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, 176 insertions, 0 deletions

diff --git a/lib/zstd/compress/hist.c b/lib/zstd/compress/hist.c
new file mode 100644
index 000000000..87145a2d9
--- /dev/null
+++ b/lib/zstd/compress/hist.c
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
+/* ******************************************************************
+ * hist : Histogram functions
+ * part of Finite State Entropy project
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
+ *
+ *  You can contact the author at :
+ *  - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *  - Public forum : https://groups.google.com/forum/#!forum/lz4c
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+
+/* --- dependencies --- */
+#include "../common/mem.h"             /* U32, BYTE, etc. */
+#include "../common/debug.h"           /* assert, DEBUGLOG */
+#include "../common/error_private.h"   /* ERROR */
+#include "hist.h"
+
+
+/* --- Error management --- */
+unsigned HIST_isError(size_t code) { return ERR_isError(code); }
+
+/*-**************************************************************
+ *  Histogram functions
+ ****************************************************************/
+void HIST_add(unsigned* count, const void* src, size_t srcSize)
+{
+    const BYTE* ip = (const BYTE*)src;
+    const BYTE* const end = ip + srcSize;
+
+    while (ip<end) {
+        count[*ip++]++;
+    }
+}
+
+unsigned HIST_count_simple(unsigned* count, unsigned* maxSymbolValuePtr,
+                           const void* src, size_t srcSize)
+{
+    const BYTE* ip = (const BYTE*)src;
+    const BYTE* const end = ip + srcSize;
+    unsigned maxSymbolValue = *maxSymbolValuePtr;
+    unsigned largestCount=0;
+
+    ZSTD_memset(count, 0, (maxSymbolValue+1) * sizeof(*count));
+    if (srcSize==0) { *maxSymbolValuePtr = 0; return 0; }
+
+    while (ip<end) {
+        assert(*ip <= maxSymbolValue);
+        count[*ip++]++;
+    }
+
+    while (!count[maxSymbolValue]) maxSymbolValue--;
+    *maxSymbolValuePtr = maxSymbolValue;
+
+    {   U32 s;
+        for (s=0; s<=maxSymbolValue; s++)
+            if (count[s] > largestCount) largestCount = count[s];
+    }
+
+    return largestCount;
+}
+
+typedef enum { trustInput, checkMaxSymbolValue } HIST_checkInput_e;
+
+/* HIST_count_parallel_wksp() :
+ * store histogram into 4 intermediate tables, recombined at the end.
+ * this design makes better use of OoO cpus,
+ * and is noticeably faster when some values are heavily repeated.
+ * But it needs some additional workspace for intermediate tables.
+ * `workSpace` must be a U32 table of size >= HIST_WKSP_SIZE_U32.
+ * @return : largest histogram frequency,
+ *           or an error code (notably when histogram's alphabet is larger than *maxSymbolValuePtr) */
+static size_t HIST_count_parallel_wksp(
+                                unsigned* count, unsigned* maxSymbolValuePtr,
+                                const void* source, size_t sourceSize,
+                                HIST_checkInput_e check,
+                                U32* const workSpace)
+{
+    const BYTE* ip = (const BYTE*)source;
+    const BYTE* const iend = ip+sourceSize;
+    size_t const countSize = (*maxSymbolValuePtr + 1) * sizeof(*count);
+    unsigned max=0;
+    U32* const Counting1 = workSpace;
+    U32* const Counting2 = Counting1 + 256;
+    U32* const Counting3 = Counting2 + 256;
+    U32* const Counting4 = Counting3 + 256;
+
+    /* safety checks */
+    assert(*maxSymbolValuePtr <= 255);
+    if (!sourceSize) {
