search for: notifier_lock

...03:59:26PM +0000, Yang, Philip wrote: >>> This test for range_blockable should be before mutex_lock, I can move >>> it up >>> >> yes, thanks. > > Okay, I wrote it like this: > > if (mmu_notifier_range_blockable(range)) > mutex_lock(&adev->notifier_lock); > else if (!mutex_trylock(&adev->notifier_lock)) > return false; > >>> Also, do you know if notifier_lock is held while calling >>> amdgpu_ttm_tt_get_user_pages_done()? Can we add a 'lock assert held' >>> to amdgpu_ttm_tt_get_user_pages_done(...

...amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); >> long r; >> >> - /* >> - * FIXME: Must hold some lock shared with >> - * amdgpu_ttm_tt_get_user_pages_done() >> - */ >> - mmu_range_set_seq(mrn, cur_seq); >> + mutex_lock(&adev->notifier_lock); >> >> - /* FIXME: Is this necessary? */ >> - if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, range->start, >> - range->end)) >> - return true; >> + mmu_range_set_seq(mrn, cur_seq); >> >> - if (!mmu_notifier_range_blockable(range...

...ange_notifier *mrn, > struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); > long r; > > - /* > - * FIXME: Must hold some lock shared with > - * amdgpu_ttm_tt_get_user_pages_done() > - */ > - mmu_range_set_seq(mrn, cur_seq); > + mutex_lock(&adev->notifier_lock); > > - /* FIXME: Is this necessary? */ > - if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, range->start, > - range->end)) > - return true; > + mmu_range_set_seq(mrn, cur_seq); > > - if (!mmu_notifier_range_blockable(range)) > + if (!mmu_notifier_range_...

On Tue, Oct 29, 2019 at 07:22:37PM +0000, Yang, Philip wrote: > Hi Jason, > > I did quick test after merging amd-staging-drm-next with the > mmu_notifier branch, which includes this set changes. The test result > has different failures, app stuck intermittently, GUI no display etc. I > am understanding the changes and will try to figure out the cause. Thanks! I'm not

On Fri, Nov 01, 2019 at 03:59:26PM +0000, Yang, Philip wrote: > > This test for range_blockable should be before mutex_lock, I can move > > it up > > > yes, thanks. Okay, I wrote it like this: if (mmu_notifier_range_blockable(range)) mutex_lock(&adev->notifier_lock); else if (!mutex_trylock(&adev->notifier_lock)) return false; > > Also, do you know if notifier_lock is held while calling > > amdgpu_ttm_tt_get_user_pages_done()? Can we add a 'lock assert held' > > to amdgpu_ttm_tt_get_user_pages_done()? > > gpu side h...

...-- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1738,6 +1738,10 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, return ret; } + /* + * FIXME: Cannot ignore the return code, must hold + * notifier_lock + */ amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); /* Mark the BO as valid unless it was invalidated diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 82823d9a8ba887..22c989bca7514c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +...

...bd37df5dd6d048..60591a5d420021 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h > @@ -1006,6 +1006,8 @@ struct amdgpu_device { > struct mutex lock_reset; > struct amdgpu_doorbell_index doorbell_index; > > + struct mutex notifier_lock; > + > int asic_reset_res; > struct work_struct xgmi_reset_work; > > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c > index 6d021ecc8d598f..47700302a08b7f 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgp...

...vers/gpu/drm/amd/amdgpu/amdgpu.h index bd37df5dd6d048..60591a5d420021 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1006,6 +1006,8 @@ struct amdgpu_device { struct mutex lock_reset; struct amdgpu_doorbell_index doorbell_index; + struct mutex notifier_lock; + int asic_reset_res; struct work_struct xgmi_reset_work; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 6d021ecc8d598f..47700302a08b7f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm...

...quot;, r); > - } > + /* FIXME: Is this necessary? */ > + if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, range->start, > + range->end)) > + return true; > + > + if (!mmu_notifier_range_blockable(range)) > + return false; > + > + mutex_lock(&adev->notifier_lock); > + r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv, true, false, > + MAX_SCHEDULE_TIMEOUT); > + mutex_unlock(&adev->notifier_lock); > + if (r <= 0) > + DRM_ERROR("(%ld) failed to wait for user bo\n", r); > + return true; > } > > +s...

