nouveau: use mmu_notifier directly for invalidate_range_start

There is no reason to get the invalidate_range_start() callback via an
indirection through hmm_mirror, just register a normal notifier directly.

Link: https://lore.kernel.org/r/20191112202231.3856-9-jgg@ziepe.ca
Tested-by: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index 668d4bd0c118f16193a347358c2442cc94351eda..577f8811925a59eec28a2dc9336b403be6a546ae 100644 (file)
--- 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 start, u64 limit)
 }
 
 static int
-nouveau_svmm_sync_cpu_device_pagetables(struct hmm_mirror *mirror,
-                                       const struct mmu_notifier_range *update)
+nouveau_svmm_invalidate_range_start(struct mmu_notifier *mn,
+                                   const struct mmu_notifier_range *update)
 {
-       struct nouveau_svmm *svmm = 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_invalidate(svmm, start,
@@ -273,19 +277,31 @@ nouveau_svmm_sync_cpu_device_pagetables(struct hmm_mirror *mirror,
        }
 
        nouveau_svmm_invalidate(svmm, start, limit);
+
+out:
        mutex_unlock(&svmm->mutex);
        return 0;
 }
 
-static void
-nouveau_svmm_release(struct hmm_mirror *mirror)
+static void nouveau_svmm_free_notifier(struct mmu_notifier *mn)
+{
+       kfree(container_of(mn, struct nouveau_svmm, notifier));
+}
+
+static const struct mmu_notifier_ops nouveau_mn_ops = {
+       .invalidate_range_start = nouveau_svmm_invalidate_range_start,
+       .free_notifier = nouveau_svmm_free_notifier,
+};
+
+static int
+nouveau_svmm_sync_cpu_device_pagetables(struct hmm_mirror *mirror,
+                                       const struct mmu_notifier_range *update)
 {
+       return 0;
 }
 
-static const struct hmm_mirror_ops
-nouveau_svmm = {
+static const struct hmm_mirror_ops nouveau_svmm = {
        .sync_cpu_device_pagetables = nouveau_svmm_sync_cpu_device_pagetables,
-       .release = nouveau_svmm_release,
 };
 
 void
@@ -294,7 +310,10 @@ nouveau_svmm_fini(struct nouveau_svmm **psvmm)
        struct nouveau_svmm *svmm = *psvmm;
        if (svmm) {
                hmm_mirror_unregister(&svmm->mirror);
-               kfree(*psvmm);
+               mutex_lock(&svmm->mutex);
+               svmm->vmm = NULL;
+               mutex_unlock(&svmm->mutex);
+               mmu_notifier_put(&svmm->notifier);
                *psvmm = NULL;
        }
 }
@@ -320,7 +339,7 @@ nouveau_svmm_init(struct drm_device *dev, void *data,
        mutex_lock(&cli->mutex);
        if (cli->svm.cli) {
                ret = -EBUSY;
-               goto done;
+               goto out_free;
        }
 
        /* Allocate a new GPU VMM that can support SVM (managed by the
@@ -335,24 +354,33 @@ nouveau_svmm_init(struct drm_device *dev, void *data,
                                .fault_replay = true,
                            }, sizeof(struct gp100_vmm_v0), &cli->svm.vmm);
        if (ret)
-               goto done;
+               goto out_free;
 
-       /* Enable HMM mirroring of CPU address-space to VMM. */
-       svmm->mm = get_task_mm(current);
-       down_write(&svmm->mm->mmap_sem);
+       down_write(&current->mm->mmap_sem);
        svmm->mirror.ops = &nouveau_svmm;
-       ret = hmm_mirror_register(&svmm->mirror, svmm->mm);
-       if (ret == 0) {
-               cli->svm.svmm = svmm;
-               cli->svm.cli = cli;
-       }
-       up_write(&svmm->mm->mmap_sem);
-       mmput(svmm->mm);
+       ret = hmm_mirror_register(&svmm->mirror, current->mm);
+       if (ret)
+               goto out_mm_unlock;
 
