From 3a2c4d55e32ad65efebdb6de44eef3bfa08bb49d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 2 Sep 2026 15:31:14 -0700 Subject: treewide: refresh kmalloc_obj() conversions This is another run of the Coccinelle script for converting kmalloc() family of allocations to kmalloc_obj() via the existing rules in scripts/coccinelle/api/kmalloc_objs.cocci This catches both the set of kmalloc() uses added since the first kmalloc_obj() conversions in v7.0 and adds a large group missed in the first pass due to Coccinelle not interacting well with the cleanup.h scoped_...() family of macros[1]. I worked around this with spatch's "--macro-file" argument to a file with all the scoped_...() macros mapped to Coccinelle's YACFE_ITERATOR[2] as that was the closest viable control flow indicator I could find. Build tested allmodconfig on x86, arm64, arm, loongarch, mips, powerpc, riscv, and s390 with no new warnings. Link: https://lore.kernel.org/lkml/202609021314.8A9C0B8@keescook/ [1] Link: https://github.com/coccinelle/coccinelle/blob/master/standard.h [2] Signed-off-by: Kees Cook --- lib/zstd/compress/hist.c | 176 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 176 insertions(+) create mode 100644 lib/zstd/compress/hist.c (limited to 'lib/zstd/compress/hist.c') 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 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 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); +} + -- cgit v1.3.1