qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: David Gibson <david@gibson.dropbear.id.au>
To: "Cédric Le Goater" <clg@kaod.org>
Cc: qemu-ppc@nongnu.org, qemu-devel@nongnu.org,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>
Subject: Re: [Qemu-devel] [PATCH v5 11/36] spapr/xive: use the VCPU id as a NVT identifier
Date: Mon, 3 Dec 2018 12:18:12 +1100	[thread overview]
Message-ID: <20181203011812.GQ30479@umbus.fritz.box> (raw)
In-Reply-To: <bed23f8a-68bb-0f88-54c4-a4dfea085e34@kaod.org>

[-- Attachment #1: Type: text/plain, Size: 8379 bytes --]

On Fri, Nov 30, 2018 at 07:56:02AM +0100, Cédric Le Goater wrote:
> On 11/30/18 2:11 AM, David Gibson wrote:
> > On Thu, Nov 29, 2018 at 04:27:31PM +0100, Cédric Le Goater wrote:
> >> [ ... ] 
> >>
> >>>>>> +/*
> >>>>>> + * The allocation of VP blocks is a complex operation in OPAL and the
> >>>>>> + * VP identifiers have a relation with the number of HW chips, the
> >>>>>> + * size of the VP blocks, VP grouping, etc. The QEMU sPAPR XIVE
> >>>>>> + * controller model does not have the same constraints and can use a
> >>>>>> + * simple mapping scheme of the CPU vcpu_id
> >>>>>> + *
> >>>>>> + * These identifiers are never returned to the OS.
> >>>>>> + */
> >>>>>> +
> >>>>>> +#define SPAPR_XIVE_VP_BASE 0x400
> >>>>>
> >>>>> 0x400 == 1024.  Could we ever have the possibility of needing to
> >>>>> consider both physical NVTs and PAPR NVTs at the same time?  
> >>>>
> >>>> They would not be in the same CAM line: OS ring vs. PHYS ring. 
> >>>
> >>> Hm.  They still inhabit the same NVT number space though, don't they?
> >>
> >> No. skiboot reserves the range of VPs for the HW at init.
> >>
> >> https://github.com/open-power/skiboot/blob/master/hw/xive.c#L1093
> > 
> > Uh.. I don't see how they're reserved is relevant.
> > 
> > What I mean is that the ENDs address the NVTs for HW endpoints by the
> > same (block, index) tuples as the NVTs for virtualized endpoints, yes?
> 
> Ah. Yes. The (block, index) tuples, fields END_W6_NVT_BLOCK and 
> END_W6_NVT_INDEX in the END structure, are all in the same number space.

Right.

> skiboot defines some ranges though.

Ok.  I guess we can rely on that for PAPR, but not for PowerNV.

> >>> I'm thinking about the END->NVT stage of the process here, rather than
> >>> the NVT->TCTX stage.
> >>>
> >>> Oh, also, you're using "VP" here which IIUC == "NVT".  Can we
> >>> standardize on one, please.
> >>
> >> VP is used in Linux/KVM Linux/Native and skiboot. Yes. it's a mess. 
> >> Let's have consistent naming in QEMU and use NVT. 
> > 
> > Right.  And to cover any inevitable missed ones is why I'd like to see
> > a cheatsheet giving both terms in the header comments somewhere.
> 
> yes. I have added a list of names in xive.h. 

Great.  Oh BTW - this is getting big enough, that I wonder if it makes
sense to create a hw/intc/xive subdir to put things in, then splitting
IVSE, IVRE, IVPE related code into separate .c files (I'd still expect
a common .h though).

> I was wondering if I should put the diagram below somewhere in a .h file 
> or under doc/specs/.

I'd prefer it in the .h file.

