| Message ID | 20200819065555.1802761-23-hch@lst.de |
|---|---|
| State | New |
| Headers | show |
| Series | None | expand |
On Wed, Aug 19, 2020 at 08:55:49AM +0200, Christoph Hellwig wrote: > Use the proper modern API to transfer cache ownership for incoherent DMA. > > Signed-off-by: Christoph Hellwig <hch@lst.de> > --- > drivers/net/ethernet/seeq/sgiseeq.c | 12 ++++++++---- > 1 file changed, 8 insertions(+), 4 deletions(-) > > diff --git a/drivers/net/ethernet/seeq/sgiseeq.c b/drivers/net/ethernet/seeq/sgiseeq.c > index 39599bbb5d45b6..f91dae16d69a19 100644 > --- a/drivers/net/ethernet/seeq/sgiseeq.c > +++ b/drivers/net/ethernet/seeq/sgiseeq.c > @@ -112,14 +112,18 @@ struct sgiseeq_private { > > static inline void dma_sync_desc_cpu(struct net_device *dev, void *addr) > { > - dma_cache_sync(dev->dev.parent, addr, sizeof(struct sgiseeq_rx_desc), > - DMA_FROM_DEVICE); > + struct sgiseeq_private *sp = netdev_priv(dev); > + > + dma_sync_single_for_cpu(dev->dev.parent, VIRT_TO_DMA(sp, addr), > + sizeof(struct sgiseeq_rx_desc), DMA_BIDIRECTIONAL); > } > > static inline void dma_sync_desc_dev(struct net_device *dev, void *addr) > { > - dma_cache_sync(dev->dev.parent, addr, sizeof(struct sgiseeq_rx_desc), > - DMA_TO_DEVICE); > + struct sgiseeq_private *sp = netdev_priv(dev); > + > + dma_sync_single_for_device(dev->dev.parent, VIRT_TO_DMA(sp, addr), > + sizeof(struct sgiseeq_rx_desc), DMA_BIDIRECTIONAL); > } this breaks ethernet on IP22 completely, but I haven't figured out why, yet. Thomas.
On Tue, Sep 01, 2020 at 05:22:09PM +0200, Thomas Bogendoerfer wrote: > On Wed, Aug 19, 2020 at 08:55:49AM +0200, Christoph Hellwig wrote: > > Use the proper modern API to transfer cache ownership for incoherent DMA. > > > > Signed-off-by: Christoph Hellwig <hch@lst.de> > > --- > > drivers/net/ethernet/seeq/sgiseeq.c | 12 ++++++++---- > > 1 file changed, 8 insertions(+), 4 deletions(-) > > > > diff --git a/drivers/net/ethernet/seeq/sgiseeq.c b/drivers/net/ethernet/seeq/sgiseeq.c > > index 39599bbb5d45b6..f91dae16d69a19 100644 > > --- a/drivers/net/ethernet/seeq/sgiseeq.c > > +++ b/drivers/net/ethernet/seeq/sgiseeq.c > > @@ -112,14 +112,18 @@ struct sgiseeq_private { > > > > static inline void dma_sync_desc_cpu(struct net_device *dev, void *addr) > > { > > - dma_cache_sync(dev->dev.parent, addr, sizeof(struct sgiseeq_rx_desc), > > - DMA_FROM_DEVICE); > > + struct sgiseeq_private *sp = netdev_priv(dev); > > + > > + dma_sync_single_for_cpu(dev->dev.parent, VIRT_TO_DMA(sp, addr), > > + sizeof(struct sgiseeq_rx_desc), DMA_BIDIRECTIONAL); > > } > > > > static inline void dma_sync_desc_dev(struct net_device *dev, void *addr) > > { > > - dma_cache_sync(dev->dev.parent, addr, sizeof(struct sgiseeq_rx_desc), > > - DMA_TO_DEVICE); > > + struct sgiseeq_private *sp = netdev_priv(dev); > > + > > + dma_sync_single_for_device(dev->dev.parent, VIRT_TO_DMA(sp, addr), > > + sizeof(struct sgiseeq_rx_desc), DMA_BIDIRECTIONAL); > > } > > this breaks ethernet on IP22 completely, but I haven't figured out why, yet. the problem is that dma_sync_single_for_cpu() doesn't flush anything for IP22, because it only flushes for CPUs which do speculation. So either MIPS arch_sync_dma_for_cpu() should always flush or sgiseeq needs to use a different sync funktion, when it wants to re-read descriptors from memory. Thomas.
On Tue, Sep 01, 2020 at 07:16:27PM +0200, Christoph Hellwig wrote: > Well, if IP22 doesn't speculate (which I'm pretty sure is the case), > dma_sync_single_for_cpu should indeeed be a no-op. But then there > also shouldn't be anything in the cache, as the previous > dma_sync_single_for_device should have invalidated it. So it seems like > we are missing one (or more) ownership transfers to the device. I'll > try to look at the the ownership management in a little more detail > tomorrow. this is the problem: /* Always check for received packets. */ sgiseeq_rx(dev, sp, hregs, sregs); so the driver will look at the rx descriptor on every interrupt, so we cache the rx descriptor on the first interrupt and if there was $no rx packet, we will only see it, if cache line gets flushed for some other reason. kick_tx() does a busy loop checking tx descriptors, with just sync_desc_cpu... Thomas.
