diff --git a/libcxx/benchmarks/CMakeLists.txt b/libcxx/benchmarks/CMakeLists.txt
--- a/libcxx/benchmarks/CMakeLists.txt
+++ b/libcxx/benchmarks/CMakeLists.txt
@@ -159,6 +159,7 @@
 set(BENCHMARK_TESTS
     algorithms.partition_point.bench.cpp
     algorithms/equal.bench.cpp
+    algorithms/for_each.bench.cpp
     algorithms/lower_bound.bench.cpp
     algorithms/make_heap.bench.cpp
     algorithms/make_heap_then_sort_heap.bench.cpp
diff --git a/libcxx/benchmarks/algorithms/for_each.bench.cpp b/libcxx/benchmarks/algorithms/for_each.bench.cpp
new file mode 100644
--- /dev/null
+++ b/libcxx/benchmarks/algorithms/for_each.bench.cpp
@@ -0,0 +1,24 @@
+//===----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include <algorithm>
+#include <benchmark/benchmark.h>
+#include <deque>
+
+static void bm_for_each(benchmark::State& state) {
+  std::deque<char> vec1(state.range(), '1');
+  for (auto _ : state) {
+    benchmark::DoNotOptimize(vec1);
+    benchmark::DoNotOptimize(std::for_each(vec1.begin(), vec1.end(), [](char& v) {
+      v = std::clamp(v, (char)10, (char)100);
+    }));
+  }
+}
+BENCHMARK(bm_for_each)->DenseRange(1, 8)->Range(16, 1 << 20);
+
+BENCHMARK_MAIN();
diff --git a/libcxx/include/__algorithm/for_each.h b/libcxx/include/__algorithm/for_each.h
--- a/libcxx/include/__algorithm/for_each.h
+++ b/libcxx/include/__algorithm/for_each.h
@@ -10,7 +10,11 @@
 #ifndef _LIBCPP___ALGORITHM_FOR_EACH_H
 #define _LIBCPP___ALGORITHM_FOR_EACH_H
 
+#include <__algorithm/for_each_segment.h>
 #include <__config>
+#include <__iterator/segmented_iterator.h>
+#include <__type_traits/enable_if.h>
+#include <__utility/move.h>
 
 #if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
 #  pragma GCC system_header
@@ -19,14 +23,25 @@
 _LIBCPP_BEGIN_NAMESPACE_STD
 
 template <class _InputIterator, class _Function>
-inline _LIBCPP_INLINE_VISIBILITY _LIBCPP_CONSTEXPR_SINCE_CXX20 _Function for_each(_InputIterator __first,
-                                                                                  _InputIterator __last,
-                                                                                  _Function __f) {
+_LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 _Function
+for_each(_InputIterator __first, _InputIterator __last, _Function __f) {
   for (; __first != __last; ++__first)
     __f(*__first);
   return __f;
 }
 
+#if _LIBCPP_STD_VER >= 20
+template <class _SegmentedIterator, class _Function>
+  requires __is_segmented_iterator<_SegmentedIterator>::value
+_LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 _Function
+for_each(_SegmentedIterator __first, _SegmentedIterator __last, _Function __func) {
+  std::__for_each_segment(__first, __last, [&](auto __lfirst, auto __llast) {
+    __func = std::for_each(__lfirst, __llast, std::move(__func));
+  });
+  return __func;
+}
+#endif // _LIBCPP_STD_VER >= 14
+
 _LIBCPP_END_NAMESPACE_STD
 
 #endif // _LIBCPP___ALGORITHM_FOR_EACH_H