From: Jason Wang <jasowang@redhat.com>
To: "Eugenio Pérez" <eperezma@redhat.com>, qemu-devel@nongnu.org
Cc: Laurent Vivier <lvivier@redhat.com>,
Parav Pandit <parav@mellanox.com>, Cindy Lu <lulu@redhat.com>,
"Michael S. Tsirkin" <mst@redhat.com>,
Juan Quintela <quintela@redhat.com>,
Richard Henderson <richard.henderson@linaro.org>,
Markus Armbruster <armbru@redhat.com>,
Gautam Dawar <gdawar@xilinx.com>,
virtualization@lists.linux-foundation.org,
Eduardo Habkost <ehabkost@redhat.com>,
Harpreet Singh Anand <hanand@xilinx.com>,
Xiao W Wang <xiao.w.wang@intel.com>, Peter Xu <peterx@redhat.com>,
Stefan Hajnoczi <stefanha@redhat.com>,
Eli Cohen <eli@mellanox.com>, Paolo Bonzini <pbonzini@redhat.com>,
Zhu Lingshan <lingshan.zhu@intel.com>,
Eric Blake <eblake@redhat.com>,
Stefano Garzarella <sgarzare@redhat.com>
Subject: Re: [PATCH 22/31] vhost: Add VhostIOVATree
Date: Sun, 30 Jan 2022 13:21:21 +0800 [thread overview]
Message-ID: <2eb07526-0143-d612-8969-097ccdf00fae@redhat.com> (raw)
In-Reply-To: <20220121202733.404989-23-eperezma@redhat.com>
在 2022/1/22 上午4:27, Eugenio Pérez 写道:
> This tree is able to look for a translated address from an IOVA address.
>
> At first glance it is similar to util/iova-tree. However, SVQ working on
> devices with limited IOVA space need more capabilities,
So did the IOVA tree (e.g l2 vtd can only work in the range of GAW and
without RMRRs).
> like allocating
> IOVA chunks or performing reverse translations (qemu addresses to iova).
This looks like a general request as well. So I wonder if we can simply
extend iova tree instead.
Thanks
>
> The allocation capability, as "assign a free IOVA address to this chunk
> of memory in qemu's address space" allows shadow virtqueue to create a
> new address space that is not restricted by guest's addressable one, so
> we can allocate shadow vqs vrings outside of it.
>
> It duplicates the tree so it can search efficiently both directions,
> and it will signal overlap if iova or the translated address is
> present in any tree.
>
> Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
> ---
> hw/virtio/vhost-iova-tree.h | 27 +++++++
> hw/virtio/vhost-iova-tree.c | 157 ++++++++++++++++++++++++++++++++++++
> hw/virtio/meson.build | 2 +-
> 3 files changed, 185 insertions(+), 1 deletion(-)
> create mode 100644 hw/virtio/vhost-iova-tree.h
> create mode 100644 hw/virtio/vhost-iova-tree.c
>
> diff --git a/hw/virtio/vhost-iova-tree.h b/hw/virtio/vhost-iova-tree.h
> new file mode 100644
> index 0000000000..610394eaf1
> --- /dev/null
> +++ b/hw/virtio/vhost-iova-tree.h
> @@ -0,0 +1,27 @@
> +/*
> + * vhost software live migration ring
> + *
> + * SPDX-FileCopyrightText: Red Hat, Inc. 2021
> + * SPDX-FileContributor: Author: Eugenio Pérez <eperezma@redhat.com>
> + *
> + * SPDX-License-Identifier: GPL-2.0-or-later
> + */
> +
> +#ifndef HW_VIRTIO_VHOST_IOVA_TREE_H
> +#define HW_VIRTIO_VHOST_IOVA_TREE_H
> +
> +#include "qemu/iova-tree.h"
> +#include "exec/memory.h"
> +
> +typedef struct VhostIOVATree VhostIOVATree;
> +
> +VhostIOVATree *vhost_iova_tree_new(uint64_t iova_first, uint64_t iova_last);
> +void vhost_iova_tree_delete(VhostIOVATree *iova_tree);
> +G_DEFINE_AUTOPTR_CLEANUP_FUNC(VhostIOVATree, vhost_iova_tree_delete);
> +
> +const DMAMap *vhost_iova_tree_find_iova(const VhostIOVATree *iova_tree,
> + const DMAMap *map);
> +int vhost_iova_tree_map_alloc(VhostIOVATree *iova_tree, DMAMap *map);
> +void vhost_iova_tree_remove(VhostIOVATree *iova_tree, const DMAMap *map);
> +
> +#endif
> diff --git a/hw/virtio/vhost-iova-tree.c b/hw/virtio/vhost-iova-tree.c
> new file mode 100644
> index 0000000000..0021dbaf54
> --- /dev/null
> +++ b/hw/virtio/vhost-iova-tree.c
> @@ -0,0 +1,157 @@
> +/*
> + * vhost software live migration ring
> + *
> + * SPDX-FileCopyrightText: Red Hat, Inc. 2021
> + * SPDX-FileContributor: Author: Eugenio Pérez <eperezma@redhat.com>
> + *
> + * SPDX-License-Identifier: GPL-2.0-or-later
> + */
> +
> +#include "qemu/osdep.h"
> +#include "qemu/iova-tree.h"
> +#include "vhost-iova-tree.h"
> +
> +#define iova_min_addr qemu_real_host_page_size
> +
> +/**
> + * VhostIOVATree, able to:
> + * - Translate iova address
> + * - Reverse translate iova address (from translated to iova)
> + * - Allocate IOVA regions for translated range (potentially slow operation)
> + *
> + * Note that it cannot remove nodes.