On Wed, Sep 02, 2020 at 11:38:09PM +0200, Thomas Bogendoerfer wrote: > the patch below fixes the problem. But is very wrong unfortunately. > static inline void dma_sync_desc_cpu(struct net_device *dev, void *addr) > { > - dma_cache_sync(dev->dev.parent, addr, sizeof(struct sgiseeq_rx_desc), > - DMA_FROM_DEVICE); > + struct sgiseeq_private *sp = netdev_priv(dev); > + > + dma_sync_single_for_device(dev->dev.parent, VIRT_TO_DMA(sp, addr), > + sizeof(struct sgiseeq_rx_desc), DMA_FROM_DEVICE); > } > > static inline void dma_sync_desc_dev(struct net_device *dev, void *addr) > { > - dma_cache_sync(dev->dev.parent, addr, sizeof(struct sgiseeq_rx_desc), > - DMA_TO_DEVICE); > + struct sgiseeq_private *sp = netdev_priv(dev); > + > + dma_sync_single_for_device(dev->dev.parent, VIRT_TO_DMA(sp, addr), > + sizeof(struct sgiseeq_rx_desc), DMA_TO_DEVICE); This is not how the DMA API works. You can only call dma_sync_single_for_{device,cpu} with the direction that the memory was mapped. It then transfer ownership to the device or the cpu, and the ownership of the memory is a fundamental concept that allows for reasoning about the caching interaction. > } > > -- > Crap can work. Given enough thrust pigs will fly, but it's not necessarily a > good idea. [ RFC1925, 2.3 ] ---end quoted text---
On Thu, Sep 03, 2020 at 10:43:02AM +0200, Christoph Hellwig wrote: > On Tue, Sep 01, 2020 at 07:38:10PM +0200, Thomas Bogendoerfer wrote: > > this is the problem: > > > > /* Always check for received packets. */ > > sgiseeq_rx(dev, sp, hregs, sregs); > > > > so the driver will look at the rx descriptor on every interrupt, so > > we cache the rx descriptor on the first interrupt and if there was > > $no rx packet, we will only see it, if cache line gets flushed for > > some other reason. > > That means a transfer back to device ownership is missing after a > (negative) check. E.g. something like this for the particular problem, although there might be other hiding elsewhere: diff --git a/drivers/net/ethernet/seeq/sgiseeq.c b/drivers/net/ethernet/seeq/sgiseeq.c index 8507ff2420143a..a1c7be8a0d1e5d 100644 --- a/drivers/net/ethernet/seeq/sgiseeq.c +++ b/drivers/net/ethernet/seeq/sgiseeq.c @@ -403,6 +403,8 @@ static inline void sgiseeq_rx(struct net_device *dev, struct sgiseeq_private *sp rd = &sp->rx_desc[sp->rx_new]; dma_sync_desc_cpu(dev, rd); } + dma_sync_desc_dev(dev, rd); + dma_sync_desc_cpu(dev, &sp->rx_desc[orig_end]); sp->rx_desc[orig_end].rdma.cntinfo &= ~(HPCDMA_EOR); dma_sync_desc_dev(dev, &sp->rx_desc[orig_end]);
diff --git a/drivers/net/ethernet/seeq/sgiseeq.c b/drivers/net/ethernet/seeq/sgiseeq.c index 39599bbb5d45b6..f91dae16d69a19 100644 --- a/drivers/net/ethernet/seeq/sgiseeq.c +++ b/drivers/net/ethernet/seeq/sgiseeq.c @@ -112,14 +112,18 @@ struct sgiseeq_private { static inline void dma_sync_desc_cpu(struct net_device *dev, void *addr) { - dma_cache_sync(dev->dev.parent, addr, sizeof(struct sgiseeq_rx_desc), - DMA_FROM_DEVICE); + struct sgiseeq_private *sp = netdev_priv(dev); + + dma_sync_single_for_cpu(dev->dev.parent, VIRT_TO_DMA(sp, addr), + sizeof(struct sgiseeq_rx_desc), DMA_BIDIRECTIONAL); } static inline void dma_sync_desc_dev(struct net_device *dev, void *addr) { - dma_cache_sync(dev->dev.parent, addr, sizeof(struct sgiseeq_rx_desc), - DMA_TO_DEVICE); + struct sgiseeq_private *sp = netdev_priv(dev); + + dma_sync_single_for_device(dev->dev.parent, VIRT_TO_DMA(sp, addr), + sizeof(struct sgiseeq_rx_desc), DMA_BIDIRECTIONAL); } static inline void hpc3_eth_reset(struct hpc3_ethregs *hregs)
Use the proper modern API to transfer cache ownership for incoherent DMA. Signed-off-by: Christoph Hellwig <hch@lst.de> --- drivers/net/ethernet/seeq/sgiseeq.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)