[nanvix] E: Link libnvx_crt0.a into python.elf

.nanvix/config.py

@@ -72,11 +72,20 @@ def toolchain_paths(
         "libssl": sr / "lib" / "libssl.a",
         "libcrypto": sr / "lib" / "libcrypto.a",
         "liblzma": sr / "lib" / "liblzma.a",
+        "libnvx_crt0": sr / "lib" / "libnvx_crt0.a",
     }
 
 
 def configure_env(toolchain: str | Path, sysroot: str | Path) -> dict[str, str]:
-    """Return the environment dict for ./configure."""
+    """Return the environment dict for ./configure.
+
+    NOTE: This helper is currently unused; the actual cpython build invokes
+    ``make -f Makefile.nanvix`` which has its own inline CONFIGURE_ENV. This
+    function is kept in sync so a future caller does not pick up stale link
+    flags. See ``Makefile.nanvix`` for the authoritative comment block
+    explaining the ``--whole-archive`` / ``--export-dynamic`` /
+    ``--allow-multiple-definition`` rationale.
+    """
     tp = toolchain_paths(toolchain, sysroot)
     sr = Path(sysroot)
     return {
@@ -96,7 +105,10 @@ def configure_env(toolchain: str | Path, sysroot: str | Path) -> dict[str, str]:
             f"-Wl,--export-dynamic -Wl,--no-dynamic-linker"
         ),
         "LIBS": (
-            f"-Wl,--start-group {tp['libposix']} {tp['libc']} {tp['libm']} "
+            f"-Wl,--whole-archive {tp['libnvx_crt0']} {tp['libposix']} "
+            f"{tp['libc']} {tp['libm']} "
+            f"-lstdc++ -lgcc -Wl,--no-whole-archive "
+            f"-Wl,--start-group "
             f"-lsqlite3 -lssl -lcrypto -lz -lbz2 -llzma -lffi -Wl,--end-group"
         ),
         "LIBSQLITE3_LIBS": f"-L{sr}/lib -lsqlite3",

Makefile.nanvix

@@ -91,6 +91,14 @@ ifdef CONFIG_NANVIX
     LIBSQLITE3 := $(DOCKER_SYSROOT_PATH)/lib/libsqlite3.a
     LIBSSL := $(DOCKER_SYSROOT_PATH)/lib/libssl.a
     LIBCRYPTO := $(DOCKER_SYSROOT_PATH)/lib/libcrypto.a
+    # libnvx_crt0 ships the executable startup symbols (`_do_start`, `_start`,
+    # `c_trampoline`).  It must be present in the Nanvix sysroot ahead of this
+    # cpython build; the existence check below fails loudly when it is not.
+    LIBNVX_CRT0 := $(DOCKER_SYSROOT_PATH)/lib/libnvx_crt0.a
+    # Host-side path used by the parse-time existence guard below.  The
+    # docker build sees the sysroot at $(DOCKER_SYSROOT_PATH); the host
+    # only sees it at $(NANVIX_HOME).
+    LIBNVX_CRT0_HOST := $(abspath $(NANVIX_HOME))/lib/libnvx_crt0.a
     BUILD_PYTHON := $(DOCKER_TOOLCHAIN_PATH)/bin/python3
   else
     TOOLCHAIN_PREFIX := $(NANVIX_TOOLCHAIN)
@@ -102,8 +110,19 @@ ifdef CONFIG_NANVIX
     LIBSQLITE3 := $(abspath $(NANVIX_HOME))/lib/libsqlite3.a
     LIBSSL := $(abspath $(NANVIX_HOME))/lib/libssl.a
     LIBCRYPTO := $(abspath $(NANVIX_HOME))/lib/libcrypto.a
+    LIBNVX_CRT0 := $(abspath $(NANVIX_HOME))/lib/libnvx_crt0.a
+    LIBNVX_CRT0_HOST := $(LIBNVX_CRT0)
     BUILD_PYTHON := $(NANVIX_TOOLCHAIN)/bin/python3
   endif
+
+  # libstdc++ / libgcc are referenced via `-l` rather than absolute paths so
+  # the GCC driver resolves them: libgcc lives under a versioned dir
+  # (`lib/gcc/i686-nanvix/<gcc-version>/libgcc.a`) and hardcoding a version
+  # would be fragile across toolchain upgrades.  Defined once at top-level
+  # because the `-l` form is identical between the docker and host build
+  # paths above.
+  LIBSTDCXX := -lstdc++
+  LIBGCC := -lgcc
 else
   ifneq ($(MAKECMDGOALS),clean)
     ifneq ($(MAKECMDGOALS),distclean)
@@ -113,7 +132,74 @@ else
   EXE=.elf
 endif
 
