The patch to add zero page migration to GPU memory inadvertantly included part of a future change which broke normal page migration to GPU memory by copying too much data and corrupting GPU memory. Fix this by only copying one page instead of a byte count.

Fixes: 9d4296a7d4b3 ("drm/nouveau/nouveau/hmm: fix migrate zero page to GPU") Signed-off-by: Ralph Campbell rcampbell@nvidia.com --- drivers/gpu/drm/nouveau/nouveau_dmem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index e5c230d9ae24..cc9993837508 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -550,7 +550,7 @@ static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, *dma_addr)) goto out_free_page; - if (drm->dmem->migrate.copy_func(drm, page_size(spage), + if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_VRAM, paddr, NOUVEAU_APER_HOST, *dma_addr)) goto out_dma_unmap; } else {

The HMM self test "migrate_multiple" can timeout on slower machines. Lower the number of loop iterations to fix this.

Signed-off-by: Ralph Campbell rcampbell@nvidia.com --- tools/testing/selftests/vm/hmm-tests.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index 79db22604019..bdfa95ac9a7d 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -45,7 +45,7 @@ struct hmm_buffer { #define TWOMEG (1 << 21) #define HMM_BUFFER_SIZE (1024 << 12) #define HMM_PATH_MAX 64 -#define NTIMES 256 +#define NTIMES 50

#define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1)))

Add a test to check that migrating a range of addresses with mixed device private pages and normal anonymous pages are all migrated.

Signed-off-by: Ralph Campbell rcampbell@nvidia.com --- lib/test_hmm.c | 22 +++++++++++++++++----- tools/testing/selftests/vm/hmm-tests.c | 18 ++++++++++++++---- 2 files changed, 31 insertions(+), 9 deletions(-)

diff --git a/lib/test_hmm.c b/lib/test_hmm.c index f7c2b51a7a9d..50bdf041770a 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -588,12 +588,24 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args,

/* * Don't migrate device private pages from our own driver or - * others. For our own we would do a device private memory copy - * not a migration and for others, we would need to fault the - * other device's page into system memory first. + * others. Other device's private pages are skipped because + * the src_owner field won't match. The migrate_vma_setup() + * will have invalidated our page tables for our own device + * private pages as part of isolating and locking the pages. + * In this case, repopulate our page table. */ - if (spage && is_zone_device_page(spage)) + if (spage && is_zone_device_page(spage)) { + unsigned long pfn = addr >> PAGE_SHIFT; + void *entry; + + mutex_lock(&dmirror->mutex); + entry = spage->zone_device_data; + if (*src & MIGRATE_PFN_WRITE) + entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE); + xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC); + mutex_unlock(&dmirror->mutex); continue; + }

dpage = dmirror_devmem_alloc_page(mdevice); if (!dpage) @@ -703,7 +715,7 @@ static int dmirror_migrate(struct dmirror *dmirror, args.dst = dst_pfns; args.start = addr; args.end = next; - args.src_owner = NULL; + args.src_owner = dmirror->mdevice; ret = migrate_vma_setup(&args); if (ret) goto out; diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index bdfa95ac9a7d..e2a36783e99d 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -881,8 +881,9 @@ TEST_F(hmm, migrate) }

/* - * Migrate anonymous memory to device private memory and fault it back to system - * memory. + * Migrate anonymous memory to device private memory and fault some of it back + * to system memory, then try migrating the resulting mix of system and device + * private memory to the device. */ TEST_F(hmm, migrate_fault) { @@ -924,8 +925,17 @@ TEST_F(hmm, migrate_fault) for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i);

- /* Fault pages back to system memory and check them. */ - for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + /* Fault half the pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / (2 * sizeof(*ptr)); ++i) + ASSERT_EQ(ptr[i], i); + + /* Migrate memory to the device again. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i);

hmm_buffer_free(buffer);

The SVM page fault handler groups faults into a range of contiguous virtual addresses and requests hmm_range_fault() to populate and return the page frame number of system memory mapped by the CPU. In preparation for supporting large pages to be mapped by the GPU, process faults one page at a time. In addition, use the hmm_range default_flags to fix a corner case where the input hmm_pfns array is not reinitialized after hmm_range_fault() returns -EBUSY and must be called again.

Signed-off-by: Ralph Campbell rcampbell@nvidia.com --- drivers/gpu/drm/nouveau/nouveau_svm.c | 199 +++++++++----------------- 1 file changed, 66 insertions(+), 133 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index ba9f9359c30e..665dede69bd1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -516,7 +516,7 @@ static const struct mmu_interval_notifier_ops nouveau_svm_mni_ops = { static void nouveau_hmm_convert_pfn(struct nouveau_drm *drm, struct hmm_range *range, u64 *ioctl_addr) { - unsigned long i, npages; + struct page *page;

/* * The ioctl_addr prepared here is passed through nvif_object_ioctl() @@ -525,42 +525,38 @@ static void nouveau_hmm_convert_pfn(struct nouveau_drm *drm, * This is all just encoding the internal hmm representation into a * different nouveau internal representation. */ - npages = (range->end - range->start) >> PAGE_SHIFT; - for (i = 0; i < npages; ++i) { - struct page *page; - - if (!(range->hmm_pfns[i] & HMM_PFN_VALID)) { - ioctl_addr[i] = 0; - continue; - } - - page = hmm_pfn_to_page(range->hmm_pfns[i]); - if (is_device_private_page(page)) - ioctl_addr[i] = nouveau_dmem_page_addr(page) | - NVIF_VMM_PFNMAP_V0_V | - NVIF_VMM_PFNMAP_V0_VRAM; - else - ioctl_addr[i] = page_to_phys(page) | - NVIF_VMM_PFNMAP_V0_V | - NVIF_VMM_PFNMAP_V0_HOST; - if (range->hmm_pfns[i] & HMM_PFN_WRITE) - ioctl_addr[i] |= NVIF_VMM_PFNMAP_V0_W; + if (!(range->hmm_pfns[0] & HMM_PFN_VALID)) { + ioctl_addr[0] = 0; + return; } + + page = hmm_pfn_to_page(range->hmm_pfns[0]); + if (is_device_private_page(page)) + ioctl_addr[0] = nouveau_dmem_page_addr(page) | + NVIF_VMM_PFNMAP_V0_V | + NVIF_VMM_PFNMAP_V0_VRAM; + else + ioctl_addr[0] = page_to_phys(page) | + NVIF_VMM_PFNMAP_V0_V | + NVIF_VMM_PFNMAP_V0_HOST; + if (range->hmm_pfns[0] & HMM_PFN_WRITE) + ioctl_addr[0] |= NVIF_VMM_PFNMAP_V0_W; }

