Re: [Intel-gfx] [PATCH v3 hmm 03/11] mm/mmu_notifiers: add a get/put scheme for the registration

ff-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Reviewed-by: Ralph Campbell --- include/linux/mmu_notifier.h | 35 mm/mmu_notifier.c| 156 +-- 2 files changed, 185 insertions(+), 6 deletions(-) diff --git a/include/linux/

Re: [Intel-gfx] [PATCH 1/5] mm: Check if mmu notifier callbacks are allowed to fail

On 8/14/19 3:14 PM, Andrew Morton wrote: On Wed, 14 Aug 2019 22:20:23 +0200 Daniel Vetter wrote: Just a bit of paranoia, since if we start pushing this deep into callchains it's hard to spot all places where an mmu notifier implementation might fail when it's not allowed to. Inspired by

Re: [Intel-gfx] [PATCH v3 hmm 00/11] Add mmu_notifier_get/put for managing mmu notifier registrations

m/hmm.c | 121 +++- mm/mmu_notifier.c| 230 +-- 25 files changed, 408 insertions(+), 559 deletions(-) For the core MM, HMM, and nouveau changes you can add: Tested-by: Ralph C

Re: [Intel-gfx] [PATCH v3 hmm 05/11] hmm: use mmu_notifier_get/put for 'struct hmm'

ere overly cautious, drivers are already not permitted to free the mirror while a range exists. Signed-off-by: Jason Gunthorpe Looks good. Reviewed-by: Ralph Campbell ___ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org https://lists.freedesktop.

Re: [Intel-gfx] [PATCH v3 hmm 11/11] mm/mmu_notifiers: remove unregister_no_release

Reviewed-by: Ralph Campbell ___ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH v3 hmm 01/11] mm/mmu_notifiers: hoist do_mmu_notifier_register down_write to the caller

to check that the callers are holding the lock as expected. Suggested-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Nice clean up. Reviewed-by: Ralph Campbell ___ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org https

Re: [Intel-gfx] [PATCH v3 hmm 02/11] mm/mmu_notifiers: do not speculatively allocate a mmu_notifier_mm

eterministic and we can use that to decide if the allocation path is required, without speculation. The actual update to mmu_notifier_mm must still be done under the mm_take_all_locks() to ensure read-side coherency. Signed-off-by: Jason Gunthorpe Looks good to me. Revi

Re: [Intel-gfx] [PATCH hmm 0/5] Adjust hmm_range_fault() API

of hmm_range_fault() All the drivers are adjusted to process in the simplified format. I would appreciated tested-by's for the two drivers, thanks! For nouveau you can add: Tested-by: Ralph Campbell ___ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org https

Re: [Intel-gfx] [PATCH hmm v2 5/5] mm/hmm: remove the customizable pfn format from hmm_range_fault

gt_pfn nvkm_vmm_iter() REF_PTES == func == gp100_vmm_pgt_pfn() dma_map_page() Acked-by: Felix Kuehling Tested-by: Ralph Campbell Signed-off-by: Jason Gunthorpe Signed-off-by: Christoph Hellwig --- Documentation/vm/hmm.rst

[Intel-gfx] [PATCH v2] drm/edid: Add quirk for OSVR HDK 2.0

-by: Ralph Campbell Tested-by: Ralph Campbell --- drivers/gpu/drm/drm_edid.c | 1 + 1 file changed, 1 insertion(+) I don't know how many of these VR headsets are still around but I have a working one and I saw an entry for HDK 1.x so I thought it would be good to add HDK 2.0. v2: The vendor ID was byte