Update libcxx to 16 Feb 2025

```
[libc++] Fix initialization-order-fiasco with iostream.cpp constructors (#126995)
[libc++] Fixes (|multi)_set spaceship operator. (#127326)
[libc++] Move unused basic_string function definition to the dylib sources (#126219)
[libc++] Avoid including <features.h> on arbitrary platforms (#125587)
[libc++][format] Disables the FTM on older MacOS versions. (#126547)
[libcxx] Add a missing include for __enable_if_t (#127016)
[libcxx] Add a missing include for __bit_iterator (#127015)
[libc++] Remove conditional for attributes that are always available (#126879)
[libc++] Remove obsolete guards for join_view being experimental (#126697)
[libc++] Extract destroy algorithms into separate headers (#126449)
[libc++][chrono] implements TAI clock. (#125550)
[libc++] Remove basic_string::__clear_and_shrink (#126050)
[libc++] Support constexpr for std::stable_sort in radix sort branch (#125284)
[libc++] Replace __is_trivially_relocatable by is_trivially_copyable (#124970)
[lib++][Format] Updates Unicode database. (#125712)
[libc++] Fix UB in bitwise logic of {std, ranges}::{fill, fill_n} algorithms (#122410)
[libc++] Also provide an alignment assumption for vector in C++03 mode (#124839)
[libc++] Fix stray usage of _LIBCPP_HAS_NO_WIDE_CHARACTERS on Windows
[libc++][TZDB] Fixes %z escaping. (#125399)
[libc++] Decrease instantiation cost of __constexpr_memmove (#125109)
[libc++] Implement N4258(Cleaning-up noexcept in the Library) (#120312)
[libc++] Optimize ranges::copy_backward for vector<bool>::iterator (#121026)
[libc++] Optimize ranges::copy{, _n} for vector<bool>::iterator (#121013)
[libc++] Refactor num_get optimization to not be ABI breaking (#121690)
[libc++] Simplify the implementation of iostream.cpp (#124103)
[libc++] Simplify vector<bool>::__construct_at_end (#119632)
[libc++] Remove some private symbols from the ABI (#121497)
[libcxx] Use _ftelli64/_fseeki64 on Windows (#123128)
[libc++] Disable CFI in __libcpp_allocate (#124805)
[libc++] Remove Android header no longer in use (#124691)
[libc++] Add more missing bits to the locale base API (#122531)
[libc++] implement std::flat_multimap (#113835)
[libc++][format][3/3] Improves formatting performance. (#108990)
[libc++] Reduce std::conjunction overhead (#124259)
[libc++][chrono] implements UTC clock. (#90393)
[libc++] Switch experimental library macros to 0/1 macros (#124030)
[libc++] Use [[clang::no_specializations]] to diagnose invalid user specializations (#118167)
[libc++] Inline basic_streambuf functions (#123379)
[libc++] Remove a few unused includes (#124025)
[libc++] Remove support for Android 4 and older (#124062)
[libc++] Avoid unnecessary instantiations for __copy_cvref_t (#123718)
[libc++] Fix input-only range handling for vector (#116157)
[libc++] Fix input-only range handling for basic_string (#116890)
[libc++] Fix no-op shrink_to_fit for vector<bool> (#120495)
[libc++] Another _LIBCPP_NODEBUG fix
[libc++] Add missing _LIBCPP_NODEBUG on internal alias
[libc++] Define an internal API for std::invoke and friends (#116637)
[libc++] Fix vector sanitization annotations on destruction (#121031)
[libc++] remove yield from atomic::wait (#120012)
[libc++] Don't implement <stdatomic.h> before C++23 (#123130)
[libc++] Enable _LIBCPP_NODEBUG again (#123318)
[libc++] Simplify when the sized global deallocations overloads are available (#114667)
```
commit_hash:c4dee431e33408d110c123c1ea677d3897276e0e

