Force inlining of the serializer helpers only in optimized builds

The seven serializer helpers marked JSON_HEDLEY_ALWAYS_INLINE are inlined
at -O0 as well, and GCC and Clang give every inlined copy its own stack
slots there. That made the recursive frame of dump_container() 2304 bytes
with Clang 21 (2048 with GCC 16), against 480 bytes in 3.12.0, so dump()
of a value nested beyond the default recursion depth limit needed 288 KiB
of stack in an unoptimized build and crashed in a 128 KiB musl thread.

Define JSON_INTERNAL_SERIALIZER_INLINE as JSON_HEDLEY_ALWAYS_INLINE when
__OPTIMIZE__ (or _MSC_VER) is defined and as plain inline otherwise, and
use it for these helpers. The frame drops to 320 bytes and dump() needs
48 KiB at the default limit. The -O2 object code is unchanged with Clang 21
and GCC 16.

Update the stack tables in json_recursion_depth_limit.md and
untrusted_input.md: copying and conversion are now the most demanding
operations at -O0.

Fixes #6116.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

.github/workflows/ubuntu.yml

@@ -25,7 +25,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -38,7 +38,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Check that Meson and pkg-config offer the CMake options
         run: make check_build_options
       - name: Install Meson
@@ -92,7 +92,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -123,7 +123,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -142,7 +142,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -168,7 +168,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -244,7 +244,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Run CMake
         run: CXX=g++-${{ matrix.compiler }} cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -262,7 +262,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -279,7 +279,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Disable filesystem support (std::filesystem is unusable) for clang 7 / 8 / 9 / 10
         run: echo "JSON_FORCED_GLOBAL_COMPILE_OPTIONS=-DJSON_HAS_FILESYSTEM=0;-DJSON_HAS_EXPERIMENTAL_FILESYSTEM=0" >> "$GITHUB_ENV"
         if: ${{ matrix.compiler == '7' || matrix.compiler == '8' || matrix.compiler == '9' || matrix.compiler == '10' }}
@@ -299,7 +299,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -319,7 +319,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build with libc++
@@ -346,7 +346,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -362,11 +362,13 @@ jobs:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           persist-credentials: false
-      # The module test uses `import std;`, which needs CMake 4.5 or newer.
-      - name: Get CMake 4.5+ and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+      # The module test uses `import std;`, which needs CMake's experimental
+      # import-std support. Its opt-in token is CMake-version-specific, so pin
+      # CMake to the version whose token is set in tests/module_cpp20/CMakeLists.txt.
+      - name: Get pinned CMake and ninja
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
         with:
-          cmakeVersion: '^4.5.0'
+          cmakeVersion: 4.3.4
       # Clang: the std library module is provided by libc++ (the image's libstdc++
       # ships none), and the image's libc++ module manifest has a broken relative
       # path — repoint it at the real module sources.
@@ -390,7 +392,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -407,7 +409,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -421,7 +423,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Run CMake
         run: cmake -S . -B build -DJSON_CI=On
       - name: Build
@@ -441,7 +443,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Run CMake
         run: cmake -S . -B build -DCMAKE_TOOLCHAIN_FILE=$EMSDK/upstream/emscripten/cmake/Modules/Platform/Emscripten.cmake -GNinja
       - name: Build
@@ -482,7 +484,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Check that the job runs natively on arm64
         run: uname -m && test "$(uname -m)" = aarch64
       - name: Run CMake

.github/workflows/windows.yml

@@ -90,7 +90,7 @@ jobs:
         with:
           persist-credentials: false
       - name: Get latest CMake and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
       - name: Set extra CXX_FLAGS for latest std_version
         # /wd5285 silences C5285 emitted by the bundled third-party doctest.h, which
         # specializes std::tuple (newly diagnosed by the VS2026 v145 toolset)
@@ -212,11 +212,13 @@ jobs:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           persist-credentials: false
-      # The module test uses `import std;`, which needs CMake 4.5 or newer.
-      - name: Get CMake 4.5+ and ninja
-        uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
+      # The module test uses `import std;`, which needs CMake's experimental
+      # import-std support. Its opt-in token is CMake-version-specific, so pin
+      # CMake to the version whose token is set in tests/module_cpp20/CMakeLists.txt.
+      - name: Get pinned CMake and ninja
+        uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
         with:
-          cmakeVersion: '^4.5.0'
+          cmakeVersion: 4.3.4
       # CMAKE_CXX_FLAGS replaces CMake's MSVC defaults (which include /EHsc), and
       # ci_module_cpp20 forwards it to the module build, so list /EHsc explicitly
       - name: Run CMake (Debug)

