qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Cédric Le Goater" <clg@redhat.com>
To: qemu-devel@nongnu.org
Cc: "Alex Williamson" <alex.williamson@redhat.com>,
	"Steve Sistare" <steven.sistare@oracle.com>,
	"Zhenzhong Duan" <zhenzhong.duan@intel.com>,
	"Cédric Le Goater" <clg@redhat.com>
Subject: [PULL 18/27] vfio/iommufd: register container for cpr
Date: Fri,  4 Jul 2025 10:45:19 +0200	[thread overview]
Message-ID: <20250704084528.1412959-19-clg@redhat.com> (raw)
In-Reply-To: <20250704084528.1412959-1-clg@redhat.com>

From: Steve Sistare <steven.sistare@oracle.com>

Register a vfio iommufd container and device for CPR, replacing the generic
CPR register call with a more specific iommufd register call.  Add a
blocker if the kernel does not support IOMMU_IOAS_CHANGE_PROCESS.

This is mostly boiler plate.  The fields to to saved and restored are added
in subsequent patches.

Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Link: https://lore.kernel.org/qemu-devel/1751493538-202042-13-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
 include/hw/vfio/vfio-cpr.h | 12 ++++++
 include/system/iommufd.h   |  1 +
 backends/iommufd.c         | 10 +++++
 hw/vfio/cpr-iommufd.c      | 86 ++++++++++++++++++++++++++++++++++++++
 hw/vfio/iommufd.c          |  6 ++-
 hw/vfio/meson.build        |  1 +
 6 files changed, 114 insertions(+), 2 deletions(-)
 create mode 100644 hw/vfio/cpr-iommufd.c

diff --git a/include/hw/vfio/vfio-cpr.h b/include/hw/vfio/vfio-cpr.h
index fa7d43ddd8eccb305751f2311d4ca8248b5052d0..87b4206d8189c1cacd7fac629da5e3823a28c7ae 100644
--- a/include/hw/vfio/vfio-cpr.h
+++ b/include/hw/vfio/vfio-cpr.h
@@ -15,7 +15,10 @@
 struct VFIOContainer;
 struct VFIOContainerBase;
 struct VFIOGroup;
+struct VFIODevice;
 struct VFIOPCIDevice;
+struct VFIOIOMMUFDContainer;
+struct IOMMUFDBackend;
 
 typedef int (*dma_map_fn)(const struct VFIOContainerBase *bcontainer,
                           hwaddr iova, ram_addr_t size, void *vaddr,
@@ -44,6 +47,15 @@ bool vfio_cpr_register_container(struct VFIOContainerBase *bcontainer,
                                  Error **errp);
 void vfio_cpr_unregister_container(struct VFIOContainerBase *bcontainer);
 
+bool vfio_iommufd_cpr_register_container(struct VFIOIOMMUFDContainer *container,
+                                         Error **errp);
+void vfio_iommufd_cpr_unregister_container(
+    struct VFIOIOMMUFDContainer *container);
+bool vfio_iommufd_cpr_register_iommufd(struct IOMMUFDBackend *be, Error **errp);
+void vfio_iommufd_cpr_unregister_iommufd(struct IOMMUFDBackend *be);
+void vfio_iommufd_cpr_register_device(struct VFIODevice *vbasedev);
+void vfio_iommufd_cpr_unregister_device(struct VFIODevice *vbasedev);
+
 int vfio_cpr_group_get_device_fd(int d, const char *name);
 
 bool vfio_cpr_container_match(struct VFIOContainer *container,
diff --git a/include/system/iommufd.h b/include/system/iommufd.h
index db5f2c716c5be6cd1313045ab6dd28eb1f8356f3..c9c72ffc4509d7b5d09e8129c5065478aa23aec0 100644
--- a/include/system/iommufd.h
+++ b/include/system/iommufd.h
@@ -32,6 +32,7 @@ struct IOMMUFDBackend {
     /*< protected >*/
     int fd;            /* /dev/iommu file descriptor */
     bool owned;        /* is the /dev/iommu opened internally */
+    Error *cpr_blocker;/* set if be does not support CPR */
     uint32_t users;
 