Author: 4JustMe4

build/sysincl/stl-to-libcxx.yml

@@ -468,11 +468,13 @@
   - __chrono/steady_clock.h:                               contrib/libs/cxxsupp/libcxx/include/__chrono/steady_clock.h
   - __chrono/sys_info.h:                                   contrib/libs/cxxsupp/libcxx/include/__chrono/sys_info.h
   - __chrono/system_clock.h:                               contrib/libs/cxxsupp/libcxx/include/__chrono/system_clock.h
+  - __chrono/tai_clock.h:                                  contrib/libs/cxxsupp/libcxx/include/__chrono/tai_clock.h
   - __chrono/time_point.h:                                 contrib/libs/cxxsupp/libcxx/include/__chrono/time_point.h
   - __chrono/time_zone.h:                                  contrib/libs/cxxsupp/libcxx/include/__chrono/time_zone.h
   - __chrono/time_zone_link.h:                             contrib/libs/cxxsupp/libcxx/include/__chrono/time_zone_link.h
   - __chrono/tzdb.h:                                       contrib/libs/cxxsupp/libcxx/include/__chrono/tzdb.h
   - __chrono/tzdb_list.h:                                  contrib/libs/cxxsupp/libcxx/include/__chrono/tzdb_list.h
+  - __chrono/utc_clock.h:                                  contrib/libs/cxxsupp/libcxx/include/__chrono/utc_clock.h
   - __chrono/weekday.h:                                    contrib/libs/cxxsupp/libcxx/include/__chrono/weekday.h
   - __chrono/year.h:                                       contrib/libs/cxxsupp/libcxx/include/__chrono/year.h
   - __chrono/year_month.h:                                 contrib/libs/cxxsupp/libcxx/include/__chrono/year_month.h
@@ -558,8 +560,11 @@
   - __filesystem/space_info.h:                             contrib/libs/cxxsupp/libcxx/include/__filesystem/space_info.h
   - __filesystem/u8path.h:                                 contrib/libs/cxxsupp/libcxx/include/__filesystem/u8path.h
   - __flat_map/flat_map.h:                                 contrib/libs/cxxsupp/libcxx/include/__flat_map/flat_map.h
+  - __flat_map/flat_multimap.h:                            contrib/libs/cxxsupp/libcxx/include/__flat_map/flat_multimap.h
   - __flat_map/key_value_iterator.h:                       contrib/libs/cxxsupp/libcxx/include/__flat_map/key_value_iterator.h
+  - __flat_map/sorted_equivalent.h:                        contrib/libs/cxxsupp/libcxx/include/__flat_map/sorted_equivalent.h
   - __flat_map/sorted_unique.h:                            contrib/libs/cxxsupp/libcxx/include/__flat_map/sorted_unique.h
+  - __flat_map/utils.h:                                    contrib/libs/cxxsupp/libcxx/include/__flat_map/utils.h
   - __format/buffer.h:                                     contrib/libs/cxxsupp/libcxx/include/__format/buffer.h
   - __format/concepts.h:                                   contrib/libs/cxxsupp/libcxx/include/__format/concepts.h
   - __format/container_adaptor.h:                          contrib/libs/cxxsupp/libcxx/include/__format/container_adaptor.h
@@ -747,13 +752,15 @@
   - __memory/compressed_pair.h:                            contrib/libs/cxxsupp/libcxx/include/__memory/compressed_pair.h
   - __memory/concepts.h:                                   contrib/libs/cxxsupp/libcxx/include/__memory/concepts.h
   - __memory/construct_at.h:                               contrib/libs/cxxsupp/libcxx/include/__memory/construct_at.h
+  - __memory/destroy.h:                                    contrib/libs/cxxsupp/libcxx/include/__memory/destroy.h
   - __memory/destruct_n.h:                                 contrib/libs/cxxsupp/libcxx/include/__memory/destruct_n.h
   - __memory/inout_ptr.h:                                  contrib/libs/cxxsupp/libcxx/include/__memory/inout_ptr.h
   - __memory/noexcept_move_assign_container.h:             contrib/libs/cxxsupp/libcxx/include/__memory/noexcept_move_assign_container.h
   - __memory/out_ptr.h:                                    contrib/libs/cxxsupp/libcxx/include/__memory/out_ptr.h
   - __memory/pointer_safety.h:                             contrib/libs/cxxsupp/libcxx/include/__memory/pointer_safety.h
   - __memory/pointer_traits.h:                             contrib/libs/cxxsupp/libcxx/include/__memory/pointer_traits.h
   - __memory/ranges_construct_at.h:                        contrib/libs/cxxsupp/libcxx/include/__memory/ranges_construct_at.h
+  - __memory/ranges_destroy.h:                             contrib/libs/cxxsupp/libcxx/include/__memory/ranges_destroy.h
   - __memory/ranges_uninitialized_algorithms.h:            contrib/libs/cxxsupp/libcxx/include/__memory/ranges_uninitialized_algorithms.h
   - __memory/raw_storage_iterator.h:                       contrib/libs/cxxsupp/libcxx/include/__memory/raw_storage_iterator.h
   - __memory/shared_count.h:                               contrib/libs/cxxsupp/libcxx/include/__memory/shared_count.h