static int nouveau_range_fault(struct nouveau_svmm *svmm, struct nouveau_drm *drm, void *data, u32 size, - unsigned long hmm_pfns[], u64 *ioctl_addr, + u64 *ioctl_addr, unsigned long hmm_flags, struct svm_notifier *notifier) { unsigned long timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); /* Have HMM fault pages within the fault window to the GPU. */ + unsigned long hmm_pfns[1]; struct hmm_range range = { .notifier = &notifier->notifier, .start = notifier->notifier.interval_tree.start, .end = notifier->notifier.interval_tree.last + 1, - .pfn_flags_mask = HMM_PFN_REQ_FAULT | HMM_PFN_REQ_WRITE, + .default_flags = hmm_flags, .hmm_pfns = hmm_pfns, }; struct mm_struct *mm = notifier->notifier.mm; @@ -575,11 +571,6 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm, ret = hmm_range_fault(&range); mmap_read_unlock(mm); if (ret) { - /* - * FIXME: the input PFN_REQ flags are destroyed on - * -EBUSY, we need to regenerate them, also for the - * other continue below - */ if (ret == -EBUSY) continue; return ret; @@ -614,17 +605,12 @@ nouveau_svm_fault(struct nvif_notify *notify) struct nvif_object *device = &svm->drm->client.device.object; struct nouveau_svmm *svmm; struct { - struct { - struct nvif_ioctl_v0 i; - struct nvif_ioctl_mthd_v0 m; - struct nvif_vmm_pfnmap_v0 p; - } i; - u64 phys[16]; + struct nouveau_pfnmap_args i; + u64 phys[1]; } args; - unsigned long hmm_pfns[ARRAY_SIZE(args.phys)]; - struct vm_area_struct *vma; + unsigned long hmm_flags; u64 inst, start, limit; - int fi, fn, pi, fill; + int fi, fn; int replay = 0, ret;

/* Parse available fault buffer entries into a cache, and update @@ -691,66 +677,53 @@ nouveau_svm_fault(struct nvif_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 invalid. + /* + * Prepare the GPU-side update of all pages within the + * fault window, determining required pages and access + * permissions based on pending faults. */ - mmap_read_lock(mm); - vma = find_vma_intersection(mm, start, limit); - if (!vma) { - SVMM_ERR(svmm, "wndw %016llx-%016llx", start, limit); - mmap_read_unlock(mm); - mmput(mm); - nouveau_svm_fault_cancel_fault(svm, buffer->fault[fi]); - continue; + args.i.p.addr = start; + args.i.p.page = PAGE_SHIFT; + args.i.p.size = PAGE_SIZE; + /* + * Determine required permissions based on GPU fault + * access flags. + * XXX: atomic? + */ + switch (buffer->fault[fi]->access) { + case 0: /* READ. */ + hmm_flags = HMM_PFN_REQ_FAULT; + break; + case 3: /* PREFETCH. */ + hmm_flags = 0; + break; + default: + hmm_flags = HMM_PFN_REQ_FAULT | HMM_PFN_REQ_WRITE; + break; } - start = max_t(u64, start, vma->vm_start); - limit = min_t(u64, limit, vma->vm_end); - mmap_read_unlock(mm); - SVMM_DBG(svmm, "wndw %016llx-%016llx", start, limit);

- if (buffer->fault[fi]->addr != start) { - SVMM_ERR(svmm, "addr %016llx", buffer->fault[fi]->addr); - mmput(mm); + mm = svmm->notifier.mm; + if (!mmget_not_zero(mm)) { nouveau_svm_fault_cancel_fault(svm, buffer->fault[fi]); continue; }

- /* Prepare the GPU-side update of all pages within the - * fault window, determining required pages and access - * permissions based on pending faults. - */ - args.i.p.page = PAGE_SHIFT; - args.i.p.addr = start; - for (fn = fi, pi = 0;;) { - /* Determine required permissions based on GPU fault - * access flags. - *XXX: atomic? - */ - switch (buffer->fault[fn]->access) { - case 0: /* READ. */ - hmm_pfns[pi++] = HMM_PFN_REQ_FAULT; - break; - case 3: /* PREFETCH. */ - hmm_pfns[pi++] = 0; - break; - default: - hmm_pfns[pi++] = HMM_PFN_REQ_FAULT | - HMM_PFN_REQ_WRITE; - break; - } - args.i.p.size = pi << PAGE_SHIFT; + notifier.svmm = svmm; + ret = mmu_interval_notifier_insert(&notifier.notifier, mm, + args.i.p.addr, args.i.p.size, + &nouveau_svm_mni_ops); + if (!ret) { + ret = nouveau_range_fault(svmm, svm->drm, &args, + sizeof(args), args.phys, hmm_flags, &notifier); + mmu_interval_notifier_remove(&notifier.notifier); + } + mmput(mm);

+ for (fn = fi; ++fn < buffer->fault_nr; ) { /* It's okay to skip over duplicate addresses from the * same SVMM as faults are ordered by access type such * that only the first one needs to be handled. @@ -758,61 +731,21 @@ nouveau_svm_fault(struct nvif_notify *notify) * ie. WRITE faults appear first, thus any handling of * pending READ faults will already be satisfied. */ - while (++fn < buffer->fault_nr && - buffer->fault[fn]->svmm == svmm && - buffer->fault[fn ]->addr == - buffer->fault[fn - 1]->addr); - - /* If the next fault is outside the window, or all GPU - * faults have been dealt with, we're done here. - */ - if (fn >= buffer->fault_nr || - buffer->fault[fn]->svmm != svmm || + if (buffer->fault[fn]->svmm != svmm || buffer->fault[fn]->addr >= limit) break; - - /* Fill in the gap between this fault and the next. */ - fill = (buffer->fault[fn ]->addr - - buffer->fault[fn - 1]->addr) >> PAGE_SHIFT; - while (--fill) - hmm_pfns[pi++] = 0; }

