From: Christoph Hellwig <hch@infradead.org>
To: Imre Kaloz <kaloz@kernel.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
linux-mips@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 21/38] MIPS: SGI-IP27: route XBridge and PIC DMA through the 32-bit window
Date: Mon, 5 Oct 2026 01:39:34 -0700 [thread overview]
Message-ID: <asNiRoPpv6dkAFD4@infradead.org> (raw)
In-Reply-To: <cce203c61386970826873f87cc9d0e6c732c3a53.1790857966.git.kaloz@kernel.org>
On Thu, Oct 01, 2026 at 06:11:56PM +0200, Imre Kaloz wrote:
> XBridge does not honour the SN0-style 64-bit direct-mapped DMA address:
> commands complete but no data moves. PIC moves no data either. Route
> both through the 2GB 32-bit window and cap bus_dma_limit at its top, so
> SWIOTLB bounces anything above it. PIC is flagged once a following
> patch enumerates it.
>
> Only XBridge (part 0xd002) is flagged; a Bridge (0xc002) behind a Hub
> keeps the 64-bit direct map. The 64MB bounce pool comes from node 0
> whenever DRAM passes 2GB, on Hub any multi-node machine. A PIC bus in
> PCI-X mode takes the window too; IRIX does not.
It's been a while, but IIRC XBridge also support 64-bit direct-mapped
DMA addresses, just differently.
If you find a late 2.4 or early 2.6 kernel, it comes with an open source
copy of the IRIX-style PCI code under arch/ia64/ that also includes the
older chips never used on Altix. It might be worth to take a look at
that for clues.
next prev parent reply other threads:[~2026-10-05 8:39 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-01 16:11 [PATCH 00/38] MIPS: SGI-IP27: add support for the IP35 (Bedrock hub) machines Imre Kaloz
2026-10-01 16:11 ` [PATCH 01/38] MIPS: Xtalk: guard the widget identification table from assembly Imre Kaloz
2026-10-01 16:11 ` [PATCH 02/38] MIPS: SGI-IP27: dump the NMI save areas the CPU scan recorded Imre Kaloz
2026-10-01 16:11 ` [PATCH 03/38] MIPS: SGI-IP27: add REMOTE_HUB_PI_S()/REMOTE_HUB_PI_L() Imre Kaloz
2026-10-01 16:11 ` [PATCH 04/38] MIPS: SGI-IP27: detect Bedrock hubs at boot Imre Kaloz
2026-10-01 16:11 ` [PATCH 05/38] MIPS: SGI-IP27: widen Kconfig for the Bedrock-based machines Imre Kaloz
2026-10-01 16:11 ` [PATCH 06/38] MIPS: SGI-IP27: fold the dead SN1 arm out of klconfig.h Imre Kaloz
2026-10-01 16:11 ` [PATCH 07/38] MIPS: SGI-IP27: choose the node address layout at runtime Imre Kaloz
2026-10-01 16:11 ` [PATCH 08/38] MIPS: SGI-IP27: add the Bedrock hub register windows Imre Kaloz
2026-10-01 16:11 ` [PATCH 09/38] MIPS: SGI-IP27: decode a Bedrock hub's node id and system size Imre Kaloz
2026-10-01 16:11 ` [PATCH 10/38] MIPS: SGI-IP27: put a Bedrock hub's boot CPU in slot 0 Imre Kaloz
2026-10-01 16:11 ` [PATCH 11/38] MIPS: SGI-IP27: lay out node memory in 1GB banks on Bedrock hubs Imre Kaloz
2026-10-01 16:11 ` [PATCH 12/38] MIPS: SGI-IP27: reserve the bottom 64MB of node 0 " Imre Kaloz
2026-10-01 16:11 ` [PATCH 13/38] MIPS: SGI-IP27: route interrupt masks and slices through both PIs Imre Kaloz
2026-10-01 16:11 ` [PATCH 14/38] MIPS: SGI-IP27: address a CPU's own PI for NMI, IPI and RT counter Imre Kaloz