> 
> Thanks,
> 
> C.  
> 
> 
> = XIVE =================================================================
> 
> The POWER9 processor comes with a new interrupt controller, called
> XIVE as "eXternal Interrupt Virtualization Engine".
> 
> 
> * Overall architecture
> 
> 
>              XIVE Interrupt Controller
>              +------------------------------------+      IPIs
>              | +---------+ +---------+ +--------+ |    +-------+
>              | |VC       | |CQ       | |PC      |----> | CORES |
>              | |     esb | |         | |        |----> |       |
>              | |     eas | |  Bridge | |   tctx |----> |       |
>              | |SC   end | |         | |    nvt | |    |       |
>  +------+    | +---------+ +----+----+ +--------+ |    +-+-+-+-+
>  | RAM  |    +------------------|-----------------+      | | |
>  |      |                       |                        | | |
>  |      |                       |                        | | |
>  |      |  +--------------------v------------------------v-v-v--+    other
>  |      <--+                     Power Bus                      +--> chips
>  |  esb |  +---------+-----------------------+------------------+
>  |  eas |            |                       |
>  |  end |        +---|-----+                 |
>  |  nvt |       +----+----+|            +----+----+
>  +------+       |SC       ||            |SC       |
>                 |         ||            |         |
>                 | PQ-bits ||            | PQ-bits |
>                 | local   |+            |  in VC  |
>                 +---------+             +---------+
>                    PCIe                 NX,NPU,CAPI
> 
>                   SC: Source Controller (aka. IVSE)
>                   VC: Virtualization Controller (aka. IVRE)
>                   PC: Presentation Controller (aka. IVPE)
>                   CQ: Common Queue (Bridge)
> 
>              PQ-bits: 2 bits source state machine (P:pending Q:queued)
>                  esb: Event State Buffer (Array of PQ bits in an IVSE)
>                  eas: Event Assignment Structure
>                  end: Event Notification Descriptor
>                  nvt: Notification Virtual Target
>                 tctx: Thread interrupt Context
> 
> 
> The XIVE IC is composed of three sub-engines :
> 
>   - Interrupt Virtualization Source Engine (IVSE), or Source
>     Controller (SC). These are found in PCI PHBs, in the PSI host
>     bridge controller, but also inside the main controller for the
>     core IPIs and other sub-chips (NX, CAP, NPU) of the
>     chip/processor. They are configured to feed the IVRE with events.
> 
>   - Interrupt Virtualization Routing Engine (IVRE) or Virtualization
>     Controller (VC). Its job is to match an event source with an Event
>     Notification Descriptor (END).
> 
>   - Interrupt Virtualization Presentation Engine (IVPE) or Presentation
>     Controller (PC). It maintains the interrupt context state of each
>     thread and handles the delivery of the external exception to the
>     thread.
> 
> 
> * XIVE internal tables
> 
> Each of the sub-engines uses a set of tables to redirect exceptions
> from event sources to CPU threads.
> 
>                                           +-------+
>   User or OS                              |  EQ   |
>       or                          +------>|entries|
>   Hypervisor                      |       |  ..   |
>     Memory                        |       +-------+
>                                   |           ^
>                                   |           |
>              +-------------------------------------------------+
>                                   |           |
>   Hypervisor      +------+    +---+--+    +---+--+   +------+
>     Memory        | ESB  |    | EAT  |    | ENDT |   | NVTT |
>    (skiboot)      +----+-+    +----+-+    +----+-+   +------+
>                     ^  |        ^  |        ^  |       ^
>                     |  |        |  |        |  |       |
>              +-------------------------------------------------+
>                     |  |        |  |        |  |       |
>                     |  |        |  |        |  |       |
>                +----|--|--------|--|--------|--|-+   +-|-----+    +------+
>                |    |  |        |  |        |  | |   | | tctx|    |Thread|
>    IPI or   ---+    +  v        +  v        +  v |---| +  .. |----->     |
>   HW events    |                                 |   |       |    |      |
>                |             IVRE                |   | IVPE  |    +------+
>                +---------------------------------+   +-------+
>             
> 
> 
> The IVSE have a 2-bits, P for pending and Q for queued, state machine
> for each source that allows events to be triggered. They are stored in
> an array, the Event State Buffer (ESB) and controlled by MMIOs.
> 
> If the event is let through, the IVRE looks up in the Event Assignment
> Structure (EAS) table for an Event Notification Descriptor (END)
> configured for the source. Each Event Notification Descriptor defines
> a notification path to a CPU and an in-memory Event Queue, in which
> will be pushed an EQ data for the OS to pull.
> 
> The IVPE determines if a Notification Virtual Target (NVT) can handle
> the event by scanning the thread contexts of the VPs dispatched on the
> processor HW threads. It maintains the interrupt context state of each
> thread in a NVT table.
> 