contrib/libs/cxxsupp/libcxx/include/__algorithm/copy.h

@@ -13,8 +13,10 @@
 #include <__algorithm/for_each_segment.h>
 #include <__algorithm/min.h>
 #include <__config>
+#include <__fwd/bit_reference.h>
 #include <__iterator/iterator_traits.h>
 #include <__iterator/segmented_iterator.h>
+#include <__memory/pointer_traits.h>
 #include <__type_traits/common_type.h>
 #include <__type_traits/enable_if.h>
 #include <__utility/move.h>
@@ -29,9 +31,129 @@ _LIBCPP_PUSH_MACROS
 
 _LIBCPP_BEGIN_NAMESPACE_STD
 
+template <class _InputIterator, class _OutputIterator>
+inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 _OutputIterator
+copy(_InputIterator __first, _InputIterator __last, _OutputIterator __result);
+
 template <class _InIter, class _Sent, class _OutIter>
 inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 pair<_InIter, _OutIter> __copy(_InIter, _Sent, _OutIter);
 
+template <class _Cp, bool _IsConst>
+_LIBCPP_CONSTEXPR_SINCE_CXX20 _LIBCPP_HIDE_FROM_ABI __bit_iterator<_Cp, false> __copy_aligned(
+    __bit_iterator<_Cp, _IsConst> __first, __bit_iterator<_Cp, _IsConst> __last, __bit_iterator<_Cp, false> __result) {
+  using _In             = __bit_iterator<_Cp, _IsConst>;
+  using difference_type = typename _In::difference_type;
+  using __storage_type  = typename _In::__storage_type;
+
+  const int __bits_per_word = _In::__bits_per_word;
+  difference_type __n       = __last - __first;
+  if (__n > 0) {
+    // do first word
+    if (__first.__ctz_ != 0) {
+      unsigned __clz       = __bits_per_word - __first.__ctz_;
+      difference_type __dn = std::min(static_cast<difference_type>(__clz), __n);
+      __n -= __dn;
+      __storage_type __m = (~__storage_type(0) << __first.__ctz_) & (~__storage_type(0) >> (__clz - __dn));
+      __storage_type __b = *__first.__seg_ & __m;
+      *__result.__seg_ &= ~__m;
+      *__result.__seg_ |= __b;
+      __result.__seg_ += (__dn + __result.__ctz_) / __bits_per_word;
+      __result.__ctz_ = static_cast<unsigned>((__dn + __result.__ctz_) % __bits_per_word);
+      ++__first.__seg_;
+      // __first.__ctz_ = 0;
+    }
+    // __first.__ctz_ == 0;
+    // do middle words
+    __storage_type __nw = __n / __bits_per_word;
+    std::copy(std::__to_address(__first.__seg_),
+              std::__to_address(__first.__seg_ + __nw),
+              std::__to_address(__result.__seg_));
+    __n -= __nw * __bits_per_word;
+    __result.__seg_ += __nw;
+    // do last word
+    if (__n > 0) {
+      __first.__seg_ += __nw;
+      __storage_type __m = ~__storage_type(0) >> (__bits_per_word - __n);
+      __storage_type __b = *__first.__seg_ & __m;
+      *__result.__seg_ &= ~__m;
+      *__result.__seg_ |= __b;
+      __result.__ctz_ = static_cast<unsigned>(__n);
+    }
+  }
+  return __result;
+}
+
+template <class _Cp, bool _IsConst>
+_LIBCPP_CONSTEXPR_SINCE_CXX20 _LIBCPP_HIDE_FROM_ABI __bit_iterator<_Cp, false> __copy_unaligned(
+    __bit_iterator<_Cp, _IsConst> __first, __bit_iterator<_Cp, _IsConst> __last, __bit_iterator<_Cp, false> __result) {
+  using _In             = __bit_iterator<_Cp, _IsConst>;
+  using difference_type = typename _In::difference_type;
