[PATCH v4 1/8] lib: prepare zstd for preboot environment

[Nick Terrell]

From: Nick Terrell <terrelln@xxxxxx>

* Don't export symbols if ZSTD_PREBOOT is defined.
* Remove a double definition of the CHECK_F macro when the zstd
  library is amalgamated.
* Switch ZSTD_copy8() to __builtin_memcpy(), because in the preboot
  environment on x86 gcc can't inline `memcpy()` otherwise.
* Limit the gcc hack in ZSTD_wildcopy() to the broken gcc version. See
  https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388.

These changes are necessary to get the build to work in the preboot
environment, and to get reasonable performance. ZSTD_copy8() and
ZSTD_wildcopy() are in the core of the zstd hot loop. So outlining
these calls to memcpy(), and having an extra branch are very
detrimental to performance.

Reviewed-by: Kees Cook <keescook@xxxxxxxxxxxx>
Tested-by: Sedat Dilek <sedat.dilek@xxxxxxxxx>
Signed-off-by: Nick Terrell <terrelln@xxxxxx>
---
 lib/zstd/decompress.c     |  2 ++
 lib/zstd/fse_decompress.c |  9 +--------
 lib/zstd/zstd_internal.h  | 14 ++++++++++++--
 3 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/lib/zstd/decompress.c b/lib/zstd/decompress.c
index 269ee9a796c1..73ded63278cf 100644
--- a/lib/zstd/decompress.c
+++ b/lib/zstd/decompress.c
@@ -2490,6 +2490,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB
 	}
 }
 
+#ifndef ZSTD_PREBOOT
 EXPORT_SYMBOL(ZSTD_DCtxWorkspaceBound);
 EXPORT_SYMBOL(ZSTD_initDCtx);
 EXPORT_SYMBOL(ZSTD_decompressDCtx);
@@ -2529,3 +2530,4 @@ EXPORT_SYMBOL(ZSTD_insertBlock);
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_DESCRIPTION("Zstd Decompressor");
+#endif
diff --git a/lib/zstd/fse_decompress.c b/lib/zstd/fse_decompress.c
index a84300e5a013..0b353530fb3f 100644
--- a/lib/zstd/fse_decompress.c
+++ b/lib/zstd/fse_decompress.c
@@ -47,6 +47,7 @@
 ****************************************************************/
 #include "bitstream.h"
 #include "fse.h"
+#include "zstd_internal.h"
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/string.h> /* memcpy, memset */
@@ -60,14 +61,6 @@
 		enum { FSE_static_assert = 1 / (int)(!!(c)) }; \
 	} /* use only *after* variable declarations */
 
-/* check and forward error code */
-#define CHECK_F(f)                  \
-	{                           \
-		size_t const e = f; \
-		if (FSE_isError(e)) \
-			return e;   \
-	}
-
 /* **************************************************************
 *  Templates
 ****************************************************************/
diff --git a/lib/zstd/zstd_internal.h b/lib/zstd/zstd_internal.h
index 1a79fab9e13a..dac753397f86 100644
--- a/lib/zstd/zstd_internal.h
+++ b/lib/zstd/zstd_internal.h
@@ -127,7 +127,14 @@ static const U32 OF_defaultNormLog = OF_DEFAULTNORMLOG;
 *  Shared functions to include for inlining
 *********************************************/
 ZSTD_STATIC void ZSTD_copy8(void *dst, const void *src) {
-	memcpy(dst, src, 8);
+	/*
+	 * zstd relies heavily on gcc being able to analyze and inline this
+	 * memcpy() call, since it is called in a tight loop. Preboot mode
+	 * is compiled in freestanding mode, which stops gcc from analyzing
+	 * memcpy(). Use __builtin_memcpy() to tell gcc to analyze this as a
+	 * regular memcpy().
+	 */
+	__builtin_memcpy(dst, src, 8);
 }
 /*! ZSTD_wildcopy() :
 *   custom version of memcpy(), can copy up to 7 bytes too many (8 bytes if length==0) */
@@ -137,13 +144,16 @@ ZSTD_STATIC void ZSTD_wildcopy(void *dst, const void *src, ptrdiff_t length)
 	const BYTE* ip = (const BYTE*)src;
 	BYTE* op = (BYTE*)dst;
 	BYTE* const oend = op + length;
-	/* Work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388.
+#if defined(GCC_VERSION) && GCC_VERSION >= 70000 && GCC_VERSION < 70200
+	/*
+	 * Work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388.
 	 * Avoid the bad case where the loop only runs once by handling the
 	 * special case separately. This doesn't trigger the bug because it
 	 * doesn't involve pointer/integer overflow.
 	 */
 	if (length <= 8)
 		return ZSTD_copy8(dst, src);
+#endif
 	do {
 		ZSTD_copy8(op, ip);
 		op += 8;
-- 
2.26.0