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, 290 insertions, 0 deletions

diff --git a/lib/crypto/sm3.c b/lib/crypto/sm3.c
new file mode 100644
index 000000000..b02b8a247
--- /dev/null
+++ b/lib/crypto/sm3.c
@@ -0,0 +1,290 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * SM3 secure hash, as specified by OSCCA GM/T 0004-2012 SM3 and described
+ * at https://datatracker.ietf.org/doc/html/draft-sca-cfrg-sm3-02
+ *
+ * Copyright (C) 2017 ARM Limited or its affiliates.
+ * Copyright (C) 2017 Gilad Ben-Yossef <gilad@benyossef.com>
+ * Copyright (C) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
+ */
+
+#include <crypto/sm3.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/unaligned.h>
+
+static const struct sm3_block_state sm3_iv = {
+	.h = {
+		SM3_IVA, SM3_IVB, SM3_IVC, SM3_IVD,
+		SM3_IVE, SM3_IVF, SM3_IVG, SM3_IVH,
+	},
+};
+
+static const u32 ____cacheline_aligned K[64] = {
+	0x79cc4519, 0xf3988a32, 0xe7311465, 0xce6228cb,
+	0x9cc45197, 0x3988a32f, 0x7311465e, 0xe6228cbc,
+	0xcc451979, 0x988a32f3, 0x311465e7, 0x6228cbce,
+	0xc451979c, 0x88a32f39, 0x11465e73, 0x228cbce6,
+	0x9d8a7a87, 0x3b14f50f, 0x7629ea1e, 0xec53d43c,
+	0xd8a7a879, 0xb14f50f3, 0x629ea1e7, 0xc53d43ce,
+	0x8a7a879d, 0x14f50f3b, 0x29ea1e76, 0x53d43cec,
+	0xa7a879d8, 0x4f50f3b1, 0x9ea1e762, 0x3d43cec5,
+	0x7a879d8a, 0xf50f3b14, 0xea1e7629, 0xd43cec53,
+	0xa879d8a7, 0x50f3b14f, 0xa1e7629e, 0x43cec53d,
+	0x879d8a7a, 0x0f3b14f5, 0x1e7629ea, 0x3cec53d4,
+	0x79d8a7a8, 0xf3b14f50, 0xe7629ea1, 0xcec53d43,
+	0x9d8a7a87, 0x3b14f50f, 0x7629ea1e, 0xec53d43c,
+	0xd8a7a879, 0xb14f50f3, 0x629ea1e7, 0xc53d43ce,
+	0x8a7a879d, 0x14f50f3b, 0x29ea1e76, 0x53d43cec,
+	0xa7a879d8, 0x4f50f3b1, 0x9ea1e762, 0x3d43cec5
+};
+
+/*
+ * Transform the message X which consists of 16 32-bit-words. See
+ * GM/T 004-2012 for details.
+ */
+#define R(i, a, b, c, d, e, f, g, h, t, w1, w2)			\
+	do {							\
+		ss1 = rol32((rol32((a), 12) + (e) + (t)), 7);	\
+		ss2 = ss1 ^ rol32((a), 12);			\
+		d += FF ## i(a, b, c) + ss2 + ((w1) ^ (w2));	\
+		h += GG ## i(e, f, g) + ss1 + (w1);		\
+		b = rol32((b), 9);				\
+		f = rol32((f), 19);				\
+		h = P0((h));					\
+	} while (0)
+
+#define R1(a, b, c, d, e, f, g, h, t, w1, w2) \
+	R(1, a, b, c, d, e, f, g, h, t, w1, w2)
+#define R2(a, b, c, d, e, f, g, h, t, w1, w2) \
+	R(2, a, b, c, d, e, f, g, h, t, w1, w2)
+
+#define FF1(x, y, z)  (x ^ y ^ z)
+#define FF2(x, y, z)  ((x & y) | (x & z) | (y & z))
+
+#define GG1(x, y, z)  FF1(x, y, z)
+#define GG2(x, y, z)  ((x & y) | (~x & z))
+
+/* Message expansion */
+#define P0(x) ((x) ^ rol32((x), 9) ^ rol32((x), 17))
+#define P1(x) ((x) ^ rol32((x), 15) ^ rol32((x), 23))
+#define I(i)  (W[i] = get_unaligned_be32(data + i * 4))
+#define W1(i) (W[i & 0x0f])
+#define W2(i) (W[i & 0x0f] =				\
+		P1(W[i & 0x0f]				\
+			^ W[(i-9) & 0x0f]		\
+			^ rol32(W[(i-3) & 0x0f], 15))	\
+		^ rol32(W[(i-13) & 0x0f], 7)		\
+		^ W[(i-6) & 0x0f])
+
+static void sm3_block_generic(struct sm3_block_state *state,
+			      const u8 data[SM3_BLOCK_SIZE], u32 W[16])
+{
+	u32 a, b, c, d, e, f, g, h, ss1, ss2;
+
+	a = state->h[0];
