| Message ID | 1380298207-29151-12-git-send-email-stefano.stabellini@eu.citrix.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Fri, Sep 27, 2013 at 05:10:00PM +0100, Stefano Stabellini wrote: > The swiotlb code has appropriate calls to dma_mark_clean in place for > buffers passed to swiotlb_map_page as an argument. However it assumes > that the swiotlb bounce buffer (io_tlb_start-io_tlb_end) is already > coherent and doesn't need any calls to dma_mark_clean. > > On ARM the swiotlb bounce buffer is not coherent (the memory is > writealloc while it should be bufferable) and therefore we need to call > dma_mark_clean appropriately on the bounce buffer code paths too. > > Note that most architecures have an empty dma_mark_clean implementation > anyway. The other architecture that uses swiotlb is IA64 and that does have an implementation where it touches on page attributes. Which means I have to figure out why my HP zx6000 won't boot with 3.11 now :-( > > Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> > --- > lib/swiotlb.c | 13 ++++++++++--- > 1 files changed, 10 insertions(+), 3 deletions(-) > > diff --git a/lib/swiotlb.c b/lib/swiotlb.c > index 4e8686c..eb45d17 100644 > --- a/lib/swiotlb.c > +++ b/lib/swiotlb.c > @@ -515,6 +515,7 @@ found: > io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT); > if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) > swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE); > + dma_mark_clean(phys_to_virt(tlb_addr), size); > > return tlb_addr; > } > @@ -547,7 +548,10 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, > * First, sync the memory before unmapping the entry > */ > if (orig_addr && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) > + { > + dma_mark_clean(phys_to_virt(tlb_addr), size); > swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE); > + } > > /* > * Return the buffer to the free list by setting the corresponding > @@ -587,17 +591,20 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, > > switch (target) { > case SYNC_FOR_CPU: > - if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) > + if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) { > + dma_mark_clean(phys_to_virt(tlb_addr), size); > swiotlb_bounce(orig_addr, tlb_addr, > size, DMA_FROM_DEVICE); > + } > else > BUG_ON(dir != DMA_TO_DEVICE); > break; > case SYNC_FOR_DEVICE: > - if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) > + if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) { > swiotlb_bounce(orig_addr, tlb_addr, > size, DMA_TO_DEVICE); > - else > + dma_mark_clean(phys_to_virt(tlb_addr), size); > + } else > BUG_ON(dir != DMA_FROM_DEVICE); > break; > default: > -- > 1.7.2.5 >
On Mon, 30 Sep 2013, Konrad Rzeszutek Wilk wrote: > On Fri, Sep 27, 2013 at 05:10:00PM +0100, Stefano Stabellini wrote: > > The swiotlb code has appropriate calls to dma_mark_clean in place for > > buffers passed to swiotlb_map_page as an argument. However it assumes > > that the swiotlb bounce buffer (io_tlb_start-io_tlb_end) is already > > coherent and doesn't need any calls to dma_mark_clean. > > > > On ARM the swiotlb bounce buffer is not coherent (the memory is > > writealloc while it should be bufferable) and therefore we need to call > > dma_mark_clean appropriately on the bounce buffer code paths too. > > > > Note that most architecures have an empty dma_mark_clean implementation > > anyway. > > The other architecture that uses swiotlb is IA64 and that does have > an implementation where it touches on page attributes. > > Which means I have to figure out why my HP zx6000 won't boot with 3.11 now :-( > Now this is a very thorny issue. Honestly I don't like the dma_mark_clean interface very much: it's one big hammer, when we actually need some finesse to handle coherency. For example on ARM some devices might not need the dma_mark_clean call, while others do. Calling it all the times is at the very best inefficient and incorrect at worst. I am thinking of calling the original map/unmap_page functions instead (arm_dma_map_page or arm_coherent_dma_map_page in the arm case). However in order to do that I would need to add more __get_dma_ops calls in both lib/swiotlb.c and drivers/xen/swiotlb-xen.c > > Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> > > --- > > lib/swiotlb.c | 13 ++++++++++--- > > 1 files changed, 10 insertions(+), 3 deletions(-) > > > > diff --git a/lib/swiotlb.c b/lib/swiotlb.c > > index 4e8686c..eb45d17 100644 > > --- a/lib/swiotlb.c > > +++ b/lib/swiotlb.c > > @@ -515,6 +515,7 @@ found: > > io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT); > > if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) > > swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE); > > + dma_mark_clean(phys_to_virt(tlb_addr), size); > > > > return tlb_addr; > > } > > @@ -547,7 +548,10 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, > > * First, sync the memory before unmapping the entry > > */ > > if (orig_addr && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) > > + { > > + dma_mark_clean(phys_to_virt(tlb_addr), size); > > swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE); > > + } > > > > /* > > * Return the buffer to the free list by setting the corresponding > > @@ -587,17 +591,20 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, > > > > switch (target) { > > case SYNC_FOR_CPU: > > - if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) > > + if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) { > > + dma_mark_clean(phys_to_virt(tlb_addr), size); > > swiotlb_bounce(orig_addr, tlb_addr, > > size, DMA_FROM_DEVICE); > > + } > > else > > BUG_ON(dir != DMA_TO_DEVICE); > > break; > > case SYNC_FOR_DEVICE: > > - if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) > > + if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) { > > swiotlb_bounce(orig_addr, tlb_addr, > > size, DMA_TO_DEVICE); > > - else > > + dma_mark_clean(phys_to_virt(tlb_addr), size); > > + } else > > BUG_ON(dir != DMA_FROM_DEVICE); > > break; > > default: > > -- > > 1.7.2.5 > > >
