On Thu, 4 Jun 2009 08:12:34 +0200 Torsten Kaiser <just.for.lkml@xxxxxxxxxxxxxx> wrote: > On Thu, Jun 4, 2009 at 2:02 AM, FUJITA Tomonori > <fujita.tomonori@xxxxxxxxxxxxx> wrote: > > On Wed, 3 Jun 2009 21:30:32 +0200 > > Torsten Kaiser <just.for.lkml@xxxxxxxxxxxxxx> wrote: > >> Still happens with 2.6.30-rc8 (see trace at the end of the email) > >> > >> As orig_n_elem is only used two times in libata-core.c I suspected a > >> corruption of the qc->sg, but adding checks for this did not trigger. > >> So I looked into lib/dma-debug.c. > >> It seems add_dma_entry() does not protect against adding the same > >> entry twice. > > > > Do you mean that add_dma_entry() doesn't protect against adding a new > > entry identical to the existing entry, right? > > Yes, as I read the hash bucket code in lib/dma-debug.c a second entry > from the same device and the same address will just be added to the > list and on unmap it will always return the first entry. It means that two different DMA operations will be performed against the same dma addresss on the same device at the same time. It doesn't happen unless there is a bug in a driver, an IOMMU or somewhere, as I wrote in the previous mail. > > Then it's not a > > dma-debug bug (it might be better for dma-debug to check it though), > > that is, such situation should not happen. > > At least the warning about the wrong unmap count is a bug in the > dma-debug, as that is not what happens on my system. > > > Probably, it's an IOMMU bug > > or a driver bug. > > Could it be just a forgotten unmap? > That would leave the old entry in the dma-debug list, but from the > driver side it would be valid to map the same place again without > corrupting any data transfer to the harddisk. Yeah, I thought about this possibility. However, you use GART IOMMU, right (you can see "PCI-DMA: using GART IOMMU." in a boot message if so)? If you use GART IOMMU, unmapped addresses are not reused. > What also would point in this direction, sometime I have seen this in my log: > [ 1004.061989] DMA-API: debugging out of memory - disabling Sounds like there is a leak... -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