- SVMM_DBG(svmm, "wndw %016llx-%016llx covering %d fault(s)", - args.i.p.addr, - args.i.p.addr + args.i.p.size, fn - fi); - - notifier.svmm = svmm; - ret = mmu_interval_notifier_insert(&notifier.notifier, - svmm->notifier.mm, - args.i.p.addr, args.i.p.size, - &nouveau_svm_mni_ops); - if (!ret) { - ret = nouveau_range_fault( - svmm, svm->drm, &args, - sizeof(args.i) + pi * sizeof(args.phys[0]), - hmm_pfns, args.phys, &notifier); - mmu_interval_notifier_remove(&notifier.notifier); - } - mmput(mm); + /* If handling failed completely, cancel all faults. */ + if (ret) { + while (fi < fn) { + struct nouveau_svm_fault *fault = + buffer->fault[fi++];

- /* Cancel any faults in the window whose pages didn't manage - * to keep their valid bit, or stay writeable when required. - * - * If handling failed completely, cancel all faults. - */ - while (fi < fn) { - struct nouveau_svm_fault *fault = buffer->fault[fi++]; - pi = (fault->addr - args.i.p.addr) >> PAGE_SHIFT; - if (ret || - !(args.phys[pi] & NVIF_VMM_PFNMAP_V0_V) || - (!(args.phys[pi] & NVIF_VMM_PFNMAP_V0_W) && - fault->access != 0 && fault->access != 3)) { nouveau_svm_fault_cancel_fault(svm, fault); - continue; } + } else replay++; - } }

/* Issue fault replay to the GPU. */

Nouveau currently only supports mapping PAGE_SIZE sized pages of system memory when shared virtual memory (SVM) is enabled. Use the new HMM_PFN_COMPOUND flag that hmm_range_fault() returns to support mapping system memory pages larger than PAGE_SIZE.

Signed-off-by: Ralph Campbell rcampbell@nvidia.com --- drivers/gpu/drm/nouveau/nouveau_svm.c | 47 ++++++++++++++----- .../gpu/drm/nouveau/nvkm/subdev/mmu/base.c | 4 ++ .../gpu/drm/nouveau/nvkm/subdev/mmu/priv.h | 2 + drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c | 8 ++-- .../drm/nouveau/nvkm/subdev/mmu/vmmgp100.c | 29 ++++++++---- 5 files changed, 66 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 665dede69bd1..a27625f3c5f9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -514,38 +514,51 @@ static const struct mmu_interval_notifier_ops nouveau_svm_mni_ops = { };

static void nouveau_hmm_convert_pfn(struct nouveau_drm *drm, - struct hmm_range *range, u64 *ioctl_addr) + struct hmm_range *range, + struct nouveau_pfnmap_args *args) { struct page *page;

/* - * The ioctl_addr prepared here is passed through nvif_object_ioctl() + * The address prepared here is passed through nvif_object_ioctl() * to an eventual DMA map in something like gp100_vmm_pgt_pfn() * * This is all just encoding the internal hmm representation into a * different nouveau internal representation. */ if (!(range->hmm_pfns[0] & HMM_PFN_VALID)) { - ioctl_addr[0] = 0; + args->p.phys[0] = 0; return; }

page = hmm_pfn_to_page(range->hmm_pfns[0]); + /* + * Only map compound pages to the GPU if the CPU is also mapping the + * page as a compound page. Otherwise, the PTE protections might not be + * consistent (e.g., CPU only maps part of a compound page). + */ + if (range->hmm_pfns[0] & HMM_PFN_COMPOUND) { + page = compound_head(page); + args->p.page = page_shift(page); + args->p.size = 1UL << args->p.page; + args->p.addr &= ~(args->p.size - 1); + } if (is_device_private_page(page)) - ioctl_addr[0] = nouveau_dmem_page_addr(page) | + args->p.phys[0] = nouveau_dmem_page_addr(page) | NVIF_VMM_PFNMAP_V0_V | NVIF_VMM_PFNMAP_V0_VRAM; else - ioctl_addr[0] = page_to_phys(page) | + args->p.phys[0] = page_to_phys(page) | NVIF_VMM_PFNMAP_V0_V | NVIF_VMM_PFNMAP_V0_HOST; if (range->hmm_pfns[0] & HMM_PFN_WRITE) - ioctl_addr[0] |= NVIF_VMM_PFNMAP_V0_W; + args->p.phys[0] |= NVIF_VMM_PFNMAP_V0_W; }

static int nouveau_range_fault(struct nouveau_svmm *svmm, - struct nouveau_drm *drm, void *data, u32 size, - u64 *ioctl_addr, unsigned long hmm_flags, + struct nouveau_drm *drm, + struct nouveau_pfnmap_args *args, u32 size, + unsigned long hmm_flags, struct svm_notifier *notifier) { unsigned long timeout = @@ -585,10 +598,10 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm, break; }

- nouveau_hmm_convert_pfn(drm, &range, ioctl_addr); + nouveau_hmm_convert_pfn(drm, &range, args);

svmm->vmm->vmm.object.client->super = true; - ret = nvif_object_ioctl(&svmm->vmm->vmm.object, data, size, NULL); + ret = nvif_object_ioctl(&svmm->vmm->vmm.object, args, size, NULL); svmm->vmm->vmm.object.client->super = false; mutex_unlock(&svmm->mutex);

@@ -717,12 +730,13 @@ nouveau_svm_fault(struct nvif_notify *notify) args.i.p.addr, args.i.p.size, &nouveau_svm_mni_ops); if (!ret) { - ret = nouveau_range_fault(svmm, svm->drm, &args, - sizeof(args), args.phys, hmm_flags, &notifier); + ret = nouveau_range_fault(svmm, svm->drm, &args.i, + sizeof(args), hmm_flags, &notifier); mmu_interval_notifier_remove(&notifier.notifier); } mmput(mm);

