Development discussions about virtio-fs
 help / color / mirror / Atom feed
From: Connor Kite <connorkite@gmail.com>
To: qemu-devel@nongnu.org
Cc: "Michael S. Tsirkin" <mst@redhat.com>,
	"Stefano Garzarella" <sgarzare@redhat.com>,
	"Alex Bennée" <alex.bennee@linaro.org>,
	"Viresh Kumar" <viresh.kumar@linaro.org>,
	"Gerd Hoffmann" <kraxel@redhat.com>,
	"Mathieu Poirier" <mathieu.poirier@linaro.org>,
	"Manos Pitsidianakis" <manos.pitsidianakis@linaro.org>,
	"Raphael Norwitz" <rnorwitz@nvidia.com>,
	"Kevin Wolf" <kwolf@redhat.com>,
	"Hanna Reitz" <hreitz@redhat.com>,
	"Marc-André Lureau" <marcandre.lureau@redhat.com>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Fam Zheng" <fam@euphon.net>,
	"Stefan Hajnoczi" <stefanha@redhat.com>,
	"Milan Zamazal" <mzamazal@redhat.com>,
	"Akihiko Odaki" <odaki@rsg.ci.i.u-tokyo.ac.jp>,
	"Dmitry Osipenko" <dmitry.osipenko@collabora.com>,
	qemu-block@nongnu.org, virtio-fs@lists.linux.dev,
	"Gonglei (Arei)" <arei.gonglei@huawei.com>,
	"zhenwei pi" <zhenwei.pi@linux.dev>,
	"Daniel P. Berrangé" <berrange@redhat.com>,
	"Eric Blake" <eblake@redhat.com>,
	"Markus Armbruster" <armbru@redhat.com>,
	"Jason Wang" <jasowangio@gmail.com>,
	"Peter Xu" <peterx@redhat.com>,
	"Eugenio Pérez" <eperezma@redhat.com>,
	"Alyssa Ross" <hi@alyssa.is>,
	"Demi Marie Obenour" <demiobenour@gmail.com>,
	"Connor Kite" <connorkite@gmail.com>,
	20260817233147.2867623-1-connorkite@gmail.com
Subject: [PATCH RFC v2 07/13] hw/virtio/vhost-user: create isolation region
Date: Mon, 17 Aug 2026 22:12:22 -0700	[thread overview]
Message-ID: <20260817-vhost-user-isolated-memory-v2-7-948aae960abb@gmail.com> (raw)
In-Reply-To: <20260817-vhost-user-isolated-memory-v2-0-948aae960abb@gmail.com>

If memory isolation mode is active for the vhost-user device adds
features to:
- Gather the size required for bounce buffers and vrings in shared
  isolation region
- Allocate the required space in an anonymous file
- Create a vhost-iova-tree with space to map entire isolation region
- Map guest memory regions and shared vrings into the tree
- Release these resources upon backend cleanup

Signed-off-by: Connor Kite <connorkite@gmail.com>
---
 hw/virtio/vhost-user.c | 136 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 136 insertions(+)

diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 1c003e4d9d..7e9233e174 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -18,6 +18,7 @@
 #include "hw/virtio/vhost-backend.h"
 #include "hw/virtio/virtio.h"
 #include "hw/virtio/virtio-net.h"
+#include "hw/virtio/vhost-iova-tree.h"
 #include "chardev/char-fe.h"
 #include "io/channel-socket.h"
 #include "system/kvm.h"
@@ -25,6 +26,7 @@
 #include "qemu/main-loop.h"
 #include "qemu/uuid.h"
 #include "qemu/sockets.h"
+#include "qemu/memfd.h"
 #include "system/runstate.h"
 #include "system/cryptodev.h"
 #include "migration/postcopy-ram.h"
@@ -320,6 +322,17 @@ static VhostUserMsg m __attribute__ ((unused));
 /* The version of the protocol we support */
 #define VHOST_USER_VERSION    (0x1)
 
+/* Memory region shared with back-end when memory-isolation is active */
+typedef struct {
+    void *shared_mem_addr; /* mapped shared memory */
+    VhostIOVATree *tree; /* controls mapping of regions into IOVA space */
+    void *vring_hva_addr; /* beginning of vring region in shared memory */
+    size_t vring_region_size; /* amount of shared memory reserved for vrings */
+    size_t size; /* size of the mapped shared memory */
+    int fd; /* descriptor of anonymous file backing shared iso region */
+    Int128 iso_iova_offset; /* translation from IOVA to hva of iso region */
+} IsolationModeCtx;
+
 struct vhost_user {
     struct vhost_dev *dev;
     /* Shared between vhost devs of the same virtio device */
@@ -353,6 +366,9 @@ struct vhost_user {
      * by the backend (see @features).
      */
     uint64_t protocol_features;
+
+    /* Data specfic to isolated memory mode */
+    IsolationModeCtx iso_mem_ctx;
 };
 
 struct scrub_regions {
@@ -1112,6 +1128,125 @@ static int vhost_user_set_mem_table_postcopy(struct vhost_dev *dev,
     return 0;
 }
 