README.md

@@ -165,8 +165,7 @@ std::ifstream f("example.json");
 json data = json::parse(f);
 ```
 
-If using modules (enabled with `NLOHMANN_JSON_BUILD_MODULES`; `import std;` needs CMake 4.5 or newer, see the
-[modules documentation](https://json.nlohmann.me/features/modules/)), this example becomes:
+If using modules (enabled with `NLOHMANN_JSON_BUILD_MODULES`), this example becomes:
 ```cpp
 import std;
 import nlohmann.json;

docs/mkdocs/docs/api/macros/json_recursion_depth_limit.md

@@ -27,7 +27,7 @@ comparison of two [`json_view`](../basic_json_view/index.md) documents has a fix
 and does not depend on it either.
 
 The call stack that these operations need grows with the limit: roughly *a few kilobytes plus a cost per level times the
-limit*, where the cost per level is up to about 2.3 KiB in an unoptimized and up to about 0.5 KiB in an optimized build
+limit*, where the cost per level is up to about 1.8 KiB in an unoptimized and up to about 0.5 KiB in an optimized build
 (see [Stack needed](#stack-needed)). The default of `128` levels is tuned for threads with ordinary stacks of a few
 hundred kilobytes or more. Set a lower limit if your threads have small stacks (RTOS tasks, fibers, threads of the musl
 C
@@ -67,7 +67,7 @@ When the macro is not defined, the library defines it to its default value.
       the levels that are descended into are counted, so the count never exceeds the limit, not even when user code (a
       copy constructor of a custom base class, say) copies a value while a copy is going on. A byte holds `255` at
       most, and the limit stays below that, so that the count cannot wrap around. (More levels would hardly be
-      useful: `254` levels need up to 576 KiB of stack in an unoptimized build already, twice as much as the
+      useful: `254` levels need up to 448 KiB of stack in an unoptimized build already, twice as much as the
       default.)
 
 ### Stack needed
@@ -83,7 +83,7 @@ Unoptimized (`-O0`):
 
 | Operation | limit 16 | limit 32 | limit 64 | limit 128 | limit 254 |
 |---|---:|---:|---:|---:|---:|
-| `dump()` and `dump(indent)`, `operator<<` | 48 / 32 | 80 / 64 | 144 / 128 | 288 / 256 | 576 / 512 |
+| `dump()` and `dump(indent)`, `operator<<` | 16 / 16 | 16 / 16 | 32 / 32 | 48 / 48 | 96 / 96 |
 | copy construction and assignment | 32 / 16 | 48 / 32 | 112 / 80 | 224 / 144 | 432 / 304 |
 | `==` | 16 / 16 | 16 / 16 | 16 / 16 | 48 / 32 | 96 / 48 |
 | `<=>` (C++20) | 16 / 16 | 16 / 16 | 32 / 32 | 64 / 64 | 144 / 128 |
@@ -123,23 +123,24 @@ The rule of thumb is
 
 > stack needed ≈ a few KiB + cost per level × limit
 
-with a cost per level of up to 2.3 KiB (`dump` at `-O0` with Clang; 2.1 KiB with GCC), 1.7 KiB for copying and merging
-(1.3 KiB with GCC), and 0.1 to 0.5 KiB for most other operations at `-O0`; and 0.5 KiB or less at `-O2`. The numbers
-come from the difference between the limits `128` and `254` in the tables, so they are rough: other compilers,
-other targets (the frames of x86-64 code are about as large), other standard libraries, `JSON_DIAGNOSTICS`, and
-sanitizers change them. Measure with your own tool chain (see the example below) rather than relying on the tables.
-The stack that your own code and the operating system need comes on top of these numbers.
+with a cost per level of up to 1.8 KiB (conversion to another `basic_json` type at `-O0` with Clang; 1.3 KiB with
+GCC), 1.7 KiB for copying and merging (1.3 KiB with GCC), 0.4 KiB for `dump`, and 0.1 to 0.5 KiB for most other
+operations at `-O0`; and 0.5 KiB or less at `-O2`. The numbers come from the difference between the limits `128` and
+`254` in the tables, so they are rough: other compilers, other targets (the frames of x86-64 code are about as large),
+other standard libraries, `JSON_DIAGNOSTICS`, and sanitizers change them. Measure with your own tool chain (see the
+example below) rather than relying on the tables. The stack that your own code and the operating system need comes on
+top of these numbers.
 
