lib: Prepare zstd for preboot environment, improve performance

These changes are necessary to get the build to work in the preboot
environment, and to get reasonable performance:

- 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.

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.

Signed-off-by: Nick Terrell <[e-mail]>
Signed-off-by: Ingo Molnar <[e-mail]>
Tested-by: Sedat Dilek <[e-mail]>
Reviewed-by: Kees Cook <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

lib/zstd/fse_decompress.c

···
 ****************************************************************/
 #include "bitstream.h"
 #include "fse.h"
+#include "zstd_internal.h"
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/string.h> /* memcpy, memset */
···
 	{                                                      \
 		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

lib/zstd/zstd_internal.h

···
 *  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) */
···
 	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;