lib: zstd: update to latest Linux zstd 1.5.2

Update the zstd implementation to match Linux zstd 1.5.2 from commit
2aa14b1ab2.

This was motivated by running into decompression corruption issues when
trying to uncompress files compressed with newer versions of zstd. zstd
users also claim significantly improved decompression times with newer
zstd versions which is a side benefit.

Original zstd code was copied from Linux commit 2aa14b1ab2 which is a
custom-built implementation based on zstd 1.3.1. Linux switched to an
implementation that is a copy of the upstream zstd code in Linux commit
e0c1b49f5b, this results in a large code diff. However this should make
future updates easier along with other benefits[1].

This commit is a straight mirror of the Linux zstd code, except to:
- update a few #include that do not translate cleanly
  - linux/swab.h -> asm/byteorder.h
  - linux/limits.h -> linux/kernel.h
  - linux/module.h -> linux/compat.h
- remove assert() from debug.h so it doesn't conflict with u-boot's
  assert()
- strip out the compressor code as was done in the previous u-boot zstd
- update existing zstd users to the new Linux zstd API
- change the #define for MEM_STATIC to use INLINE_KEYWORD for codesize
- add a new KConfig option that sets zstd build options to minify code
  based on zstd's ZSTD_LIB_MINIFY[2].

These changes were tested by booting a zstd 1.5.2 compressed kernel inside a
FIT. And the squashfs changes by loading a file from zstd compressed squashfs
with sqfsload. buildman was used to compile test other boards and check for
binary bloat, as follows:

> $ buildman -b zstd2 --boards dh_imx6,m53menlo,mvebu_espressobin-88f3720,sandbox,sandbox64,stm32mp15_dhcom_basic,stm32mp15_dhcor_basic,turris_mox,turris_omnia -sS
> Summary of 6 commits for 9 boards (8 threads, 1 job per thread)
> 01: Merge branch '2023-01-10-platform-updates'
>        arm:  w+   m53menlo dh_imx6
> 02: lib: zstd: update to latest Linux zstd 1.5.2
>    aarch64: (for 2/2 boards) all -3186.0 rodata +920.0 text -4106.0
>        arm: (for 5/5 boards) all +1254.4 rodata +940.0 text +314.4
>    sandbox: (for 2/2 boards) all -4452.0 data -16.0 rodata +640.0 text -5076.0

[1] https://github.com/torvalds/linux/commit/e0c1b49f5b674cca7b10549c53b3791d0bbc90a8
[2] https://github.com/facebook/zstd/blob/f302ad8811643c428c4e3498e28f53a0578020d3/lib/libzstd.mk#L31

Signed-off-by: Brandon Maier <brandon.maier@collins.com>
[trini: Set ret to -EINVAL for the error of "failed to detect
compressed" to fix warning, drop ZSTD_SRCSIZEHINT_MAX for non-Linux host
tool builds]
Signed-off-by: Tom Rini <trini@konsulko.com>

