diff options
33 files changed, 370 insertions, 1013 deletions
diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst index 7b6eeda5a7c0..7d90964abbb0 100644 --- a/Documentation/vm/hmm.rst +++ b/Documentation/vm/hmm.rst @@ -336,33 +336,6 @@ directly using struct page for device memory which left most kernel code paths unaware of the difference. We only need to make sure that no one ever tries to map those pages from the CPU side. -HMM provides a set of helpers to register and hotplug device memory as a new -region needing a struct page. This is offered through a very simple API:: - - struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, - struct device *device, - unsigned long size); - void hmm_devmem_remove(struct hmm_devmem *devmem); - -The hmm_devmem_ops is where most of the important things are:: - - struct hmm_devmem_ops { - void (*free)(struct hmm_devmem *devmem, struct page *page); - vm_fault_t (*fault)(struct hmm_devmem *devmem, - struct vm_area_struct *vma, - unsigned long addr, - struct page *page, - unsigned flags, - pmd_t *pmdp); - }; - -The first callback (free()) happens when the last reference on a device page is -dropped. This means the device page is now free and no longer used by anyone. -The second callback happens whenever the CPU tries to access a device page -which it cannot do. This second callback must trigger a migration back to -system memory. - - Migration to and from device memory =================================== diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 2540d3b2588c..a2923c5c1982 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -131,17 +131,9 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct page *page; + struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap); int ret; - /* - * If we have an altmap then we need to skip over any reserved PFNs - * when querying the zone. - */ - page = pfn_to_page(start_pfn); - if (altmap) - page += vmem_altmap_offset(altmap); - __remove_pages(page_zone(page), start_pfn, nr_pages, altmap); /* Remove htab bolted mappings for this section of memory */ diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 0f01c7b1d217..08bbf648827b 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1213,13 +1213,9 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct page *page = pfn_to_page(start_pfn); - struct zone *zone; + struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap); + struct zone *zone = page_zone(page); - /* With altmap the first mapped page is offset from @start */ - if (altmap) - page += vmem_altmap_offset(altmap); - zone = page_zone(page); __remove_pages(zone, start_pfn, nr_pages, altmap); kernel_physical_mapping_remove(start, start + size); } diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h index b4177aafbbd1..c915889d1769 100644 --- a/drivers/dax/dax-private.h +++ b/drivers/dax/dax-private.h @@ -43,8 +43,6 @@ struct dax_region { * @target_node: effective numa node if dev_dax memory range is onlined * @dev - device core * @pgmap - pgmap for memmap setup / lifetime (driver owned) - * @ref: pgmap reference count (driver owned) - * @cmp: @ref final put completion (driver owned) */ struct dev_dax { struct dax_region *region; @@ -52,8 +50,6 @@ struct dev_dax { int target_node; struct device dev; struct dev_pagemap pgmap; - struct percpu_ref ref; - struct completion cmp; }; static inline struct dev_dax *to_dev_dax(struct device *dev) diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 8465d12fecba..1af823b2fe6b 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -14,37 +14,6 @@ #include "dax-private.h" #include "bus.h" -static struct