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, 67 insertions, 0 deletions

diff --git a/lib/crypto/powerpc/sha1.h b/lib/crypto/powerpc/sha1.h
new file mode 100644
index 000000000..e2c010f03
--- /dev/null
+++ b/lib/crypto/powerpc/sha1.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * SHA-1 optimized for PowerPC
+ *
+ * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
+ */
+
+#include <asm/switch_to.h>
+#include <linux/preempt.h>
+
+#ifdef CONFIG_SPE
+/*
+ * MAX_BYTES defines the number of bytes that are allowed to be processed
+ * between preempt_disable() and preempt_enable(). SHA1 takes ~1000
+ * operations per 64 bytes. e500 cores can issue two arithmetic instructions
+ * per clock cycle using one 32/64 bit unit (SU1) and one 32 bit unit (SU2).
+ * Thus 2KB of input data will need an estimated maximum of 18,000 cycles.
+ * Headroom for cache misses included. Even with the low end model clocked
+ * at 667 MHz this equals to a critical time window of less than 27us.
+ *
+ */
+#define MAX_BYTES 2048
+
+asmlinkage void ppc_spe_sha1_transform(struct sha1_block_state *state,
+				       const u8 *data, u32 nblocks);
+
+static void spe_begin(void)
+{
+	/* We just start SPE operations and will save SPE registers later. */
+	preempt_disable();
+	enable_kernel_spe();
+}
+
+static void spe_end(void)
+{
+	disable_kernel_spe();
+	/* reenable preemption */
+	preempt_enable();
+}
+
+static void sha1_blocks(struct sha1_block_state *state,
+			const u8 *data, size_t nblocks)
+{
+	do {
+		u32 unit = min_t(size_t, nblocks, MAX_BYTES / SHA1_BLOCK_SIZE);
+
+		spe_begin();
+		ppc_spe_sha1_transform(state, data, unit);
+		spe_end();
+
+		data += unit * SHA1_BLOCK_SIZE;
+		nblocks -= unit;
+	} while (nblocks);
+}
+#else /* CONFIG_SPE */
+asmlinkage void powerpc_sha_transform(struct sha1_block_state *state,
+				      const u8 data[SHA1_BLOCK_SIZE]);
+
+static void sha1_blocks(struct sha1_block_state *state,
+			const u8 *data, size_t nblocks)
+{
+	do {
+		powerpc_sha_transform(state, data);
+		data += SHA1_BLOCK_SIZE;
+	} while (--nblocks);
+}
+#endif /* !CONFIG_SPE */