Re: [PATCH kernel 2/3] pci-ioda: Set PCI_BUS_FLAGS_MSI_REMAP for IODA host bridge

From	Benjamin Herrenschmidt <benh@kernel.crashing.org>
Newsgroups	linux.kernel
Subject	Re: [PATCH kernel 2/3] pci-ioda: Set PCI_BUS_FLAGS_MSI_REMAP for IODA host bridge
Date	2017-06-15 13:00 +0200
Message-ID	<tSAFl-1qG-39@gated-at.bofh.it> (permalink)
References	<tSvPj-6SP-3@gated-at.bofh.it> <tSvPj-6SP-1@gated-at.bofh.it> <tSzgd-Gu-3@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Thu, 2017-06-15 at 19:25 +1000, Michael Ellerman wrote:
> Alexey Kardashevskiy <aik@ozlabs.ru> writes:
> 
> > From: Yongji Xie <elohimes@gmail.com>
> > 
> > Any IODA host bridge have the capability of IRQ remapping.
> > So we set PCI_BUS_FLAGS_MSI_REMAP when this kind of host birdge
> > is detected.
> 
> Where's the code that actually enforces this property?
> 
> It would be good to have a comment in pnv_pci_ioda_root_bridge_prepare()
> (probably), pointing to that code, so that we can remember the
> relationship between the two.

Actually it's not so much remapping as:

 - The bridge can enforce that the interrupt is allowed for a given
partition

 - Because the interrupts are handled via the hypervisor, the latter
can do the remapping.

But the effect is the same, so yes we want the flag. On P9 with XIVE
exploitation we also have HW remapping on top.

Cheers,
Ben.

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

[PATCH kernel 2/3] pci-ioda: Set PCI_BUS_FLAGS_MSI_REMAP for IODA host bridge Alexey Kardashevskiy <aik@ozlabs.ru> - 2017-06-15 07:50 +0200
  Re: [PATCH kernel 2/3] pci-ioda: Set PCI_BUS_FLAGS_MSI_REMAP for IODA host bridge Michael Ellerman <mpe@ellerman.id.au> - 2017-06-15 11:30 +0200
    Re: [PATCH kernel 2/3] pci-ioda: Set PCI_BUS_FLAGS_MSI_REMAP for  IODA host bridge Benjamin Herrenschmidt <benh@kernel.crashing.org> - 2017-06-15 13:00 +0200

csiph-web