1 files changed, 0 insertions, 213 deletions

diff --git a/lib/zstd/entropy_common.c b/lib/zstd/entropy_common.c
deleted file mode 100644
index 071fef997e7..00000000000
--- a/lib/zstd/entropy_common.c
+++ /dev/null
@@ -1,213 +0,0 @@
-// SPDX-License-Identifier: (GPL-2.0 or BSD-2-Clause)
-/*
- * Common functions of New Generation Entropy library
- * Copyright (C) 2016, Yann Collet.
- *
- * You can contact the author at :
- * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
- */
-
-/* *************************************
-*  Dependencies
-***************************************/
-#include "error_private.h" /* ERR_*, ERROR */
-#include "fse.h"
-#include "huf.h"
-#include "mem.h"
-
-/*===   Version   ===*/
-unsigned FSE_versionNumber(void) { return FSE_VERSION_NUMBER; }
-
-/*===   Error Management   ===*/
-unsigned FSE_isError(size_t code) { return ERR_isError(code); }
-
-unsigned HUF_isError(size_t code) { return ERR_isError(code); }
-
-/*-**************************************************************
-*  FSE NCount encoding-decoding
-****************************************************************/
-size_t FSE_readNCount(short *normalizedCounter, unsigned *maxSVPtr, unsigned *tableLogPtr, const void *headerBuffer, size_t hbSize)
-{
-	const BYTE *const istart = (const BYTE *)headerBuffer;
-	const BYTE *const iend = istart + hbSize;
-	const BYTE *ip = istart;
-	int nbBits;
-	int remaining;
-	int threshold;
-	U32 bitStream;
-	int bitCount;
-	unsigned charnum = 0;
-	int previous0 = 0;
-
-	if (hbSize < 4)
-		return ERROR(srcSize_wrong);
-	bitStream = ZSTD_readLE32(ip);
-	nbBits = (bitStream & 0xF) + FSE_MIN_TABLELOG; /* extract tableLog */
-	if (nbBits > FSE_TABLELOG_ABSOLUTE_MAX)
-		return ERROR(tableLog_tooLarge);
-	bitStream >>= 4;
-	bitCount = 4;
-	*tableLogPtr = nbBits;
-	remaining = (1 << nbBits) + 1;
-	threshold = 1 << nbBits;
-	nbBits++;
-
-	while ((remaining > 1) & (charnum <= *maxSVPtr)) {
-		if (previous0) {
-			unsigned n0 = charnum;
-			while ((bitStream & 0xFFFF) == 0xFFFF) {
-				n0 += 24;
-				if (ip < iend - 5) {
-					ip += 2;
-					bitStream = ZSTD_readLE32(ip) >> bitCount;
-				} else {
-					bitStream >>= 16;
-					bitCount += 16;
-				}
-			}
-			while ((bitStream & 3) == 3) {
-				n0 += 3;
-				bitStream >>= 2;
-				bitCount += 2;
-			}
-			n0 += bitStream & 3;
-			bitCount += 2;
-			if (n0 > *maxSVPtr)
-				return ERROR(maxSymbolValue_tooSmall);
-			while (charnum < n0)
-				normalizedCounter[charnum++] = 0;
-			if ((ip <= iend - 7) || (ip + (bitCount >> 3) <= iend - 4)) {
-				ip += bitCount >> 3;
-				bitCount &= 7;
-				bitStream = ZSTD_readLE32(ip) >> bitCount;
-			} else {
-				bitStream >>= 2;
-			}
-		}
-		{
-			int const max = (2 * threshold - 1) - remaining;
-			int count;
-
-			if ((bitStream & (threshold - 1)) < (U32)max) {
-				count = bitStream & (threshold - 1);
-				bitCount += nbBits - 1;
-			} else {
-				count = bitStream & (2 * threshold - 1);
-				if (count >= threshold)
-					count -= max;
-				bitCount += nbBits;
-			}
-
-			count--;				 /* extra accuracy */
-			remaining -= count < 0 ? -count : count; /* -1 means +1 */
-			normalizedCounter[charnum++] = (short)count;
-			previous0 = !count;
-			while (remaining < threshold) {
-				nbBits--;
-				threshold >>= 1;
-			}
-