-done:
+       svmm->notifier.ops = &nouveau_mn_ops;
+       ret = __mmu_notifier_register(&svmm->notifier, current->mm);
        if (ret)
-               nouveau_svmm_fini(&svmm);
+               goto out_hmm_unregister;
+       /* Note, ownership of svmm transfers to mmu_notifier */
+
+       cli->svm.svmm = svmm;
+       cli->svm.cli = cli;
+       up_write(&current->mm->mmap_sem);
        mutex_unlock(&cli->mutex);
+       return 0;
+
+out_hmm_unregister:
+       hmm_mirror_unregister(&svmm->mirror);
+out_mm_unlock:
+       up_write(&current->mm->mmap_sem);
+out_free:
+       mutex_unlock(&cli->mutex);
+       kfree(svmm);
        return ret;
 }
 
@@ -494,12 +522,12 @@ nouveau_range_fault(struct nouveau_svmm *svmm, struct hmm_range *range)
 
        ret = hmm_range_register(range, &svmm->mirror);
        if (ret) {
-               up_read(&svmm->mm->mmap_sem);
+               up_read(&svmm->notifier.mm->mmap_sem);
                return (int)ret;
        }
 
        if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) {
-               up_read(&svmm->mm->mmap_sem);
+               up_read(&svmm->notifier.mm->mmap_sem);
                return -EBUSY;
        }
 
@@ -507,7 +535,7 @@ nouveau_range_fault(struct nouveau_svmm *svmm, struct hmm_range *range)
        if (ret <= 0) {
                if (ret == 0)
                        ret = -EBUSY;
-               up_read(&svmm->mm->mmap_sem);
+               up_read(&svmm->notifier.mm->mmap_sem);
                hmm_range_unregister(range);
                return ret;
        }
@@ -587,12 +615,15 @@ nouveau_svm_fault(struct nvif_notify *notify)
        args.i.p.version = 0;
 
        for (fi = 0; fn = fi + 1, fi < buffer->fault_nr; fi = fn) {
+               struct mm_struct *mm;
+
                /* Cancel any faults from non-SVM channels. */
                if (!(svmm = buffer->fault[fi]->svmm)) {
                        nouveau_svm_fault_cancel_fault(svm, buffer->fault[fi]);
                        continue;
                }
                SVMM_DBG(svmm, "addr %016llx", buffer->fault[fi]->addr);
+               mm = svmm->notifier.mm;
 
                /* We try and group handling of faults within a small
                 * window into a single update.
@@ -609,11 +640,11 @@ nouveau_svm_fault(struct nvif_notify *notify)
                /* Intersect fault window with the CPU VMA, cancelling
                 * the fault if the address is invalid.
                 */
-               down_read(&svmm->mm->mmap_sem);
-               vma = find_vma_intersection(svmm->mm, start, limit);
+               down_read(&mm->mmap_sem);
+               vma = find_vma_intersection(mm, start, limit);
                if (!vma) {
                        SVMM_ERR(svmm, "wndw %016llx-%016llx", start, limit);
-                       up_read(&svmm->mm->mmap_sem);
+                       up_read(&mm->mmap_sem);
                        nouveau_svm_fault_cancel_fault(svm, buffer->fault[fi]);
                        continue;
                }
@@ -623,7 +654,7 @@ nouveau_svm_fault(struct nvif_notify *notify)
 
                if (buffer->fault[fi]->addr != start) {
                        SVMM_ERR(svmm, "addr %016llx", buffer->fault[fi]->addr);
-                       up_read(&svmm->mm->mmap_sem);
+                       up_read(&mm->mmap_sem);
                        nouveau_svm_fault_cancel_fault(svm, buffer->fault[fi]);
                        continue;
                }
@@ -704,7 +735,7 @@ again:
                                                NULL);
                        svmm->vmm->vmm.object.client->super = false;
                        mutex_unlock(&svmm->mutex);
-                       up_read(&svmm->mm->mmap_sem);
+                       up_read(&mm->mmap_sem);
                }
 
                /* Cancel any faults in the window whose pages didn't manage