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 14/27] vfio/iommufd: use IOMMU_IOAS_MAP_FILE
Date: Fri,  4 Jul 2025 10:45:15 +0200	[thread overview]
Message-ID: <20250704084528.1412959-15-clg@redhat.com> (raw)
In-Reply-To: <20250704084528.1412959-1-clg@redhat.com>

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

Use IOMMU_IOAS_MAP_FILE when the mapped region is backed by a file.
Such a mapping can be preserved without modification during CPR,
because it depends on the file's address space, which does not change,
rather than on the process's address space, which does change.

Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Link: https://lore.kernel.org/qemu-devel/1751493538-202042-9-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
 include/hw/vfio/vfio-container-base.h | 15 +++++++++++++++
 hw/vfio/container-base.c              |  9 +++++++++
 hw/vfio/iommufd.c                     | 13 +++++++++++++
 3 files changed, 37 insertions(+)

diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
index 3cd86ec59e1a4605dea92fadeca5816145ae409b..bded6e993ffd34910f5583bf8e94c81c41f4885f 100644
--- a/include/hw/vfio/vfio-container-base.h
+++ b/include/hw/vfio/vfio-container-base.h
@@ -167,6 +167,21 @@ struct VFIOIOMMUClass {
     int (*dma_map)(const VFIOContainerBase *bcontainer,
                    hwaddr iova, ram_addr_t size,
                    void *vaddr, bool readonly, MemoryRegion *mr);
+    /**
+     * @dma_map_file
+     *
+     * Map a file range for the container.
+     *
+     * @bcontainer: #VFIOContainerBase to use for map
+     * @iova: start address to map
+     * @size: size of the range to map
+     * @fd: descriptor of the file to map
+     * @start: starting file offset of the range to map
+     * @readonly: map read only if true
+     */
+    int (*dma_map_file)(const VFIOContainerBase *bcontainer,
+                        hwaddr iova, ram_addr_t size,
+                        int fd, unsigned long start, bool readonly);
     /**
      * @dma_unmap
      *
diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c
index d834bd482290a8b195f94c07832b7f8020504c3a..56304978e1e8ec456e0eb5f13e8bddc091e76208 100644
--- a/hw/vfio/container-base.c
+++ b/hw/vfio/container-base.c
@@ -78,7 +78,16 @@ int vfio_container_dma_map(VFIOContainerBase *bcontainer,
                            void *vaddr, bool readonly, MemoryRegion *mr)
 {
     VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
+    RAMBlock *rb = mr->ram_block;
+    int mfd = rb ? qemu_ram_get_fd(rb) : -1;
 
+    if (mfd >= 0 && vioc->dma_map_file) {
+        unsigned long start = vaddr - qemu_ram_get_host_addr(rb);
+        unsigned long offset = qemu_ram_get_fd_offset(rb);
+
+        return vioc->dma_map_file(bcontainer, iova, size, mfd, start + offset,
+                                  readonly);
+    }
     g_assert(vioc->dma_map);
     return vioc->dma_map(bcontainer, iova, size, vaddr, readonly, mr);
 }
diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c
index d3efef71afd4fd9e68455cefe7666c9f70e8c61e..962a1e2b1f28b297cc876fffa2677bd525479c8c 100644
--- a/hw/vfio/iommufd.c
+++ b/hw/vfio/iommufd.c
@@ -45,6 +45,18 @@ static int iommufd_cdev_map(const VFIOContainerBase *bcontainer, hwaddr iova,
                                    iova, size, vaddr, readonly);
 }
 
+static int iommufd_cdev_map_file(const VFIOContainerBase *bcontainer,
+                                 hwaddr iova, ram_addr_t size,
+                                 int fd, unsigned long start, bool readonly)
+{
+    const VFIOIOMMUFDContainer *container =
+        container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer);
+
+    return iommufd_backend_map_file_dma(container->be,
+                                        container->ioas_id,
+                                        iova, size, fd, start, readonly);
+}
+
 static int iommufd_cdev_unmap(const VFIOContainerBase *bcontainer,
                               hwaddr iova, ram_addr_t size,
                               IOMMUTLBEntry *iotlb, bool unmap_all)
@@ -807,6 +819,7 @@ static void vfio_iommu_iommufd_class_init(ObjectClass *klass, const void *data)
     VFIOIOMMUClass *vioc = VFIO_IOMMU_CLASS(klass);
 
     vioc->dma_map = iommufd_cdev_map;
+    vioc->dma_map_file = iommufd_cdev_map_file;
     vioc->dma_unmap = iommufd_cdev_unmap;
     vioc->attach_device = iommufd_cdev_attach;
     vioc->detach_device = iommufd_cdev_detach;
-- 
2.50.0



  parent reply	other threads:[~2025-07-04  8:47 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 ` Cédric Le Goater [this message]
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 ` [PULL 18/27] vfio/iommufd: register container for cpr Cédric Le Goater
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=20250704084528.1412959-15-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).