+ limit = args.i.p.addr + args.i.p.size; for (fn = fi; ++fn < buffer->fault_nr; ) { /* It's okay to skip over duplicate addresses from the * same SVMM as faults are ordered by access type such @@ -730,9 +744,16 @@ nouveau_svm_fault(struct nvif_notify *notify) * * ie. WRITE faults appear first, thus any handling of * pending READ faults will already be satisfied. + * But if a large page is mapped, make sure subsequent + * fault addresses have sufficient access permission. */ if (buffer->fault[fn]->svmm != svmm || - buffer->fault[fn]->addr >= limit) + buffer->fault[fn]->addr >= limit || + (buffer->fault[fi]->access == 0 /* READ. */ && + !(args.phys[0] & NVIF_VMM_PFNMAP_V0_V)) || + (buffer->fault[fi]->access != 0 /* READ. */ && + buffer->fault[fi]->access != 3 /* PREFETCH. */ && + !(args.phys[0] & NVIF_VMM_PFNMAP_V0_W))) break; }

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c index de91e9a26172..ecea365d72ad 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c @@ -94,6 +94,8 @@ nvkm_mmu_ptp_get(struct nvkm_mmu *mmu, u32 size, bool zero) } pt->ptp = ptp; pt->sub = true; + pt->ptei_shift = 3; + pt->page_shift = PAGE_SHIFT;

/* Sub-allocate from parent object, removing PTP from cache * if there's no more free slots left. @@ -203,6 +205,8 @@ nvkm_mmu_ptc_get(struct nvkm_mmu *mmu, u32 size, u32 align, bool zero) return NULL; pt->ptc = ptc; pt->sub = false; + pt->ptei_shift = 3; + pt->page_shift = PAGE_SHIFT;

ret = nvkm_memory_new(mmu->subdev.device, NVKM_MEM_TARGET_INST, size, align, zero, &pt->memory); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/priv.h index 479b02344271..f2162bb35bea 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/priv.h @@ -55,6 +55,8 @@ struct nvkm_mmu_pt { struct nvkm_memory *memory; bool sub; u16 base; + u8 ptei_shift; + u8 page_shift; u64 addr; struct list_head head; }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c index 67b00dcef4b8..c7581f4f313e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c @@ -562,6 +562,9 @@ nvkm_vmm_iter(struct nvkm_vmm *vmm, const struct nvkm_vmm_page *page, /* Handle PTE updates. */ if (!REF_PTES || REF_PTES(&it, pfn, ptei, ptes)) { struct nvkm_mmu_pt *pt = pgt->pt[type]; + + pt->page_shift = page->shift; + pt->ptei_shift = ilog2(desc->size); if (MAP_PTES || CLR_PTES) { if (MAP_PTES) MAP_PTES(vmm, pt, ptei, ptes, map); @@ -1204,7 +1207,6 @@ nvkm_vmm_pfn_unmap(struct nvkm_vmm *vmm, u64 addr, u64 size) /*TODO: * - Avoid PT readback (for dma_unmap etc), this might end up being dealt * with inside HMM, which would be a lot nicer for us to deal with. - * - Multiple page sizes (particularly for huge page support). * - Support for systems without a 4KiB page size. */ int @@ -1220,8 +1222,8 @@ nvkm_vmm_pfn_map(struct nvkm_vmm *vmm, u8 shift, u64 addr, u64 size, u64 *pfn) /* Only support mapping where the page size of the incoming page * array matches a page size available for direct mapping. */ - while (page->shift && page->shift != shift && - page->desc->func->pfn == NULL) + while (page->shift && (page->shift != shift || + page->desc->func->pfn == NULL)) page++;

if (!page->shift || !IS_ALIGNED(addr, 1ULL << shift) || diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c index d86287565542..94507cb2cf75 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c @@ -39,12 +39,15 @@ gp100_vmm_pfn_unmap(struct nvkm_vmm *vmm,

nvkm_kmap(pt->memory); while (ptes--) { - u32 datalo = nvkm_ro32(pt->memory, pt->base + ptei * 8 + 0); - u32 datahi = nvkm_ro32(pt->memory, pt->base + ptei * 8 + 4); + u32 datalo = nvkm_ro32(pt->memory, + pt->base + (ptei << pt->ptei_shift) + 0); + u32 datahi = nvkm_ro32(pt->memory, + pt->base + (ptei << pt->ptei_shift) + 4); u64 data = (u64)datahi << 32 | datalo; if ((data & (3ULL << 1)) != 0) { addr = (data >> 8) << 12; - dma_unmap_page(dev, addr, PAGE_SIZE, DMA_BIDIRECTIONAL); + dma_unmap_page(dev, addr, 1UL << pt->page_shift, + DMA_BIDIRECTIONAL); } ptei++; } @@ -58,11 +61,14 @@ gp100_vmm_pfn_clear(struct nvkm_vmm *vmm, bool dma = false; nvkm_kmap(pt->memory); while (ptes--) { - u32 datalo = nvkm_ro32(pt->memory, pt->base + ptei * 8 + 0); - u32 datahi = nvkm_ro32(pt->memory, pt->base + ptei * 8 + 4); + u32 datalo = nvkm_ro32(pt->memory, + pt->base + (ptei << pt->ptei_shift) + 0); + u32 datahi = nvkm_ro32(pt->memory, + pt->base + (ptei << pt->ptei_shift) + 4); u64 data = (u64)datahi << 32 | datalo; if ((data & BIT_ULL(0)) && (data & (3ULL << 1)) != 0) { - VMM_WO064(pt, vmm, ptei * 8, data & ~BIT_ULL(0)); + VMM_WO064(pt, vmm, ptei << pt->ptei_shift, + data & ~BIT_ULL(0)); dma = true; } ptei++; @@ -87,7 +93,8 @@ gp100_vmm_pgt_pfn(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt, if (!(*map->pfn & NVKM_VMM_PFN_VRAM)) { addr = *map->pfn >> NVKM_VMM_PFN_ADDR_SHIFT; addr = dma_map_page(dev, pfn_to_page(addr), 0, - PAGE_SIZE, DMA_BIDIRECTIONAL); + 1UL << pt->page_shift, + DMA_BIDIRECTIONAL); if (!WARN_ON(dma_mapping_error(dev, addr))) { data |= addr >> 4; data |= 2ULL << 1; /* SYSTEM_COHERENT_MEMORY. */ @@ -99,7 +106,7 @@ gp100_vmm_pgt_pfn(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt, data |= BIT_ULL(0); /* VALID. */ }