+  using __storage_type  = typename _In::__storage_type;
+
+  const int __bits_per_word = _In::__bits_per_word;
+  difference_type __n       = __last - __first;
+  if (__n > 0) {
+    // do first word
+    if (__first.__ctz_ != 0) {
+      unsigned __clz_f     = __bits_per_word - __first.__ctz_;
+      difference_type __dn = std::min(static_cast<difference_type>(__clz_f), __n);
+      __n -= __dn;
+      __storage_type __m   = (~__storage_type(0) << __first.__ctz_) & (~__storage_type(0) >> (__clz_f - __dn));
+      __storage_type __b   = *__first.__seg_ & __m;
+      unsigned __clz_r     = __bits_per_word - __result.__ctz_;
+      __storage_type __ddn = std::min<__storage_type>(__dn, __clz_r);
+      __m                  = (~__storage_type(0) << __result.__ctz_) & (~__storage_type(0) >> (__clz_r - __ddn));
+      *__result.__seg_ &= ~__m;
+      if (__result.__ctz_ > __first.__ctz_)
+        *__result.__seg_ |= __b << (__result.__ctz_ - __first.__ctz_);
+      else
+        *__result.__seg_ |= __b >> (__first.__ctz_ - __result.__ctz_);
+      __result.__seg_ += (__ddn + __result.__ctz_) / __bits_per_word;
+      __result.__ctz_ = static_cast<unsigned>((__ddn + __result.__ctz_) % __bits_per_word);
+      __dn -= __ddn;
+      if (__dn > 0) {
+        __m = ~__storage_type(0) >> (__bits_per_word - __dn);
+        *__result.__seg_ &= ~__m;
+        *__result.__seg_ |= __b >> (__first.__ctz_ + __ddn);
+        __result.__ctz_ = static_cast<unsigned>(__dn);
+      }
+      ++__first.__seg_;
+      // __first.__ctz_ = 0;
+    }
+    // __first.__ctz_ == 0;
+    // do middle words
+    unsigned __clz_r   = __bits_per_word - __result.__ctz_;
+    __storage_type __m = ~__storage_type(0) << __result.__ctz_;
+    for (; __n >= __bits_per_word; __n -= __bits_per_word, ++__first.__seg_) {
+      __storage_type __b = *__first.__seg_;
+      *__result.__seg_ &= ~__m;
+      *__result.__seg_ |= __b << __result.__ctz_;
+      ++__result.__seg_;
+      *__result.__seg_ &= __m;
+      *__result.__seg_ |= __b >> __clz_r;
+    }
+    // do last word
+    if (__n > 0) {
+      __m                 = ~__storage_type(0) >> (__bits_per_word - __n);
+      __storage_type __b  = *__first.__seg_ & __m;
+      __storage_type __dn = std::min(__n, static_cast<difference_type>(__clz_r));
+      __m                 = (~__storage_type(0) << __result.__ctz_) & (~__storage_type(0) >> (__clz_r - __dn));
+      *__result.__seg_ &= ~__m;
+      *__result.__seg_ |= __b << __result.__ctz_;
+      __result.__seg_ += (__dn + __result.__ctz_) / __bits_per_word;
+      __result.__ctz_ = static_cast<unsigned>((__dn + __result.__ctz_) % __bits_per_word);
+      __n -= __dn;
+      if (__n > 0) {
+        __m = ~__storage_type(0) >> (__bits_per_word - __n);
+        *__result.__seg_ &= ~__m;
+        *__result.__seg_ |= __b >> __dn;
+        __result.__ctz_ = static_cast<unsigned>(__n);
+      }
+    }
+  }
+  return __result;
+}
+
 struct __copy_impl {
   template <class _InIter, class _Sent, class _OutIter>
   _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 pair<_InIter, _OutIter>
@@ -95,6 +217,16 @@ struct __copy_impl {
     }
   }
 