> + */
> +struct VhostIOVATree {
> + /* First addresable iova address in the device */
> + uint64_t iova_first;
> +
> + /* Last addressable iova address in the device */
> + uint64_t iova_last;
> +
> + /* IOVA address to qemu memory maps. */
> + IOVATree *iova_taddr_map;
> +
> + /* QEMU virtual memory address to iova maps */
> + GTree *taddr_iova_map;
> +};
> +
> +static gint vhost_iova_tree_cmp_taddr(gconstpointer a, gconstpointer b,
> + gpointer data)
> +{
> + const DMAMap *m1 = a, *m2 = b;
> +
> + if (m1->translated_addr > m2->translated_addr + m2->size) {
> + return 1;
> + }
> +
> + if (m1->translated_addr + m1->size < m2->translated_addr) {
> + return -1;
> + }
> +
> + /* Overlapped */
> + return 0;
> +}
> +
> +/**
> + * Create a new IOVA tree
> + *
> + * Returns the new IOVA tree
> + */
> +VhostIOVATree *vhost_iova_tree_new(hwaddr iova_first, hwaddr iova_last)
> +{
> + VhostIOVATree *tree = g_new(VhostIOVATree, 1);
> +
> + /* Some devices does not like 0 addresses */
> + tree->iova_first = MAX(iova_first, iova_min_addr);
> + tree->iova_last = iova_last;
> +
> + tree->iova_taddr_map = iova_tree_new();
> + tree->taddr_iova_map = g_tree_new_full(vhost_iova_tree_cmp_taddr, NULL,
> + NULL, g_free);
> + return tree;
> +}
> +
> +/**
> + * Delete an iova tree
> + */
> +void vhost_iova_tree_delete(VhostIOVATree *iova_tree)
> +{
> + iova_tree_destroy(iova_tree->iova_taddr_map);
> + g_tree_unref(iova_tree->taddr_iova_map);
> + g_free(iova_tree);
> +}
> +
> +/**
> + * Find the IOVA address stored from a memory address
> + *
> + * @tree The iova tree
> + * @map The map with the memory address
> + *
> + * Return the stored mapping, or NULL if not found.
> + */
> +const DMAMap *vhost_iova_tree_find_iova(const VhostIOVATree *tree,
> + const DMAMap *map)
> +{
> + return g_tree_lookup(tree->taddr_iova_map, map);
> +}
> +
> +/**
> + * Allocate a new mapping
> + *
> + * @tree The iova tree
> + * @map The iova map
> + *
> + * Returns:
> + * - IOVA_OK if the map fits in the container
> + * - IOVA_ERR_INVALID if the map does not make sense (like size overflow)
> + * - IOVA_ERR_OVERLAP if the tree already contains that map
> + * - IOVA_ERR_NOMEM if tree cannot allocate more space.
> + *
> + * It returns assignated iova in map->iova if return value is VHOST_DMA_MAP_OK.
