[RFC PATCH] vring: Force use of DMA API for ARM-based systems

[Will Deacon]

On Mon, Jan 09, 2017 at 11:24:04AM +0000, Robin Murphy wrote:
> On 06/01/17 21:51, Andy Lutomirski wrote:
> > On Fri, Jan 6, 2017 at 10:32 AM, Robin Murphy <robin.murphy at arm.com> wrote:
> >> On 06/01/17 17:48, Jean-Philippe Brucker wrote:
> >>> It used to work with 4.9, but since 9491ae4 ("mm: don't cap request size
> >>> based on read-ahead setting") unlocked read-ahead, we quickly run into
> >>> the limit of swiotlb and panic:
> >>>
> >>> [    5.382359] virtio-mmio 1c130000.virtio_block: swiotlb buffer is full
> >>> (sz: 491520 bytes)
> >>> [    5.382452] virtio-mmio 1c130000.virtio_block: DMA: Out of SW-IOMMU
> >>> space for 491520 bytes
> >>> [    5.382531] Kernel panic - not syncing: DMA: Random memory could be
> >>> DMA written
> >>> ...
> >>> [    5.383148] [<ffff0000083ad754>] swiotlb_map_page+0x194/0x1a0
> >>> [    5.383226] [<ffff000008096bb8>] __swiotlb_map_page+0x20/0x88
> >>> [    5.383320] [<ffff0000084bf738>] vring_map_one_sg.isra.1+0x70/0x88
> >>> [    5.383417] [<ffff0000084c04fc>] virtqueue_add_sgs+0x2ec/0x4e8
> >>> [    5.383505] [<ffff00000856d99c>] __virtblk_add_req+0x9c/0x1a8
> >>> ...
> >>> [    5.384449] [<ffff0000081829c4>] ondemand_readahead+0xfc/0x2b8
> >>>
> >>> Commit 9491ae4 caps the read-ahead request to a limit set by the backing
> >>> device. For virtio-blk, it is infinite (as set by the call to
> >>> blk_queue_max_hw_sectors in virtblk_probe).
> >>>
> >>> I'm not sure how to fix this. Setting an arbitrary sector limit in the
> >>> virtio-blk driver seems unfair to other users. Maybe we should check if
> >>> the device is behind a hardware IOMMU before using the DMA API?
> >>
> >> Hmm, this looks more like the virtio_block device simply has the wrong
> >> DMA mask to begin with. For virtio-pci we set the streaming DMA mask to
> >> 64 bits - should a platform device not be similarly capable?
> > 
> > If it's not, then turning off DMA API will cause random corruption.
> > ISTM one way or another the bug is in either the DMA ops or in the
> > driver initialization.
> 
> OK, having looked a little deeper, I reckon virtio_mmio_probe() is
> indeed missing a dma_set_mask() call compared to its PCI friends. The
> only question then is where does virtio-mmio stand with respect to
> legacy/modern/44-bit/64-bit etc.?

Legacy virtio-mmio has a variable page granule (GuestPageSize), so the
44-bit limitation shouldn't apply. The legacy spec doesn't actually
initialise GuestPageSize in the example initialisation sequence, but
Linux does. Non-legacy uses absolute, 64-bit addresses regardless of
transport, so yes, it might be as simple as adding:

	dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));

to virtio_mmio_probe. Jean-Philippe -- does that fix things for you?

Will