- VMM_WO064(pt, vmm, ptei++ * 8, data); + VMM_WO064(pt, vmm, ptei++ << pt->ptei_shift, data); map->pfn++; } nvkm_done(pt->memory); @@ -264,6 +271,9 @@ gp100_vmm_desc_pd0 = { .sparse = gp100_vmm_pd0_sparse, .pde = gp100_vmm_pd0_pde, .mem = gp100_vmm_pd0_mem, + .pfn = gp100_vmm_pgt_pfn, + .pfn_clear = gp100_vmm_pfn_clear, + .pfn_unmap = gp100_vmm_pfn_unmap, };

static void @@ -286,6 +296,9 @@ gp100_vmm_desc_pd1 = { .unmap = gf100_vmm_pgt_unmap, .sparse = gp100_vmm_pgt_sparse, .pde = gp100_vmm_pd1_pde, + .pfn = gp100_vmm_pgt_pfn, + .pfn_clear = gp100_vmm_pfn_clear, + .pfn_unmap = gp100_vmm_pfn_unmap, };

const struct nvkm_vmm_desc

When migrating system memory to device private memory, if the source address range is a valid VMA range and there is no memory or a zero page, the source PFN array is marked as valid but with no PFN. This lets the device driver allocate private memory and clear it, then insert the new device private struct page into the CPU's page tables when migrate_vma_pages() is called. migrate_vma_pages() only inserts the new page if the VMA is an anonymous range. There is no point in telling the device driver to allocate device private memory and then throwing it away. Instead, mark the source PFN array entries as not migrating to avoid this overhead.

Signed-off-by: Ralph Campbell rcampbell@nvidia.com --- mm/migrate.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c index 24535281cea3..87c52e0ee580 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2178,9 +2178,13 @@ static int migrate_vma_collect_hole(unsigned long start, { struct migrate_vma *migrate = walk->private; unsigned long addr; + unsigned long flags; + + /* Only allow populating anonymous memory */ + flags = vma_is_anonymous(walk->vma) ? MIGRATE_PFN_MIGRATE : 0;

for (addr = start; addr < end; addr += PAGE_SIZE) { - migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE; + migrate->src[migrate->npages] = flags; migrate->dst[migrate->npages] = 0; migrate->npages++; migrate->cpages++; @@ -2748,7 +2752,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, pte_t *ptep;

/* Only allow populating anonymous memory */ - if (!vma_is_anonymous(vma)) + if (WARN_ON_ONCE(!vma_is_anonymous(vma))) goto abort;

pgdp = pgd_offset(mm, addr);

Add some basic stand alone self tests for migrating system memory to device private memory and back.

Signed-off-by: Ralph Campbell rcampbell@nvidia.com --- lib/test_hmm.c | 323 ++++++++++++++++++++----- tools/testing/selftests/vm/hmm-tests.c | 292 ++++++++++++++++++++++ 2 files changed, 560 insertions(+), 55 deletions(-)

diff --git a/lib/test_hmm.c b/lib/test_hmm.c index db5d2e8d7420..f4e2e8731366 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -92,6 +92,7 @@ struct dmirror_device { unsigned long calloc; unsigned long cfree; struct page *free_pages; + struct page *free_huge_pages; spinlock_t lock; /* protects the above */ };

@@ -443,6 +444,7 @@ static int dmirror_write(struct dmirror *dmirror, struct hmm_dmirror_cmd *cmd) }

static bool dmirror_allocate_chunk(struct dmirror_device *mdevice, + bool is_huge, struct page **ppage) { struct dmirror_chunk *devmem; @@ -502,16 +504,39 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice, pfn_first, pfn_last);

spin_lock(&mdevice->lock); - for (pfn = pfn_first; pfn < pfn_last; pfn++) { + for (pfn = pfn_first; pfn < pfn_last; ) { struct page *page = pfn_to_page(pfn);

+#ifdef CONFIG_TRANSPARENT_HUGEPAGE + /* + * Check for PMD aligned PFN and create a huge page. + * Check for "< pfn_last - 1" so that the last two huge pages + * are used for normal pages. + */ + if ((pfn & (HPAGE_PMD_NR - 1)) == 0 && + pfn + HPAGE_PMD_NR < pfn_last - 1) { + prep_compound_page(page, HPAGE_PMD_ORDER); + page->zone_device_data = mdevice->free_huge_pages; + mdevice->free_huge_pages = page; + pfn += HPAGE_PMD_NR; + percpu_ref_put_many(page->pgmap->ref, HPAGE_PMD_NR - 1); + continue; + } +#endif page->zone_device_data = mdevice->free_pages; mdevice->free_pages = page; + pfn++; } if (ppage) { - *ppage = mdevice->free_pages; - mdevice->free_pages = (*ppage)->zone_device_data; - mdevice->calloc++; + if (is_huge) { + *ppage = mdevice->free_huge_pages; + mdevice->free_huge_pages = (*ppage)->zone_device_data; + mdevice->calloc += 1UL << compound_order(*ppage); + } else { + *ppage = mdevice->free_pages; + mdevice->free_pages = (*ppage)->zone_device_data; + mdevice->calloc++; + } } spin_unlock(&mdevice->lock);

@@ -527,7 +552,8 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice, return false; }

-static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice) +static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice, + bool is_huge) { struct page *dpage = NULL; struct page *rpage; @@ -542,17 +568,40 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)

spin_lock(&mdevice->lock);

