@@ -51,6 +51,9 @@ CFLAGS-$(CONFIG_INDIRECT_THUNK) += -fno-
$(call cc-option-add,CFLAGS-stack-boundary,CC,-mpreferred-stack-boundary=3)
export CFLAGS-stack-boundary
+CFLAGS += $(call cc-option,$(CC),-mmemcpy-strategy=unrolled_loop:16:noalign$(comma)libcall:-1:noalign)
+CFLAGS += $(call cc-option,$(CC),-mmemset-strategy=unrolled_loop:16:noalign$(comma)libcall:-1:noalign)
+
ifeq ($(CONFIG_UBSAN),y)
# Don't enable alignment sanitisation. x86 has efficient unaligned accesses,
# and various things (ACPI tables, hypercall pages, stubs, etc) are wont-fix.
Stop the compiler from inlining non-trivial memset() and memcpy() (for memset() see e.g. map_vcpu_info() or kimage_load_segments() for examples). This way we even keep the compiler from using REP STOSQ / REP MOVSQ when we'd prefer REP STOSB / REP MOVSB (when ERMS is available). With gcc10 this yields a modest .text size reduction (release build) of around 2k. Unfortunately these options aren't understood by the clang versions I have readily available for testing with; I'm unaware of equivalents. Note also that using cc-option-add is not an option here, or at least I couldn't make things work with it (in case the option was not supported by the compiler): The embedded comma in the option looks to be getting in the way. Requested-by: Andrew Cooper <andrew.cooper3@citrix.com> Signed-off-by: Jan Beulich <jbeulich@suse.com> --- v2: New. --- The boundary values are of course up for discussion - I wasn't really certain whether to use 16 or 32; I'd be less certain about using yet larger values. Similarly whether to permit the compiler to emit REP STOSQ / REP MOVSQ for known size, properly aligned blocks is up for discussion.