     /*< public >*/
diff --git a/backends/iommufd.c b/backends/iommufd.c
index 87f81a05f6465cabc5673745f95947db2bb4a4fb..c554ce5385dd603ba35f97167ab8031750ecdc2f 100644
--- a/backends/iommufd.c
+++ b/backends/iommufd.c
@@ -108,6 +108,13 @@ bool iommufd_backend_connect(IOMMUFDBackend *be, Error **errp)
         }
         be->fd = fd;
     }
+    if (!be->users && !vfio_iommufd_cpr_register_iommufd(be, errp)) {
+        if (be->owned) {
+            close(be->fd);
+            be->fd = -1;
+        }
+        return false;
+    }
     be->users++;
 
     trace_iommufd_backend_connect(be->fd, be->owned, be->users);
@@ -125,6 +132,9 @@ void iommufd_backend_disconnect(IOMMUFDBackend *be)
         be->fd = -1;
     }
 out:
+    if (!be->users) {
+        vfio_iommufd_cpr_unregister_iommufd(be);
+    }
     trace_iommufd_backend_disconnect(be->fd, be->users);
 }
 
diff --git a/hw/vfio/cpr-iommufd.c b/hw/vfio/cpr-iommufd.c
new file mode 100644
index 0000000000000000000000000000000000000000..2f58b43793c048188ed61b560dcae1965383f061
--- /dev/null
+++ b/hw/vfio/cpr-iommufd.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright (c) 2024-2025 Oracle and/or its affiliates.
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "hw/vfio/vfio-cpr.h"
+#include "migration/blocker.h"
+#include "migration/cpr.h"
+#include "migration/migration.h"
+#include "migration/vmstate.h"
+#include "system/iommufd.h"
+#include "vfio-iommufd.h"
+
+static bool vfio_cpr_supported(IOMMUFDBackend *be, Error **errp)
+{
+    if (!iommufd_change_process_capable(be)) {
+        if (errp) {
+            error_setg(errp, "vfio iommufd backend does not support "
+                       "IOMMU_IOAS_CHANGE_PROCESS");
+        }
+        return false;
+    }
+    return true;
+}
+
+static const VMStateDescription iommufd_cpr_vmstate = {
+    .name = "iommufd",
+    .version_id = 0,
+    .minimum_version_id = 0,
+    .needed = cpr_incoming_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+bool vfio_iommufd_cpr_register_iommufd(IOMMUFDBackend *be, Error **errp)
+{
+    Error **cpr_blocker = &be->cpr_blocker;
+
+    if (!vfio_cpr_supported(be, cpr_blocker)) {
+        return migrate_add_blocker_modes(cpr_blocker, errp,
+                                         MIG_MODE_CPR_TRANSFER, -1) == 0;
+    }
+
+    vmstate_register(NULL, -1, &iommufd_cpr_vmstate, be);
+
+    return true;
+}
+
+void vfio_iommufd_cpr_unregister_iommufd(IOMMUFDBackend *be)
+{
+    vmstate_unregister(NULL, &iommufd_cpr_vmstate, be);
+    migrate_del_blocker(&be->cpr_blocker);
+}
+
+bool vfio_iommufd_cpr_register_container(VFIOIOMMUFDContainer *container,
+                                         Error **errp)
+{
+    VFIOContainerBase *bcontainer = &container->bcontainer;
+
+    migration_add_notifier_mode(&bcontainer->cpr_reboot_notifier,
+                                vfio_cpr_reboot_notifier,
+                                MIG_MODE_CPR_REBOOT);
+
+    vfio_cpr_add_kvm_notifier();
+
+    return true;
+}
+
+void vfio_iommufd_cpr_unregister_container(VFIOIOMMUFDContainer *container)
+{
+    VFIOContainerBase *bcontainer = &container->bcontainer;
+
+    migration_remove_notifier(&bcontainer->cpr_reboot_notifier);
+}
+
+void vfio_iommufd_cpr_register_device(VFIODevice *vbasedev)
+{
+}
+
+void vfio_iommufd_cpr_unregister_device(VFIODevice *vbasedev)
+{
+}
diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index 962a1e2b1f28b297cc876fffa2677bd525479c8c..ff291be2356d1a2f59aa6dc7953dc3fc00a627bd 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -446,7 +446,7 @@ static void iommufd_cdev_container_destroy(VFIOIOMMUFDContainer *container)
     if (!QLIST_EMPTY(&bcontainer->device_list)) {
         return;
     }
-    vfio_cpr_unregister_container(bcontainer);
+    vfio_iommufd_cpr_unregister_container(container);
     vfio_listener_unregister(bcontainer);
     iommufd_backend_free_id(container->be, container->ioas_id);
     object_unref(container);
@@ -592,7 +592,7 @@ static bool iommufd_cdev_attach(const char *name, VFIODevice *vbasedev,
         goto err_listener_register;
     }
 
-    if (!vfio_cpr_register_container(bcontainer, errp)) {
+    if (!vfio_iommufd_cpr_register_container(container, errp)) {
         goto err_listener_register;
     }
 
@@ -623,6 +623,7 @@ found_container:
     }
 
     vfio_device_prepare(vbasedev, bcontainer, &dev_info);
+    vfio_iommufd_cpr_register_device(vbasedev);
 
     trace_iommufd_cdev_device_info(vbasedev->name, devfd, vbasedev->num_irqs,
                                    vbasedev->num_regions, vbasedev->flags);
@@ -660,6 +661,7 @@ static void iommufd_cdev_detach(VFIODevice *vbasedev)
     iommufd_cdev_container_destroy(container);
     vfio_address_space_put(space);
 
