search for: nouveau_svmm

...git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 668d4bd0c118f1..577f8811925a59 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -88,6 +88,7 @@ nouveau_ivmm_find(struct nouveau_svm *svm, u64 inst) } struct nouveau_svmm { + struct mmu_notifier notifier; struct nouveau_vmm *vmm; struct { unsigned long start; @@ -96,7 +97,6 @@ struct nouveau_svmm { struct mutex mutex; - struct mm_struct *mm; struct hmm_mirror mirror; }; @@ -251,10 +251,11 @@ nouveau_svmm_invalidate(struct nouveau_svmm *svmm, u64 st...

...8b9e3c2a5b3..511fe04cd680 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -140,6 +140,7 @@ static vm_fault_t nouveau_dmem_fault_copy_one(struct nouveau_drm *drm, { struct device *dev = drm->dev->dev; struct page *dpage, *spage; + struct nouveau_svmm *svmm; spage = migrate_pfn_to_page(args->src[0]); if (!spage || !(args->src[0] & MIGRATE_PFN_MIGRATE)) @@ -154,14 +155,19 @@ static vm_fault_t nouveau_dmem_fault_copy_one(struct nouveau_drm *drm, if (dma_mapping_error(dev, *dma_addr)) goto error_free_page; + svmm = spage->...

...f --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index df9bf1fd1bc0..0343e48d41d7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -88,7 +88,7 @@ nouveau_ivmm_find(struct nouveau_svm *svm, u64 inst) } struct nouveau_svmm { - struct mmu_notifier notifier; + struct mm_struct *mm; struct nouveau_vmm *vmm; struct { unsigned long start; @@ -98,6 +98,13 @@ struct nouveau_svmm { struct mutex mutex; }; +struct svmm_interval { + struct mmu_interval_notifier notifier; + struct nouveau_svmm *svmm; +}; + +static co...

We'll need the nouveau_svmm structure to improve the function soon. For now this allows using the svmm->mm reference to unlock the mmap_sem, and thus the same dereference chain that the caller uses to lock and unlock it. Signed-off-by: Christoph Hellwig <hch at lst.de> --- drivers/gpu/drm/nouveau/nouveau_svm.c | 12...

...b5a523..b889d5ec4c7e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -485,14 +485,14 @@ nouveau_range_done(struct hmm_range *range) } static int -nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range) +nouveau_range_fault(struct nouveau_svmm *svmm, struct hmm_range *range) { long ret; range->default_flags = 0; range->pfn_flags_mask = -1UL; - ret = hmm_range_register(range, mirror, + ret = hmm_range_register(range, &svmm->mirror, range->start, range->end, PAGE_SHIFT); if (ret) { @@ -689,7 +689...

On Tue, Jul 30, 2019 at 08:51:53AM +0300, Christoph Hellwig wrote: > This avoid having to abuse the vma field in struct hmm_range to unlock > the mmap_sem. I think the change inside hmm_range_fault got lost on rebase, it is now using: up_read(&range->hmm->mm->mmap_sem); But, yes, lets change it to use svmm->mm and try to keep struct hmm opaque to drivers

On Tue, Jul 30, 2019 at 12:35:59PM +0000, Jason Gunthorpe wrote: > On Tue, Jul 30, 2019 at 08:51:53AM +0300, Christoph Hellwig wrote: > > This avoid having to abuse the vma field in struct hmm_range to unlock > > the mmap_sem. > > I think the change inside hmm_range_fault got lost on rebase, it is > now using: > >

On Tue, Jul 30, 2019 at 03:10:38PM +0200, Christoph Hellwig wrote: > On Tue, Jul 30, 2019 at 12:35:59PM +0000, Jason Gunthorpe wrote: > > On Tue, Jul 30, 2019 at 08:51:53AM +0300, Christoph Hellwig wrote: > > > This avoid having to abuse the vma field in struct hmm_range to unlock > > > the mmap_sem. > > > > I think the change inside hmm_range_fault got lost

...1 file changed, 98 insertions(+), 80 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 577f8811925a59..712c99918551bc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -96,8 +96,6 @@ struct nouveau_svmm { } unmanaged; struct mutex mutex; - - struct hmm_mirror mirror; }; #define SVMM_DBG(s,f,a...) \ @@ -293,23 +291,11 @@ static const struct mmu_notifier_ops nouveau_mn_ops = { .free_notifier = nouveau_svmm_free_notifier, }; -static i...

On Mon, Jan 13, 2020 at 02:47:02PM -0800, Ralph Campbell wrote: > void > nouveau_svmm_fini(struct nouveau_svmm **psvmm) > { > struct nouveau_svmm *svmm = *psvmm; > + struct mmu_interval_notifier *mni; > + > if (svmm) { > mutex_lock(&svmm->mutex); > + while (true) { > + mni = mmu_interval_notifier_find(svmm->mm, > + &nouveau_svm...

