[PATCH -next V7 0/7] riscv: Optimize function trace

[Guo Ren]

On Thu, Feb 9, 2023 at 9:51 AM Guo Ren <guoren at kernel.org> wrote:
>
> On Thu, Feb 9, 2023 at 6:29 AM David Laight <David.Laight at aculab.com> wrote:
> >
> > > >   # Note: aligned to 8 bytes
> > > >   addr-08               // Literal (first 32-bits)      // patched to ops ptr
> > > >   addr-04               // Literal (last 32-bits)       // patched to ops ptr
> > > >   addr+00       func:   mv      t0, ra
> > > We needn't "mv t0, ra" here because our "jalr" could work with t0 and
> > > won't affect ra. Let's do it in the trampoline code, and then we can
> > > save another word here.
> > > >   addr+04               auipc   t1, ftrace_caller
> > > >   addr+08               jalr    ftrace_caller(t1)
> >
> > Is that some kind of 'load high' and 'add offset' pair?
> Yes.
>
> > I guess 64bit kernels guarantee to put all module code
> > within +-2G of the main kernel?
> Yes, 32-bit is enough. So we only need one 32-bit literal size for the
> current rv64, just like CONFIG_32BIT.
We need kernel_addr_base + this 32-bit Literal.

@Mark Rutland
What do you think the idea about reducing one more 32-bit in
call-site? (It also sould work for arm64.)

>
> >
> > > Here is the call-site:
> > >    # Note: aligned to 8 bytes
> > >    addr-08               // Literal (first 32-bits)      // patched to ops ptr
> > >    addr-04               // Literal (last 32-bits)       // patched to ops ptr
> > >    addr+00               auipc   t0, ftrace_caller
> > >    addr+04               jalr    ftrace_caller(t0)
> >
> > Could you even do something like:
> >         addr-n  call ftrace-function
> >         addr-n+x        literals
> >         addr+0  nop or jmp addr-n
> >         addr+4  function_code
> Yours cost one more instruction, right?
>          addr-12  auipc
>          addr-8    jalr
>          addr-4    // Literal (32-bits)
>          addr+0   nop or jmp addr-n // one more?
>          addr+4   function_code
>
> > So that all the code executed when tracing is enabled
> > is before the label and only one 'nop' is in the body.
> > The called code can use the return address to find the
> > literals and then modify it to return to addr+4.
> > The code cost when trace is enabled is probably irrelevant
> > here - dominated by what happens later.
> > It probably isn't even worth aligning a 64bit constant.
> > Doing two reads probably won't be noticable.
> >
> > What you do want to ensure is that the initial patch is
> > overwriting nop - just in case the gap isn't there.
> >
> >         David
> >
> > -
> > Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
> > Registration No: 1397386 (Wales)
>
>
>
> --
> Best Regards
>  Guo Ren



-- 
Best Regards
 Guo Ren