+  template <class _Cp, bool _IsConst>
+  _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 pair<__bit_iterator<_Cp, _IsConst>, __bit_iterator<_Cp, false> >
+  operator()(__bit_iterator<_Cp, _IsConst> __first,
+             __bit_iterator<_Cp, _IsConst> __last,
+             __bit_iterator<_Cp, false> __result) const {
+    if (__first.__ctz_ == __result.__ctz_)
+      return std::make_pair(__last, std::__copy_aligned(__first, __last, __result));
+    return std::make_pair(__last, std::__copy_unaligned(__first, __last, __result));
+  }
+
   // At this point, the iterators have been unwrapped so any `contiguous_iterator` has been unwrapped to a pointer.
   template <class _In, class _Out, __enable_if_t<__can_lower_copy_assignment_to_memmove<_In, _Out>::value, int> = 0>
   _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 pair<_In*, _Out*>
@@ -110,7 +242,7 @@ __copy(_InIter __first, _Sent __last, _OutIter __result) {
 }
 
 template <class _InputIterator, class _OutputIterator>
-inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 _OutputIterator
+_LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 _OutputIterator
 copy(_InputIterator __first, _InputIterator __last, _OutputIterator __result) {
   return std::__copy(__first, __last, __result).second;
 }

contrib/libs/cxxsupp/libcxx/include/__algorithm/copy_backward.h

@@ -10,11 +10,14 @@
 #define _LIBCPP___ALGORITHM_COPY_BACKWARD_H
 
 #include <__algorithm/copy_move_common.h>
+#include <__algorithm/copy_n.h>
 #include <__algorithm/iterator_operations.h>
 #include <__algorithm/min.h>
 #include <__config>
+#include <__fwd/bit_reference.h>
 #include <__iterator/iterator_traits.h>
 #include <__iterator/segmented_iterator.h>
+#include <__memory/pointer_traits.h>
 #include <__type_traits/common_type.h>
 #include <__type_traits/enable_if.h>
 #include <__type_traits/is_constructible.h>
@@ -34,6 +37,124 @@ template <class _AlgPolicy, class _InIter, class _Sent, class _OutIter>
 _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 pair<_InIter, _OutIter>
 __copy_backward(_InIter __first, _Sent __last, _OutIter __result);
 