...UG((s)->drm, "svm: "f"\n", ##a) #define SVM_ERR(s,f,a...) NV_WARN((s)->drm, "svm: "f"\n", ##a) +struct nouveau_pfnmap_args { + struct nvif_ioctl_v0 i; + struct nvif_ioctl_mthd_v0 m; + struct nvif_vmm_pfnmap_v0 p; +}; + struct nouveau_ivmm { struct nouveau_svmm *svmm; u64 inst; @@ -734,6 +740,86 @@ nouveau_svm_fault(struct nvif_notify *notify) return NVIF_NOTIFY_KEEP; } +static inline struct nouveau_pfnmap_args * +nouveau_pfns_to_args(void *pfns) +{ + struct nvif_vmm_pfnmap_v0 *p = + container_of(pfns, struct nvif_vmm_pfnmap_v0, phys); + + return...

...UG((s)->drm, "svm: "f"\n", ##a) #define SVM_ERR(s,f,a...) NV_WARN((s)->drm, "svm: "f"\n", ##a) +struct nouveau_pfnmap_args { + struct nvif_ioctl_v0 i; + struct nvif_ioctl_mthd_v0 m; + struct nvif_vmm_pfnmap_v0 p; +}; + struct nouveau_ivmm { struct nouveau_svmm *svmm; u64 inst; @@ -782,6 +788,85 @@ nouveau_svm_fault(struct nvif_notify *notify) return NVIF_NOTIFY_KEEP; } +static inline struct nouveau_pfnmap_args * +nouveau_pfns_to_args(void *pfns) +{ + struct nvif_vmm_pfnmap_v0 *p = + container_of(pfns, struct nvif_vmm_pfnmap_v0, phys); + + return...

Originally patch 4 was targeted for Jason's rdma tree since other HMM related changes were queued there. Now that those have been merged, these patches just contain changes to nouveau so they could go through any tree. I guess Ben Skeggs' tree would be appropriate. Changes since v2: Added patches 1-3 to fix some minor issues. Eliminated nouveau_find_svmm() since it is easily found.

...ng proper fencing so that would need to be implemented first) - the migrate ioctl is disconnected from the svm part and thus we would need first to implement svm reference counting and take a reference at begining of migration process and release it at the end ie struct nouveau_svmm needs refcounting of some sort. I let Ben decides what he likes best for that. - i rather not have an extra pfns array, i am pretty sure we can directly feed what we get from the dma array to the svm code to update the GPU page table Observation that can be delayed to latter...

...au_svm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 93ed43c..8d56bd6 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -649,7 +649,7 @@ struct nouveau_svmm { range.values = nouveau_svm_pfn_values; range.pfn_shift = NVIF_VMM_PFNMAP_V0_ADDR_SHIFT; again: - ret = hmm_vma_fault(&range, true); + ret = hmm_range_fault(&range, true); if (ret == 0) { mutex_lock(&svmm->mutex); if (!hmm_vma_range_done(&range)) { -- 1.9.1

The goal for this series is to avoid device private memory TLB invalidations when migrating a range of addresses from system memory to device private memory and some of those pages have already been migrated. The approach taken is to introduce a new mmu notifier invalidation event type and use that in the device driver to skip invalidation callbacks from migrate_vma_setup(). The device driver is

On 1/14/20 5:00 AM, Jason Gunthorpe wrote: > On Mon, Jan 13, 2020 at 02:47:02PM -0800, Ralph Campbell wrote: >> void >> nouveau_svmm_fini(struct nouveau_svmm **psvmm) >> { >> struct nouveau_svmm *svmm = *psvmm; >> + struct mmu_interval_notifier *mni; >> + >> if (svmm) { >> mutex_lock(&svmm->mutex); >> + while (true) { >> + mni = mmu_interval_notifier_find(svmm...

One fix and a minor cleanup. Only compile-tested due to lack of HW, so I'd be happy if someone with access to HW could test. But not sure how easy this is to trigger. Likely some concurrent MADV_DONTNEED on the PTE we just converted might be able to trigger it. Cc: Karol Herbst <kherbst at redhat.com> Cc: Lyude Paul <lyude at redhat.com> Cc: Danilo Krummrich <dakr at

The goal for this series is to avoid device private memory TLB invalidations when migrating a range of addresses from system memory to device private memory and some of those pages have already been migrated. The approach taken is to introduce a new mmu notifier invalidation event type and use that in the device driver to skip invalidation callbacks from migrate_vma_setup(). The device driver is

hmm_range_fault() returns an array of page frame numbers and flags for how the pages are mapped in the requested process' page tables. The PFN can be used to get the struct page with hmm_pfn_to_page() and the page size order can be determined with compound_order(page) but if the page is larger than order 0 (PAGE_SIZE), there is no indication that the page is mapped using a larger page size. To