> + */
> +int vhost_iova_tree_map_alloc(VhostIOVATree *tree, DMAMap *map)
> +{
> + /* Some vhost devices does not like addr 0. Skip first page */
> + hwaddr iova_first = tree->iova_first ?: qemu_real_host_page_size;
> + DMAMap *new;
> + int r;
> +
> + if (map->translated_addr + map->size < map->translated_addr ||
> + map->perm == IOMMU_NONE) {
> + return IOVA_ERR_INVALID;
> + }
> +
> + /* Check for collisions in translated addresses */
> + if (vhost_iova_tree_find_iova(tree, map)) {
> + return IOVA_ERR_OVERLAP;
> + }
> +
> + /* Allocate a node in IOVA address */
> + r = iova_tree_alloc(tree->iova_taddr_map, map, iova_first,
> + tree->iova_last);
> + if (r != IOVA_OK) {
> + return r;
> + }
> +
> + /* Allocate node in qemu -> iova translations */
> + new = g_malloc(sizeof(*new));
> + memcpy(new, map, sizeof(*new));
> + g_tree_insert(tree->taddr_iova_map, new, new);
> + return IOVA_OK;
> +}
> +
> +/**
> + * Remove existing mappings from iova tree
> + *
> + * @param iova_tree The vhost iova tree
> + * @param map The map to remove
> + */
> +void vhost_iova_tree_remove(VhostIOVATree *iova_tree, const DMAMap *map)
> +{
> + const DMAMap *overlap;
> +
> + iova_tree_remove(iova_tree->iova_taddr_map, map);
> + while ((overlap = vhost_iova_tree_find_iova(iova_tree, map))) {
> + g_tree_remove(iova_tree->taddr_iova_map, overlap);
> + }
> +}
> diff --git a/hw/virtio/meson.build b/hw/virtio/meson.build
> index 2dc87613bc..6047670804 100644
> --- a/hw/virtio/meson.build
> +++ b/hw/virtio/meson.build
> @@ -11,7 +11,7 @@ softmmu_ss.add(when: 'CONFIG_ALL', if_true: files('vhost-stub.c'))
>
> virtio_ss = ss.source_set()
> virtio_ss.add(files('virtio.c'))
> -virtio_ss.add(when: 'CONFIG_VHOST', if_true: files('vhost.c', 'vhost-backend.c', 'vhost-shadow-virtqueue.c'))
> +virtio_ss.add(when: 'CONFIG_VHOST', if_true: files('vhost.c', 'vhost-backend.c', 'vhost-shadow-virtqueue.c', 'vhost-iova-tree.c'))
> virtio_ss.add(when: 'CONFIG_VHOST_USER', if_true: files('vhost-user.c'))
> virtio_ss.add(when: 'CONFIG_VHOST_VDPA', if_true: files('vhost-vdpa.c'))
> virtio_ss.add(when: 'CONFIG_VIRTIO_BALLOON', if_true: files('virtio-balloon.c'))
next prev parent reply other threads:[~2022-01-30 5:23 UTC|newest]
Thread overview: 130+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-01-21 20:27 [PATCH 00/31] vDPA shadow virtqueue Eugenio Pérez
2022-01-21 20:27 ` [PATCH 01/31] vdpa: Reorder virtio/vhost-vdpa.c functions Eugenio Pérez
2022-01-28 5:59 ` Jason Wang
2022-01-28 7:57 ` Eugenio Perez Martin
2022-02-21 7:31 ` Jason Wang
2022-02-21 7:42 ` Eugenio Perez Martin
2022-01-21 20:27 ` [PATCH 02/31] vhost: Add VhostShadowVirtqueue Eugenio Pérez
2022-01-26 8:53 ` Eugenio Perez Martin
2022-01-28 6:00 ` Jason Wang
2022-01-28 8:10 ` Eugenio Perez Martin
2022-01-21 20:27 ` [PATCH 03/31] vdpa: Add vhost_svq_get_dev_kick_notifier Eugenio Pérez
2022-01-28 6:03 ` Jason Wang
2022-01-31 9:33 ` Eugenio Perez Martin
2022-01-21 20:27 ` [PATCH 04/31] vdpa: Add vhost_svq_set_svq_kick_fd Eugenio Pérez
2022-01-28 6:29 ` Jason Wang
2022-01-31 10:18 ` Eugenio Perez Martin
2022-02-08 8:47 ` Jason Wang
2022-02-18 18:22 ` Eugenio Perez Martin