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

  reply	other threads:[~2018-12-03  2:27 UTC|newest]

Thread overview: 184+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-16 10:56 [Qemu-devel] [PATCH v5 00/36] ppc: support for the XIVE interrupt controller (POWER9) Cédric Le Goater
2018-11-16 10:56 ` [Qemu-devel] [PATCH v5 01/36] ppc/xive: introduce a XIVE interrupt source model Cédric Le Goater
2018-11-22  3:05   ` David Gibson
2018-11-22  7:25     ` Cédric Le Goater
2018-11-23  0:31       ` David Gibson
2018-11-23  8:21         ` Cédric Le Goater
2018-11-26  8:14         ` Cédric Le Goater
2018-11-16 10:56 ` [Qemu-devel] [PATCH v5 02/36] ppc/xive: add support for the LSI interrupt sources Cédric Le Goater
2018-11-22  3:19   ` David Gibson
2018-11-22  7:39     ` Cédric Le Goater
2018-11-23  1:08       ` David Gibson
2018-11-23 13:28         ` Cédric Le Goater
2018-11-26  5:39           ` David Gibson
2018-11-26 11:20             ` Cédric Le Goater
2018-11-26 23:48               ` David Gibson
2018-11-27  7:30                 ` Cédric Le Goater
2018-11-16 10:56 ` [Qemu-devel] [PATCH v5 03/36] ppc/xive: introduce the XiveFabric interface Cédric Le Goater
2018-11-16 10:56 ` [Qemu-devel] [PATCH v5 04/36] ppc/xive: introduce the XiveRouter model Cédric Le Goater
2018-11-22  4:11   ` David Gibson
2018-11-22  7:53     ` Cédric Le Goater
2018-11-23  3:50       ` David Gibson
2018-11-23  8:06         ` Cédric Le Goater
2018-11-27  1:54           ` David Gibson
2018-11-27  8:45             ` Cédric Le Goater
2018-11-22  4:44   ` David Gibson
2018-11-22  6:50     ` Benjamin Herrenschmidt
2018-11-22  7:59       ` Cédric Le Goater
2018-11-23  1:17         ` David Gibson
2018-11-23  1:10       ` David Gibson
2018-11-23 10:28         ` Cédric Le Goater
2018-11-26  5:44           ` David Gibson
2018-11-26  9:39             ` Cédric Le Goater
2018-11-27  0:11               ` David Gibson
2018-11-27  7:30                 ` Cédric Le Goater
2018-11-27 22:56                   ` David Gibson
2018-11-16 10:56 ` [Qemu-devel] [PATCH v5 05/36] ppc/xive: introduce the XIVE Event Notification Descriptors Cédric Le Goater
2018-11-22  4:41   ` David Gibson
2018-11-22  6:49     ` Benjamin Herrenschmidt
2018-11-23  3:51       ` David Gibson
2018-11-22 21:47     ` Cédric Le Goater
2018-11-23  4:35       ` David Gibson
2018-11-23 11:01         ` Cédric Le Goater
2018-11-29  4:46           ` David Gibson
2018-11-16 10:56 ` [Qemu-devel] [PATCH v5 06/36] ppc/xive: add support for the END Event State buffers Cédric Le Goater
2018-11-22  5:13   ` David Gibson
2018-11-22 21:58     ` Cédric Le Goater
2018-11-23  4:36       ` David Gibson
2018-11-23  7:28         ` Cédric Le Goater
2018-11-26  5:54           ` David Gibson
2018-11-29 22:06     ` Cédric Le Goater
2018-11-30  1:04       ` David Gibson
2018-11-30  6:41         ` Cédric Le Goater
2018-12-03  1:14           ` David Gibson
2018-12-03 16:19             ` Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 07/36] ppc/xive: introduce the XIVE interrupt thread context Cédric Le Goater
2018-11-23  5:08   ` David Gibson
2018-11-25 20:35     ` Cédric Le Goater
2018-11-27  5:07       ` David Gibson
2018-11-27 12:47         ` Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 08/36] ppc/xive: introduce a simplified XIVE presenter Cédric Le Goater
2018-11-27 23:49   ` David Gibson
2018-11-28  2:34     ` Benjamin Herrenschmidt
2018-11-28 10:59     ` Cédric Le Goater
2018-11-29  0:47       ` David Gibson
2018-11-29  3:39         ` Benjamin Herrenschmidt
2018-11-29 17:51           ` Cédric Le Goater
