search for: svmm_dbg

...ouveau_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 const struct mmu_interval_notifier_ops nouveau_svm_mni_ops; + #define SVMM_DBG(s,f,a...) \ NV_DEBUG((s)->vmm->cli->drm, "svm-%p: "f"\n", (s), ##a) #define SVMM_ERR(s,f,a...) \ @@ -236,6 +243,8 @@ nouveau_svmm_join(struct nouveau_svmm *svmm, u...

...m.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 int -nouveau_svmm_sync_cpu_device_pagetables(struct hmm_mirror *mirror, - const struct mmu_n...

...f_notify *notify) * window into a single update. */ start = buffer->fault[fi]->addr; - limit = start + (ARRAY_SIZE(args.phys) << PAGE_SHIFT); + limit = start + PAGE_SIZE; if (start < svmm->unmanaged.limit) limit = min_t(u64, limit, svmm->unmanaged.start); - SVMM_DBG(svmm, "wndw %016llx-%016llx", start, limit); - mm = svmm->notifier.mm; - if (!mmget_not_zero(mm)) { - nouveau_svm_fault_cancel_fault(svm, buffer->fault[fi]); - continue; - } - - /* Intersect fault window with the CPU VMA, cancelling - * the fault if the address is invali...

...f_notify *notify) * window into a single update. */ start = buffer->fault[fi]->addr; - limit = start + (ARRAY_SIZE(args.phys) << PAGE_SHIFT); + limit = start + PAGE_SIZE; if (start < svmm->unmanaged.limit) limit = min_t(u64, limit, svmm->unmanaged.start); - SVMM_DBG(svmm, "wndw %016llx-%016llx", start, limit); - mm = svmm->notifier.mm; - if (!mmget_not_zero(mm)) { - nouveau_svm_fault_cancel_fault(svm, buffer->fault[fi]); - continue; - } - - /* Intersect fault window with the CPU VMA, cancelling - * the fault if the address is invali...

...container_of(mirror, typeof(*svmm), mirror); + struct nouveau_svmm *svmm = + container_of(mn, struct nouveau_svmm, notifier); unsigned long start = update->start; unsigned long limit = update->end; @@ -264,6 +265,9 @@ nouveau_svmm_sync_cpu_device_pagetables(struct hmm_mirror *mirror, SVMM_DBG(svmm, "invalidate %016lx-%016lx", start, limit); mutex_lock(&svmm->mutex); + if (unlikely(!svmm->vmm)) + goto out; + if (limit > svmm->unmanaged.start && start < svmm->unmanaged.limit) { if (start < svmm->unmanaged.start) { nouveau_svmm_in...

The goal for this series is to introduce the hmm_range_fault() output array flags HMM_PFN_PMD and HMM_PFN_PUD. This allows a device driver to know that a given 4K PFN is actually mapped by the CPU using either a PMD sized or PUD sized CPU page table entry and therefore the device driver can safely map system memory using larger device MMU PTEs. The series is based on 5.8.0-rc3 and is intended for

...ouveau_svm.c @@ -93,17 +93,6 @@ nouveau_ivmm_find(struct nouveau_svm *svm, u64 inst) return NULL; } -struct nouveau_svmm { - struct mmu_notifier notifier; - struct nouveau_vmm *vmm; - struct { - unsigned long start; - unsigned long limit; - } unmanaged; - - struct mutex mutex; -}; - #define SVMM_DBG(s,f,a...) \ NV_DEBUG((s)->vmm->cli->drm, "svm-%p: "f"\n", (s), ##a) #define SVMM_ERR(s,f,a...) \ @@ -246,7 +235,7 @@ nouveau_svmm_join(struct nouveau_svmm *svmm, u...