...fd_gpuvm.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c > @@ -1738,6 +1738,10 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, > return ret; > } > > + /* > + * FIXME: Cannot ignore the return code, must hold > + * notifier_lock > + */ > amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); > > /* Mark the BO as valid unless it was invalidated > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c > index 2e53feed40e230..76771f5f0b60ab 100644 > --- a/dr...

...-- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1738,6 +1738,10 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, return ret; } + /* + * FIXME: Cannot ignore the return code, must hold + * notifier_lock + */ amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); /* Mark the BO as valid unless it was invalidated diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 2e53feed40e230..76771f5f0b60ab 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +...

From: Jason Gunthorpe <jgg at mellanox.com> 8 of the mmu_notifier using drivers (i915_gem, radeon_mn, umem_odp, hfi1, scif_dma, vhost, gntdev, hmm) drivers are using a common pattern where they only use invalidate_range_start/end and immediately check the invalidating range against some driver data structure to tell if the driver is interested. Half of them use an interval_tree, the others

From: Jason Gunthorpe <jgg at mellanox.com> 8 of the mmu_notifier using drivers (i915_gem, radeon_mn, umem_odp, hfi1, scif_dma, vhost, gntdev, hmm) drivers are using a common pattern where they only use invalidate_range_start/end and immediately check the invalidating range against some driver data structure to tell if the driver is interested. Half of them use an interval_tree, the others

From: Jason Gunthorpe <jgg at mellanox.com> The API is a bit complicated for the uses we actually have, and disucssions for simplifying have come up a number of times. This small series removes the customizable pfn format and simplifies the return code of hmm_range_fault() All the drivers are adjusted to process in the simplified format. I would appreciated tested-by's for the two

From: Jason Gunthorpe <jgg at mellanox.com> The API is a bit complicated for the uses we actually have, and disucssions for simplifying have come up a number of times. This small series removes the customizable pfn format and simplifies the return code of hmm_range_fault() All the drivers are adjusted to process in the simplified format. I would appreciated tested-by's for the two

...)) { + range->hmm_pfns = kvmalloc_array(ttm->num_pages, + sizeof(*range->hmm_pfns), GFP_KERNEL); + if (unlikely(!range->hmm_pfns)) { r = -ENOMEM; goto out_free_ranges; } @@ -867,7 +853,7 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) * the notifier_lock, and mmu_interval_read_retry() must be done first. */ for (i = 0; i < ttm->num_pages; i++) - pages[i] = hmm_device_entry_to_page(range, range->pfns[i]); + pages[i] = hmm_pfn_to_page(range->hmm_pfns[i]); gtt->range = range; mmput(mm); @@ -877,7 +863,7 @@ int amdgpu_ttm_tt...

...)) { + range->hmm_pfns = kvmalloc_array(ttm->num_pages, + sizeof(*range->hmm_pfns), GFP_KERNEL); + if (unlikely(!range->hmm_pfns)) { r = -ENOMEM; goto out_free_ranges; } @@ -867,7 +853,7 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) * the notifier_lock, and mmu_interval_read_retry() must be done first. */ for (i = 0; i < ttm->num_pages; i++) - pages[i] = hmm_device_entry_to_page(range, range->pfns[i]); + pages[i] = hmm_pfn_to_page(range->hmm_pfns[i]); gtt->range = range; mmput(mm); @@ -877,7 +863,7 @@ int amdgpu_ttm_tt...

...c_array(ttm->num_pages, > + sizeof(*range->hmm_pfns), GFP_KERNEL); > + if (unlikely(!range->hmm_pfns)) { > r = -ENOMEM; > goto out_free_ranges; > } > @@ -867,7 +853,7 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) > * the notifier_lock, and mmu_interval_read_retry() must be done first. > */ > for (i = 0; i < ttm->num_pages; i++) > - pages[i] = hmm_device_entry_to_page(range, range->pfns[i]); > + pages[i] = hmm_pfn_to_page(range->hmm_pfns[i]); > > gtt->range = range; > mmput(mm); &g...