All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Michael S. Tsirkin" <mst@redhat.com>
To: qemu-devel@nongnu.org
Cc: Peter Maydell <peter.maydell@linaro.org>,
	Stefan Hajnoczi <stefanha@redhat.com>,
	Maxime Coquelin <maxime.coquelin@redhat.com>,
	Wei Wang <wei.w.wang@intel.com>
Subject: [Qemu-devel] [PULL 20/25] vhost-user: document memory accesses
Date: Thu, 21 Dec 2017 16:29:45 +0200	[thread overview]
Message-ID: <1513866427-27125-21-git-send-email-mst@redhat.com> (raw)
In-Reply-To: <1513866427-27125-1-git-send-email-mst@redhat.com>

From: Stefan Hajnoczi <stefanha@redhat.com>

The vhost-user protocol specification does not define "guest address"
and "user address".  It does not explain how to access memory given such
addresses.

This patch explains how memory access works, including the IOTLB.

Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Maxime Coquelin <maxime.coquelin@redhat.com>
Cc: Wei Wang <wei.w.wang@intel.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
 docs/interop/vhost-user.txt | 33 ++++++++++++++++++++++++++++++---
 1 file changed, 30 insertions(+), 3 deletions(-)

diff --git a/docs/interop/vhost-user.txt b/docs/interop/vhost-user.txt
index fd8ac56..d49444e 100644
--- a/docs/interop/vhost-user.txt
+++ b/docs/interop/vhost-user.txt
@@ -66,11 +66,14 @@ Depending on the request type, payload can be:
 
    Index: a 32-bit vring index
    Flags: a 32-bit vring flags
-   Descriptor: a 64-bit user address of the vring descriptor table
-   Used: a 64-bit user address of the vring used ring
-   Available: a 64-bit user address of the vring available ring
+   Descriptor: a 64-bit ring address of the vring descriptor table
+   Used: a 64-bit ring address of the vring used ring
+   Available: a 64-bit ring address of the vring available ring
    Log: a 64-bit guest address for logging
 
+   Note that a ring address is an IOVA if VIRTIO_F_IOMMU_PLATFORM has been
+   negotiated.  Otherwise it is a user address.
+
  * Memory regions description
    ---------------------------------------------------
    | num regions | padding | region0 | ... | region7 |
@@ -273,6 +276,30 @@ Once the source has finished migration, rings will be stopped by
 the source. No further update must be done before rings are
 restarted.
 
+Memory access
+-------------
+
+The master sends a list of vhost memory regions to the slave using the
+VHOST_USER_SET_MEM_TABLE message.  Each region has two base addresses: a guest
+address and a user address.
+
+Messages contain guest addresses and/or user addresses to reference locations
+within the shared memory.  The mapping of these addresses works as follows.
+
+User addresses map to the vhost memory region containing that user address.
+
+When the VIRTIO_F_IOMMU_PLATFORM feature has not been negotiated:
+
+ * Guest addresses map to the vhost memory region containing that guest
+   address.
+
+When the VIRTIO_F_IOMMU_PLATFORM feature has been negotiated:
+
+ * Guest addresses are also called I/O virtual addresses (IOVAs).  They are
+   translated to user addresses via the IOTLB.
+
+ * The vhost memory region guest address is not used.
+
 IOMMU support
 -------------
 
