* DMA-API: cacheline tracking ENOMEM, dma-debug disabled due to nouveau ? @ 2019-08-14 14:50 Corentin Labbe 2019-08-14 17:49 ` Daniel Vetter 0 siblings, 1 reply; 6+ messages in thread From: Corentin Labbe @ 2019-08-14 14:50 UTC (permalink / raw) To: bskeggs, airlied, daniel, hch, m.szyprowski, robin.murphy Cc: dri-devel, nouveau, linux-kernel, iommu Hello Since lot of release (at least since 4.19), I hit the following error message: DMA-API: cacheline tracking ENOMEM, dma-debug disabled After hitting that, I try to check who is creating so many DMA mapping and see: cat /sys/kernel/debug/dma-api/dump | cut -d' ' -f2 | sort | uniq -c 6 ahci 257 e1000e 6 ehci-pci 5891 nouveau 24 uhci_hcd Does nouveau having this high number of DMA mapping is normal ? Regards ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: DMA-API: cacheline tracking ENOMEM, dma-debug disabled due to nouveau ? 2019-08-14 14:50 DMA-API: cacheline tracking ENOMEM, dma-debug disabled due to nouveau ? Corentin Labbe @ 2019-08-14 17:49 ` Daniel Vetter 2019-08-15 13:35 ` Christoph Hellwig 2019-08-16 14:31 ` Corentin Labbe 0 siblings, 2 replies; 6+ messages in thread From: Daniel Vetter @ 2019-08-14 17:49 UTC (permalink / raw) To: Corentin Labbe Cc: bskeggs, airlied, daniel, hch, m.szyprowski, robin.murphy, dri-devel, nouveau, linux-kernel, iommu On Wed, Aug 14, 2019 at 04:50:33PM +0200, Corentin Labbe wrote: > Hello > > Since lot of release (at least since 4.19), I hit the following error message: > DMA-API: cacheline tracking ENOMEM, dma-debug disabled > > After hitting that, I try to check who is creating so many DMA mapping and see: > cat /sys/kernel/debug/dma-api/dump | cut -d' ' -f2 | sort | uniq -c > 6 ahci > 257 e1000e > 6 ehci-pci > 5891 nouveau > 24 uhci_hcd > > Does nouveau having this high number of DMA mapping is normal ? Yeah seems perfectly fine for a gpu. -Daniel -- Daniel Vetter Software Engineer, Intel Corporation http://blog.ffwll.ch ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: DMA-API: cacheline tracking ENOMEM, dma-debug disabled due to nouveau ? 2019-08-14 17:49 ` Daniel Vetter @ 2019-08-15 13:35 ` Christoph Hellwig 2019-08-15 13:50 ` Robin Murphy 2019-08-16 14:31 ` Corentin Labbe 1 sibling, 1 reply; 6+ messages in thread From: Christoph Hellwig @ 2019-08-15 13:35 UTC (permalink / raw) To: Corentin Labbe, bskeggs, airlied, hch, m.szyprowski, robin.murphy, dri-devel, nouveau, linux-kernel, iommu On Wed, Aug 14, 2019 at 07:49:27PM +0200, Daniel Vetter wrote: > On Wed, Aug 14, 2019 at 04:50:33PM +0200, Corentin Labbe wrote: > > Hello > > > > Since lot of release (at least since 4.19), I hit the following error message: > > DMA-API: cacheline tracking ENOMEM, dma-debug disabled > > > > After hitting that, I try to check who is creating so many DMA mapping and see: > > cat /sys/kernel/debug/dma-api/dump | cut -d' ' -f2 | sort | uniq -c > > 6 ahci > > 257 e1000e > > 6 ehci-pci > > 5891 nouveau > > 24 uhci_hcd > > > > Does nouveau having this high number of DMA mapping is normal ? > > Yeah seems perfectly fine for a gpu. That is a lot and apparently overwhelm the dma-debug tracking. Robin rewrote this code in Linux 4.21 to work a little better, so I'm curious why this might have changes in 4.19, as dma-debug did not change at all there. ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: DMA-API: cacheline tracking ENOMEM, dma-debug disabled due to nouveau ? 2019-08-15 13:35 ` Christoph Hellwig @ 2019-08-15 13:50 ` Robin Murphy 0 siblings, 0 replies; 6+ messages in thread From: Robin Murphy @ 2019-08-15 13:50 UTC (permalink / raw) To: Christoph Hellwig, Corentin Labbe, bskeggs, airlied, m.szyprowski, dri-devel, nouveau, linux-kernel, iommu On 15/08/2019 14:35, Christoph Hellwig wrote: > On Wed, Aug 14, 2019 at 07:49:27PM +0200, Daniel Vetter wrote: >> On Wed, Aug 14, 2019 at 04:50:33PM +0200, Corentin Labbe wrote: >>> Hello >>> >>> Since lot of release (at least since 4.19), I hit the following error message: >>> DMA-API: cacheline tracking ENOMEM, dma-debug disabled >>> >>> After hitting that, I try to check who is creating so many DMA mapping and see: >>> cat /sys/kernel/debug/dma-api/dump | cut -d' ' -f2 | sort | uniq -c >>> 6 ahci >>> 257 e1000e >>> 6 ehci-pci >>> 5891 nouveau >>> 24 uhci_hcd >>> >>> Does nouveau having this high number of DMA mapping is normal ? >> >> Yeah seems perfectly fine for a gpu. > > That is a lot and apparently overwhelm the dma-debug tracking. Robin > rewrote this code in Linux 4.21 to work a little better, so I'm curious > why this might have changes in 4.19, as dma-debug did not change at > all there. FWIW, the cacheline tracking entries are a separate thing from the dma-debug entries that I rejigged - judging by those numbers there should still be plenty of free dma-debug entries, but for some reason it has failed to extend the radix tree :/ Robin. ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: DMA-API: cacheline tracking ENOMEM, dma-debug disabled due to nouveau ? 2019-08-14 17:49 ` Daniel Vetter 2019-08-15 13:35 ` Christoph Hellwig @ 2019-08-16 14:31 ` Corentin Labbe 2019-08-16 18:45 ` Daniel Vetter 1 sibling, 1 reply; 6+ messages in thread From: Corentin Labbe @ 2019-08-16 14:31 UTC (permalink / raw) To: bskeggs, airlied, hch, m.szyprowski, robin.murphy, dri-devel, nouveau, linux-kernel, iommu On Wed, Aug 14, 2019 at 07:49:27PM +0200, Daniel Vetter wrote: > On Wed, Aug 14, 2019 at 04:50:33PM +0200, Corentin Labbe wrote: > > Hello > > > > Since lot of release (at least since 4.19), I hit the following error message: > > DMA-API: cacheline tracking ENOMEM, dma-debug disabled > > > > After hitting that, I try to check who is creating so many DMA mapping and see: > > cat /sys/kernel/debug/dma-api/dump | cut -d' ' -f2 | sort | uniq -c > > 6 ahci > > 257 e1000e > > 6 ehci-pci > > 5891 nouveau > > 24 uhci_hcd > > > > Does nouveau having this high number of DMA mapping is normal ? > > Yeah seems perfectly fine for a gpu. Note that it never go down and when I terminate my X session, it stays the same. So without any "real" GPU work, does it is still normal to have so many active mapping ? For example, when doing some transfer, the ahci mapping number changes and then always go down to 6. ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: DMA-API: cacheline tracking ENOMEM, dma-debug disabled due to nouveau ? 2019-08-16 14:31 ` Corentin Labbe @ 2019-08-16 18:45 ` Daniel Vetter 0 siblings, 0 replies; 6+ messages in thread From: Daniel Vetter @ 2019-08-16 18:45 UTC (permalink / raw) To: Corentin Labbe Cc: Ben Skeggs, Dave Airlie, Christoph Hellwig, Marek Szyprowski, Robin Murphy, dri-devel, Nouveau Dev, Linux Kernel Mailing List, list@263.net:IOMMU DRIVERS <iommu@lists.linux-foundation.org>, Joerg Roedel <joro@8bytes.org>, On Fri, Aug 16, 2019 at 4:31 PM Corentin Labbe <clabbe.montjoie@gmail.com> wrote: > On Wed, Aug 14, 2019 at 07:49:27PM +0200, Daniel Vetter wrote: > > On Wed, Aug 14, 2019 at 04:50:33PM +0200, Corentin Labbe wrote: > > > Hello > > > > > > Since lot of release (at least since 4.19), I hit the following error message: > > > DMA-API: cacheline tracking ENOMEM, dma-debug disabled > > > > > > After hitting that, I try to check who is creating so many DMA mapping and see: > > > cat /sys/kernel/debug/dma-api/dump | cut -d' ' -f2 | sort | uniq -c > > > 6 ahci > > > 257 e1000e > > > 6 ehci-pci > > > 5891 nouveau > > > 24 uhci_hcd > > > > > > Does nouveau having this high number of DMA mapping is normal ? > > > > Yeah seems perfectly fine for a gpu. > > Note that it never go down and when I terminate my X session, it stays the same. > So without any "real" GPU work, does it is still normal to have so many active mapping ? Might just be the dma_alloc cache. It should go down under memory pressure I think. Otherwise might also be a leak. > For example, when doing some transfer, the ahci mapping number changes and then always go down to 6. gpu drivers tend to cache everything, all the time ... -Daniel -- Daniel Vetter Software Engineer, Intel Corporation +41 (0) 79 365 57 48 - http://blog.ffwll.ch ^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2019-08-16 18:45 UTC | newest] Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2019-08-14 14:50 DMA-API: cacheline tracking ENOMEM, dma-debug disabled due to nouveau ? Corentin Labbe 2019-08-14 17:49 ` Daniel Vetter 2019-08-15 13:35 ` Christoph Hellwig 2019-08-15 13:50 ` Robin Murphy 2019-08-16 14:31 ` Corentin Labbe 2019-08-16 18:45 ` Daniel Vetter
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).