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, 186 insertions, 0 deletions

diff --git a/arch/alpha/lib/checksum.c b/arch/alpha/lib/checksum.c
new file mode 100644
index 000000000..27b2a9edf
--- /dev/null
+++ b/arch/alpha/lib/checksum.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * arch/alpha/lib/checksum.c
+ *
+ * This file contains network checksum routines that are better done
+ * in an architecture-specific manner due to speed..
+ * Comments in other versions indicate that the algorithms are from RFC1071
+ *
+ * accelerated versions (and 21264 assembly versions ) contributed by
+ *	Rick Gorton	<rick.gorton@alpha-processor.com>
+ */
+ 
+#include <linux/module.h>
+#include <linux/string.h>
+#include <net/checksum.h>
+
+#include <asm/byteorder.h>
+#include <asm/checksum.h>
+
+static inline unsigned short from64to16(unsigned long x)
+{
+	/* Using extract instructions is a bit more efficient
+	   than the original shift/bitmask version.  */
+
+	union {
+		unsigned long	ul;
+		unsigned int	ui[2];
+		unsigned short	us[4];
+	} in_v, tmp_v, out_v;
+
+	in_v.ul = x;
+	tmp_v.ul = (unsigned long) in_v.ui[0] + (unsigned long) in_v.ui[1];
+
+	/* Since the bits of tmp_v.sh[3] are going to always be zero,
+	   we don't have to bother to add that in.  */
+	out_v.ul = (unsigned long) tmp_v.us[0] + (unsigned long) tmp_v.us[1]
+			+ (unsigned long) tmp_v.us[2];
+
+	/* Similarly, out_v.us[2] is always zero for the final add.  */
+	return out_v.us[0] + out_v.us[1];
+}
+
+/*
+ * computes the checksum of the TCP/UDP pseudo-header
+ * returns a 16-bit checksum, already complemented.
+ */
+__sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+			  __u32 len, __u8 proto, __wsum sum)
+{
+	return (__force __sum16)~from64to16(
+		(__force u64)saddr + (__force u64)daddr +
+		(__force u64)sum + ((len + proto) << 8));
+}
+EXPORT_SYMBOL(csum_tcpudp_magic);
+
+__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+			  __u32 len, __u8 proto, __wsum sum)
+{
+	unsigned long result;
+
+	result = (__force u64)saddr + (__force u64)daddr +
+		 (__force u64)sum + ((len + proto) << 8);
+
+	/* Fold down to 32-bits so we don't lose in the typedef-less 
+	   network stack.  */
+	/* 64 to 33 */
+	result = (result & 0xffffffff) + (result >> 32);
+	/* 33 to 32 */
+	result = (result & 0xffffffff) + (result >> 32);
+	return (__force __wsum)result;
+}
+EXPORT_SYMBOL(csum_tcpudp_nofold);
+
+/*
+ * Do a 64-bit checksum on an arbitrary memory area..
+ *
+ * This isn't a great routine, but it's not _horrible_ either. The
+ * inner loop could be unrolled a bit further, and there are better
+ * ways to do the carry, but this is reasonable.
+ */
+static inline unsigned long do_csum(const unsigned char * buff, int len)
+{
+	int odd, count;
+	unsigned long result = 0;
+
+	if (len <= 0)
+		goto out;
+	odd = 1 & (unsigned long) buff;
+	if (odd) {
+		result = *buff << 8;
+		len--;
+		buff++;
+	}
+	count = len >> 1;		/* nr of 16-bit words.. */
+	if (count) {
+		if (2 & (unsigned long) buff) {
+			result += *(unsigned short *) buff;
+			count--;
+			len -= 2;
+			buff += 2;
+		}
+		count >>= 1;		/* nr of 32-bit words.. */
+		if (count) {
+			if (4 & (unsigned long) buff) {
+				result += *(unsigned int *) buff;
+				count--;
+				len -= 4;
+				buff += 4;
+			}
+			count >>= 1;	/* nr of 64-bit words.. */
+			if (count) {
+				unsigned long carry = 0;
+				do {
+					unsigned long w = *(unsigned long *) buff;
+					count--;
+					buff += 8;
+					result += carry;
+					result += w;
+					carry = (w > result);
+				} while (count);
+				result += carry;
+				result = (result & 0xffffffff) + (result >> 32);
+			}
+			if (len & 4) {
+				result += *(unsigned int *) buff;
+				buff += 4;
+			}
+		}
+		if (len & 2) {
+			result += *(unsigned short *) buff;
+			buff += 2;
+		}
+	}
+	if (len & 1)
+		result += *buff;
+	result = from64to16(result);
+	if (odd)
+		result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
+out:
+	return result;
+}
+
+/*
+ *	This is a version of ip_compute_csum() optimized for IP headers,
+ *	which always checksum on 4 octet boundaries.
+ */
+__sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	return (__force __sum16)~do_csum(iph,ihl*4);
+}
+EXPORT_SYMBOL(ip_fast_csum);
+
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic
+ *
+ * this function must be called with even lengths, except
+ * for the last fragment, which may be odd
+ *
+ * it's best to have buff aligned on a 32-bit boundary
+ */
+__wsum csum_partial(const void *buff, int len, __wsum sum)
+{
+	unsigned long result = do_csum(buff, len);
+
+	/* add in old sum, and carry.. */
+	result += (__force u32)sum;
+	/* 32+c bits -> 32 bits */
+	result = (result & 0xffffffff) + (result >> 32);
+	return (__force __wsum)result;
+}
+
+EXPORT_SYMBOL(csum_partial);
+
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+__sum16 ip_compute_csum(const void *buff, int len)
+{
+	return (__force __sum16)~from64to16(do_csum(buff,len));
+}
+EXPORT_SYMBOL(ip_compute_csum);