- if (mdevice->free_pages) { + if (is_huge && mdevice->free_huge_pages) { + dpage = mdevice->free_huge_pages; + mdevice->free_huge_pages = dpage->zone_device_data; + mdevice->calloc += 1UL << compound_order(dpage); + spin_unlock(&mdevice->lock); + } else if (!is_huge && mdevice->free_pages) { dpage = mdevice->free_pages; mdevice->free_pages = dpage->zone_device_data; mdevice->calloc++; spin_unlock(&mdevice->lock); } else { spin_unlock(&mdevice->lock); - if (!dmirror_allocate_chunk(mdevice, &dpage)) + if (!dmirror_allocate_chunk(mdevice, is_huge, &dpage)) goto error; }

+ if (is_huge) { + unsigned int nr_pages = 1U << compound_order(dpage); + unsigned int i; + struct page **tpage; + + tpage = kmap(rpage); + for (i = 0; i < nr_pages; i++, tpage++) { + *tpage = alloc_page(GFP_HIGHUSER); + if (!*tpage) { + while (i--) + __free_page(*--tpage); + kunmap(rpage); + goto error; + } + } + kunmap(rpage); + } + dpage->zone_device_data = rpage; get_page(dpage); lock_page(dpage); @@ -569,16 +618,17 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args, struct dmirror_device *mdevice = dmirror->mdevice; const unsigned long *src = args->src; unsigned long *dst = args->dst; - unsigned long addr; + unsigned long end_pfn = args->end >> PAGE_SHIFT; + unsigned long pfn;

- for (addr = args->start; addr < args->end; addr += PAGE_SIZE, - src++, dst++) { + for (pfn = args->start >> PAGE_SHIFT; pfn < end_pfn; ) { struct page *spage; struct page *dpage; struct page *rpage; + bool is_huge;

if (!(*src & MIGRATE_PFN_MIGRATE)) - continue; + goto next;

/* * Note that spage might be NULL which is OK since it is an @@ -595,7 +645,6 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args, * In this case, repopulate our page table. */ if (spage && is_zone_device_page(spage)) { - unsigned long pfn = addr >> PAGE_SHIFT; void *entry;

mutex_lock(&dmirror->mutex); @@ -604,18 +653,14 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args, entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE); xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC); mutex_unlock(&dmirror->mutex); - continue; + goto next; }

- dpage = dmirror_devmem_alloc_page(mdevice); + /* This flag is only set if a whole huge page is migrated. */ + is_huge = *src & MIGRATE_PFN_COMPOUND; + dpage = dmirror_devmem_alloc_page(mdevice, is_huge); if (!dpage) - continue; - - rpage = dpage->zone_device_data; - if (spage) - copy_highpage(rpage, spage); - else - clear_highpage(rpage); + goto next;

/* * Normally, a device would use the page->zone_device_data to @@ -623,6 +668,7 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args, * the simulated device memory and that page holds the pointer * to the mirror. */ + rpage = dpage->zone_device_data; rpage->zone_device_data = dmirror;

*dst = migrate_pfn(page_to_pfn(dpage)) | @@ -630,6 +676,37 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args, if ((*src & MIGRATE_PFN_WRITE) || (!spage && args->vma->vm_flags & VM_WRITE)) *dst |= MIGRATE_PFN_WRITE; + + if (is_huge) { + struct page **tpage; + unsigned int order = compound_order(dpage); + unsigned long endp = pfn + (1UL << order); + + *dst |= MIGRATE_PFN_COMPOUND; + tpage = kmap(rpage); + while (pfn < endp) { + if (spage) { + copy_highpage(*tpage, spage); + spage++; + } else + clear_highpage(*tpage); + tpage++; + pfn++; + src++; + dst++; + } + kunmap(rpage); + continue; + } + + if (spage) + copy_highpage(rpage, spage); + else + clear_highpage(rpage); +next: + pfn++; + src++; + dst++; } }

@@ -641,38 +718,76 @@ static int dmirror_migrate_finalize_and_map(struct migrate_vma *args, const unsigned long *src = args->src; const unsigned long *dst = args->dst; unsigned long pfn; + int ret = 0;

/* Map the migrated pages into the device's page tables. */ mutex_lock(&dmirror->mutex);

- for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++, - src++, dst++) { + for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); ) { + unsigned long mpfn; struct page *dpage; + struct page *rpage; void *entry;

if (!(*src & MIGRATE_PFN_MIGRATE)) - continue; + goto next;

- dpage = migrate_pfn_to_page(*dst); + mpfn = *dst; + dpage = migrate_pfn_to_page(mpfn); if (!dpage) - continue; + goto next;

/* * Store the page that holds the data so the page table * doesn't have to deal with ZONE_DEVICE private pages. */ - entry = dpage->zone_device_data; - if (*dst & MIGRATE_PFN_WRITE) + rpage = dpage->zone_device_data; + if (mpfn & MIGRATE_PFN_COMPOUND) { + struct page **tpage; + unsigned int order = compound_order(dpage); + unsigned long end_pfn = pfn + (1UL << order); + + ret = 0; + tpage = kmap(rpage); + while (pfn < end_pfn) { + entry = *tpage; + if (mpfn & MIGRATE_PFN_WRITE) + entry = xa_tag_pointer(entry, + DPT_XA_TAG_WRITE); + entry = xa_store(&dmirror->pt, pfn, entry, + GFP_KERNEL); + if (xa_is_err(entry)) { + ret = xa_err(entry); + break; + } + tpage++; + pfn++; + src++; + dst++; + } + kunmap(rpage); + if (ret) + goto err; + continue; + } + + entry = rpage; + if (mpfn & MIGRATE_PFN_WRITE) entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE); entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC); if (xa_is_err(entry)) { mutex_unlock(&dmirror->mutex); return xa_err(entry); } +next: + pfn++; + src++; + dst++; }