The goal for this series is to introduce the hmm_pfn_to_map_order() function. This allows a device driver to know that a given 4K PFN is actually mapped by the CPU using a larger sized CPU page table entry and therefore the device driver can safely map system memory using larger device MMU PTEs. The series is based on 5.8.0-rc3 and is intended for Jason Gunthorpe's hmm tree. These were

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

...const struct mmu_notifier_range *update) { struct nouveau_svmm *svmm = container_of(mirror, typeof(*svmm), mirror); unsigned long start = update->start; unsigned long limit = update->end; - if (!update->blockable) + if (!mmu_notifier_range_blockable(update)) return -EAGAIN; SVMM_DBG(svmm, "invalidate %016lx-%016lx", start, limit); diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 9f32586684c9..659e25a15700 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -340,29 +340,6 @@ static inline uint64_t hmm_device_entry_from_pfn(const struct hmm_range...

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.

This series adds new functions to the mmu interval notifier API to allow device drivers with MMUs to dynamically mirror a process' page tables based on device faults and invalidation callbacks. The Nouveau driver is updated to use the extended API and a set of stand alone self tests is added to help validate and maintain correctness. The patches are based on linux-5.5.0-rc6 and are for

These patches apply to linux-5.8.0-rc1. Patches 1-3 should probably go into 5.8, the others can be queued for 5.9. Patches 4-6 improve the HMM self tests. Patch 7-8 prepare nouveau for the meat of this series which adds support and testing for compound page mapping of system memory (patches 9-11) and compound page migration to device private memory (patches 12-16). Since these changes are split

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

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

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

...<< PAGE_SHIFT; @@ -737,7 +733,7 @@ nouveau_svm_fault(struct nvif_notify *notify) fill = (buffer->fault[fn ]->addr - buffer->fault[fn - 1]->addr) >> PAGE_SHIFT; while (--fill) - args.phys[pi++] = NVIF_VMM_PFNMAP_V0_NONE; + hmm_pfns[pi++] = 0; } SVMM_DBG(svmm, "wndw %016llx-%016llx covering %d fault(s)", @@ -753,7 +749,7 @@ nouveau_svm_fault(struct nvif_notify *notify) ret = nouveau_range_fault( svmm, svm->drm, &args, sizeof(args.i) + pi * sizeof(args.phys[0]), - args.phys, &notifier); + hmm_pfns, args.phys,...

...<< PAGE_SHIFT; @@ -737,7 +768,7 @@ nouveau_svm_fault(struct nvif_notify *notify) fill = (buffer->fault[fn ]->addr - buffer->fault[fn - 1]->addr) >> PAGE_SHIFT; while (--fill) - args.phys[pi++] = NVIF_VMM_PFNMAP_V0_NONE; + hmm_pfns[pi++] = 0; } SVMM_DBG(svmm, "wndw %016llx-%016llx covering %d fault(s)", @@ -753,7 +784,7 @@ nouveau_svm_fault(struct nvif_notify *notify) ret = nouveau_range_fault( svmm, svm->drm, &args, sizeof(args.i) + pi * sizeof(args.phys[0]), - args.phys, &notifier); + hmm_pfns, args.phys,...

...@@ nouveau_svm_fault(struct nvif_notify *notify) > fill = (buffer->fault[fn ]->addr - > buffer->fault[fn - 1]->addr) >> PAGE_SHIFT; > while (--fill) > - args.phys[pi++] = NVIF_VMM_PFNMAP_V0_NONE; > + hmm_pfns[pi++] = 0; > } > > SVMM_DBG(svmm, "wndw %016llx-%016llx covering %d fault(s)", > @@ -753,7 +749,7 @@ nouveau_svm_fault(struct nvif_notify *notify) > ret = nouveau_range_fault( > svmm, svm->drm, &args, > sizeof(args.i) + pi * sizeof(args.phys[0]), > - args.phys, &notifier);...

This series adds support for transparent huge page migration to migrate_vma_*() and adds nouveau SVM and HMM selftests as consumers. Earlier versions were posted previously [1] and [2]. The patches apply cleanly to the linux-mm 5.10.0-rc2 tree. There are a lot of other THP patches being posted. I don't think there are any semantic conflicts but there may be some merge conflicts depending on