 Which limit to choose, for the stack that you can spare for the library (the largest limit of those measured
 for which the slowest operation needs at most that much):
 
 | Stack for the library | optimized (`-O2`) | unoptimized (`-O0`) |
 |---|---:|---:|
-| 32 KiB | 64 | 0 |
-| 64 KiB | 128 | 16 |
-| 128 KiB (the default stack of threads on musl) | 254 | 32 |
-| 256 KiB | 254 | 64 |
-| 512 KiB | 254 | 128 |
+| 32 KiB | 64 | 16 |
+| 64 KiB | 128 | 32 |
+| 128 KiB (the default stack of threads on musl) | 254 | 64 |
+| 256 KiB | 254 | 128 |
+| 512 KiB | 254 | 254 |
 | 1 MiB or more | 254 | 254 |
 
 ### Speed

docs/mkdocs/docs/features/modules.md

@@ -9,19 +9,7 @@ Importing the module instead of including the header reduces the compile time of
 ## Requirements
 The `nlohmann.json` module requires that the build system is configured to build and resolve modules when imported. Obviously, as modules were introduced in C++20, this feature can only be used in C++20 and subsequent versions.
 
-To enable building the `nlohmann.json` module (which is not done by default), set the CMake option
-[`NLOHMANN_JSON_BUILD_MODULES`](../integration/cmake.md#nlohmann_json_build_modules) and link the
-`nlohmann_json_modules` target.
-
-With CMake, building the module needs:
-
-- CMake 3.28 or newer, and
-- a generator that scans for modules: Ninja (1.11 or newer), Ninja Multi-Config, or Visual Studio 2022 or newer.
-
-The example below also uses `import std;`. CMake supports it without experimental opt-in since version 4.5, and then
-only with the Ninja generators and these toolchains: Clang 18.1.2 or newer (with libc++ or libstdc++), MSVC toolset 14.36
-(Visual Studio 17.6) or newer, and GCC 15 or newer (GCC 16 on macOS). With older CMake versions, `import std;` needs
-CMake's version-specific experimental opt-in.
+To enable building the `nlohmann.json` module (which is not done by default), the macro `NLOHMANN_JSON_BUILD_MODULES` must be passed to the build system.
 
 ## Example
 When using modules rather than headers, the previous example for creating a `json` object through a JSON file, would instead be:
@@ -79,7 +67,7 @@ and should not be used directly:
 
 ## Known issues
 
-C++20 modules support is exercised in CI with CMake 4.5 and `import std;` against current GCC and Clang on Ubuntu, and the default MSVC toolset on Windows Server 2022 — there is no documented minimum compiler version, unlike feature-test-macro-gated features such as [`JSON_HAS_RANGES`](../api/macros/json_has_ranges.md).
+C++20 modules support is exercised in CI against current GCC and Clang on Ubuntu, and the default MSVC toolset on Windows Server 2022 — there is no documented minimum compiler version, unlike feature-test-macro-gated features such as [`JSON_HAS_RANGES`](../api/macros/json_has_ranges.md).
 
 !!! info "Known compiler issues"
 

docs/mkdocs/docs/features/parsing/untrusted_input.md

@@ -64,13 +64,13 @@ stack for the nesting.)
 
 The call stack still needs room for the levels that are recursed into, and the default limit assumes a stack of ordinary
 size. The stack that an operation needs is roughly proportional to the limit; with the default of 128 levels, the most
-demanding operation (`dump` in an unoptimized build) needed up to 288 KiB, and an optimized build needed 48 KiB or less,
-in measurements on macOS with arm64. The most demanding operation needed this much stack at the limits `0`, `32`,
-`128`, and `254`:
+demanding operations (copying a value and converting it to another `basic_json` type, in an unoptimized build) needed
+up to 224 KiB, and an optimized build needed 48 KiB or less, in measurements on macOS with arm64. The most demanding
+operation needed this much stack at the limits `0`, `32`, `128`, and `254`:
 
 | Stack needed, in KiB | limit 0 | limit 32 | limit 128 (default) | limit 254 |
 |---|---:|---:|---:|---:|
-| unoptimized build (`-O0`) | 16 or less | 80 | 288 | 576 |
+| unoptimized build (`-O0`) | 16 or less | 64 | 224 | 448 |
 | optimized build (`-O2`) | 16 or less | 16 or less | 48 | 112 |
 