2026-10-01 16:11 ` [PATCH 15/38] MIPS: SGI-IP27: take a CPU's node from the CPU table in per_cpu_init() Imre Kaloz
2026-10-01 16:11 ` [PATCH 16/38] MIPS: SGI-IP27: resolve the mapped-kernel node shift at runtime Imre Kaloz
2026-10-01 16:11 ` [PATCH 17/38] MIPS: SGI-IP27: load the kernel at node offset 0x40000 Imre Kaloz
2026-10-01 16:11 ` [PATCH 18/38] MIPS: SGI-IP27: xbow_probe(): recognize KLTYPE_PBRICK_XBOW Imre Kaloz
2026-10-01 16:11 ` [PATCH 19/38] MIPS: ip27_defconfig: enable the IOC3 MFD, its cell drivers and tg3 Imre Kaloz
2026-10-01 16:11 ` [PATCH 20/38] net: ethernet: sgi: ioc3-eth: apply the DMA attributes only to 64-bit addresses Imre Kaloz
2026-10-01 16:11 ` [PATCH 21/38] MIPS: SGI-IP27: route XBridge and PIC DMA through the 32-bit window Imre Kaloz
2026-10-05 8:39 ` Christoph Hellwig [this message]
2026-10-05 13:15 ` Imre Kaloz
2026-10-01 16:11 ` [PATCH 22/38] MIPS: SGI-IP27: recognize the PXBow crossbar Imre Kaloz
2026-10-01 16:11 ` [PATCH 23/38] MIPS: PCI: xtalk-bridge: recognize the PIC widget's 64-bit-only registers Imre Kaloz
2026-10-01 16:11 ` [PATCH 24/38] MIPS: PCI: xtalk-bridge: match PIC's register-level differences Imre Kaloz
2026-10-01 16:12 ` [PATCH 25/38] rtc: m48t35: support the SGI IP35 timekeeper's 1968 year base Imre Kaloz
2026-10-03 1:33 ` sashiko-bot
2026-10-01 16:12 ` [PATCH 26/38] mfd: ioc3: add support for IOC4 Imre Kaloz
2026-10-03 1:33 ` sashiko-bot
2026-10-01 16:12 ` [PATCH 27/38] MIPS: SGI-IP27: dispatch the early console between IOC3 and IOC4 Imre Kaloz
2026-10-01 16:12 ` [PATCH 28/38] MIPS: SGI-IP27: add L1 system controller support Imre Kaloz
2026-10-01 16:12 ` [PATCH 29/38] MIPS: SGI-IP27: wire the L1 into reset and the Ethernet address Imre Kaloz
2026-10-01 16:12 ` [PATCH 30/38] MIPS: PCI: xtalk-bridge: take the board part number from the L1 Imre Kaloz
2026-10-01 16:12 ` [PATCH 31/38] mfd: ioc3: add IP34 system-board entry to ioc3_infos[] Imre Kaloz
2026-10-02 10:02 ` Lee Jones
2026-10-02 10:29 ` Imre Kaloz
2026-10-01 16:12 ` [PATCH 32/38] net: ethernet: sgi: ioc3-eth: fall back to the platform MAC address Imre Kaloz
2026-10-01 16:12 ` [PATCH 33/38] MIPS: SGI-IP27: don't register a w1 master on an XBridge or PIC Imre Kaloz
2026-10-01 16:12 ` [PATCH 34/38] MIPS: SGI-IP27: report a Bedrock machine as SGI IP35 Imre Kaloz
2026-10-01 16:12 ` [PATCH 35/38] MIPS: SGI-IP27: identify the machine by the L1 brick type Imre Kaloz
2026-10-01 16:12 ` [PATCH 36/38] MIPS: SGI-IP27: register the Odyssey graphics widget Imre Kaloz
2026-10-01 16:12 ` [PATCH 37/38] MIPS: SGI-IP27: take the console from the KLCONFIG header on IP35 Imre Kaloz
2026-10-01 16:12 ` [PATCH 38/38] MIPS: SGI-IP27: give each CPU its own topology package id Imre Kaloz
2026-10-02 15:46 ` [PATCH 00/38] MIPS: SGI-IP27: add support for the IP35 (Bedrock hub) machines Thomas Bogendoerfer
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=asNiRoPpv6dkAFD4@infradead.org \
--to=hch@infradead.org \
--cc=kaloz@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mips@vger.kernel.org \
--cc=tsbogend@alpha.franken.de \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.