+	b = state->h[1];
+	c = state->h[2];
+	d = state->h[3];
+	e = state->h[4];
+	f = state->h[5];
+	g = state->h[6];
+	h = state->h[7];
+
+	R1(a, b, c, d, e, f, g, h, K[0], I(0), I(4));
+	R1(d, a, b, c, h, e, f, g, K[1], I(1), I(5));
+	R1(c, d, a, b, g, h, e, f, K[2], I(2), I(6));
+	R1(b, c, d, a, f, g, h, e, K[3], I(3), I(7));
+	R1(a, b, c, d, e, f, g, h, K[4], W1(4), I(8));
+	R1(d, a, b, c, h, e, f, g, K[5], W1(5), I(9));
+	R1(c, d, a, b, g, h, e, f, K[6], W1(6), I(10));
+	R1(b, c, d, a, f, g, h, e, K[7], W1(7), I(11));
+	R1(a, b, c, d, e, f, g, h, K[8], W1(8), I(12));
+	R1(d, a, b, c, h, e, f, g, K[9], W1(9), I(13));
+	R1(c, d, a, b, g, h, e, f, K[10], W1(10), I(14));
+	R1(b, c, d, a, f, g, h, e, K[11], W1(11), I(15));
+	R1(a, b, c, d, e, f, g, h, K[12], W1(12), W2(16));
+	R1(d, a, b, c, h, e, f, g, K[13], W1(13), W2(17));
+	R1(c, d, a, b, g, h, e, f, K[14], W1(14), W2(18));
+	R1(b, c, d, a, f, g, h, e, K[15], W1(15), W2(19));
+
+	R2(a, b, c, d, e, f, g, h, K[16], W1(16), W2(20));
+	R2(d, a, b, c, h, e, f, g, K[17], W1(17), W2(21));
+	R2(c, d, a, b, g, h, e, f, K[18], W1(18), W2(22));
+	R2(b, c, d, a, f, g, h, e, K[19], W1(19), W2(23));
+	R2(a, b, c, d, e, f, g, h, K[20], W1(20), W2(24));
+	R2(d, a, b, c, h, e, f, g, K[21], W1(21), W2(25));
+	R2(c, d, a, b, g, h, e, f, K[22], W1(22), W2(26));
+	R2(b, c, d, a, f, g, h, e, K[23], W1(23), W2(27));
+	R2(a, b, c, d, e, f, g, h, K[24], W1(24), W2(28));
+	R2(d, a, b, c, h, e, f, g, K[25], W1(25), W2(29));
+	R2(c, d, a, b, g, h, e, f, K[26], W1(26), W2(30));
+	R2(b, c, d, a, f, g, h, e, K[27], W1(27), W2(31));
+	R2(a, b, c, d, e, f, g, h, K[28], W1(28), W2(32));
+	R2(d, a, b, c, h, e, f, g, K[29], W1(29), W2(33));
+	R2(c, d, a, b, g, h, e, f, K[30], W1(30), W2(34));
+	R2(b, c, d, a, f, g, h, e, K[31], W1(31), W2(35));
+
+	R2(a, b, c, d, e, f, g, h, K[32], W1(32), W2(36));
+	R2(d, a, b, c, h, e, f, g, K[33], W1(33), W2(37));
+	R2(c, d, a, b, g, h, e, f, K[34], W1(34), W2(38));
+	R2(b, c, d, a, f, g, h, e, K[35], W1(35), W2(39));
+	R2(a, b, c, d, e, f, g, h, K[36], W1(36), W2(40));
+	R2(d, a, b, c, h, e, f, g, K[37], W1(37), W2(41));
+	R2(c, d, a, b, g, h, e, f, K[38], W1(38), W2(42));
+	R2(b, c, d, a, f, g, h, e, K[39], W1(39), W2(43));
+	R2(a, b, c, d, e, f, g, h, K[40], W1(40), W2(44));
+	R2(d, a, b, c, h, e, f, g, K[41], W1(41), W2(45));
+	R2(c, d, a, b, g, h, e, f, K[42], W1(42), W2(46));
+	R2(b, c, d, a, f, g, h, e, K[43], W1(43), W2(47));
+	R2(a, b, c, d, e, f, g, h, K[44], W1(44), W2(48));
+	R2(d, a, b, c, h, e, f, g, K[45], W1(45), W2(49));
+	R2(c, d, a, b, g, h, e, f, K[46], W1(46), W2(50));
+	R2(b, c, d, a, f, g, h, e, K[47], W1(47), W2(51));
+
+	R2(a, b, c, d, e, f, g, h, K[48], W1(48), W2(52));
+	R2(d, a, b, c, h, e, f, g, K[49], W1(49), W2(53));
+	R2(c, d, a, b, g, h, e, f, K[50], W1(50), W2(54));
+	R2(b, c, d, a, f, g, h, e, K[51], W1(51), W2(55));
+	R2(a, b, c, d, e, f, g, h, K[52], W1(52), W2(56));
+	R2(d, a, b, c, h, e, f, g, K[53], W1(53), W2(57));
+	R2(c, d, a, b, g, h, e, f, K[54], W1(54), W2(58));
+	R2(b, c, d, a, f, g, h, e, K[55], W1(55), W2(59));
+	R2(a, b, c, d, e, f, g, h, K[56], W1(56), W2(60));