+static void cleanup_isolation_regions(struct vhost_dev *dev)
+{
+    struct vhost_user *u = dev->opaque;
+    if (u->iso_mem_ctx.shared_mem_addr) {
+        vhost_iova_tree_delete(u->iso_mem_ctx.tree);
+        qemu_memfd_free(u->iso_mem_ctx.shared_mem_addr,
+                        u->iso_mem_ctx.size,
+                        u->iso_mem_ctx.fd);
+        memset(&u->iso_mem_ctx, 0, sizeof(IsolationModeCtx));
+    }
+}
+
+__attribute__((unused))
+static int init_isolation_regions(struct vhost_dev *dev,
+                                  VhostUserMsg *msg,
+                                  int *fds, size_t *fd_num)
+{
+    Error *err = NULL;
+    struct vhost_user *u = dev->opaque;
+    uint32_t nregions = dev->mem->nregions;
+
+    g_autofree DMAMap *buffer_regions = g_new0(DMAMap, nregions);
+    size_t buffer_reg_size = 0;
+    size_t total_vring_size = 0;
+    size_t total_mmap_size;
+    char *reg_name;
+    uint64_t first_IOVA_addr;
+    uint64_t last_IOVA_addr;
+    DMAMap *map;
+    DMAMap vring_map;
+    int r;
+
+    msg->hdr.request = VHOST_USER_SET_MEM_TABLE;
+
+    /* In case of reset, clear old regions */
+    cleanup_isolation_regions(dev);
+
+    /* Gather information for bounce buffers to be mapped */
+    for (u_int32_t i = 0; i < nregions; i++) {
+        hwaddr size = ROUND_UP(dev->mem->regions[i].memory_size,
+                      qemu_real_host_page_size());
+        buffer_regions[i].size = size - 1;
+        buffer_regions[i].perm = IOMMU_RW;
+
+        buffer_reg_size += size;
+    }
+
+    /* Get space required for all vrings */
+    for (int i = 0; i < dev->nvqs; i++) {
+        VirtQueue *vq = virtio_get_queue(dev->vdev, dev->vq_index + i);
+        total_vring_size += vhost_svq_vring_total_size(dev->vdev, vq);
+    }
+
+    total_mmap_size = buffer_reg_size + total_vring_size;
+    u->iso_mem_ctx.size = total_mmap_size;
+
+    /* Allocate and map an anonymous file to hold the isolation region */
+    reg_name = g_strconcat("iso_mem_", dev->vdev->name, NULL);
+    u->iso_mem_ctx.shared_mem_addr = qemu_memfd_alloc(reg_name,
+                                     total_mmap_size,
+                                     F_SEAL_GROW | F_SEAL_SHRINK | F_SEAL_SEAL,
+                                     &u->iso_mem_ctx.fd, &err);
+
+    assert(u->iso_mem_ctx.fd >= 0);
+    g_free(reg_name);
+
+    if (err) {
+        error_report_err(err);
+        cleanup_isolation_regions(dev);
+        return -1;
+    }
+
+    /* vhost-iova-tree enforces non-zero lower address */
+    first_IOVA_addr = qemu_real_host_page_size();
+    last_IOVA_addr = first_IOVA_addr + total_mmap_size - 1;
+    assert(last_IOVA_addr > first_IOVA_addr);
+
+    /* Use 128-bit operation in case of large negative offset */
+    u->iso_mem_ctx.iso_iova_offset =
+        int128_sub(int128_make64((uint64_t)u->iso_mem_ctx.shared_mem_addr),
+        int128_make64(first_IOVA_addr));
+
+    /*
+     * Instantiates iova tree sized to map bounce buffers and vrings to the
+     * isolation region in host va.
+     */
+    u->iso_mem_ctx.tree =
+        vhost_iova_tree_new(first_IOVA_addr, last_IOVA_addr);
+
+    /* Map vrings into IOVA tree */
+    vring_map.perm = IOMMU_RW;
+    vring_map.size = total_vring_size - 1;
+    r = vhost_iova_tree_map_alloc(u->iso_mem_ctx.tree, &vring_map,
+                                  (hwaddr)u->iso_mem_ctx.shared_mem_addr);
+
+    if (r != IOVA_OK) {
+        cleanup_isolation_regions(dev);
+        return r;
+    }
+
+    u->iso_mem_ctx.vring_hva_addr = (void *)int128_get64(
+                                    int128_add(int128_make64(vring_map.iova),
+                                               u->iso_mem_ctx.iso_iova_offset));
+    u->iso_mem_ctx.vring_region_size = total_vring_size;
+
+    for (int i = 0; i < nregions; i++) {
+        map = &buffer_regions[i];
+        r = vhost_iova_tree_map_alloc_gpa(u->iso_mem_ctx.tree, map,
+                                          dev->mem->regions[i].guest_phys_addr);
+
+        if (r != IOVA_OK) {
+            cleanup_isolation_regions(dev);
+            return r;
+        }
+    }
+
+    return 0;
+}
+
 static int vhost_user_set_mem_table(struct vhost_dev *dev,
                                     struct vhost_memory *mem)
 {
@@ -2684,6 +2819,7 @@ static int vhost_user_backend_cleanup(struct vhost_dev *dev)
     g_free(u->region_rb_offset);
     u->region_rb_offset = NULL;
     u->region_rb_len = 0;
+    cleanup_isolation_regions(dev);
     g_free(u);
     dev->opaque = 0;
 

