From 6e5b3d4265971a0494c4ef016597f65c41651ed9 Mon Sep 17 00:00:00 2001
From: Simon Glass <sjg@chromium.org>
Date: Sun, 26 Jan 2025 11:43:22 -0700
Subject: [PATCH] lib: Mark lz4 as relocation code
Mark the lz4 decompression code as needed by relocation. This is used to
decompress the next-phase image.
Drop the 'safe' versions from SPL as they are not needed. Change the
static array to a local one, to avoid a crash errors when trying to
access the data from relocated code. Make this conditional to avoid a
code-size increase when SPL_RELOC is not used/
Signed-off-by: Simon Glass <sjg@chromium.org>
---
lib/lz4.c | 37 ++++++++++++++++++++++++++-----------
lib/lz4_wrapper.c | 2 +-
2 files changed, 27 insertions(+), 12 deletions(-)
diff --git a/lib/lz4.c b/lib/lz4.c
index 63955a0b178..c718659c590 100644
--- a/lib/lz4.c
+++ b/lib/lz4.c
@@ -33,15 +33,16 @@
#include <linux/bug.h>
#include <asm/unaligned.h>
#include <u-boot/lz4.h>
+#include <asm/sections.h>
#define FORCE_INLINE inline __attribute__((always_inline))
-static FORCE_INLINE u16 LZ4_readLE16(const void *src)
+__rcode static FORCE_INLINE u16 LZ4_readLE16(const void *src)
{
return get_unaligned_le16(src);
}
-static FORCE_INLINE void LZ4_copy8(void *dst, const void *src)
+__rcode static FORCE_INLINE void LZ4_copy8(void *dst, const void *src)
{
put_unaligned(get_unaligned((const u64 *)src), (u64 *)dst);
}
@@ -53,7 +54,7 @@ typedef int32_t S32;
typedef uint64_t U64;
typedef uintptr_t uptrval;
-static FORCE_INLINE void LZ4_write32(void *memPtr, U32 value)
+__rcode static FORCE_INLINE void LZ4_write32(void *memPtr, U32 value)
{
put_unaligned(value, (U32 *)memPtr);
}
@@ -63,7 +64,7 @@ static FORCE_INLINE void LZ4_write32(void *memPtr, U32 value)
**************************************/
/* customized version of memcpy, which may overwrite up to 7 bytes beyond dstEnd */
-static void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd)
+__rcode static void LZ4_wildCopy(void *dstPtr, const void *srcPtr, void *dstEnd)
{
BYTE* d = (BYTE*)dstPtr;
const BYTE* s = (const BYTE*)srcPtr;
@@ -111,6 +112,17 @@ typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive;
#define assert(condition) ((void)0)
#endif
+/*
+ * spl_reloc needs all necessary data to be set up within its code, since the
+ * code is relocated at runtime. Unfortunately this increase code-size slightly
+ * so only do it if spl_reloc is enabled
+ */
+#if CONFIG_IS_ENABLED(RELOC_LOADER)
+#define STATIC
+#else
+#define STATIC static
+#endif
+
/*
* LZ4_decompress_generic() :
* This generic decompression function covers all use cases.
@@ -118,7 +130,7 @@ typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive;
* Note that it is important for performance that this function really get inlined,
* in order to remove useless branches during compilation optimization.
*/
-static FORCE_INLINE int LZ4_decompress_generic(
+__rcode static FORCE_INLINE int LZ4_decompress_generic(
const char * const src,
char * const dst,
int srcSize,
@@ -141,6 +153,8 @@ static FORCE_INLINE int LZ4_decompress_generic(
const size_t dictSize
)
{
+ STATIC const unsigned int inc32table[8] = {0, 1, 2, 1, 0, 4, 4, 4};
+ STATIC const int dec64table[8] = {0, 0, 0, -1, -4, 1, 2, 3};
const BYTE *ip = (const BYTE *) src;
const BYTE * const iend = ip + srcSize;
@@ -149,8 +163,6 @@ static FORCE_INLINE int LZ4_decompress_generic(
BYTE *cpy;
const BYTE * const dictEnd = (const BYTE *)dictStart + dictSize;
- static const unsigned int inc32table[8] = {0, 1, 2, 1, 0, 4, 4, 4};
- static const int dec64table[8] = {0, 0, 0, -1, -4, 1, 2, 3};
const int safeDecode = (endOnInput == endOnInputSize);
const int checkOffset = ((safeDecode) && (dictSize < (int)(64 * KB)));
@@ -514,8 +526,9 @@ _output_error:
return (int) (-(((const char *)ip) - src)) - 1;
}
-int LZ4_decompress_safe(const char *source, char *dest,
- int compressedSize, int maxDecompressedSize)
+#ifndef CONFIG_SPL_BUILD
+__rcode int LZ4_decompress_safe(const char *source, char *dest,
+ int compressedSize, int maxDecompressedSize)
{
return LZ4_decompress_generic(source, dest,
compressedSize, maxDecompressedSize,
@@ -523,11 +536,13 @@ int LZ4_decompress_safe(const char *source, char *dest,
noDict, (BYTE *)dest, NULL, 0);
}
-int LZ4_decompress_safe_partial(const char *src, char *dst,
- int compressedSize, int targetOutputSize, int dstCapacity)
+__rcode int LZ4_decompress_safe_partial(const char *src, char *dst,
+ int compressedSize,
+ int targetOutputSize, int dstCapacity)
{
dstCapacity = min(targetOutputSize, dstCapacity);
return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity,
endOnInputSize, partial_decode,
noDict, (BYTE *)dst, NULL, 0);
}
+#endif
diff --git a/lib/lz4_wrapper.c b/lib/lz4_wrapper.c
index 4d48e7b0e8b..b1204511170 100644
--- a/lib/lz4_wrapper.c
+++ b/lib/lz4_wrapper.c
@@ -15,7 +15,7 @@
#define LZ4F_BLOCKUNCOMPRESSED_FLAG 0x80000000U
-int ulz4fn(const void *src, size_t srcn, void *dst, size_t *dstn)
+__rcode int ulz4fn(const void *src, size_t srcn, void *dst, size_t *dstn)
{
const void *end = dst + *dstn;
const void *in = src;