This patchset adds a trivial helper function, is_buffer_dma_capable() and cleans up some IOMMU implementations. This function is to to see if a memory region is DMA-capable or not with the arguments, the dma_mask (or coherent_dma_mask) of a device and the address and size of a memory region. It's useful for IOMMUs that don't do virtual mappings at all times. The patch for swiotlb is a bug fix (the rest are just cleanups). Currently, swiotlb doesn't take account of the size of a memory region to see if if the memory region is DMA-capable. = arch/x86/kernel/pci-gart_64.c | 16 +++------------- arch/x86/kernel/pci-nommu.c | 10 ++++++---- include/linux/dma-mapping.h | 5 +++++ lib/swiotlb.c | 15 ++++++++------- 4 files changed, 22 insertions(+), 24 deletions(-) --
| Jens Axboe | Re: [BUG] New Kernel Bugs |
| Faik Uygur | Re: Linux 2.6.21-rc1 |
| Ingo Molnar | [patch 02/13] syslets: add syslet.h include file, user API/ABI definitions |
| Greg Kroah-Hartman | [PATCH 001/196] Chinese: Add the known_regression URI to the HOWTO |
git: | |
| Jarek Poplawski | Re: [PATCH] pkt_sched: Destroy gen estimators under rtnl_lock(). |
| Gerrit Renker | [PATCH 27/37] dccp: Integration of dynamic feature activation - part 2 (server side) |
| Jarek Poplawski | Re: Data corruption issue with splice() on 2.6.27.10 |
| Steven Rostedt | Re: -rt scheduling: wakeup bug? |