On Wed, Oct 02, 2013 at 06:31:57PM +0100, Stefano Stabellini wrote: > On Mon, 30 Sep 2013, Konrad Rzeszutek Wilk wrote: > > On Fri, Sep 27, 2013 at 05:10:00PM +0100, Stefano Stabellini wrote: > > > The swiotlb code has appropriate calls to dma_mark_clean in place for > > > buffers passed to swiotlb_map_page as an argument. However it assumes > > > that the swiotlb bounce buffer (io_tlb_start-io_tlb_end) is already > > > coherent and doesn't need any calls to dma_mark_clean. > > > > > > On ARM the swiotlb bounce buffer is not coherent (the memory is > > > writealloc while it should be bufferable) and therefore we need to call > > > dma_mark_clean appropriately on the bounce buffer code paths too. > > > > > > Note that most architecures have an empty dma_mark_clean implementation > > > anyway. > > > > The other architecture that uses swiotlb is IA64 and that does have > > an implementation where it touches on page attributes. > > > > Which means I have to figure out why my HP zx6000 won't boot with 3.11 now :-( > > > > Now this is a very thorny issue. > > Honestly I don't like the dma_mark_clean interface very much: it's one > big hammer, when we actually need some finesse to handle coherency. > > For example on ARM some devices might not need the dma_mark_clean call, > while others do. Calling it all the times is at the very best > inefficient and incorrect at worst. > > I am thinking of calling the original map/unmap_page functions instead > (arm_dma_map_page or arm_coherent_dma_map_page in the arm case). > However in order to do that I would need to add more __get_dma_ops calls in > both lib/swiotlb.c and drivers/xen/swiotlb-xen.c I think that is OK for the Xen-SWIOTLB case. For the lib/swiotlb - would that mean that non-Xen-ARM would use the SWIOTLB? If so, I am OK with that too. > > > > > Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> > > > --- > > > lib/swiotlb.c | 13 ++++++++++--- > > > 1 files changed, 10 insertions(+), 3 deletions(-) > > > > > > diff --git a/lib/swiotlb.c b/lib/swiotlb.c > > > index 4e8686c..eb45d17 100644 > > > --- a/lib/swiotlb.c > > > +++ b/lib/swiotlb.c > > > @@ -515,6 +515,7 @@ found: > > > io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT); > > > if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) > > > swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE); > > > + dma_mark_clean(phys_to_virt(tlb_addr), size); > > > > > > return tlb_addr; > > > } > > > @@ -547,7 +548,10 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, > > > * First, sync the memory before unmapping the entry > > > */ > > > if (orig_addr && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) > > > + { > > > + dma_mark_clean(phys_to_virt(tlb_addr), size); > > > swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE); > > > + } > > > > > > /* > > > * Return the buffer to the free list by setting the corresponding > > > @@ -587,17 +591,20 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, > > > > > > switch (target) { > > > case SYNC_FOR_CPU: > > > - if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) > > > + if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) { > > > + dma_mark_clean(phys_to_virt(tlb_addr), size); > > > swiotlb_bounce(orig_addr, tlb_addr, > > > size, DMA_FROM_DEVICE); > > > + } > > > else > > > BUG_ON(dir != DMA_TO_DEVICE); > > > break; > > > case SYNC_FOR_DEVICE: > > > - if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) > > > + if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) { > > > swiotlb_bounce(orig_addr, tlb_addr, > > > size, DMA_TO_DEVICE); > > > - else > > > + dma_mark_clean(phys_to_virt(tlb_addr), size); > > > + } else > > > BUG_ON(dir != DMA_FROM_DEVICE); > > > break; > > > default: > > > -- > > > 1.7.2.5 > > > > >
diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 4e8686c..eb45d17 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -515,6 +515,7 @@ found: io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT); if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE); + dma_mark_clean(phys_to_virt(tlb_addr), size); return tlb_addr; } @@ -547,7 +548,10 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, * First, sync the memory before unmapping the entry */ if (orig_addr && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) + { + dma_mark_clean(phys_to_virt(tlb_addr), size); swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE); + } /* * Return the buffer to the free list by setting the corresponding @@ -587,17 +591,20 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, switch (target) { case SYNC_FOR_CPU: - if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) + if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) { + dma_mark_clean(phys_to_virt(tlb_addr), size); swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE); + } else BUG_ON(dir != DMA_TO_DEVICE); break; case SYNC_FOR_DEVICE: - if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) + if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) { swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE); - else + dma_mark_clean(phys_to_virt(tlb_addr), size); + } else BUG_ON(dir != DMA_FROM_DEVICE); break; default:
The swiotlb code has appropriate calls to dma_mark_clean in place for buffers passed to swiotlb_map_page as an argument. However it assumes that the swiotlb bounce buffer (io_tlb_start-io_tlb_end) is already coherent and doesn't need any calls to dma_mark_clean. On ARM the swiotlb bounce buffer is not coherent (the memory is writealloc while it should be bufferable) and therefore we need to call dma_mark_clean appropriately on the bounce buffer code paths too. Note that most architecures have an empty dma_mark_clean implementation anyway. Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> --- lib/swiotlb.c | 13 ++++++++++--- 1 files changed, 10 insertions(+), 3 deletions(-)