416600
  // http://www.openrce.org/articles/full_view/21

  assert_true(record->number_parameters == 3);
  assert_true(record->exception_information[0] == 0x19930520);

  auto thrown_ptr = record->exception_information[1];
  auto thrown = kernel_memory()->TranslateVirtual(thrown_ptr);
  auto vftable_ptr = *reinterpret_cast<xe::be<uint32_t>*>(thrown);

  auto throw_info_ptr = record->exception_information[2];
  auto throw_info =
      kernel_memory()->TranslateVirtual<x_s__ThrowInfo*>(throw_info_ptr);
  auto catchable_types =
      kernel_memory()->TranslateVirtual<x_s__CatchableTypeArray*>(
          throw_info->catchable_type_array_ptr);

  // xe::debugging::Break();
  XELOGE("Guest attempted to throw a C++ exception!");
}

void RtlRaiseException_entry(pointer_t<X_EXCEPTION_RECORD> record,
                             const ppc_context_t& ppc_context) {
  switch (record->code) {
    case 0x406D1388: {
      HandleSetThreadName(record);
      return;
    }
    case 0xE06D7363: {
      // Heavy diagnostics are OFF by default: in a mission the cache flush
      // throws constantly, and these dumps (esp. the cache-manager tree walk on
      // a corrupted map) allocate gigabytes per throw. Stock behaviour is just
      // HandleCppException below.
      if (cvars::cache_throw_diag) {
        LogGuestThrow(record, ppc_context);
      }
      // Fix A: dispatch to the catch handler. On success this does not return
      // (it reenters the guest at the catch frame). Disproven for the cache
      // crash and default-off; also skip its (allocating) frame walk unless a
      // diagnostic/dispatch knob is set.
      if ((cvars::eh_dispatch || cvars::cache_throw_diag) &&
          DispatchGuestCatch(record, ppc_context)) {
        return;
      }
      HandleCppException(record);
      return;
    }
  }

  // TODO(benvanik): unwinding.
  // This is going to suck.
  // xe::debugging::Break();

  // RtlRaiseException definitely wasn't a noreturn function, we can return
  // safe-ish
  XELOGE("Guest attempted to trigger a breakpoint!");
}
DECLARE_XBOXKRNL_EXPORT2(RtlRaiseException, kDebug, kStub, kImportant);

void KeBugCheckEx_entry(dword_t code, dword_t param1, dword_t param2,
                        dword_t param3, dword_t param4) {
  auto msg =
      fmt::format("*** STOP: 0x{:08X} (0x{:08X}, 0x{:08X}, 0x{:08X}, 0x{:08X})",
                  static_cast<uint32_t>(code), static_cast<uint32_t>(param1),
                  static_cast<uint32_t>(param2), static_cast<uint32_t>(param3),
                  static_cast<uint32_t>(param4));
  XELOGE("{}", msg);
  fflush(stdout);

  if (xe::debugging::IsDebuggerAttached()) {
    xe::debugging::Break();
  }

  // Show crash dialog and suspend the guest thread instead of killing the
  // host process.
  auto current_thread = kernel::XThread::GetCurrentThread();
  const auto* emulator = kernel_state()->emulator();
  auto* display_window = emulator->display_window();
  auto* imgui_drawer = emulator->imgui_drawer();
  if (display_window && imgui_drawer) {
    auto dlg_msg = fmt::format(
        "The guest kernel has crashed (KeBugCheck).\n\n{}\n\n"
        "The faulting thread has been suspended.",
        msg);
    display_window->app_context().CallInUIThreadSynchronous(
        [imgui_drawer, &dlg_msg]() {
          xe::ui::ImGuiDialog::ShowMessageBox(imgui_drawer,
                                              "Guest Kernel Crash", dlg_msg);
        });
  }

  if (current_thread) {
    current_thread->Suspend(nullptr);
  }
}
DECLARE_XBOXKRNL_EXPORT2(KeBugCheckEx, kDebug, kStub, kImportant);

void KeBugCheck_entry(dword_t code) { KeBugCheckEx_entry(code, 0, 0, 0, 0); }
DECLARE_XBOXKRNL_EXPORT2(KeBugCheck, kDebug, kImplemented, kImportant);

}  // namespace xboxkrnl
}  // namespace kernel
}  // namespace xe

DECLARE_XBOXKRNL_EMPTY_REGISTER_EXPORTS(Debug);