-- 
MST

  parent reply	other threads:[~2017-12-21 14:30 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-12-21 14:27 [Qemu-devel] [PULL 00/25] pc, pci, virtio: features, fixes, cleanups Michael S. Tsirkin
2017-12-21 14:27 ` [Qemu-devel] [PULL 01/25] smbios: support setting OEM strings table Michael S. Tsirkin
2017-12-21 14:28 ` [Qemu-devel] [PULL 02/25] qdev-properties: add UUID property type Michael S. Tsirkin
2017-12-21 14:28 ` [Qemu-devel] [PULL 03/25] vmgenid: use " Michael S. Tsirkin
2017-12-21 14:28 ` [Qemu-devel] [PULL 04/25] tests: add test to check VirtQueue object Michael S. Tsirkin
2017-12-21 14:28 ` [Qemu-devel] [PULL 05/25] pci: Rename root bus initialization functions for clarity Michael S. Tsirkin
2017-12-21 14:28 ` [Qemu-devel] [PULL 06/25] pci: Move bridge data structures from pci_bus.h to pci_bridge.h Michael S. Tsirkin
2017-12-21 14:28 ` [Qemu-devel] [PULL 07/25] pci: Add pci_dev_bus_num() helper Michael S. Tsirkin
2017-12-21 14:28   ` Michael S. Tsirkin
2017-12-21 14:28 ` [Qemu-devel] [PULL 08/25] pci: Eliminate redundant PCIDevice::bus pointer Michael S. Tsirkin
2017-12-21 14:28   ` Michael S. Tsirkin
2017-12-21 14:29 ` [Qemu-devel] [PULL 09/25] pci: Eliminate pci_find_primary_bus() Michael S. Tsirkin
2017-12-21 14:29 ` [Qemu-devel] [PULL 10/25] virtio_error: don't invoke status callbacks Michael S. Tsirkin
2018-02-13 20:53   ` [Qemu-devel] [Qemu-stable] " Peter Lieven
2018-02-13 22:23     ` Michael S. Tsirkin
2018-02-14 21:12       ` Peter Lieven
2017-12-21 14:29 ` [Qemu-devel] [PULL 11/25] tests/pxe-test: Remove unnecessary special case test functions Michael S. Tsirkin
2017-12-21 14:29 ` [Qemu-devel] [PULL 12/25] tests/pxe-test: Use table of testcases rather than open-coding Michael S. Tsirkin
2017-12-21 14:29 ` [Qemu-devel] [PULL 13/25] tests/pxe-test: Test net booting over IPv6 in some cases Michael S. Tsirkin
2017-12-21 14:29 ` [Qemu-devel] [PULL 14/25] tests/pxe-test: Add some extra tests Michael S. Tsirkin
2017-12-21 14:29 ` [Qemu-devel] [PULL 15/25] hw/block/nvme: QOM'ify PCI NVME Michael S. Tsirkin
2017-12-21 20:38   ` Michael S. Tsirkin
2017-12-21 23:02     ` Philippe Mathieu-Daudé
2017-12-21 14:29 ` [Qemu-devel] [PULL 16/25] hw/pci-host/piix: QOM'ify the IGD Passthrough host bridge Michael S. Tsirkin
2017-12-21 14:29 ` [Qemu-devel] [PULL 17/25] hw/pci-host/xilinx: QOM'ify the AXI-PCIe " Michael S. Tsirkin
2017-12-21 14:29 ` [Qemu-devel] [PULL 18/25] hw/pci: remove obsolete PCIDevice->init() Michael S. Tsirkin
2017-12-21 14:29 ` [Qemu-devel] [PULL 19/25] vhost-user: fix indentation in protocol specification Michael S. Tsirkin
2017-12-21 14:29 ` Michael S. Tsirkin [this message]
2017-12-21 14:30 ` [Qemu-devel] [PULL 23/25] virtio-pci: Don't force Subsystem Vendor ID = Vendor ID Michael S. Tsirkin
2017-12-21 14:31 ` [Qemu-devel] [PULL 24/25] dump-guest-memory.py: fix "You can't do that without a process to debug" Michael S. Tsirkin
2017-12-21 14:31 ` [Qemu-devel] [PULL 25/25] smbus: do not immediately complete commands Michael S. Tsirkin
2017-12-21 14:33 ` [Qemu-devel] [PULL 21/25] intel_iommu: remove X86_IOMMU_PCI_DEVFN_MAX Michael S. Tsirkin
2017-12-21 14:34 ` [Qemu-devel] [PULL 22/25] intel_iommu: fix error param in string Michael S. Tsirkin
2017-12-21 20:26 ` [Qemu-devel] [PULL 00/25] pc, pci, virtio: features, fixes, cleanups Peter Maydell
2017-12-21 20:37   ` Michael S. Tsirkin
2017-12-21 23:05     ` Peter Maydell
2017-12-21 23:42       ` Michael S. Tsirkin
2017-12-22  0:44         ` Philippe Mathieu-Daudé
2017-12-21 23:05     ` Philippe Mathieu-Daudé
2017-12-21 23:43       ` Michael S. Tsirkin
2018-01-08  9:14         ` Peter Maydell
2018-01-08 17:04           ` Michael S. Tsirkin
2018-01-08 18:10           ` Michael S. Tsirkin
2018-01-09  1:10             ` David Gibson
2018-01-09  4:09               ` Michael S. Tsirkin
2018-01-16  2:48               ` Michael S. Tsirkin
2018-01-16  6:28                 ` Jason Wang
2018-01-16  6:33                   ` Jason Wang
2018-01-16  8:03                   ` Dmitry Fleytman
2018-01-17  3:14                     ` Jason Wang
2018-01-09  4:11           ` Michael S. Tsirkin
2018-01-11 15:31             ` Peter Maydell
2018-01-11 19:59               ` Michael S. Tsirkin
2018-01-11 20:06               ` Michael S. Tsirkin
2018-01-11 21:05               ` Michael S. Tsirkin
2018-01-12 10:44                 ` Peter Maydell
2018-01-12 16:02                   ` Michael S. Tsirkin

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=1513866427-27125-21-git-send-email-mst@redhat.com \
    --to=mst@redhat.com \
    --cc=maxime.coquelin@redhat.com \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=stefanha@redhat.com \
    --cc=wei.w.wang@intel.com \
    /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.