From: Paolo Bonzini <pbonzini@redhat.com>
To: Peter Maydell <peter.maydell@linaro.org>
Cc: QEMU Developers <qemu-devel@nongnu.org>,
"Michael S. Tsirkin" <mst@redhat.com>
Subject: Re: [Qemu-devel] [PATCH v2 00/38] Delay destruction of memory regions to instance_finalize
Date: Wed, 18 Sep 2013 15:28:43 +0200 [thread overview]
Message-ID: <5239AA8B.2090200@redhat.com> (raw)
In-Reply-To: <CAFEAcA8s8CqPuBfsvj+dHt-9TEAOuiPd1NC2yjYk4O5GozARTQ@mail.gmail.com>
Il 18/09/2013 15:19, Peter Maydell ha scritto:
> > There's nothing magic, really. Both PV and real devices have been doing
> > it forever by placing some registers in RAM instead of MMIO, and
> > communicating synchronization points via interrupts and doorbell registers.
>
> Sure, but that's a hardware design choice, it's different from
> ripping out the assumptions about device behaviour from
> underneath an existing driver.
That's why I wrote:
Devices have to request BQL-free MMIO explicitly. You can just use all
the infrastructure to do unlocked bus-master DMA, you can limit BQL-free
MMIO to PV devices, or to extremely simple devices, or to one or two
highly-optimized registers.
Of course the choice of what's safe and what's not depends on the
hardware design and on what the device can expect from the drivers (the
PCI spec doesn't forbid putting additional requirements).
Paolo
prev parent reply other threads:[~2013-09-18 13:28 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-09-03 12:32 [Qemu-devel] [PATCH v2 00/38] Delay destruction of memory regions to instance_finalize Paolo Bonzini
2013-09-03 12:32 ` [Qemu-devel] [PATCH 01/38] qdev: document assumption that unrealize is followed by finalize Paolo Bonzini
2013-09-17 9:00 ` Michael S. Tsirkin
2013-09-03 12:32 ` [Qemu-devel] [PATCH 02/38] pci: split exit and finalize Paolo Bonzini
2013-09-17 9:16 ` Michael S. Tsirkin
2013-09-17 9:56 ` Paolo Bonzini
2013-09-17 10:23 ` Paolo Bonzini
2013-09-17 10:06 ` Michael S. Tsirkin
2013-09-03 12:32 ` [Qemu-devel] [PATCH 03/38] ac97: use instance_finalize instead of exit Paolo Bonzini
2013-09-03 12:32 ` [Qemu-devel] [PATCH 04/38] es1370: " Paolo Bonzini
2013-09-03 12:32 ` [Qemu-devel] [PATCH 05/38] hda: reclaim memory in " Paolo Bonzini
2013-09-03 12:32 ` [Qemu-devel] [PATCH 06/38] serial: " Paolo Bonzini
2013-09-03 12:32 ` [Qemu-devel] [PATCH 07/38] tpci200: use " Paolo Bonzini
2013-09-03 12:32 ` [Qemu-devel] [PATCH 08/38] pci-assign: reclaim memory in " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 09/38] ahci: " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 10/38] msix: split msix_free from msix_uninit Paolo Bonzini
2013-09-17 9:21 ` Michael S. Tsirkin
2013-09-17 9:56 ` Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 11/38] cmd646: use instance_finalize instead of exit Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 12/38] ide/piix: " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 13/38] ide/via: " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 14/38] ivshmem: reclaim memory in " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 15/38] pci-testdev: use " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 16/38] vfio: reclaim memory in " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 17/38] e1000: use " Paolo Bonzini
2013-09-17 9:27 ` Michael S. Tsirkin
2013-09-17 10:13 ` Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 18/38] eepro100: " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 19/38] ne2000: " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 20/38] pcnet: " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 21/38] rtl8139: " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 22/38] vmxnet3: reclaim memory in " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 23/38] shpc: split shpc_free from shpc_cleanup Paolo Bonzini
2013-09-17 9:24 ` Michael S. Tsirkin
2013-09-17 9:58 ` Paolo Bonzini
2013-09-17 10:03 ` Michael S. Tsirkin
2013-09-03 12:33 ` [Qemu-devel] [PATCH 24/38] pci_bridge: split pci_bridge_free from pci_bridge_exitfn Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 25/38] pcie_aer: pcie_aer_exit really frees stuff Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 26/38] pci_bridge: reclaim memory in instance_finalize instead of exit Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 27/38] ioh4320: " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 28/38] xio3130-downstream: " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 29/38] xio3130-upstream: " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 30/38] pcie: do not recreate mmcfg I/O region, use an alias instead Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 31/38] esp: use instance_finalize instead of exit Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 32/38] lsi: " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 33/38] pvscsi: reclaim memory in " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 34/38] usb-uhci: use " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 35/38] virtio-pci: reclaim memory in " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 36/38] wdt_i6300esb: use " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 37/38] xen_pt: reclaim memory in " Paolo Bonzini
2013-09-03 12:33 ` [Qemu-devel] [PATCH 38/38] tpm: move add/del_subregion to realize/unrealize Paolo Bonzini
2013-09-16 16:35 ` [Qemu-devel] [PATCH v2 00/38] Delay destruction of memory regions to instance_finalize Paolo Bonzini
2013-09-17 6:44 ` Wenchao Xia
2013-09-17 10:01 ` Paolo Bonzini
2013-09-20 6:16 ` Wenchao Xia
2013-09-17 9:31 ` Michael S. Tsirkin
2013-09-17 12:47 ` Michael S. Tsirkin
2013-09-17 14:41 ` Paolo Bonzini
2013-09-17 14:45 ` Michael S. Tsirkin
2013-09-17 15:41 ` Paolo Bonzini
2013-09-17 15:59 ` Michael S. Tsirkin
2013-09-17 16:13 ` Paolo Bonzini
2013-09-17 16:29 ` Michael S. Tsirkin
2013-09-17 16:58 ` Paolo Bonzini
2013-09-17 17:07 ` Michael S. Tsirkin
2013-09-17 17:16 ` Paolo Bonzini
2013-09-17 17:26 ` Michael S. Tsirkin
2013-09-17 19:07 ` Paolo Bonzini
2013-09-17 19:51 ` Michael S. Tsirkin
2013-09-17 22:02 ` Paolo Bonzini
2013-09-18 5:48 ` Michael S. Tsirkin
2013-09-18 7:40 ` Paolo Bonzini
2013-09-18 8:41 ` Michael S. Tsirkin
2013-09-18 11:26 ` Paolo Bonzini
2013-09-18 11:56 ` Peter Maydell
2013-09-18 13:11 ` Paolo Bonzini
2013-09-18 13:19 ` Peter Maydell
2013-09-18 13:28 ` Paolo Bonzini [this message]
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=5239AA8B.2090200@redhat.com \
--to=pbonzini@redhat.com \
--cc=mst@redhat.com \
--cc=peter.maydell@linaro.org \
--cc=qemu-devel@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).