+    vfio_iommufd_cpr_unregister_device(vbasedev);
     iommufd_cdev_unbind_and_disconnect(vbasedev);
     close(vbasedev->fd);
 }
diff --git a/hw/vfio/meson.build b/hw/vfio/meson.build
index 63ea39307601cce4b0783766f68c4cf8d9af71f9..7a881740a6d8d2d6f4f78024020060f2e11623eb 100644
--- a/hw/vfio/meson.build
+++ b/hw/vfio/meson.build
@@ -31,6 +31,7 @@ system_ss.add(when: 'CONFIG_VFIO', if_true: files(
 ))
 system_ss.add(when: ['CONFIG_VFIO', 'CONFIG_IOMMUFD'], if_true: files(
   'iommufd.c',
+  'cpr-iommufd.c',
 ))
 system_ss.add(when: 'CONFIG_VFIO_PCI', if_true: files(
   'display.c',
-- 
2.50.0



  parent reply	other threads:[~2025-07-04  8:48 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-07-04  8:45 [PULL 00/27] vfio queue Cédric Le Goater
2025-07-04  8:45 ` [PULL 01/27] vfio/container: Fix potential SIGSEGV when recover from unmap-all-vaddr failure Cédric Le Goater
2025-07-04  8:45 ` [PULL 02/27] vfio/container: Fix vfio_container_post_load() Cédric Le Goater
2025-07-04  8:45 ` [PULL 03/27] vfio-user: do not register vfio-user container with cpr Cédric Le Goater
2025-07-04  8:45 ` [PULL 04/27] i386/tdx: Build TDX only for 64-bit target Cédric Le Goater
2025-07-04  8:45 ` [PULL 05/27] b4: Drop linktrailermask Cédric Le Goater
2025-07-04  8:45 ` [PULL 06/27] Makefile: prune quilt source files for cscope Cédric Le Goater
2025-07-04  8:45 ` [PULL 07/27] vfio-pci: preserve MSI Cédric Le Goater
2025-07-04  8:45 ` [PULL 08/27] vfio-pci: preserve INTx Cédric Le Goater
2025-07-04  8:45 ` [PULL 09/27] migration: close kvm after cpr Cédric Le Goater
2025-07-04  8:45 ` [PULL 10/27] migration: cpr_get_fd_param helper Cédric Le Goater
2025-07-04  8:45 ` [PULL 11/27] backends/iommufd: iommufd_backend_map_file_dma Cédric Le Goater
2025-07-04  8:45 ` [PULL 12/27] backends/iommufd: change process ioctl Cédric Le Goater
2025-07-04  8:45 ` [PULL 13/27] physmem: qemu_ram_get_fd_offset Cédric Le Goater
2025-07-04  8:45 ` [PULL 14/27] vfio/iommufd: use IOMMU_IOAS_MAP_FILE Cédric Le Goater
2025-07-04  8:45 ` [PULL 15/27] vfio/iommufd: invariant device name Cédric Le Goater
2025-07-04  8:45 ` [PULL 16/27] vfio/iommufd: add vfio_device_free_name Cédric Le Goater
2025-07-04  8:45 ` [PULL 17/27] vfio/iommufd: device name blocker Cédric Le Goater
2025-07-04  8:45 ` Cédric Le Goater [this message]
2025-07-04  8:45 ` [PULL 19/27] migration: vfio cpr state hook Cédric Le Goater
2025-07-04  8:45 ` [PULL 20/27] vfio/iommufd: cpr state Cédric Le Goater
2025-07-04  8:45 ` [PULL 21/27] vfio/iommufd: preserve descriptors Cédric Le Goater
2025-07-04  8:45 ` [PULL 22/27] vfio/iommufd: reconstruct device Cédric Le Goater
2025-07-04  8:45 ` [PULL 23/27] vfio/iommufd: reconstruct hwpt Cédric Le Goater
2025-07-04  8:45 ` [PULL 24/27] vfio/iommufd: change process Cédric Le Goater
2025-07-04  8:45 ` [PULL 25/27] iommufd: preserve DMA mappings Cédric Le Goater
2025-07-04  8:45 ` [PULL 26/27] vfio/container: delete old cpr register Cédric Le Goater
2025-07-04  8:45 ` [PULL 27/27] vfio: doc changes for cpr Cédric Le Goater
2025-07-04 17:49 ` [PULL 00/27] vfio queue Stefan Hajnoczi

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=20250704084528.1412959-19-clg@redhat.com \
    --to=clg@redhat.com \
    --cc=alex.williamson@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=steven.sistare@oracle.com \
    --cc=zhenzhong.duan@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).