2018-11-30  1:09             ` David Gibson
2018-12-03 17:05         ` Cédric Le Goater
2018-12-04  1:54           ` David Gibson
2018-12-04 17:04             ` Cédric Le Goater
2018-12-05  1:40               ` David Gibson
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 09/36] ppc/xive: notify the CPU when the interrupt priority is more privileged Cédric Le Goater
2018-11-28  0:13   ` David Gibson
2018-11-28  2:32     ` Benjamin Herrenschmidt
2018-11-28  2:41       ` David Gibson
2018-11-28  3:00         ` Eric Blake
2018-11-28 11:30     ` Cédric Le Goater
2018-11-29  0:49       ` David Gibson
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 10/36] spapr/xive: introduce a XIVE interrupt controller Cédric Le Goater
2018-11-28  0:52   ` David Gibson
2018-11-28 16:27     ` Cédric Le Goater
2018-11-29  0:54       ` David Gibson
2018-11-29 14:37         ` Cédric Le Goater
2018-11-29 22:36           ` David Gibson
2018-12-04 17:12       ` Cédric Le Goater
2018-12-05  1:41         ` David Gibson
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 11/36] spapr/xive: use the VCPU id as a NVT identifier Cédric Le Goater
2018-11-28  2:39   ` David Gibson
2018-11-28 16:48     ` Cédric Le Goater
2018-11-29  1:00       ` David Gibson
2018-11-29 15:27         ` Cédric Le Goater
2018-11-30  1:11           ` David Gibson
2018-11-30  6:56             ` Cédric Le Goater
2018-12-03  1:18               ` David Gibson [this message]
2018-12-03 16:30                 ` Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 12/36] spapr: initialize VSMT before initializing the IRQ backend Cédric Le Goater
2018-11-28  2:57   ` David Gibson
2018-11-28  9:35     ` [Qemu-devel] [Qemu-ppc] " Greg Kurz
2018-11-28 16:50       ` Cédric Le Goater
2018-11-28 16:59         ` Greg Kurz
2018-11-29  1:02       ` David Gibson
2018-11-29  6:56         ` Greg Kurz
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 13/36] spapr: introduce a spapr_irq_init() routine Cédric Le Goater
2018-11-28  2:59   ` David Gibson
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 14/36] spapr: modify the irq backend 'init' method Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 15/36] spapr: introdude a new machine IRQ backend for XIVE Cédric Le Goater
2018-11-28  3:28   ` David Gibson
2018-11-28 17:16     ` Cédric Le Goater
2018-11-29  1:07       ` David Gibson
2018-11-29 15:34         ` Cédric Le Goater
2018-11-29 22:39           ` David Gibson
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 16/36] spapr: add hcalls support for the XIVE exploitation interrupt mode Cédric Le Goater
2018-11-28  4:25   ` David Gibson
2018-11-28 22:21     ` Cédric Le Goater
2018-11-29  1:23       ` David Gibson
2018-11-29 16:04         ` Cédric Le Goater
2018-11-30  1:23           ` David Gibson
2018-11-30  8:07             ` Cédric Le Goater
2018-12-03  1:36               ` David Gibson
2018-12-03 16:49                 ` Cédric Le Goater
2018-12-04  1:56                   ` David Gibson
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 17/36] spapr: add device tree support for the XIVE exploitation mode Cédric Le Goater
2018-11-28  4:31   ` David Gibson
2018-11-28 22:26     ` Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 18/36] spapr: allocate the interrupt thread context under the CPU core Cédric Le Goater
2018-11-28  4:39   ` David Gibson
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 19/36] spapr: add a 'pseries-3.1-xive' machine type Cédric Le Goater
2018-11-28  4:42   ` David Gibson
2018-11-28 22:37     ` Cédric Le Goater
2018-12-04 15:14       ` Cédric Le Goater
2018-12-05  1:44         ` David Gibson
