Message-ID: <20260127085835.GQ13967@unreal>
Date: Tue, 27 Jan 2026 10:58:35 +0200
From: Leon Romanovsky <leon@...nel.org>
To: Pranjal Shrivastava <praan@...gle.com>
Cc: Sumit Semwal <sumit.semwal@...aro.org>,
	Christian König <christian.koenig@....com>,
	Alex Deucher <alexander.deucher@....com>,
	David Airlie <airlied@...il.com>, Simona Vetter <simona@...ll.ch>,
	Gerd Hoffmann <kraxel@...hat.com>,
	Dmitry Osipenko <dmitry.osipenko@...labora.com>,
	Gurchetan Singh <gurchetansingh@...omium.org>,
	Chia-I Wu <olvaffe@...il.com>,
	Maarten Lankhorst <maarten.lankhorst@...ux.intel.com>,
	Maxime Ripard <mripard@...nel.org>,
	Thomas Zimmermann <tzimmermann@...e.de>,
	Lucas De Marchi <lucas.demarchi@...el.com>,
	Thomas Hellström <thomas.hellstrom@...ux.intel.com>,
	Rodrigo Vivi <rodrigo.vivi@...el.com>,
	Jason Gunthorpe <jgg@...pe.ca>, Kevin Tian <kevin.tian@...el.com>,
	Joerg Roedel <joro@...tes.org>, Will Deacon <will@...nel.org>,
	Robin Murphy <robin.murphy@....com>,
	Felix Kuehling <Felix.Kuehling@....com>,
	Alex Williamson <alex@...zbot.org>,
	Ankit Agrawal <ankita@...dia.com>,
	Vivek Kasireddy <vivek.kasireddy@...el.com>,
	linux-media@...r.kernel.org, dri-devel@...ts.freedesktop.org,
	linaro-mm-sig@...ts.linaro.org, linux-kernel@...r.kernel.org,
	amd-gfx@...ts.freedesktop.org, virtualization@...ts.linux.dev,
	intel-xe@...ts.freedesktop.org, linux-rdma@...r.kernel.org,
	iommu@...ts.linux.dev, kvm@...r.kernel.org
Subject: Re: [PATCH v5 4/8] vfio: Wait for dma-buf invalidation to complete

On Mon, Jan 26, 2026 at 08:53:57PM +0000, Pranjal Shrivastava wrote:
> On Sat, Jan 24, 2026 at 09:14:16PM +0200, Leon Romanovsky wrote:
> > From: Leon Romanovsky <leonro@...dia.com>
> > 
> > dma-buf invalidation is handled asynchronously by the hardware, so VFIO
> > must wait until all affected objects have been fully invalidated.
> > 
> > In addition, the dma-buf exporter is expecting that all importers unmap any
> > buffers they previously mapped.
> > 
> > Fixes: 5d74781ebc86 ("vfio/pci: Add dma-buf export support for MMIO regions")
> > Signed-off-by: Leon Romanovsky <leonro@...dia.com>
> > ---
> >  drivers/vfio/pci/vfio_pci_dmabuf.c | 71 ++++++++++++++++++++++++++++++++++++--
> >  1 file changed, 68 insertions(+), 3 deletions(-)