2022-01-21 20:27 ` [PATCH 05/31] vhost: Add Shadow VirtQueue kick forwarding capabilities Eugenio Pérez
2022-01-28 6:32 ` Jason Wang
2022-01-31 10:48 ` Eugenio Perez Martin
2022-01-21 20:27 ` [PATCH 06/31] vhost: Route guest->host notification through shadow virtqueue Eugenio Pérez
2022-01-28 6:56 ` Jason Wang
2022-01-31 11:33 ` Eugenio Perez Martin
2022-02-08 9:02 ` Jason Wang
2022-01-21 20:27 ` [PATCH 07/31] vhost: dd vhost_svq_get_svq_call_notifier Eugenio Pérez
2022-01-29 7:57 ` Jason Wang
2022-01-29 17:49 ` Eugenio Perez Martin
2022-01-21 20:27 ` [PATCH 08/31] vhost: Add vhost_svq_set_guest_call_notifier Eugenio Pérez
2022-01-21 20:27 ` [PATCH 09/31] vhost-vdpa: Take into account SVQ in vhost_vdpa_set_vring_call Eugenio Pérez
2022-01-29 8:05 ` Jason Wang
2022-01-31 15:34 ` Eugenio Perez Martin
2022-02-08 3:23 ` Jason Wang
2022-02-18 12:35 ` Eugenio Perez Martin
2022-02-21 7:39 ` Jason Wang
2022-02-21 8:01 ` Eugenio Perez Martin
2022-02-22 7:18 ` Jason Wang
2022-01-21 20:27 ` [PATCH 10/31] vhost: Route host->guest notification through shadow virtqueue Eugenio Pérez
2022-01-21 20:27 ` [PATCH 11/31] vhost: Add vhost_svq_valid_device_features to shadow vq Eugenio Pérez
2022-01-29 8:11 ` Jason Wang
2022-01-31 15:49 ` Eugenio Perez Martin
2022-02-01 10:57 ` Eugenio Perez Martin
2022-02-08 3:37 ` Jason Wang
2022-02-26 9:11 ` Liuxiangdong via
2022-02-26 11:12 ` Eugenio Perez Martin
2022-01-21 20:27 ` [PATCH 12/31] vhost: Add vhost_svq_valid_guest_features " Eugenio Pérez
2022-01-21 20:27 ` [PATCH 13/31] vhost: Add vhost_svq_ack_guest_features " Eugenio Pérez
2022-01-21 20:27 ` [PATCH 14/31] virtio: Add vhost_shadow_vq_get_vring_addr Eugenio Pérez
2022-01-21 20:27 ` [PATCH 15/31] vdpa: Add vhost_svq_get_num Eugenio Pérez
2022-01-29 8:14 ` Jason Wang
2022-01-31 16:36 ` Eugenio Perez Martin
2022-01-21 20:27 ` [PATCH 16/31] vhost: pass queue index to vhost_vq_get_addr Eugenio Pérez
2022-01-29 8:20 ` Jason Wang
2022-01-31 17:44 ` Eugenio Perez Martin
2022-02-08 6:58 ` Jason Wang
2022-01-21 20:27 ` [PATCH 17/31] vdpa: adapt vhost_ops callbacks to svq Eugenio Pérez
2022-01-30 4:03 ` Jason Wang
2022-01-31 18:58 ` Eugenio Perez Martin
2022-02-08 3:57 ` Jason Wang
2022-02-17 17:13 ` Eugenio Perez Martin
2022-02-21 7:15 ` Jason Wang
2022-02-21 17:22 ` Eugenio Perez Martin
2022-02-22 3:16 ` Jason Wang
2022-02-22 7:42 ` Eugenio Perez Martin
2022-02-22 7:59 ` Jason Wang
2022-01-21 20:27 ` [PATCH 18/31] vhost: Shadow virtqueue buffers forwarding Eugenio Pérez
2022-01-30 4:42 ` Jason Wang
2022-02-01 17:08 ` Eugenio Perez Martin
2022-02-08 8:11 ` Jason Wang
2022-02-22 19:01 ` Eugenio Perez Martin
2022-02-23 2:03 ` Jason Wang
2022-01-30 6:46 ` Jason Wang
2022-02-01 11:25 ` Eugenio Perez Martin
2022-02-08 8:15 ` Jason Wang
2022-02-17 12:48 ` Eugenio Perez Martin
2022-02-21 7:43 ` Jason Wang
2022-02-21 8:15 ` Eugenio Perez Martin
2022-02-22 7:26 ` Jason Wang
2022-02-22 8:55 ` Eugenio Perez Martin
2022-02-23 2:26 ` Jason Wang
2022-01-21 20:27 ` [PATCH 19/31] utils: Add internal DMAMap to iova-tree Eugenio Pérez
2022-01-21 20:27 ` [PATCH 20/31] util: Store DMA entries in a list Eugenio Pérez