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 20/36] spapr: add classes for the XIVE models Cédric Le Goater
2018-11-28  5:13   ` David Gibson
2018-11-28 22:38     ` Cédric Le Goater
2018-11-29  2:59       ` David Gibson
2018-11-29 16:06         ` Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 21/36] spapr: extend the sPAPR IRQ backend for XICS migration Cédric Le Goater
2018-11-28  5:54   ` David Gibson
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 22/36] spapr/xive: add models for KVM support Cédric Le Goater
2018-11-28  5:52   ` David Gibson
2018-11-28 22:45     ` Cédric Le Goater
2018-11-29  3:33       ` David Gibson
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 23/36] spapr/xive: add migration support for KVM Cédric Le Goater
2018-11-29  3:43   ` David Gibson
2018-11-29 16:19     ` Cédric Le Goater
2018-11-30  1:24       ` David Gibson
2018-11-30  7:04         ` Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 24/36] spapr: add a 'reset' method to the sPAPR IRQ backend Cédric Le Goater
2018-11-29  3:47   ` David Gibson
2018-11-29 16:21     ` Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 25/36] spapr: set the interrupt presenter at reset Cédric Le Goater
2018-11-29  4:03   ` David Gibson
2018-11-29 16:28     ` Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 26/36] spapr: add a 'pseries-3.1-dual' machine type Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 27/36] sysbus: add a sysbus_mmio_unmap() helper Cédric Le Goater
2018-11-29  4:09   ` David Gibson
2018-11-29 16:36     ` Cédric Le Goater
2018-12-03 15:52       ` Cédric Le Goater
2018-12-04  1:59         ` David Gibson
2018-12-03 17:48     ` Peter Maydell
2018-12-04 12:33       ` Cédric Le Goater
2018-12-04 13:04         ` Peter Maydell
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 28/36] ppc/xics: introduce a icp_kvm_init() routine Cédric Le Goater
2018-11-29  4:08   ` David Gibson
2018-11-29 16:36     ` Cédric Le Goater
2018-11-29 22:43       ` David Gibson
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 29/36] ppc/xics: remove abort() in icp_kvm_init() Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 30/36] spapr: check for KVM IRQ device activation Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 31/36] spapr/xive: export the spapr_xive_kvm_init() routine Cédric Le Goater
2018-11-29  4:11   ` David Gibson
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 32/36] spapr/rtas: modify spapr_rtas_register() to remove RTAS handlers Cédric Le Goater
2018-11-29  4:12   ` David Gibson
2018-11-29 16:40     ` Cédric Le Goater
2018-11-29 22:44       ` David Gibson
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 33/36] spapr: introduce routines to delete the KVM IRQ device Cédric Le Goater
2018-11-29  4:17   ` David Gibson
2018-11-29 16:41     ` Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 34/36] spapr: add KVM support to the 'dual' machine Cédric Le Goater
2018-11-29  4:22   ` David Gibson
2018-11-29 17:07     ` Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 35/36] ppc: externalize ppc_get_vcpu_by_pir() Cédric Le Goater
2018-11-16 10:57 ` [Qemu-devel] [PATCH v5 36/36] ppc/pnv: add XIVE support Cédric Le Goater
2018-12-03  2:26   ` David Gibson
2018-12-06 15:14     ` Cédric Le Goater

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20181203011812.GQ30479@umbus.fritz.box \
    --to=david@gibson.dropbear.id.au \
    --cc=benh@kernel.crashing.org \
    --cc=clg@kaod.org \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-ppc@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).