Re: [GIT PULL] Please pull powerpc/linux.git powerpc-6.1-1 tag

[Andrew Donnellan]

On Mon, 2022-10-10 at 16:26 -0600, Jason A. Donenfeld wrote:
> 
> Bisected:
> 
> 7e92e01b724526b98cbc7f03dd4afa0295780d56 is the first bad commit
> commit 7e92e01b724526b98cbc7f03dd4afa0295780d56
> Author: Rohan McLure <rmclure@xxxxxxxxxxxxx>
> Date:   Wed Sep 21 16:56:01 2022 +1000
> 
>     powerpc: Provide syscall wrapper
> 
>     Implement syscall wrapper as per s390, x86, arm64. When enabled
>     cause handlers to accept parameters from a stack frame rather
> than
>     from user scratch register state. This allows for user registers
> to be
>     safely cleared in order to reduce caller influence on speculation
>     within syscall routine. The wrapper is a macro that emits syscall
>     handler symbols that call into the target handler, obtaining its
>     parameters from a struct pt_regs on the stack.
> 
>     As registers are already saved to the stack prior to calling
>     system_call_exception, it appears that this function is executed
> more
>     efficiently with the new stack-pointer convention than with
> parameters
>     passed by registers, avoiding the allocation of a stack frame for
> this
>     method. On a 32-bit system, we see >20% performance increases on
> the
>     null_syscall microbenchmark, and on a Power 8 the performance
> gains
>     amortise the cost of clearing and restoring registers which is
>     implemented at the end of this series, seeing final result of
> ~5.6%
>     performance improvement on null_syscall.
> 
>     Syscalls are wrapped in this fashion on all platforms except for
> the
>     Cell processor as this commit does not provide SPU support. This
> can be
>     quickly fixed in a successive patch, but requires
> spu_sys_callback to
>     allocate a pt_regs structure to satisfy the wrapped calling
> convention.
> 
>     Co-developed-by: Andrew Donnellan <ajd@xxxxxxxxxxxxx>
>     Signed-off-by: Andrew Donnellan <ajd@xxxxxxxxxxxxx>
>     Signed-off-by: Rohan McLure <rmclure@xxxxxxxxxxxxx>
>     Reviewed-by: Nicholas Piggin <npiggin@xxxxxxxx>
>     [mpe: Make incompatible with COMPAT to retain clearing of high
> bits of args]
>     Signed-off-by: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
>     Link:
> https://lore.kernel.org/r/20220921065605.1051927-22-rmclure@xxxxxxxxxxxxx

Thanks for bisecting, this is interesting! Could you provide your
.config and the environment you're running in? Your reproducer doesn't
seem to trigger it on my baremetal POWER8 pseries_le_defconfig.

-- 
Andrew Donnellan    OzLabs, ADL Canberra
ajd@xxxxxxxxxxxxx   IBM Australia Limited