Den mån 21 jan. 2019 kl 20:12 skrev Jesper Dangaard Brouer :
>
> On Mon, 21 Jan 2019 17:53:45 +0100
> Björn Töpel wrote:
>
> > > If that jump tables are a common problem, I wonder, why the compiler
> > > cannot be adapted to generate better performing code or an option passed
> > > to the compiler
On Mon, 21 Jan 2019 17:53:45 +0100
Björn Töpel wrote:
> > If that jump tables are a common problem, I wonder, why the compiler
> > cannot be adapted to generate better performing code or an option passed
> > to the compiler.
> >
>
> It might make sense to use -fno-jump-tables or a better value
On Mon, 21 Jan 2019 17:33:56 +0100
bjorn.to...@gmail.com wrote:
> From: Björn Töpel
>
> GCC will generate jump tables for switch-statements with more than 5
> case statements. An entry into the jump table is an indirect call,
> which means that for CONFIG_RETPOLINE builds, this is rather
> expen
Den mån 21 jan. 2019 kl 17:42 skrev Paul Menzel :
>
> Dear Björn,
>
>
> On 01/21/19 17:33, bjorn.to...@gmail.com wrote:
> > From: Björn Töpel
> >
> > GCC will generate jump tables for switch-statements with more than 5
> > case statements. An entry into the jump table is an indirect call,
> > whic
Dear Björn,
On 01/21/19 17:33, bjorn.to...@gmail.com wrote:
> From: Björn Töpel
>
> GCC will generate jump tables for switch-statements with more than 5
> case statements. An entry into the jump table is an indirect call,
> which means that for CONFIG_RETPOLINE builds, this is rather
> expensiv
From: Björn Töpel
GCC will generate jump tables for switch-statements with more than 5
case statements. An entry into the jump table is an indirect call,
which means that for CONFIG_RETPOLINE builds, this is rather
expensive.
This commit replaces the switch-statement that acts on the XDP program