dev_dax *ref_to_dev_dax(struct percpu_ref *ref) -{ - return container_of(ref, struct dev_dax, ref); -} - -static void dev_dax_percpu_release(struct percpu_ref *ref) -{ - struct dev_dax *dev_dax = ref_to_dev_dax(ref); - - dev_dbg(&dev_dax->dev, "%s\n", __func__); - complete(&dev_dax->cmp); -} - -static void dev_dax_percpu_exit(struct percpu_ref *ref) -{ - struct dev_dax *dev_dax = ref_to_dev_dax(ref); - - dev_dbg(&dev_dax->dev, "%s\n", __func__); - wait_for_completion(&dev_dax->cmp); - percpu_ref_exit(ref); -} - -static void dev_dax_percpu_kill(struct percpu_ref *data) -{ - struct percpu_ref *ref = data; - struct dev_dax *dev_dax = ref_to_dev_dax(ref); - - dev_dbg(&dev_dax->dev, "%s\n", __func__); - percpu_ref_kill(ref); -} - static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma, const char *func) { @@ -459,15 +428,7 @@ int dev_dax_probe(struct device *dev) return -EBUSY; } - init_completion(&dev_dax->cmp); - rc = percpu_ref_init(&dev_dax->ref, dev_dax_percpu_release, 0, - GFP_KERNEL); - if (rc) - return rc; - - dev_dax->pgmap.ref = &dev_dax->ref; - dev_dax->pgmap.kill = dev_dax_percpu_kill; - dev_dax->pgmap.cleanup = dev_dax_percpu_exit; + dev_dax->pgmap.type = MEMORY_DEVICE_DEVDAX; addr = devm_memremap_pages(dev, &dev_dax->pgmap); if (IS_ERR(addr)) return PTR_ERR(addr); diff --git a/drivers/dax/pmem/core.c b/drivers/dax/pmem/core.c index f9f51786d556..6eb6dfdf19bf 100644 --- a/drivers/dax/pmem/core.c +++ b/drivers/dax/pmem/core.c @@ -16,7 +16,7 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys) struct dev_dax *dev_dax; struct nd_namespace_io *nsio; struct dax_region *dax_region; - struct dev_pagemap pgmap = { 0 }; + struct dev_pagemap pgmap = { }; struct nd_namespace_common *ndns; struct nd_dax *nd_dax = to_nd_dax(dev); struct nd_pfn *nd_pfn = &nd_dax->nd_pfn; diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig index dba2613f7180..96b9814e6d06 100644 --- a/drivers/gpu/drm/nouveau/Kconfig +++ b/drivers/gpu/drm/nouveau/Kconfig @@ -84,11 +84,11 @@ config DRM_NOUVEAU_BACKLIGHT config DRM_NOUVEAU_SVM bool "(EXPERIMENTAL) Enable SVM (Shared Virtual Memory) support" - depends on ARCH_HAS_HMM + depends on DEVICE_PRIVATE depends on DRM_NOUVEAU + depends on HMM_MIRROR depends on STAGING - select HMM_MIRROR - select DEVICE_PRIVATE + select MIGRATE_VMA_HELPER default n help Say Y here if you want to enable experimental support for diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 40c47d6a7d78..42c026010938 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -72,7 +72,8 @@ struct nouveau_dmem_migrate { }; struct nouveau_dmem { - struct hmm_devmem *devmem; + struct nouveau_drm *drm; + struct dev_pagemap pagemap; struct nouveau_dmem_migrate migrate; struct list_head chunk_free; struct list_head chunk_full; @@ -80,6 +81,11 @@ struct nouveau_dmem { struct mutex mutex; }; +static inline struct nouveau_dmem *page_to_dmem(struct page *page) +{ + return container_of(page->pgmap, struct nouveau_dmem, pagemap); +} + struct nouveau_dmem_fault { struct nouveau_drm *drm; struct nouveau_fence *fence; @@ -96,14 +102,10 @@ struct nouveau_migrate { unsigned long dma_nr; }; -static void -nouveau_dmem_free(struct hmm_devmem *devmem, struct page *page) +static void nouveau_dmem_page_free(struct page *page) { - struct nouveau_dmem_chunk *chunk; - unsigned long idx; - - chunk = (void *)hmm_devmem_page_get_drvdata(page); - idx = page_to_pfn(page) - chunk->pfn_first; + struct nouveau_dmem_chunk *chunk = page->zone_device_data; + unsigned long idx = page_to_pfn(page) - chunk->pfn_first; /* * FIXME: @@ -148,11 +150,12 @@ nouveau_dmem_fault_alloc_and_copy(struct