+        ZSTD_memset(count, 0, countSize);
+        *maxSymbolValuePtr = 0;
+        return 0;
+    }
+    ZSTD_memset(workSpace, 0, 4*256*sizeof(unsigned));
+
+    /* by stripes of 16 bytes */
+    {   U32 cached = MEM_read32(ip); ip += 4;
+        while (ip < iend-15) {
+            U32 c = cached; cached = MEM_read32(ip); ip += 4;
+            Counting1[(BYTE) c     ]++;
+            Counting2[(BYTE)(c>>8) ]++;
+            Counting3[(BYTE)(c>>16)]++;
+            Counting4[       c>>24 ]++;
+            c = cached; cached = MEM_read32(ip); ip += 4;
+            Counting1[(BYTE) c     ]++;
+            Counting2[(BYTE)(c>>8) ]++;
+            Counting3[(BYTE)(c>>16)]++;
+            Counting4[       c>>24 ]++;
+            c = cached; cached = MEM_read32(ip); ip += 4;
+            Counting1[(BYTE) c     ]++;
+            Counting2[(BYTE)(c>>8) ]++;
+            Counting3[(BYTE)(c>>16)]++;
+            Counting4[       c>>24 ]++;
+            c = cached; cached = MEM_read32(ip); ip += 4;
+            Counting1[(BYTE) c     ]++;
+            Counting2[(BYTE)(c>>8) ]++;
+            Counting3[(BYTE)(c>>16)]++;
+            Counting4[       c>>24 ]++;
+        }
+        ip-=4;
+    }
+
+    /* finish last symbols */
+    while (ip<iend) Counting1[*ip++]++;
+
+    {   U32 s;
+        for (s=0; s<256; s++) {
+            Counting1[s] += Counting2[s] + Counting3[s] + Counting4[s];
+            if (Counting1[s] > max) max = Counting1[s];
+    }   }
+
+    {   unsigned maxSymbolValue = 255;
+        while (!Counting1[maxSymbolValue]) maxSymbolValue--;
+        if (check && maxSymbolValue > *maxSymbolValuePtr) return ERROR(maxSymbolValue_tooSmall);
+        *maxSymbolValuePtr = maxSymbolValue;
+        ZSTD_memmove(count, Counting1, countSize);   /* in case count & Counting1 are overlapping */
+    }
+    return (size_t)max;
+}
+
+/* HIST_countFast_wksp() :
+ * Same as HIST_countFast(), but using an externally provided scratch buffer.
+ * `workSpace` is a writable buffer which must be 4-bytes aligned,
+ * `workSpaceSize` must be >= HIST_WKSP_SIZE
+ */
+size_t HIST_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                          const void* source, size_t sourceSize,
+                          void* workSpace, size_t workSpaceSize)
+{
+    if (sourceSize < 1500) /* heuristic threshold */
+        return HIST_count_simple(count, maxSymbolValuePtr, source, sourceSize);
+    if ((size_t)workSpace & 3) return ERROR(GENERIC);  /* must be aligned on 4-bytes boundaries */
+    if (workSpaceSize < HIST_WKSP_SIZE) return ERROR(workSpace_tooSmall);
+    return HIST_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, trustInput, (U32*)workSpace);
+}
+
+/* HIST_count_wksp() :
+ * Same as HIST_count(), but using an externally provided scratch buffer.
+ * `workSpace` size must be table of >= HIST_WKSP_SIZE_U32 unsigned */
+size_t HIST_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                       const void* source, size_t sourceSize,
+                       void* workSpace, size_t workSpaceSize)
+{
+    if ((size_t)workSpace & 3) return ERROR(GENERIC);  /* must be aligned on 4-bytes boundaries */
+    if (workSpaceSize < HIST_WKSP_SIZE) return ERROR(workSpace_tooSmall);
+    if (*maxSymbolValuePtr < 255)
+        return HIST_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, checkMaxSymbolValue, (U32*)workSpace);
+    *maxSymbolValuePtr = 255;
+    return HIST_countFast_wksp(count, maxSymbolValuePtr, source, sourceSize, workSpace, workSpaceSize);
+}
+