+template <class _Cp, bool _IsConst>
+_LIBCPP_CONSTEXPR_SINCE_CXX20 _LIBCPP_HIDE_FROM_ABI __bit_iterator<_Cp, false> __copy_backward_aligned(
+    __bit_iterator<_Cp, _IsConst> __first, __bit_iterator<_Cp, _IsConst> __last, __bit_iterator<_Cp, false> __result) {
+  using _In             = __bit_iterator<_Cp, _IsConst>;
+  using difference_type = typename _In::difference_type;
+  using __storage_type  = typename _In::__storage_type;
+
+  const int __bits_per_word = _In::__bits_per_word;
+  difference_type __n       = __last - __first;
+  if (__n > 0) {
+    // do first word
+    if (__last.__ctz_ != 0) {
+      difference_type __dn = std::min(static_cast<difference_type>(__last.__ctz_), __n);
+      __n -= __dn;
+      unsigned __clz     = __bits_per_word - __last.__ctz_;
+      __storage_type __m = (~__storage_type(0) << (__last.__ctz_ - __dn)) & (~__storage_type(0) >> __clz);
+      __storage_type __b = *__last.__seg_ & __m;
+      *__result.__seg_ &= ~__m;
+      *__result.__seg_ |= __b;
+      __result.__ctz_ = static_cast<unsigned>(((-__dn & (__bits_per_word - 1)) + __result.__ctz_) % __bits_per_word);
+      // __last.__ctz_ = 0
+    }
+    // __last.__ctz_ == 0 || __n == 0
+    // __result.__ctz_ == 0 || __n == 0
+    // do middle words
+    __storage_type __nw = __n / __bits_per_word;
+    __result.__seg_ -= __nw;
+    __last.__seg_ -= __nw;
+    std::copy_n(std::__to_address(__last.__seg_), __nw, std::__to_address(__result.__seg_));
+    __n -= __nw * __bits_per_word;
+    // do last word
+    if (__n > 0) {
+      __storage_type __m = ~__storage_type(0) << (__bits_per_word - __n);
+      __storage_type __b = *--__last.__seg_ & __m;
+      *--__result.__seg_ &= ~__m;
+      *__result.__seg_ |= __b;
+      __result.__ctz_ = static_cast<unsigned>(-__n & (__bits_per_word - 1));
+    }
+  }
+  return __result;
+}
+
+template <class _Cp, bool _IsConst>
+_LIBCPP_CONSTEXPR_SINCE_CXX20 _LIBCPP_HIDE_FROM_ABI __bit_iterator<_Cp, false> __copy_backward_unaligned(
+    __bit_iterator<_Cp, _IsConst> __first, __bit_iterator<_Cp, _IsConst> __last, __bit_iterator<_Cp, false> __result) {
+  using _In             = __bit_iterator<_Cp, _IsConst>;
+  using difference_type = typename _In::difference_type;
+  using __storage_type  = typename _In::__storage_type;
+
+  const int __bits_per_word = _In::__bits_per_word;
+  difference_type __n       = __last - __first;
+  if (__n > 0) {
+    // do first word
+    if (__last.__ctz_ != 0) {
+      difference_type __dn = std::min(static_cast<difference_type>(__last.__ctz_), __n);
+      __n -= __dn;
+      unsigned __clz_l     = __bits_per_word - __last.__ctz_;
+      __storage_type __m   = (~__storage_type(0) << (__last.__ctz_ - __dn)) & (~__storage_type(0) >> __clz_l);
+      __storage_type __b   = *__last.__seg_ & __m;
+      unsigned __clz_r     = __bits_per_word - __result.__ctz_;
+      __storage_type __ddn = std::min(__dn, static_cast<difference_type>(__result.__ctz_));
+      if (__ddn > 0) {
+        __m = (~__storage_type(0) << (__result.__ctz_ - __ddn)) & (~__storage_type(0) >> __clz_r);
+        *__result.__seg_ &= ~__m;
+        if (__result.__ctz_ > __last.__ctz_)
+          *__result.__seg_ |= __b << (__result.__ctz_ - __last.__ctz_);
+        else
