> -----Original Message-----
> From: Thomas Monjalon <tho...@monjalon.net>
> Sent: Wednesday, April 22, 2020 16:24
> To: Wang, Haiyue <haiyue.w...@intel.com>
> Cc: dev@dpdk.org; Burakov, Anatoly <anatoly.bura...@intel.com>;
> vattun...@marvell.com;
> jer...@marvell.com; alex.william...@redhat.com; david.march...@redhat.com
> Subject: Re: [PATCH v9 2/2] eal: support for VFIO-PCI VF token
>
> 22/04/2020 07:08, Haiyue Wang:
> > --- a/devtools/libabigail.abignore
> > +++ b/devtools/libabigail.abignore
> > +[suppress_function]
> > + name = rte_vfio_setup_device
>
> There is no comment to justify ignoring this symbol.
>
> The current policy is to reject any change in libabigail.abignore
> which could be better handled with (unfinished) rte_internal mark.
>
>
While updating the vfio patch, also doing the ABI things. Found that:
1). [suppress_function]
name = rte_vfio_setup_device
can make CI happy, but not scale.
2). rte_internal is beautiful, but make CI cry :
https://patchwork.dpdk.org/patch/69109/
1 Removed function:
[D] 'function int rte_vfio_setup_device(const char*, const char*, int*,
vfio_device_info*)' {rte_vfio_setup_device@@DPDK_20.0}