 A thread with a smaller stack (a task of a real-time operating system, a fiber, or a thread of the musl C library, whose

docs/mkdocs/docs/integration/cmake.md

@@ -269,9 +269,6 @@ target_link_libraries(myproject PRIVATE nlohmann_json_modules)
 target_compile_definitions(myproject PRIVATE NLOHMANN_JSON_BUILD_MODULES)
 ```
 
-If `main.cpp` also uses `import std;`, the project needs CMake 4.5 or newer and a Ninja generator; see
-[Modules](../features/modules.md#requirements) for the supported toolchains.
-
 ## See also
 
 - [Macros](../api/macros/index.md) - reference of all macros

include/nlohmann/detail/macro_scope.hpp

@@ -230,6 +230,16 @@
 // detail/recursion_depth_limit.hpp. Like JSON_NO_THREAD_LOCAL it is neither part
 // of the ABI tag nor undefined at the end of json.hpp.
 
+// forced inlining of the serializer's helpers only in optimized builds: at -O0,
+// GCC and Clang give every inlined copy its own stack slots, which made the
+// recursive frame of serializer::dump_container() about 2.3 KB (MSVC does not
+// expand __forceinline at /Ob0, so it keeps it)
+#if defined(__OPTIMIZE__) || defined(_MSC_VER)
+    #define JSON_INTERNAL_SERIALIZER_INLINE JSON_HEDLEY_ALWAYS_INLINE
+#else
+    #define JSON_INTERNAL_SERIALIZER_INLINE inline
+#endif
+
 // allow disabling exceptions
 #if (defined(__cpp_exceptions) || defined(__EXCEPTIONS) || defined(_CPPUNWIND)) && !defined(JSON_NOEXCEPTION)
     #define JSON_THROW(exception) throw exception

include/nlohmann/detail/macro_unscope.hpp

@@ -11,6 +11,7 @@
 // clean up
 #undef JSON_ASSERT
 #undef JSON_INTERNAL_CATCH
+#undef JSON_INTERNAL_SERIALIZER_INLINE
 #undef JSON_THROW
 #undef JSON_PRIVATE_UNLESS_TESTED
 #undef NLOHMANN_BASIC_JSON_TPL_DECLARATION

include/nlohmann/detail/output/serializer.hpp

@@ -265,7 +265,7 @@ class serializer
     for a container; writing them from here spares each the entry and exit of
     that function.
     */
-    JSON_HEDLEY_ALWAYS_INLINE void dump_element(const BasicJsonType& val,
+    JSON_INTERNAL_SERIALIZER_INLINE void dump_element(const BasicJsonType& val,
             const std::size_t current_indent,
             const std::size_t depth)
     {
@@ -971,7 +971,7 @@ class serializer
     }
 
     /// write out the bytes pending in @ref string_buffer and reset @a bytes
-    JSON_HEDLEY_ALWAYS_INLINE void emit_pending(std::size_t& bytes)
+    JSON_INTERNAL_SERIALIZER_INLINE void emit_pending(std::size_t& bytes)
     {
         if (bytes != 0)
         {
@@ -983,7 +983,7 @@ class serializer
     /// write buffer and reset index if fewer than 13 bytes are left, as this
     /// is the maximal number of bytes to be written ("\uxxxx\uxxxx\0") for one
     /// code point
-    JSON_HEDLEY_ALWAYS_INLINE void reserve_string_buffer(std::size_t& bytes)
+    JSON_INTERNAL_SERIALIZER_INLINE void reserve_string_buffer(std::size_t& bytes)
     {
         if (string_buffer.size() - bytes < 13)
         {
@@ -1344,7 +1344,7 @@ class serializer
           inlining both into the pretty-printing loops once @ref dump_escaped
           has grown, which made indented output up to 13% slower
     */
-    JSON_HEDLEY_ALWAYS_INLINE void put_indent(std::size_t indent)
+    JSON_INTERNAL_SERIALIZER_INLINE void put_indent(std::size_t indent)
     {
         // closing braces at the outermost level ask for no indentation at all
         if (indent == 0)
@@ -1398,7 +1398,7 @@ class serializer
     its room and four stores of the indentation, see @ref put_short_literal_indent.
     */
     template<std::size_t N>
-    JSON_HEDLEY_ALWAYS_INLINE void put_literal_indent(const char (&s)[N], const std::size_t indent) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    JSON_INTERNAL_SERIALIZER_INLINE void put_literal_indent(const char (&s)[N], const std::size_t indent) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