<...>

> > @@ -333,7 +359,37 @@ void vfio_pci_dma_buf_move(struct vfio_pci_core_device *vdev, bool revoked)
> >  			dma_resv_lock(priv->dmabuf->resv, NULL);
> >  			priv->revoked = revoked;
> >  			dma_buf_invalidate_mappings(priv->dmabuf);
> > +			dma_resv_wait_timeout(priv->dmabuf->resv,
> > +					      DMA_RESV_USAGE_BOOKKEEP, false,
> > +					      MAX_SCHEDULE_TIMEOUT);
> >  			dma_resv_unlock(priv->dmabuf->resv);
> > +			if (revoked) {
> > +				kref_put(&priv->kref, vfio_pci_dma_buf_done);
> > +				/* Let's wait till all DMA unmap are completed. */
> > +				wait = wait_for_completion_timeout(
> > +					&priv->comp, secs_to_jiffies(1));
> 
> Is the 1-second constant sufficient for all hardware, or should the 
> invalidate_mappings() contract require the callback to block until 
> speculative reads are strictly fenced? I'm wondering about a case where
> a device's firmware has a high response latency, perhaps due to internal
> management tasks like error recovery or thermal and it exceeds the 1s 
> timeout. 
> 
> If the device is in the middle of a large DMA burst and the firmware is
> slow to flush the internal pipelines to a fully "quiesced"
> read-and-discard state, reclaiming the memory at exactly 1.001 seconds
> risks triggering platform-level faults..
> 
> Since the wen explicitly permit these speculative reads until unmap is
> complete, relying on a hardcoded timeout in the exporter seems to 
> introduce a hardware-dependent race condition that could compromise
> system stability via IOMMU errors or AER faults. 
> 
> Should the importer instead be required to guarantee that all 
> speculative access has ceased before the invalidation call returns?

It is guaranteed by the dma_resv_wait_timeout() call above. That call ensures
that the hardware has completed all pending operations. The 1‑second delay is
meant to catch cases where an in-kernel DMA unmap call is missing, which should
not trigger any DMA activity at that point.

So yes, one second is more than sufficient.

Thanks

> 
> Thanks
> Praan
> 
> > +				/*
> > +				 * If you see this WARN_ON, it means that
> > +				 * importer didn't call unmap in response to
> > +				 * dma_buf_invalidate_mappings() which is not
> > +				 * allowed.
> > +				 */
> > +				WARN(!wait,
> > +				     "Timed out waiting for DMABUF unmap, importer has a broken invalidate_mapping()");
> > +			} else {
> > +				/*
> > +				 * Kref is initialize again, because when revoke
> > +				 * was performed the reference counter was decreased
> > +				 * to zero to trigger completion.
> > +				 */
> > +				kref_init(&priv->kref);
> > +				/*
> > +				 * There is no need to wait as no mapping was
> > +				 * performed when the previous status was
> > +				 * priv->revoked == true.
> > +				 */
> > +				reinit_completion(&priv->comp);
> > +			}
> >  		}
> >  		fput(priv->dmabuf->file);
> >  	}
> > @@ -346,6 +402,8 @@ void vfio_pci_dma_buf_cleanup(struct vfio_pci_core_device *vdev)
> >  
> >  	down_write(&vdev->memory_lock);
> >  	list_for_each_entry_safe(priv, tmp, &vdev->dmabufs, dmabufs_elm) {
> > +		unsigned long wait;
> > +
> >  		if (!get_file_active(&priv->dmabuf->file))
> >  			continue;
> >  
> > @@ -354,7 +412,14 @@ void vfio_pci_dma_buf_cleanup(struct vfio_pci_core_device *vdev)
> >  		priv->vdev = NULL;
> >  		priv->revoked = true;
> >  		dma_buf_invalidate_mappings(priv->dmabuf);
> > +		dma_resv_wait_timeout(priv->dmabuf->resv,
> > +				      DMA_RESV_USAGE_BOOKKEEP, false,
> > +				      MAX_SCHEDULE_TIMEOUT);
> >  		dma_resv_unlock(priv->dmabuf->resv);
> > +		kref_put(&priv->kref, vfio_pci_dma_buf_done);
> > +		wait = wait_for_completion_timeout(&priv->comp,
> > +						   secs_to_jiffies(1));
> > +		WARN_ON(!wait);
> >  		vfio_device_put_registration(&vdev->vdev);
> >  		fput(priv->dmabuf->file);
> >  	}
> > 
> > -- 
> > 2.52.0
> > 
> > 
> 

Powered by blists - more mailing lists