-- 
2.43.0


  parent reply	other threads:[~2026-08-18  5:12 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-18  5:12 [PATCH RFC v2 00/13] vhost-user: isolated memory Connor Kite
2026-08-18  5:12 ` [PATCH RFC v2 01/13] vhost-user: Consolidate chardev property definitions Connor Kite
2026-08-18  5:12 ` [PATCH RFC v2 02/13] util/iova-tree: g_tree_foreach wrapper Connor Kite
2026-08-18  5:12 ` [PATCH RFC v2 03/13] hw/virtio: iova_tree_foreach wrapper Connor Kite
2026-08-18  5:12 ` [PATCH RFC v2 04/13] hw/virtio/vhost-shadow-virtqueue: used callback Connor Kite
2026-08-19  6:23   ` Akihiko Odaki
2026-08-20  1:06     ` Connor Kite
2026-08-20  5:15       ` Akihiko Odaki
2026-08-20 23:42         ` Connor Kite
2026-08-21  7:21           ` Akihiko Odaki
2026-08-18  5:12 ` [PATCH RFC v2 05/13] hw/virtio/vhost-shadow-virtqueue: specified vring placement Connor Kite
2026-08-18  5:12 ` [PATCH RFC v2 06/13] vhost-user: add memory_isolation to VhostUserState Connor Kite
2026-08-18  5:12 ` Connor Kite [this message]
2026-08-19  7:36   ` [PATCH RFC v2 07/13] hw/virtio/vhost-user: create isolation region Akihiko Odaki
2026-08-21  2:57     ` Connor Kite
2026-08-18  5:12 ` [PATCH RFC v2 08/13] hw/virtio/vhost-user: send isolation regions to device Connor Kite
2026-08-18 11:31   ` Akihiko Odaki
2026-08-18  5:12 ` [PATCH RFC v2 09/13] hw/virtio/vhost-user: add shadow virtqueues and eventfd intercepts Connor Kite
2026-08-18 12:34   ` Akihiko Odaki
2026-08-20 20:38     ` Connor Kite
2026-08-18  5:12 ` [PATCH RFC v2 10/13] hw/virtio/vhost-user: handle data movement with shadow vqs Connor Kite
2026-08-19  7:37   ` Akihiko Odaki
2026-08-18  5:12 ` [PATCH RFC v2 11/13] vhost-user: Add memory-isolation qdev property to vhost-user devices Connor Kite
2026-08-18  5:12 ` [PATCH RFC v2 12/13] backends/cryptodev-vhost-user: add memory isolation bool Connor Kite
2026-08-20  9:00   ` Markus Armbruster
2026-08-18  5:12 ` [PATCH RFC v2 13/13] net/vhost-user: add memory isolation Connor Kite
2026-08-19  7:37   ` Akihiko Odaki
2026-08-20  1:22     ` Connor Kite
2026-08-20  9:02   ` Markus Armbruster
2026-08-21  0:39     ` Connor Kite
2026-08-21  5:54       ` Markus Armbruster

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=20260817-vhost-user-isolated-memory-v2-7-948aae960abb@gmail.com \
    --to=connorkite@gmail.com \
    --cc=20260817233147.2867623-1-connorkite@gmail.com \
    --cc=alex.bennee@linaro.org \
    --cc=arei.gonglei@huawei.com \
    --cc=armbru@redhat.com \
    --cc=berrange@redhat.com \
    --cc=demiobenour@gmail.com \
    --cc=dmitry.osipenko@collabora.com \
    --cc=eblake@redhat.com \
    --cc=eperezma@redhat.com \
    --cc=fam@euphon.net \
    --cc=hi@alyssa.is \
    --cc=hreitz@redhat.com \
    --cc=jasowangio@gmail.com \
    --cc=kraxel@redhat.com \
    --cc=kwolf@redhat.com \
    --cc=manos.pitsidianakis@linaro.org \
    --cc=marcandre.lureau@redhat.com \
    --cc=mathieu.poirier@linaro.org \
    --cc=mst@redhat.com \
    --cc=mzamazal@redhat.com \
    --cc=odaki@rsg.ci.i.u-tokyo.ac.jp \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=rnorwitz@nvidia.com \
    --cc=sgarzare@redhat.com \
    --cc=stefanha@redhat.com \
    --cc=viresh.kumar@linaro.org \
    --cc=virtio-fs@lists.linux.dev \
    --cc=zhenwei.pi@linux.dev \
    /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