     {
         if (JSON_HEDLEY_LIKELY(put_short_literal_indent(s, indent)))
         {
@@ -1418,7 +1418,7 @@ class serializer
     @a indent is wider or the write buffer lacks the room.
     */
     template<std::size_t N>
-    JSON_HEDLEY_ALWAYS_INLINE bool put_short_literal_indent(const char (&s)[N], const std::size_t indent) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    JSON_INTERNAL_SERIALIZER_INLINE bool put_short_literal_indent(const char (&s)[N], const std::size_t indent) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
     {
         constexpr std::size_t length = N - 1;
         if (indent > 32 || write_buffer_pos + length + 32 > write_buffer.size())
@@ -1445,7 +1445,7 @@ class serializer
     write-through path for oversized runs.
     */
     template<std::size_t N>
-    JSON_HEDLEY_ALWAYS_INLINE void put_literal(const char (&s)[N]) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    JSON_INTERNAL_SERIALIZER_INLINE void put_literal(const char (&s)[N]) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
     {
         static_assert(N >= 2, "put_literal expects a non-empty string literal");
         // the array bound counts the terminating NUL, which is not written

single_include/nlohmann/json.hpp

@@ -2603,6 +2603,16 @@ JSON_HEDLEY_DIAGNOSTIC_POP
 // detail/recursion_depth_limit.hpp. Like JSON_NO_THREAD_LOCAL it is neither part
 // of the ABI tag nor undefined at the end of json.hpp.
 
+// forced inlining of the serializer's helpers only in optimized builds: at -O0,
+// GCC and Clang give every inlined copy its own stack slots, which made the
+// recursive frame of serializer::dump_container() about 2.3 KB (MSVC does not
+// expand __forceinline at /Ob0, so it keeps it)
+#if defined(__OPTIMIZE__) || defined(_MSC_VER)
+    #define JSON_INTERNAL_SERIALIZER_INLINE JSON_HEDLEY_ALWAYS_INLINE
+#else
+    #define JSON_INTERNAL_SERIALIZER_INLINE inline
+#endif
+
 // allow disabling exceptions
 #if (defined(__cpp_exceptions) || defined(__EXCEPTIONS) || defined(_CPPUNWIND)) && !defined(JSON_NOEXCEPTION)
     #define JSON_THROW(exception) throw exception
@@ -36985,7 +36995,7 @@ class serializer
     for a container; writing them from here spares each the entry and exit of
     that function.
     */
-    JSON_HEDLEY_ALWAYS_INLINE void dump_element(const BasicJsonType& val,
+    JSON_INTERNAL_SERIALIZER_INLINE void dump_element(const BasicJsonType& val,
             const std::size_t current_indent,
             const std::size_t depth)
     {
@@ -37691,7 +37701,7 @@ class serializer
     }
 
     /// write out the bytes pending in @ref string_buffer and reset @a bytes
-    JSON_HEDLEY_ALWAYS_INLINE void emit_pending(std::size_t& bytes)
+    JSON_INTERNAL_SERIALIZER_INLINE void emit_pending(std::size_t& bytes)
     {
         if (bytes != 0)
         {
@@ -37703,7 +37713,7 @@ class serializer
     /// write buffer and reset index if fewer than 13 bytes are left, as this
     /// is the maximal number of bytes to be written ("\uxxxx\uxxxx\0") for one
     /// code point
-    JSON_HEDLEY_ALWAYS_INLINE void reserve_string_buffer(std::size_t& bytes)
+    JSON_INTERNAL_SERIALIZER_INLINE void reserve_string_buffer(std::size_t& bytes)
     {
         if (string_buffer.size() - bytes < 13)
         {
@@ -38064,7 +38074,7 @@ class serializer
           inlining both into the pretty-printing loops once @ref dump_escaped
           has grown, which made indented output up to 13% slower
     */
-    JSON_HEDLEY_ALWAYS_INLINE void put_indent(std::size_t indent)
+    JSON_INTERNAL_SERIALIZER_INLINE void put_indent(std::size_t indent)