+# Existence check for libnvx_crt0.a.
+#
+# libnvx_crt0.a is the executable startup archive (`_do_start` / `_start` /
+# `c_trampoline`) introduced by the Nanvix `nvx-crt0` crate split. cpython
+# requires a Nanvix sysroot that ships it. If the user is building against
+# an older sysroot snapshot, fail at make-parse time with an actionable
+# message rather than producing a python.elf with no entry point.
+#
+# Skip the guard for `clean` / `distclean` (which should work against any
+# sysroot, including ones with no libnvx_crt0.a).  Empty MAKECMDGOALS is
+# treated as a build because `make` with no target invokes `all`.
+ifdef CONFIG_NANVIX
+GUARD_GOALS := $(filter-out clean distclean,$(or $(MAKECMDGOALS),build))
+ifneq ($(GUARD_GOALS),)
+ifeq ($(wildcard $(LIBNVX_CRT0_HOST)),)
+$(error libnvx_crt0.a not found at $(LIBNVX_CRT0_HOST). Update the Nanvix sysroot to one that ships libnvx_crt0.a (the nvx-crt0 crate must be present and built into the sysroot lib/ directory).)
+endif
+endif
+endif
+
 # Configure environment variables
+#
+# Linker flag rationale:
+#
+# `-Wl,--export-dynamic`: put every globally-defined symbol from python.elf
+# into its `.dynsym`. Extension `.so`s (numpy's `_multiarray_umath.so`, ssl,
+# etc.) leave C/C++ runtime symbols UND and resolve them against python.elf
+# at dlopen() time. Without this, those `.so`s fail to load.
+#
+# `-Wl,--allow-multiple-definition`: tolerates duplicate symbol definitions
+# that arise from forcing every libposix / libc / libm / libstdc++ / libgcc
+# object into python.elf via `--whole-archive` below. The biggest set is
+# newlib's long-double math helpers (`frexpl`, `llrintl`, `lrintl`, `rintl`
+# are defined in three different newlib directories simultaneously — a
+# newlib build-system bug). Other known overlaps include libposix vs. libc
+# (`_start`, `copysign[f]`, `getenv`, `setenv`, `unsetenv`, `environ`,
+# `isatty`), libc vs. libm (`frexp`, `ldexp`, `modf`, `isnan`, `isinf`,
+# `scalbn`, …), libm vs. libstdc++ (`hypotf`), libgcc internal duplicates
+# (`__x86.get_pc_thunk.*`), and a libc / libgcc `__eprintf`. The set is
+# large and toolchain-build-version-dependent; treating the link as
+# multiple-definition-tolerant is the only practical workaround until each
+# upstream is fixed. Remove this flag once the contributing duplicates are
+# resolved upstream.
+#
+# `LIBS` segment 1 (`--whole-archive ... --no-whole-archive`): force every
+# object from libnvx_crt0, libposix, libc, libm, libstdc++, and libgcc into
+# python.elf so the runtime symbols extension `.so`s depend on are embedded
+# and re-exported via `--export-dynamic`. Without `--whole-archive`, the
+# static linker drops unreferenced objects (e.g. `fscanf`, `longjmp`,
+# `strtold_l` for numpy; `operator new/delete[]`, `__cxa_*`, `_Unwind_*`,
+# `std::type_info` vtables for any C++ extension) and subsequent dlopen()
+# of those `.so`s fails with "symbol not found".
+#
+# `libnvx_crt0` is listed first inside `--whole-archive`. Today, libposix.a
+# still ships its own copy of the startup symbols (`_start`, `_do_start`,
+# `c_trampoline`) because `nvx` builds them in under the `staticlib`
+# feature. With `--allow-multiple-definition` (above) the linker takes the
+# first definition, so listing libnvx_crt0 first selects the standalone
+# crt0 copy of `_start` and friends. This is an intentional behaviour
+# change: future Nanvix versions remove the duplicate from libposix, after
+# which libnvx_crt0 is the sole provider. Listing it first today keeps
+# python.elf using a consistent `_start` source across both states.
+#
+# `LIBS` segment 2 (`--start-group ... --end-group`): the external add-on
+# libraries (sqlite3, ssl, crypto, z, bz2, lzma, ffi). The group is needed
+# only for their inter-archive circular dependencies; they resolve symbols
+# from libposix/libc/libm/libstdc++ against the already-embedded objects
+# from segment 1.
 CONFIGURE_ENV = \
 	CC="$(TOOLCHAIN_PREFIX)/bin/i686-nanvix-gcc" \
 	CXX="$(TOOLCHAIN_PREFIX)/bin/i686-nanvix-g++" \
@@ -123,7 +209,7 @@ CONFIGURE_ENV = \
 	CFLAGS="-O3 -fomit-frame-pointer -fno-unwind-tables -fno-asynchronous-unwind-tables -I$(SYSROOT_PATH)/include" \
 	CFLAGS_NODIST="-fno-semantic-interposition" \
 	LDFLAGS="-L$(SYSROOT_PATH)/lib -T$(SYSROOT_PATH)/lib/user.ld -Wl,--allow-multiple-definition -no-pie -Wl,--export-dynamic -Wl,--no-dynamic-linker" \
-	LIBS="-Wl,--start-group $(LIBPOSIX) $(LIBC) $(LIBM) -lsqlite3 -lssl -lcrypto -lz -lbz2 -llzma -lffi -Wl,--end-group" \
+	LIBS="-Wl,--whole-archive $(LIBNVX_CRT0) $(LIBPOSIX) $(LIBC) $(LIBM) $(LIBSTDCXX) $(LIBGCC) -Wl,--no-whole-archive -Wl,--start-group -lsqlite3 -lssl -lcrypto -lz -lbz2 -llzma -lffi -Wl,--end-group" \
 	LIBSQLITE3_LIBS="-L$(SYSROOT_PATH)/lib -lsqlite3" \
 	LIBSQLITE3_CFLAGS="-I$(SYSROOT_PATH)/include" \
 	ZLIB_LIBS="-L$(SYSROOT_PATH)/lib -lz" \