+err: mutex_unlock(&dmirror->mutex); - return 0; + return ret; }

static int dmirror_migrate(struct dmirror *dmirror, @@ -682,8 +797,8 @@ static int dmirror_migrate(struct dmirror *dmirror, unsigned long size = cmd->npages << PAGE_SHIFT; struct mm_struct *mm = dmirror->notifier.mm; struct vm_area_struct *vma; - unsigned long src_pfns[64]; - unsigned long dst_pfns[64]; + unsigned long *src_pfns; + unsigned long *dst_pfns; struct dmirror_bounce bounce; struct migrate_vma args; unsigned long next; @@ -698,6 +813,17 @@ static int dmirror_migrate(struct dmirror *dmirror, if (!mmget_not_zero(mm)) return -EINVAL;

+ src_pfns = kmalloc_array(PTRS_PER_PTE, sizeof(*src_pfns), GFP_KERNEL); + if (!src_pfns) { + ret = -ENOMEM; + goto out_put; + } + dst_pfns = kmalloc_array(PTRS_PER_PTE, sizeof(*dst_pfns), GFP_KERNEL); + if (!dst_pfns) { + ret = -ENOMEM; + goto out_free_src; + } + mmap_read_lock(mm); for (addr = start; addr < end; addr = next) { vma = find_vma(mm, addr); @@ -706,7 +832,7 @@ static int dmirror_migrate(struct dmirror *dmirror, ret = -EINVAL; goto out; } - next = min(end, addr + (ARRAY_SIZE(src_pfns) << PAGE_SHIFT)); + next = min(end, addr + (PTRS_PER_PTE << PAGE_SHIFT)); if (next > vma->vm_end) next = vma->vm_end;

@@ -725,6 +851,8 @@ static int dmirror_migrate(struct dmirror *dmirror, dmirror_migrate_finalize_and_map(&args, dmirror); migrate_vma_finalize(&args); } + kfree(dst_pfns); + kfree(src_pfns); mmap_read_unlock(mm); mmput(mm);

@@ -746,6 +874,10 @@ static int dmirror_migrate(struct dmirror *dmirror,

out: mmap_read_unlock(mm); + kfree(dst_pfns); +out_free_src: + kfree(src_pfns); +out_put: mmput(mm); return ret; } @@ -986,18 +1118,37 @@ static const struct file_operations dmirror_fops = {

static void dmirror_devmem_free(struct page *page) { - struct page *rpage = page->zone_device_data; + struct page *rpage = compound_head(page)->zone_device_data; + unsigned int order = compound_order(page); + unsigned int nr_pages = 1U << order; struct dmirror_device *mdevice;

- if (rpage) + if (rpage) { + if (order) { + unsigned int i; + struct page **tpage; + void *kaddr; + + kaddr = kmap_atomic(rpage); + tpage = kaddr; + for (i = 0; i < nr_pages; i++, tpage++) + __free_page(*tpage); + kunmap_atomic(kaddr); + } __free_page(rpage); + }

mdevice = dmirror_page_to_device(page);

spin_lock(&mdevice->lock); - mdevice->cfree++; - page->zone_device_data = mdevice->free_pages; - mdevice->free_pages = page; + if (order) { + page->zone_device_data = mdevice->free_huge_pages; + mdevice->free_huge_pages = page; + } else { + page->zone_device_data = mdevice->free_pages; + mdevice->free_pages = page; + } + mdevice->cfree += nr_pages; spin_unlock(&mdevice->lock); }

@@ -1010,24 +1161,51 @@ static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args, unsigned long end = args->end; unsigned long addr;

- for (addr = start; addr < end; addr += PAGE_SIZE, - src++, dst++) { - struct page *dpage, *spage; + for (addr = start; addr < end; ) { + struct page *spage, *dpage; + unsigned int order = 0; + unsigned int nr_pages = 1; + unsigned int i;

spage = migrate_pfn_to_page(*src); if (!spage || !(*src & MIGRATE_PFN_MIGRATE)) - continue; + goto next; + order = compound_order(spage); + nr_pages = 1U << order; + /* The source page is the ZONE_DEVICE private page. */ spage = spage->zone_device_data;

- dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr); - if (!dpage) - continue; + if (order) + dpage = alloc_transhugepage(args->vma, addr); + else + dpage = alloc_pages_vma(GFP_HIGHUSER_MOVABLE, 0, + args->vma, addr, + numa_node_id(), false); + + if (!dpage || compound_order(dpage) != order) + return VM_FAULT_OOM;

lock_page(dpage); - copy_highpage(dpage, spage); *dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; if (*src & MIGRATE_PFN_WRITE) *dst |= MIGRATE_PFN_WRITE; + if (order) { + struct page **tpage; + + *dst |= MIGRATE_PFN_COMPOUND; + tpage = kmap(spage); + for (i = 0; i < nr_pages; i++) { + copy_highpage(dpage, *tpage); + tpage++; + dpage++; + } + kunmap(spage); + } else + copy_highpage(dpage, spage); +next: + addr += PAGE_SIZE << order; + src += nr_pages; + dst += nr_pages; } return 0; } @@ -1037,39 +1215,74 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf) struct migrate_vma args; unsigned long src_pfns; unsigned long dst_pfns; + struct page *page; struct page *rpage; + unsigned int order; struct dmirror *dmirror; vm_fault_t ret;

+ page = compound_head(vmf->page); + order = compound_order(page); + /* * Normally, a device would use the page->zone_device_data to point to * the mirror but here we use it to hold the page for the simulated * device memory and that page holds the pointer to the mirror. */ - rpage = vmf->page->zone_device_data; + rpage = page->zone_device_data; dmirror = rpage->zone_device_data;

- /* FIXME demonstrate how we can adjust migrate range */ + if (order) { + args.start = vmf->address & (PAGE_MASK << order); + args.end = args.start + (PAGE_SIZE << order); + args.src = kcalloc(PTRS_PER_PTE, sizeof(*args.src), + GFP_KERNEL); + if (!args.src) + return VM_FAULT_OOM; + args.dst = kcalloc(PTRS_PER_PTE, sizeof(*args.dst), + GFP_KERNEL); + if (!args.dst) { + ret = VM_FAULT_OOM; + goto error_src; + } + } else { + args.start = vmf->address; + args.end = args.start + PAGE_SIZE; + args.src = &src_pfns; + args.dst = &dst_pfns; + } args.vma = vmf->vma; - args.start = vmf->address; - args.end = args.start + PAGE_SIZE; - args.src = &src_pfns; - args.dst = &dst_pfns; args.src_owner = dmirror->mdevice;

