search for: dma_alloc_coherent_mask

When running a 32bit kernel there are still some pci devices capable of 64bit addressing (eg. sound/pci/hda/hda_intel.c) If these drivers are setting: dev->coherent_dma_mask = 0xFFFFFFFFFFFFFFFF why dma_alloc_coherent_mask is returning unsigned long instead of dma_addr_t resulting in truncation of the dma_mask to 32bit if running a 32bit kernel? There are some examples where the dma_alloc_coherent running 32bit kernel can return a machine address bigger than 32bit. This can be true in particular if running the 32b...

...clared inside parameter list /usr/src/linux-2.6.31_pvops-xen-rebase.master.tree-2009-08-31/arch/x86/include/asm/dma-mapping.h:60: error: parameter 4 ('dir') has incomplete type /usr/src/linux-2.6.31_pvops-xen-rebase.master.tree-2009-08-31/arch/x86/include/asm/dma-mapping.h: In function 'dma_alloc_coherent_mask': /usr/src/linux-2.6.31_pvops-xen-rebase.master.tree-2009-08-31/arch/x86/include/asm/dma-mapping.h:77: error: dereferencing pointer to incomplete type /usr/src/linux-2.6.31_pvops-xen-rebase.master.tree-2009-08-31/arch/x86/include/asm/dma-mapping.h:79: error: implicit declaration of function ...

On 09/02/09 01:10, Mitchell E Berger wrote: > I apologize for writing to you directly instead of through an officially > supported channel. No problem. > I''ve filed a bug against glibc in Redhat''s Bugzilla > for an issue that only seems to surface on 64-bit Xen paravirt guests > on AMD hosts. Filing this bug with the distro involved seemed to make > sense,

Hi all, this patch series enables xen-swiotlb on arm and arm64. It has been heavily reworked compared to the previous versions in order to achieve better performances and to address review comments. We are not using dma_mark_clean to ensure coherency anymore. We call the platform implementation of map_page and unmap_page. We assume that dom0 has been mapped 1:1 (physical address == machine