+	R2(d, a, b, c, h, e, f, g, K[57], W1(57), W2(61));
+	R2(c, d, a, b, g, h, e, f, K[58], W1(58), W2(62));
+	R2(b, c, d, a, f, g, h, e, K[59], W1(59), W2(63));
+	R2(a, b, c, d, e, f, g, h, K[60], W1(60), W2(64));
+	R2(d, a, b, c, h, e, f, g, K[61], W1(61), W2(65));
+	R2(c, d, a, b, g, h, e, f, K[62], W1(62), W2(66));
+	R2(b, c, d, a, f, g, h, e, K[63], W1(63), W2(67));
+
+	state->h[0] ^= a;
+	state->h[1] ^= b;
+	state->h[2] ^= c;
+	state->h[3] ^= d;
+	state->h[4] ^= e;
+	state->h[5] ^= f;
+	state->h[6] ^= g;
+	state->h[7] ^= h;
+}
+#undef R
+#undef R1
+#undef R2
+#undef I
+#undef W1
+#undef W2
+
+static void __maybe_unused sm3_blocks_generic(struct sm3_block_state *state,
+					      const u8 *data, size_t nblocks)
+{
+	u32 W[16];
+
+	do {
+		sm3_block_generic(state, data, W);
+		data += SM3_BLOCK_SIZE;
+	} while (--nblocks);
+
+	memzero_explicit(W, sizeof(W));
+}
+
+#ifdef CONFIG_CRYPTO_LIB_SM3_ARCH
+#include "sm3.h" /* $(SRCARCH)/sm3.h */
+#else
+#define sm3_blocks sm3_blocks_generic
+#endif
+
+void sm3_init(struct sm3_ctx *ctx)
+{
+	ctx->state = sm3_iv;
+	ctx->bytecount = 0;
+}
+EXPORT_SYMBOL_GPL(sm3_init);
+
+void sm3_update(struct sm3_ctx *ctx, const u8 *data, size_t len)
+{
+	size_t partial = ctx->bytecount % SM3_BLOCK_SIZE;
+
+	ctx->bytecount += len;
+
+	if (partial + len >= SM3_BLOCK_SIZE) {
+		size_t nblocks;
+
+		if (partial) {
+			size_t l = SM3_BLOCK_SIZE - partial;
+
+			memcpy(&ctx->buf[partial], data, l);
+			data += l;
+			len -= l;
+
+			sm3_blocks(&ctx->state, ctx->buf, 1);
+		}
+
+		nblocks = len / SM3_BLOCK_SIZE;
+		len %= SM3_BLOCK_SIZE;
+
+		if (nblocks) {
+			sm3_blocks(&ctx->state, data, nblocks);
+			data += nblocks * SM3_BLOCK_SIZE;
+		}
+		partial = 0;
+	}
+	if (len)
+		memcpy(&ctx->buf[partial], data, len);
+}
+EXPORT_SYMBOL_GPL(sm3_update);
+
+static void __sm3_final(struct sm3_ctx *ctx, u8 out[SM3_DIGEST_SIZE])
+{
+	u64 bitcount = ctx->bytecount << 3;
+	size_t partial = ctx->bytecount % SM3_BLOCK_SIZE;
+
+	ctx->buf[partial++] = 0x80;
+	if (partial > SM3_BLOCK_SIZE - 8) {
+		memset(&ctx->buf[partial], 0, SM3_BLOCK_SIZE - partial);
+		sm3_blocks(&ctx->state, ctx->buf, 1);
+		partial = 0;
+	}
+	memset(&ctx->buf[partial], 0, SM3_BLOCK_SIZE - 8 - partial);
+	*(__be64 *)&ctx->buf[SM3_BLOCK_SIZE - 8] = cpu_to_be64(bitcount);
+	sm3_blocks(&ctx->state, ctx->buf, 1);
+
+	for (size_t i = 0; i < SM3_DIGEST_SIZE; i += 4)
+		put_unaligned_be32(ctx->state.h[i / 4], out + i);
+}
+
+void sm3_final(struct sm3_ctx *ctx, u8 out[SM3_DIGEST_SIZE])
+{
+	__sm3_final(ctx, out);
+	memzero_explicit(ctx, sizeof(*ctx));
+}
+EXPORT_SYMBOL_GPL(sm3_final);
+
+void sm3(const u8 *data, size_t len, u8 out[SM3_DIGEST_SIZE])
+{
+	struct sm3_ctx ctx;
+
+	sm3_init(&ctx);
+	sm3_update(&ctx, data, len);
+	sm3_final(&ctx, out);
+}
+EXPORT_SYMBOL_GPL(sm3);
+
+#ifdef sm3_mod_init_arch
+static int __init sm3_mod_init(void)
+{
+	sm3_mod_init_arch();
+	return 0;
+}
+subsys_initcall(sm3_mod_init);
+
+static void __exit sm3_mod_exit(void)
+{
+}
+module_exit(sm3_mod_exit);
+#endif
+
+MODULE_DESCRIPTION("SM3 library functions");
+MODULE_LICENSE("GPL v2");