     {
         // closing braces at the outermost level ask for no indentation at all
         if (indent == 0)
@@ -38118,7 +38128,7 @@ class serializer
     its room and four stores of the indentation, see @ref put_short_literal_indent.
     */
     template<std::size_t N>
-    JSON_HEDLEY_ALWAYS_INLINE void put_literal_indent(const char (&s)[N], const std::size_t indent) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    JSON_INTERNAL_SERIALIZER_INLINE void put_literal_indent(const char (&s)[N], const std::size_t indent) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
     {
         if (JSON_HEDLEY_LIKELY(put_short_literal_indent(s, indent)))
         {
@@ -38138,7 +38148,7 @@ class serializer
     @a indent is wider or the write buffer lacks the room.
     */
     template<std::size_t N>
-    JSON_HEDLEY_ALWAYS_INLINE bool put_short_literal_indent(const char (&s)[N], const std::size_t indent) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    JSON_INTERNAL_SERIALIZER_INLINE bool put_short_literal_indent(const char (&s)[N], const std::size_t indent) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
     {
         constexpr std::size_t length = N - 1;
         if (indent > 32 || write_buffer_pos + length + 32 > write_buffer.size())
@@ -38165,7 +38175,7 @@ class serializer
     write-through path for oversized runs.
     */
     template<std::size_t N>
-    JSON_HEDLEY_ALWAYS_INLINE void put_literal(const char (&s)[N]) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    JSON_INTERNAL_SERIALIZER_INLINE void put_literal(const char (&s)[N]) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
     {
         static_assert(N >= 2, "put_literal expects a non-empty string literal");
         // the array bound counts the terminating NUL, which is not written
@@ -47885,6 +47895,7 @@ struct formatter<nlohmann::NLOHMANN_BASIC_JSON_TPL, char> // NOLINT(cert-dcl58-c
 // clean up
 #undef JSON_ASSERT
 #undef JSON_INTERNAL_CATCH
+#undef JSON_INTERNAL_SERIALIZER_INLINE
 #undef JSON_THROW
 #undef JSON_PRIVATE_UNLESS_TESTED
 #undef NLOHMANN_BASIC_JSON_TPL_DECLARATION

tests/module_cpp20/CMakeLists.txt

@@ -1,6 +1,11 @@
-# `import std;` (used by main.cpp) is supported without experimental opt-in
-# since CMake 4.5: it is available to every target that scans for C++ modules.
-cmake_minimum_required(VERSION 4.5)
+cmake_minimum_required(VERSION 3.30)
+
+# `import std;` (used by main.cpp) needs CMake's experimental C++ import-std
+# support. The accepted token is CMake-version-specific; this value matches the
+# CMake version pinned in the ci_module_cpp20 CI jobs (4.3.x). If that pin is
+# bumped, this token must be updated to match (configuration fails loudly
+# otherwise).
+set(CMAKE_EXPERIMENTAL_CXX_IMPORT_STD "451f2fe2-a8a2-47c3-bc32-94786d8fc91b")
 
 project(json_test CXX)
 
@@ -8,6 +13,7 @@ project(json_test CXX)
 set(CMAKE_CXX_STANDARD 23)
 set(CMAKE_CXX_STANDARD_REQUIRED ON)
 set(CMAKE_CXX_EXTENSIONS OFF)
+set(CMAKE_CXX_MODULE_STD ON)
 
 set(NLOHMANN_JSON_BUILD_MODULES ON CACHE BOOL "Enable nlohmann.json module support")
 

tests/module_cpp20/main.cpp

@@ -17,8 +17,8 @@ using namespace nlohmann::literals;
 // Standard-library facilities are pulled in via `import std;` rather than
 // textual `#include`s: mixing `import` with textual standard headers does not
 // compile under GCC's C++20 modules implementation, whereas `import std;` works
-// across GCC, Clang, and MSVC. This requires C++23 and CMake 4.5 or newer;
-// see CMakeLists.txt.
+// across GCC, Clang, and MSVC. This requires C++23 and CMake's (experimental)
+// import-std support; see CMakeLists.txt.
 int main()
 {
     // basic_json / json: parsing and value access