vm_area_struct *vma, if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE)) continue; - dpage = hmm_vma_alloc_locked_page(vma, addr); + dpage = alloc_page_vma(GFP_HIGHUSER, vma, addr); if (!dpage) { dst_pfns[i] = MIGRATE_PFN_ERROR; continue; } + lock_page(dpage); dst_pfns[i] = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; @@ -194,7 +197,7 @@ nouveau_dmem_fault_alloc_and_copy(struct vm_area_struct *vma, dst_addr = fault->dma[fault->npages++]; - chunk = (void *)hmm_devmem_page_get_drvdata(spage); + chunk = spage->zone_device_data; src_addr = page_to_pfn(spage) - chunk->pfn_first; src_addr = (src_addr << PAGE_SHIFT) + chunk->bo->bo.offset; @@ -259,29 +262,21 @@ static const struct migrate_vma_ops nouveau_dmem_fault_migrate_ops = { .finalize_and_map = nouveau_dmem_fault_finalize_and_map, }; -static vm_fault_t -nouveau_dmem_fault(struct hmm_devmem *devmem, - struct vm_area_struct *vma, - unsigned long addr, - const struct page *page, - unsigned int flags, - pmd_t *pmdp) +static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) { - struct drm_device *drm_dev = dev_get_drvdata(devmem->device); + struct nouveau_dmem *dmem = page_to_dmem(vmf->page); unsigned long src[1] = {0}, dst[1] = {0}; - struct nouveau_dmem_fault fault = {0}; + struct nouveau_dmem_fault fault = { .drm = dmem->drm }; int ret; - - /* * FIXME what we really want is to find some heuristic to migrate more * than just one page on CPU fault. When such fault happens it is very * likely that more surrounding page will CPU fault too. */ - fault.drm = nouveau_drm(drm_dev); - ret = migrate_vma(&nouveau_dmem_fault_migrate_ops, vma, addr, - addr + PAGE_SIZE, src, dst, &fault); + ret = migrate_vma(&nouveau_dmem_fault_migrate_ops, vmf->vma, + vmf->address, vmf->address + PAGE_SIZE, + src, dst, &fault); if (ret) return VM_FAULT_SIGBUS; @@ -291,10 +286,9 @@ nouveau_dmem_fault(struct hmm_devmem *devmem, return 0; } -static const struct hmm_devmem_ops -nouveau_dmem_devmem_ops = { - .free = nouveau_dmem_free, - .fault = nouveau_dmem_fault, +static const struct dev_pagemap_ops nouveau_dmem_pagemap_ops = { + .page_free = nouveau_dmem_page_free, + .migrate_to_ram = nouveau_dmem_migrate_to_ram, }; static int @@ -580,7 +574,8 @@ void nouveau_dmem_init(struct nouveau_drm *drm) { struct device *device = drm->dev->dev; - unsigned long i, size; + struct resource *res; + unsigned long i, size, pfn_first; int ret; /* This only make sense on PASCAL or newer */ @@ -590,6 +585,7 @@ nouveau_dmem_init(struct nouveau_drm *drm) if (!(drm->dmem = kzalloc(sizeof(*drm->dmem), GFP_KERNEL))) return; + drm->dmem->drm = drm; mutex_init(&drm->dmem->mutex); INIT_LIST_HEAD(&drm->dmem->chunk_free); INIT_LIST_HEAD(&drm->dmem->chunk_full); @@ -599,11 +595,8 @@ nouveau_dmem_init(struct nouveau_drm *drm) /* Initialize migration dma helpers before registering memory */ ret = nouveau_dmem_migrate_init(drm); - if (ret) { - kfree(drm->dmem); - drm->dmem = NULL; - return; - } + if (ret) + goto out_free; /* * FIXME we need some kind of policy to decide how much VRAM we @@ -611,14 +604,16 @@ nouveau_dmem_init(struct nouveau_drm *drm) * and latter if we want to do thing like over commit then we * could revisit this. */ - drm->dmem->devmem = hmm_devmem_add(&nouveau_dmem_devmem_ops, - device, size); - if (IS_ERR(drm->dmem->devmem)) { - kfree(drm->dmem); - drm->dmem = NULL; - return; - } - + res = devm_request_free_mem_region(device, &iomem_resource, size); + if (IS_ERR(res)) + goto out_free; + drm->dmem->pagemap.type = MEMORY_DEVICE_PRIVATE; + drm->dmem->pagemap.res = *res; + drm->dmem->pagemap.ops = &nouveau_dmem_pagemap_ops; + if (IS_ERR(devm_memremap_pages(device, &drm->dmem->pagemap))) + goto out_free; + + pfn_first = res->start >> PAGE_SHIFT; for (i = 0; i < (size / DMEM_CHUNK_SIZE); ++i) { struct nouveau_dmem_chunk *chunk; struct page *page; @@ -631,17 +626,19 @@ nouveau_dmem_init(struct nouveau_drm *drm) } chunk->drm = drm; - chunk->pfn_first = drm->dmem->devmem->pfn_first; - chunk->pfn_first += (i * DMEM_CHUNK_NPAGES); + chunk->pfn_first = pfn_first + (i * DMEM_CHUNK_NPAGES); list_add_tail(&chunk->list, &drm->dmem->chunk_empty); page = pfn_to_page(chunk->pfn_first); - for (j = 0; j < DMEM_CHUNK_NPAGES; ++j, ++page) { - hmm_devmem_page_set_drvdata(page, (long)chunk); - } + for (j = 0; j < DMEM_CHUNK_NPAGES; ++j, ++page) + page->zone_device_data = chunk; } NV_INFO(drm, "DMEM: registered %ldMB of device memory\n", size >> 20); + return; +out_free: + kfree(drm->dmem); + drm->dmem = NULL; } static void @@ -697,7 +694,7 @@ nouveau_dmem_migrate_alloc_and_copy(struct vm_area_struct *vma, if (!dpage || dst_pfns[i] == MIGRATE_PFN_ERROR) continue; - chunk = (void *)hmm_devmem_page_get_drvdata(dpage); + chunk = dpage->zone_device_data; dst_addr = page_to_pfn(dpage) - chunk->pfn_first; dst_addr = (dst_addr << PAGE_SHIFT) + chunk->bo->bo.offset; @@ -832,13 +829,7 @@ out: static inline bool nouveau_dmem_page(struct nouveau_drm *drm, struct page *page) { - if (!is_device_private_page(page)) - return false; - - if (drm->dmem->devmem != page->pgmap->data) - return false; - - return true; + return is_device_private_page(page) && drm->dmem == page_to_dmem(page); } void @@ -867,7 +858,7 @@ nouveau_dmem_convert_pfn(struct nouveau_drm *drm, continue; } - chunk = (void *)hmm_devmem_page_get_drvdata(page); + chunk = page->zone_device_data; addr = page_to_pfn(page) - chunk->pfn_first; addr = (addr + chunk->bo->bo.mem.start) << PAGE_SHIFT; diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index 0f81fc56bbfd..55fb6b7433ed 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -622,7 +622,6 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap) if (offset < reserve) return -EINVAL; nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns); - pgmap->altmap_valid = false; } else if (nd_pfn->mode == PFN_MODE_PMEM) { nd_pfn->npfns = PFN_SECTION_ALIGN_UP((resource_size(res) - offset) / PAGE_SIZE); @@ -634,7 +633,7 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap) memcpy(altmap, &__altmap, sizeof(*altmap)); altmap->free = PHYS_PFN(offset - reserve); altmap->alloc = 0; - pgmap->altmap_valid = true; + pgmap->flags |= PGMAP_ALTMAP_VALID; } else return -ENXIO; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 24d7fe7c74ed..e7d8cc9f41e8 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -303,24 +303,24 @@ static const struct attribute_group *pmem_attribute_groups[] = { NULL, }; -static void __pmem_release_queue(struct percpu_ref *ref) +static void pmem_pagemap_cleanup(struct dev_pagemap *pgmap) { - struct request_queue *q; + struct request_queue *q = + container_of(pgmap->ref, struct request_queue, q_usage_counter); - q = container_of(ref, typeof(*q), q_usage_counter); blk_cleanup_queue(q); } -static void pmem_release_queue(void *ref) +static void pmem_release_queue(void *pgmap) { - __pmem_release_queue(ref); + pmem_pagemap_cleanup(pgmap); } -static void pmem_freeze_queue(struct percpu_ref *ref) +static void pmem_pagemap_kill(struct dev_pagemap *pgmap) { - struct request_queue *q; + struct request_queue *q = + container_of(pgmap->ref, struct request_queue, q_usage_counter); - q = container_of(ref, typeof(*q), q_usage_counter); blk_freeze_queue_start(q); } @@ -334,26 +334,16 @@ static void pmem_release_disk(void *__pmem) put_disk(pmem->disk); } -static void pmem_release_pgmap_ops(void *__pgmap) -{ - dev_pagemap_put_ops(); -} - -static void fsdax_pagefree(struct page *page, void *data) +static void pmem_pagemap_page_free(struct page *page) { wake_up_var(&page->_refcount); } -static int setup_pagemap_fsdax(struct device *dev, struct dev_pagemap *pgmap) -{ - dev_pagemap_get_ops(); - if (devm_add_action_or_reset(dev, pmem_release_pgmap_ops, pgmap)) - return -ENOMEM; - pgmap->type = MEMORY_DEVICE_FS_DAX; - pgmap->page_free = fsdax_pagefree; - - return 0; -} +static const struct dev_pagemap_ops fsdax_pagemap_ops = { + .page_free = pmem_pagemap_page_free, + .kill = pmem_pagemap_kill, + .cleanup = pmem_pagemap_cleanup, +}; static int pmem_attach_disk(struct device *dev, struct nd_namespace_common *ndns) @@ -409,11 +399,9 @@ static int pmem_attach_disk(struct device *dev, pmem->pfn_flags = PFN_DEV; pmem->pgmap.ref = &q->q_usage_counter; - pmem->pgmap.kill = pmem_freeze_queue; - pmem->pgmap.cleanup = __pmem_release_queue; if (is_nd_pfn(dev)) { - if (setup_pagemap_fsdax(dev, &pmem->pgmap)) - return -ENOMEM; + pmem->pgmap.type = MEMORY_DEVICE_FS_DAX; + pmem->pgmap.ops = &fsdax_pagemap_ops; addr = devm_memremap_pages(dev, &pmem->pgmap); pfn_sb = nd_pfn->pfn_sb; pmem->data_offset = le64_to_cpu(pfn_sb->dataoff); @@ -424,15 +412,14 @@ static int pmem_attach_disk(struct device *dev, bb_res.start += pmem->data_offset; } else if (pmem_should_map_pages(dev)) { memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res)); - pmem->pgmap.altmap_valid = false; - if (setup_pagemap_fsdax(dev, &pmem->pgmap)) - return -ENOMEM; + pmem->pgmap.type = MEMORY_DEVICE_FS_DAX; + pmem->pgmap.ops = &fsdax_pagemap_ops; addr = devm_memremap_pages(dev, &pmem->pgmap); pmem->pfn_flags |= PFN_MAP; memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res)); } else { if (devm_add_action_or_reset(dev, pmem_release_queue, - &q->q_usage_counter)) + &pmem->pgmap)) return -ENOMEM; addr = devm_memremap(dev, pmem->phys_addr, pmem->size, ARCH_MEMREMAP_PMEM); diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index a4994aa3acc0..a3073ce16520 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -25,12 +25,6 @@ struct pci_p2pdma { bool p2pmem_published; }; -struct p2pdma_pagemap { - struct dev_pagemap pgmap; - struct percpu_ref ref; - struct completion ref_done; -}; - static ssize_t size_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -79,31 +73,6 @@ static const struct attribute_group p2pmem_group = { .name = "p2pmem", }; -static struct p2pdma_pagemap *to_p2p_pgmap(struct percpu_ref *ref) -{ - return container_of(ref, struct p2pdma_pagemap, ref); -} - -static void pci_p2pdma_percpu_release(struct percpu_ref *ref) -{ - struct p2pdma_pagemap *p2p_pgmap = to_p2p_pgmap(ref); - - complete(&p2p_pgmap->ref_done); -} - -static void pci_p2pdma_percpu_kill(struct percpu_ref *ref) -{ - percpu_ref_kill(ref); -} - -static void pci_p2pdma_percpu_cleanup(struct percpu_ref *ref) -{ - struct p2pdma_pagemap *p2p_pgmap = to_p2p_pgmap(ref); - - wait_for_completion(&p2p_pgmap->ref_done); - percpu_ref_exit(&p2p_pgmap->ref); -} - static void pci_p2pdma_release(void *data) { struct pci_dev *pdev = data; @@ -166,7 +135,6 @@ out: int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, u64 offset) { - struct p2pdma_pagemap *p2p_pgmap; struct dev_pagemap *pgmap; void *addr; int error; @@ -189,27 +157,15 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, return error; } - p2p_pgmap = devm_kzalloc(&pdev->dev, sizeof(*p2p_pgmap), GFP_KERNEL); - if (!p2p_pgmap) + pgmap = devm_kzalloc(&pdev->dev, sizeof(*pgmap), GFP_KERNEL); + if (!pgmap) return -ENOMEM; - - init_completion(&p2p_pgmap->ref_done); - error = percpu_ref_init(&p2p_pgmap->ref, - pci_p2pdma_percpu_release, 0, GFP_KERNEL); - if (error) - goto pgmap_free; - - pgmap = &p2p_pgmap->pgmap; - pgmap->res.start = pci_resource_start(pdev, bar) + offset; pgmap->res.end = pgmap->res.start + size - 1; pgmap->res.flags = pci_resource_flags(pdev, bar); - pgmap->ref = &p2p_pgmap->ref; pgmap->type = MEMORY_DEVICE_PCI_P2PDMA; pgmap->pci_p2pdma_bus_offset = pci_bus_address(pdev, bar) - pci_resource_start(pdev, bar); - pgmap->kill = pci_p2pdma_percpu_kill; - pgmap->cleanup = pci_p2pdma_percpu_cleanup; addr = devm_memremap_pages(&pdev->dev, pgmap); if (IS_ERR(addr)) { @@ -220,7 +176,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, error = gen_pool_add_owner(pdev->p2pdma->pool, (unsigned long)addr, pci_bus_address(pdev, bar) + offset, resource_size(&pgmap->res), dev_to_node(&pdev->dev), - &p2p_pgmap->ref); + pgmap->ref); if (error) goto pages_free; @@ -232,7 +188,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, pages_free: devm_memunmap_pages(&pdev->dev, pgmap); pgmap_free: - devm_kfree(&pdev->dev, p2p_pgmap); + devm_kfree(&pdev->dev, pgmap); return error; } EXPORT_SYMBOL_GPL(pci_p2pdma_add_resource); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 01d4eb0e6bd1..74d8f00b3615 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1279,7 +1279,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, if (pm->show_pfn) frame = pte_pfn(pte); flags |= PM_PRESENT; - page = _vm_normal_page(vma, addr, pte, true); + page = vm_normal_page(vma, addr, pte); if (pte_soft_dirty(pte)) flags |= PM_SOFT_DIRTY; } else if (is_swap_pte(pte)) { diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 0fa8ea34ccef..b8a08b2a10ca 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -62,7 +62,7 @@ #include <linux/kconfig.h> #include <asm/pgtable.h> -#if IS_ENABLED(CONFIG_HMM) +#ifdef CONFIG_HMM_MIRROR #include <linux/device.h> #include <linux/migrate.h> @@ -324,9 +324,6 @@ static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range, return hmm_device_entry_from_pfn(range, pfn); } - - -#if IS_ENABLED(CONFIG_HMM_MIRROR) /* * Mirroring: how to synchronize device page table with CPU page table. * @@ -550,197 +547,4 @@ static inline void hmm_mm_init(struct mm_struct *mm) static inline void hmm_mm_init(struct mm_struct *mm) {} #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ -#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC) -struct hmm_devmem; - -struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma, - unsigned long addr); - -/* - * struct hmm_devmem_ops - callback for ZONE_DEVICE memory events - * - * @free: call when refcount on page reach 1 and thus is no longer use - * @fault: call when there is a page fault to unaddressable memory - * - * Both callback happens from page_free() and page_fault() callback of struct - * dev_pagemap respectively. See include/linux/memremap.h for more details on - * those. - * - * The hmm_devmem_ops callback are just here to provide a coherent and - * uniq API to device driver and device driver should not register their - * own page_free() or page_fault() but rely on the hmm_devmem_ops call- - * back. - */ -struct hmm_devmem_ops { - /* - * free() - free a device page - * @devmem: device memory structure (see struct hmm_devmem) - * @page: pointer to struct page being freed - * - * Call back occurs whenever a device page refcount reach 1 which - * means that no one is holding any reference on the page anymore - * (ZONE_DEVICE page have an elevated refcount of 1 as default so - * that they are not