-			if ((ip <= iend - 7) || (ip + (bitCount >> 3) <= iend - 4)) {
-				ip += bitCount >> 3;
-				bitCount &= 7;
-			} else {
-				bitCount -= (int)(8 * (iend - 4 - ip));
-				ip = iend - 4;
-			}
-			bitStream = ZSTD_readLE32(ip) >> (bitCount & 31);
-		}
-	} /* while ((remaining>1) & (charnum<=*maxSVPtr)) */
-	if (remaining != 1)
-		return ERROR(corruption_detected);
-	if (bitCount > 32)
-		return ERROR(corruption_detected);
-	*maxSVPtr = charnum - 1;
-
-	ip += (bitCount + 7) >> 3;
-	return ip - istart;
-}
-
-/*! HUF_readStats() :
-	Read compact Huffman tree, saved by HUF_writeCTable().
-	`huffWeight` is destination buffer.
-	`rankStats` is assumed to be a table of at least HUF_TABLELOG_MAX U32.
-	@return : size read from `src` , or an error Code .
-	Note : Needed by HUF_readCTable() and HUF_readDTableX?() .
-*/
-size_t HUF_readStats_wksp(BYTE *huffWeight, size_t hwSize, U32 *rankStats, U32 *nbSymbolsPtr, U32 *tableLogPtr, const void *src, size_t srcSize, void *workspace, size_t workspaceSize)
-{
-	U32 weightTotal;
-	const BYTE *ip = (const BYTE *)src;
-	size_t iSize;
-	size_t oSize;
-
-	if (!srcSize)
-		return ERROR(srcSize_wrong);
-	iSize = ip[0];
-	/* memset(huffWeight, 0, hwSize);   */ /* is not necessary, even though some analyzer complain ... */
-
-	if (iSize >= 128) { /* special header */
-		oSize = iSize - 127;
-		iSize = ((oSize + 1) / 2);
-		if (iSize + 1 > srcSize)
-			return ERROR(srcSize_wrong);
-		if (oSize >= hwSize)
-			return ERROR(corruption_detected);
-		ip += 1;
-		{
-			U32 n;
-			for (n = 0; n < oSize; n += 2) {
-				huffWeight[n] = ip[n / 2] >> 4;
-				huffWeight[n + 1] = ip[n / 2] & 15;
-			}
-		}
-	} else {						 /* header compressed with FSE (normal case) */
-		if (iSize + 1 > srcSize)
-			return ERROR(srcSize_wrong);
-		oSize = FSE_decompress_wksp(huffWeight, hwSize - 1, ip + 1, iSize, 6, workspace, workspaceSize); /* max (hwSize-1) values decoded, as last one is implied */
-		if (FSE_isError(oSize))
-			return oSize;
-	}
-
-	/* collect weight stats */
-	memset(rankStats, 0, (HUF_TABLELOG_MAX + 1) * sizeof(U32));
-	weightTotal = 0;
-	{
-		U32 n;
-		for (n = 0; n < oSize; n++) {
-			if (huffWeight[n] >= HUF_TABLELOG_MAX)
-				return ERROR(corruption_detected);
-			rankStats[huffWeight[n]]++;
-			weightTotal += (1 << huffWeight[n]) >> 1;
-		}
-	}
-	if (weightTotal == 0)
-		return ERROR(corruption_detected);
-
-	/* get last non-null symbol weight (implied, total must be 2^n) */
-	{
-		U32 const tableLog = BIT_highbit32(weightTotal) + 1;
-		if (tableLog > HUF_TABLELOG_MAX)
-			return ERROR(corruption_detected);
-		*tableLogPtr = tableLog;
-		/* determine last weight */
-		{
-			U32 const total = 1 << tableLog;
-			U32 const rest = total - weightTotal;
-			U32 const verif = 1 << BIT_highbit32(rest);
-			U32 const lastWeight = BIT_highbit32(rest) + 1;
-			if (verif != rest)
-				return ERROR(corruption_detected); /* last value must be a clean power of 2 */
-			huffWeight[oSize] = (BYTE)lastWeight;
-			rankStats[lastWeight]++;
-		}
-	}
-
-	/* check tree construction validity */
-	if ((rankStats[1] < 2) || (rankStats[1] & 1))
-		return ERROR(corruption_detected); /* by construction : at least 2 elts of rank 1, must be even */
-
-	/* results */
-	*nbSymbolsPtr = (U32)(oSize + 1);
-	return iSize + 1;
-}