On Wed, Jan 23, 2019 at 02:56:00PM +0800, Jason Wang wrote:
>
> On 2019/1/23 上午11:49, Michael S. Tsirkin wrote:
> > On Wed, Jan 23, 2019 at 11:08:04AM +0800, Jason Wang wrote:
> > > On 2019/1/23 上午1:03, Tiwei Bie wrote:
> > > > This patch introduces the support for VIRTIO_F_ORDER_PLATFORM.
> > > > When this feature is negotiated, driver will use the barriers
> > > > suitable for hardware devices.
> > > >
> > > > Signed-off-by: Tiwei Bie <tiwei.bie@xxxxxxxxx>
> > > > ---
> > > > drivers/virtio/virtio_ring.c | 8 ++++++++
> > > > include/uapi/linux/virtio_config.h | 6 ++++++
> > > > 2 files changed, 14 insertions(+)
> > > >
> > > > diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
> > > > index cd7e755484e3..27d3f057493e 100644
> > > > --- a/drivers/virtio/virtio_ring.c
> > > > +++ b/drivers/virtio/virtio_ring.c
> > > > @@ -1609,6 +1609,9 @@ static struct virtqueue *vring_create_virtqueue_packed(
> > > > !context;
> > > > vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
> > > > + if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM))
> > > > + vq->weak_barriers = false;
> > > > +
> > > > vq->packed.ring_dma_addr = ring_dma_addr;
> > > > vq->packed.driver_event_dma_addr = driver_event_dma_addr;
> > > > vq->packed.device_event_dma_addr = device_event_dma_addr;
> > > > @@ -2079,6 +2082,9 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
> > > > !context;
> > > > vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
> > > > + if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM))
> > > > + vq->weak_barriers = false;
> > > > +
> > > > vq->split.queue_dma_addr = 0;
> > > > vq->split.queue_size_in_bytes = 0;
> > > > @@ -2213,6 +2219,8 @@ void vring_transport_features(struct virtio_device *vdev)
> > > > break;
> > > > case VIRTIO_F_RING_PACKED:
> > > > break;
> > > > + case VIRTIO_F_ORDER_PLATFORM:
> > > > + break;
> > > > default:
> > > > /* We don't understand this bit. */
> > > > __virtio_clear_bit(vdev, i);
> > > > diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
> > > > index 1196e1c1d4f6..ff8e7dc9d4dd 100644
> > > > --- a/include/uapi/linux/virtio_config.h
> > > > +++ b/include/uapi/linux/virtio_config.h
> > > > @@ -78,6 +78,12 @@
> > > > /* This feature indicates support for the packed virtqueue layout. */
> > > > #define VIRTIO_F_RING_PACKED 34
> > > > +/*
> > > > + * This feature indicates that memory accesses by the driver and the
> > > > + * device are ordered in a way described by the platform.
> > > > + */
> > > > +#define VIRTIO_F_ORDER_PLATFORM 36
> > > > +
> > > > /*
> > > > * Does the device support Single Root I/O Virtualization?
> > > > */
> > >
> > > I wonder whether or not this is sufficient. Is dma barrier implies a mmio
> > > barrier? Looks not.
> > IIUC we don't need an mmio barrier because we are using a
> > serializing API: Documentation/memory-barriers.txt says:
> >
> > Note that, when using writel(), a prior
> > wmb() is not needed to guarantee that the cache coherent memory writes
> > have completed before writing to the MMIO region.
>
>
> Ah, I get this.
>
>
> >
> >
> > > See ia64/include/asm/barrier.h:
> > >
> > > * Note: "mb()" and its variants cannot be used as a fence to order
> > > * accesses to memory mapped I/O registers. For that, mf.a needs to
> > > * be used. However, we don't want to always use mf.a because (a)
> > > * it's (presumably) much slower than mf and (b) mf.a is supported for
> > > * sequential memory pages only.
> > > */
> > > #define mb() ia64_mf()
> > > #define rmb() mb()
> > > #define wmb() mb()
> > >
> > > #define dma_rmb() mb()
> > > =>efine dma_wmb() mb()
> > >
> > > Thanks
> > Frankly no idea about ia64.
>
>
> Neither did me.
>
>
> > Sorry. Are any less esoteric platforms
> > affected?
> >
>
> E.g ppc64?
So
void iowrite32(u32 val, void __iomem *addr)
{
writel(val, addr);
}
and that eventually gets to this one:
#define DEF_MMIO_OUT_D(name, size, insn) \
static inline void name(volatile u##size __iomem *addr, u##size val) \
{ \
__asm__ __volatile__("sync;"#insn"%U0%X0 %1,%0" \
: "=m" (*addr) : "r" (val) : "memory"); \
IO_SET_SYNC_FLAG(); \
}
and
#ifdef CONFIG_PPC64
#define IO_SET_SYNC_FLAG() do { local_paca->io_sync = 1; } while(0)
#else
#define IO_SET_SYNC_FLAG()
#endif
> define dma_wmb() __asm__ __volatile__ (stringify_in_c(SMPWMB) : :
> :"memo\
> ry")
>
> /*
> * Enforce synchronisation of stores vs. spin_unlock
> * (this does it explicitly, though our implementation of spin_unlock
I don't know which spin_unlock does it refer to here.
> * does it implicitely too)
> */
> static inline void mmiowb(void)
> {
> unsigned long tmp;
>
> __asm__ __volatile__("sync; li %0,0; stb %0,%1(13)"
> : "=&r" (tmp) : "i" (offsetof(struct paca_struct, io_sync))
> : "memory");
> }
So sync+set io_sync here and sync+io_sync above.
> dma_wmb() is lwsync which is more lightweight than sync I guess?
>
> Thanks
>
Sounds about right.
--
MST
_______________________________________________
Virtualization mailing list
Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