+          *__result.__seg_ |= __b >> (__last.__ctz_ - __result.__ctz_);
+        __result.__ctz_ = static_cast<unsigned>(((-__ddn & (__bits_per_word - 1)) + __result.__ctz_) % __bits_per_word);
+        __dn -= __ddn;
+      }
+      if (__dn > 0) {
+        // __result.__ctz_ == 0
+        --__result.__seg_;
+        __result.__ctz_ = static_cast<unsigned>(-__dn & (__bits_per_word - 1));
+        __m             = ~__storage_type(0) << __result.__ctz_;
+        *__result.__seg_ &= ~__m;
+        __last.__ctz_ -= __dn + __ddn;
+        *__result.__seg_ |= __b << (__result.__ctz_ - __last.__ctz_);
+      }
+      // __last.__ctz_ = 0
+    }
+    // __last.__ctz_ == 0 || __n == 0
+    // __result.__ctz_ != 0 || __n == 0
+    // do middle words
+    unsigned __clz_r   = __bits_per_word - __result.__ctz_;
+    __storage_type __m = ~__storage_type(0) >> __clz_r;
+    for (; __n >= __bits_per_word; __n -= __bits_per_word) {
+      __storage_type __b = *--__last.__seg_;
+      *__result.__seg_ &= ~__m;
+      *__result.__seg_ |= __b >> __clz_r;
+      *--__result.__seg_ &= __m;
+      *__result.__seg_ |= __b << __result.__ctz_;
+    }
+    // do last word
+    if (__n > 0) {
+      __m                 = ~__storage_type(0) << (__bits_per_word - __n);
+      __storage_type __b  = *--__last.__seg_ & __m;
+      __clz_r             = __bits_per_word - __result.__ctz_;
+      __storage_type __dn = std::min(__n, static_cast<difference_type>(__result.__ctz_));
+      __m                 = (~__storage_type(0) << (__result.__ctz_ - __dn)) & (~__storage_type(0) >> __clz_r);
+      *__result.__seg_ &= ~__m;
+      *__result.__seg_ |= __b >> (__bits_per_word - __result.__ctz_);
+      __result.__ctz_ = static_cast<unsigned>(((-__dn & (__bits_per_word - 1)) + __result.__ctz_) % __bits_per_word);
+      __n -= __dn;
+      if (__n > 0) {
+        // __result.__ctz_ == 0
+        --__result.__seg_;
+        __result.__ctz_ = static_cast<unsigned>(-__n & (__bits_per_word - 1));
+        __m             = ~__storage_type(0) << __result.__ctz_;
+        *__result.__seg_ &= ~__m;
+        *__result.__seg_ |= __b << (__result.__ctz_ - (__bits_per_word - __n - __dn));
+      }
+    }
+  }
+  return __result;
+}
+
 template <class _AlgPolicy>
 struct __copy_backward_impl {
   template <class _InIter, class _Sent, class _OutIter>
@@ -107,6 +228,16 @@ struct __copy_backward_impl {
     }
   }
 
+  template <class _Cp, bool _IsConst>
+  _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 pair<__bit_iterator<_Cp, _IsConst>, __bit_iterator<_Cp, false> >
+  operator()(__bit_iterator<_Cp, _IsConst> __first,
+             __bit_iterator<_Cp, _IsConst> __last,
+             __bit_iterator<_Cp, false> __result) {
+    if (__last.__ctz_ == __result.__ctz_)
+      return std::make_pair(__last, std::__copy_backward_aligned(__first, __last, __result));
+    return std::make_pair(__last, std::__copy_backward_unaligned(__first, __last, __result));
+  }
+
   // At this point, the iterators have been unwrapped so any `contiguous_iterator` has been unwrapped to a pointer.
   template <class _In, class _Out, __enable_if_t<__can_lower_copy_assignment_to_memmove<_In, _Out>::value, int> = 0>
   _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 pair<_In*, _Out*>