kbuild: rust: keep Rust objects out of Clang LTO with inline helpersgrafted

Under `CONFIG_LTO_CLANG` + `CONFIG_RUST_INLINE_HELPERS`, one may hit
`objtool` errors such as:

    vmlinux.o: error: objtool: _R..._3Gsp4boot+0xd6a:
    can't find jump dest instruction at .text._R..._3Gsp4boot+0x1dfd

The reason is that in such builds, the Clang invocation that compiles
the combined Rust plus helpers bitcode emits LLVM bitcode (again) --
the final code generation happens in the linker's LTO step, which the
`-mllvm` trap options passed to Clang do not reach.

This, in turn, means that unreachable traps are missing, and the
impossible paths do not merely fallthrough to the next symbol, but past
the end of their own section, since LTO builds place each function in
its own section.

Thus filter `CC_FLAGS_LTO` out of the Clang invocation, so that it always
emits machine code directly, with the traps in place.

Assisted-by: LLM
Cc: Gary Guo <gary@garyguo.net>
Cc: Boqun Feng <boqun@kernel.org>
Cc: Alice Ryhl <aliceryhl@google.com>
Cc: Matthew Maurer <mmaurer@google.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Fixes: 3a2486cc1da5 ("kbuild: rust: provide an option to inline C helpers into Rust")
Acked-by: Gary Guo <gary@garyguo.net>
Link: https://patch.msgid.link/20260816133233.197500-2-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>

1 files changed, 76 insertions, 0 deletions

diff --git a/lib/crypto/powerpc/chacha.h b/lib/crypto/powerpc/chacha.h
new file mode 100644
index 000000000..1df6e1ce3
--- /dev/null
+++ b/lib/crypto/powerpc/chacha.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * ChaCha stream cipher (P10 accelerated)
+ *
+ * Copyright 2023- IBM Corp. All rights reserved.
+ */
+
+#include <crypto/internal/simd.h>
+#include <linux/kernel.h>
+#include <linux/cpufeature.h>
+#include <linux/sizes.h>
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+
+asmlinkage void chacha_p10le_8x(const struct chacha_state *state, u8 *dst,
+				const u8 *src, unsigned int len, int nrounds);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_p10);
+
+static void vsx_begin(void)
+{
+	preempt_disable();
+	enable_kernel_vsx();
+}
+
+static void vsx_end(void)
+{
+	disable_kernel_vsx();
+	preempt_enable();
+}
+
+static void chacha_p10_do_8x(struct chacha_state *state, u8 *dst, const u8 *src,
+			     unsigned int bytes, int nrounds)
+{
+	unsigned int l = bytes & ~0x0FF;
+
+	if (l > 0) {
+		chacha_p10le_8x(state, dst, src, l, nrounds);
+		bytes -= l;
+		src += l;
+		dst += l;
+		state->x[12] += l / CHACHA_BLOCK_SIZE;
+	}
+
+	if (bytes > 0)
+		chacha_crypt_generic(state, dst, src, bytes, nrounds);
+}
+
+#define hchacha_block_arch hchacha_block_generic /* not implemented yet */
+
+static void chacha_crypt_arch(struct chacha_state *state, u8 *dst,
+			      const u8 *src, unsigned int bytes, int nrounds)
+{
+	if (!static_branch_likely(&have_p10) || bytes <= CHACHA_BLOCK_SIZE ||
+	    !crypto_simd_usable())
+		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+	do {
+		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+		vsx_begin();
+		chacha_p10_do_8x(state, dst, src, todo, nrounds);
+		vsx_end();
+
+		bytes -= todo;
+		src += todo;
+		dst += todo;
+	} while (bytes);
+}
+
+#define chacha_mod_init_arch chacha_mod_init_arch
+static void chacha_mod_init_arch(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_31))
+		static_branch_enable(&have_p10);
+}