2022-01-21 20:27 ` [PATCH 21/31] util: Add iova_tree_alloc Eugenio Pérez
2022-01-24 4:32 ` Peter Xu
2022-01-24 9:20 ` Eugenio Perez Martin
2022-01-24 11:07 ` Peter Xu
2022-01-25 9:40 ` Eugenio Perez Martin
2022-01-27 8:06 ` Peter Xu
2022-01-27 9:24 ` Eugenio Perez Martin
2022-01-28 3:57 ` Peter Xu
2022-01-28 5:55 ` Jason Wang
2022-01-28 7:48 ` Eugenio Perez Martin
2022-02-15 19:34 ` Eugenio Pérez
2022-02-15 19:34 ` [PATCH] util: Add iova_tree_alloc Eugenio Pérez
2022-02-16 7:25 ` Peter Xu
2022-01-30 5:06 ` [PATCH 21/31] " Jason Wang
2022-01-21 20:27 ` [PATCH 22/31] vhost: Add VhostIOVATree Eugenio Pérez
2022-01-30 5:21 ` Jason Wang [this message]
2022-02-01 17:27 ` Eugenio Perez Martin
2022-02-08 8:17 ` Jason Wang
2022-01-21 20:27 ` [PATCH 23/31] vdpa: Add custom IOTLB translations to SVQ Eugenio Pérez
2022-01-30 5:57 ` Jason Wang
2022-01-31 19:11 ` Eugenio Perez Martin
2022-02-08 8:19 ` Jason Wang
2022-01-21 20:27 ` [PATCH 24/31] vhost: Add vhost_svq_get_last_used_idx Eugenio Pérez
2022-01-21 20:27 ` [PATCH 25/31] vdpa: Adapt vhost_vdpa_get_vring_base to SVQ Eugenio Pérez
2022-01-21 20:27 ` [PATCH 26/31] vdpa: Clear VHOST_VRING_F_LOG at vhost_vdpa_set_vring_addr in SVQ Eugenio Pérez
2022-01-21 20:27 ` [PATCH 27/31] vdpa: Never set log_base addr if SVQ is enabled Eugenio Pérez
2022-01-21 20:27 ` [PATCH 28/31] vdpa: Expose VHOST_F_LOG_ALL on SVQ Eugenio Pérez
2022-01-30 6:50 ` Jason Wang
2022-02-01 11:45 ` Eugenio Perez Martin
2022-02-08 8:25 ` Jason Wang
2022-02-16 15:53 ` Eugenio Perez Martin
2022-02-17 6:02 ` Jason Wang
2022-02-17 8:22 ` Eugenio Perez Martin
2022-02-22 7:41 ` Jason Wang
2022-02-22 8:05 ` Eugenio Perez Martin
2022-02-23 3:46 ` Jason Wang
2022-02-23 8:06 ` Eugenio Perez Martin
2022-02-24 3:45 ` Jason Wang
2022-01-21 20:27 ` [PATCH 29/31] vdpa: Make ncs autofree Eugenio Pérez
2022-01-30 6:51 ` Jason Wang
2022-02-01 17:10 ` Eugenio Perez Martin
2022-01-21 20:27 ` [PATCH 30/31] vdpa: Move vhost_vdpa_get_iova_range to net/vhost-vdpa.c Eugenio Pérez
2022-01-30 6:53 ` Jason Wang
2022-02-01 17:11 ` Eugenio Perez Martin
2022-01-21 20:27 ` [PATCH 31/31] vdpa: Add x-svq to NetdevVhostVDPAOptions Eugenio Pérez
2022-01-28 6:02 ` [PATCH 00/31] vDPA shadow virtqueue Jason Wang
2022-01-31 9:15 ` Eugenio Perez Martin
2022-02-08 8:27 ` Jason Wang
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=2eb07526-0143-d612-8969-097ccdf00fae@redhat.com \
--to=jasowang@redhat.com \
--cc=armbru@redhat.com \
--cc=eblake@redhat.com \
--cc=ehabkost@redhat.com \
--cc=eli@mellanox.com \
--cc=eperezma@redhat.com \
--cc=gdawar@xilinx.com \
--cc=hanand@xilinx.com \
--cc=lingshan.zhu@intel.com \
--cc=lulu@redhat.com \
--cc=lvivier@redhat.com \
--cc=mst@redhat.com \
--cc=parav@mellanox.com \
--cc=pbonzini@redhat.com \
--cc=peterx@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=quintela@redhat.com \
--cc=richard.henderson@linaro.org \
--cc=sgarzare@redhat.com \
--cc=stefanha@redhat.com \
--cc=virtualization@lists.linux-foundation.org \
--cc=xiao.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 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).