- if (migrate_vma_setup(&args)) - return VM_FAULT_SIGBUS; + if (migrate_vma_setup(&args)) { + ret = VM_FAULT_SIGBUS; + goto error_dst; + }

ret = dmirror_devmem_fault_alloc_and_copy(&args, dmirror->mdevice); if (ret) - return ret; + goto error_fin; migrate_vma_pages(&args); /* * No device finalize step is needed since migrate_vma_setup() will * have already invalidated the device page table. */ migrate_vma_finalize(&args); + if (order) { + kfree(args.dst); + kfree(args.src); + } return 0; + +error_fin: + migrate_vma_finalize(&args); +error_dst: + if (args.dst != &dst_pfns) + kfree(args.dst); +error_src: + if (args.src != &src_pfns) + kfree(args.src); + return ret; }

static const struct dev_pagemap_ops dmirror_devmem_ops = { @@ -1093,7 +1306,7 @@ static int dmirror_device_init(struct dmirror_device *mdevice, int id) return ret;

/* Build a list of free ZONE_DEVICE private struct pages */ - dmirror_allocate_chunk(mdevice, NULL); + dmirror_allocate_chunk(mdevice, false, NULL);

return 0; } diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index e0fa864d03fa..d58a6f5280b7 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -1442,4 +1442,296 @@ TEST_F(hmm2, double_map) hmm_buffer_free(buffer); }

+/* + * Migrate private anonymous huge empty page. + */ +TEST_F(hmm, migrate_anon_huge_empty) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + void *old_ptr; + void *map; + int *ptr; + int ret; + + size = TWOMEG; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = 2 * size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + memset(buffer->mirror, 0xFF, size); + + buffer->ptr = mmap(NULL, 2 * size, + PROT_READ, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + npages = size >> self->page_shift; + map = (void *)ALIGN((uintptr_t)buffer->ptr, size); + ret = madvise(map, size, MADV_HUGEPAGE); + ASSERT_EQ(ret, 0); + old_ptr = buffer->ptr; + buffer->ptr = map; + + /* Migrate memory to device. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], 0); + + buffer->ptr = old_ptr; + hmm_buffer_free(buffer); +} + +/* + * Migrate private anonymous huge zero page. + */ +TEST_F(hmm, migrate_anon_huge_zero) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + void *old_ptr; + void *map; + int *ptr; + int ret; + int val; + + size = TWOMEG; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = 2 * size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + memset(buffer->mirror, 0xFF, size); + + buffer->ptr = mmap(NULL, 2 * size, + PROT_READ, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + npages = size >> self->page_shift; + map = (void *)ALIGN((uintptr_t)buffer->ptr, size); + ret = madvise(map, size, MADV_HUGEPAGE); + ASSERT_EQ(ret, 0); + old_ptr = buffer->ptr; + buffer->ptr = map; + + /* Initialize a read-only zero huge page. */ + val = *(int *)buffer->ptr; + ASSERT_EQ(val, 0); + + /* Migrate memory to device. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], 0); + + /* Fault pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) { + ASSERT_EQ(ptr[i], 0); + /* If it asserts once, it probably will 500,000 times */ + if (ptr[i] != 0) + break; + } + + buffer->ptr = old_ptr; + hmm_buffer_free(buffer); +} + +/* + * Migrate private anonymous huge page. + */ +TEST_F(hmm, migrate_anon_huge) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + void *old_ptr; + void *map; + int *ptr; + int ret; + + size = TWOMEG; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = 2 * size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + memset(buffer->mirror, 0xFF, size); + + buffer->ptr = mmap(NULL, 2 * size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + npages = size >> self->page_shift; + map = (void *)ALIGN((uintptr_t)buffer->ptr, size); + ret = madvise(map, size, MADV_HUGEPAGE); + ASSERT_EQ(ret, 0); + old_ptr = buffer->ptr; + buffer->ptr = map; + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + buffer->ptr = old_ptr; + hmm_buffer_free(buffer); +} + +/* + * Migrate private anonymous huge page and free. + */ +TEST_F(hmm, migrate_anon_huge_free) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + void *old_ptr; + void *map; + int *ptr; + int ret; + + size = TWOMEG; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = 2 * size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + memset(buffer->mirror, 0xFF, size); + + buffer->ptr = mmap(NULL, 2 * size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + npages = size >> self->page_shift; + map = (void *)ALIGN((uintptr_t)buffer->ptr, size); + ret = madvise(map, size, MADV_HUGEPAGE); + ASSERT_EQ(ret, 0); + old_ptr = buffer->ptr; + buffer->ptr = map; + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + /* Try freeing it. */ + ret = madvise(map, size, MADV_FREE); + ASSERT_EQ(ret, 0); + + buffer->ptr = old_ptr; + hmm_buffer_free(buffer); +} + +/* + * Migrate private anonymous huge page and fault back to sysmem. + */ +TEST_F(hmm, migrate_anon_huge_fault) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + void *old_ptr; + void *map; + int *ptr; + int ret; + + size = TWOMEG; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = 2 * size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + memset(buffer->mirror, 0xFF, size); + + buffer->ptr = mmap(NULL, 2 * size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + npages = size >> self->page_shift; + map = (void *)ALIGN((uintptr_t)buffer->ptr, size); + ret = madvise(map, size, MADV_HUGEPAGE); + ASSERT_EQ(ret, 0); + old_ptr = buffer->ptr; + buffer->ptr = map; + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + /* Fault pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) { + ASSERT_EQ(ptr[i], i); + /* If it asserts once, it probably will 500,000 times */ + if (ptr[i] != i) + break; + } + + buffer->ptr = old_ptr; + hmm_buffer_free(buffer); +} + TEST_HARNESS_MAIN