Messages in this thread | | | Date | Fri, 16 Dec 2022 11:05:05 -0800 | From | Conor Dooley <> | Subject | Re: [PATCH] riscv: avoid enabling vectorized code generation |
| |
Hey Saleem,
On 16 December 2022 10:50:12 GMT-08:00, Saleem Abdulrasool <abdulras@google.com> wrote: >The compiler is free to generate vectorized operations for zero'ing >memory. The kernel does not use the vector unit on RISCV, similar to >architectures such as x86 where we use `-mno-mmx` et al to prevent the >implicit vectorization. Perform a similar check for >`-mno-implicit-float` to avoid this on RISC-V targets. > >Signed-off-by: Saleem Abdulrasool <abdulras@google.com> >--- > arch/riscv/Makefile | 4 ++++ > 1 file changed, 4 insertions(+) > >diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile >index 0d13b597cb55..68433476a96e 100644 >--- a/arch/riscv/Makefile >+++ b/arch/riscv/Makefile >@@ -89,6 +89,10 @@ KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax) > # architectures. It's faster to have GCC emit only aligned accesses. > KBUILD_CFLAGS += $(call cc-option,-mstrict-align) > >+# Ensure that we do not vectorize the kernel code when the `v` extension is >+# enabled. This mirrors the `-mno-mmx` et al on x86.
The v extension should not be enabled at all though, right? Excuse my naivity here, but what am I missing? The vector support thread is here: https://lore.kernel.org/linux-riscv/20220921214439.1491510-1-stillson@rivosinc.com/
What have I missed that causes a problem without that patchset? And if I have missed something, this patch needs to be cc: stable?
Thanks, Conor.
>+KBUILD_CFLAGS += $(call cc-option,-mno-implicit-float) >+ > ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y) > prepare: stack_protector_prepare > stack_protector_prepare: prepare0
| |