KVM: selftests: Implement memcmp(), memcpy(), and memset() for guest use

Implement memcmp(), memcpy(), and memset() to override the compiler's
built-in versions in order to guarantee that the compiler won't generate
out-of-line calls to external functions via the PLT.  This allows the
helpers to be safely used in guest code, as KVM selftests don't support
dynamic loading of guest code.

Steal the implementations from the kernel's generic versions, sans the
optimizations in memcmp() for unaligned accesses.

Put the utilities in a separate compilation unit and build with
-ffreestanding to fudge around a gcc "feature" where it will optimize
memset(), memcpy(), etc... by generating a recursive call.  I.e. the
compiler optimizes itself into infinite recursion.  Alternatively, the
individual functions could be tagged with
optimize("no-tree-loop-distribute-patterns"), but using "optimize" for
anything but debug is discouraged, and Linus NAK'd the use of the flag
in the kernel proper[*].

https://lore.kernel.org/lkml/CAHk-=wik-oXnUpfZ6Hw37uLykc-_P0Apyn2XuX-odh-3Nzop8w@mail.gmail.com

Cc: Andrew Jones <andrew.jones@linux.dev>
Cc: Anup Patel <anup@brainfault.org>
Cc: Atish Patra <atishp@atishpatra.org>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Janosch Frank <frankja@linux.ibm.com>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220928233652.783504-2-seanjc@google.com>
Reviewed-by: Andrew Jones <andrew.jones@linux.dev>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

tools/testing/selftests/kvm/Makefile

@@ -48,6 +48,8 @@ LIBKVM += lib/rbtree.c
 LIBKVM += lib/sparsebit.c
 LIBKVM += lib/test_util.c
 
+LIBKVM_STRING += lib/string_override.c
+
 LIBKVM_x86_64 += lib/x86_64/apic.c
 LIBKVM_x86_64 += lib/x86_64/handlers.S
 LIBKVM_x86_64 += lib/x86_64/perf_test_util.c
@@ -220,7 +222,8 @@ LIBKVM_C := $(filter %.c,$(LIBKVM))
 LIBKVM_S := $(filter %.S,$(LIBKVM))
 LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
 LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
-LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
+LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING))
+LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ)
 
 EXTRA_CLEAN += $(LIBKVM_OBJS) cscope.*
 
@@ -231,6 +234,12 @@ $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
 $(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
+# Compile the string overrides as freestanding to prevent the compiler from
+# generating self-referential code, e.g. without "freestanding" the compiler may
+# "optimize" memcmp() by invoking memcmp(), thus causing infinite recursion.
+$(LIBKVM_STRING_OBJ): $(OUTPUT)/%.o: %.c
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c -ffreestanding $< -o $@
+
 x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
 $(TEST_GEN_PROGS): $(LIBKVM_OBJS)
 $(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS)

tools/testing/selftests/kvm/lib/string_override.c

@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <stddef.h>
+
+/*
+ * Override the "basic" built-in string helpers so that they can be used in
+ * guest code.  KVM selftests don't support dynamic loading in guest code and
+ * will jump into the weeds if the compiler decides to insert an out-of-line
+ * call via the PLT.
+ */
+int memcmp(const void *cs, const void *ct, size_t count)
+{
+	const unsigned char *su1, *su2;
+	int res = 0;
+
+	for (su1 = cs, su2 = ct; 0 < count; ++su1, ++su2, count--) {
+		if ((res = *su1 - *su2) != 0)
+			break;
+	}
+	return res;
+}
+
+void *memcpy(void *dest, const void *src, size_t count)
+{
+	char *tmp = dest;
+	const char *s = src;
+
+	while (count--)
+		*tmp++ = *s++;
+	return dest;
+}
+
+void *memset(void *s, int c, size_t count)
+{
+	char *xs = s;
+
+	while (count--)
+		*xs++ = c;
+	return s;
+}