release to the general page allocator). - * - * Note that callback has exclusive ownership of the page (as no - * one is holding any reference). - */ - void (*free)(struct hmm_devmem *devmem, struct page *page); - /* - * fault() - CPU page fault or get user page (GUP) - * @devmem: device memory structure (see struct hmm_devmem) - * @vma: virtual memory area containing the virtual address - * @addr: virtual address that faulted or for which there is a GUP - * @page: pointer to struct page backing virtual address (unreliable) - * @flags: FAULT_FLAG_* (see include/linux/mm.h) - * @pmdp: page middle directory - * Return: VM_FAULT_MINOR/MAJOR on success or one of VM_FAULT_ERROR - * on error - * - * The callback occurs whenever there is a CPU page fault or GUP on a - * virtual address. This means that the device driver must migrate the - * page back to regular memory (CPU accessible). - * - * The device driver is free to migrate more than one page from the - * fault() callback as an optimization. However if the device decides - * to migrate more than one page it must always priotirize the faulting - * address over the others. - * - * The struct page pointer is only given as a hint to allow quick - * lookup of internal device driver data. A concurrent migration - * might have already freed that page and the virtual address might - * no longer be backed by it. So it should not be modified by the - * callback. - * - * Note that mmap semaphore is held in read mode at least when this - * callback occurs, hence the vma is valid upon callback entry. - */ - vm_fault_t (*fault)(struct hmm_devmem *devmem, - struct vm_area_struct *vma, - unsigned long addr, - const struct page *page, - unsigned int flags, - pmd_t *pmdp); -}; - -/* - * struct hmm_devmem - track device memory - * - * @completion: completion object for device memory - * @pfn_first: first pfn for this resource (set by hmm_devmem_add()) - * @pfn_last: last pfn for this resource (set by hmm_devmem_add()) - * @resource: IO resource reserved for this chunk of memory - * @pagemap: device page map for that chunk - * @device: device to bind resource to - * @ops: memory operations callback - * @ref: per CPU refcount - * @page_fault: callback when CPU fault on an unaddressable device page - * - * This is a helper structure for device drivers that do not wish to implement - * the gory details related to hotplugging new memoy and allocating struct - * pages. - * - * Device drivers can directly use ZONE_DEVICE memory on their own if they - * wish to do so. - * - * The page_fault() callback must migrate page back, from device memory to - * system memory, so that the CPU can access it. This might fail for various - * reasons (device issues, device have been unplugged, ...). When such error - * conditions happen, the page_fault() callback must return VM_FAULT_SIGBUS and - * set the CPU page table entry to "poisoned". - * - * Note that because memory cgroup charges are transferred to the device memory, - * this should never fail due to memory restrictions. However, allocation - * of a regular system page might still fail because we are out of memory. If - * that happens, the page_fault() callback must return VM_FAULT_OOM. - * - * The page_fault() callback can also try to migrate back multiple pages in one - * chunk, as an optimization. It must, however, prioritize the faulting address - * over all the others. - */ -typedef vm_fault_t (*dev_page_fault_t)(struct vm_area_struct *vma, - unsigned long addr, - const struct page *page, - unsigned int flags, - pmd_t *pmdp); - -struct hmm_devmem { - struct completion completion; - unsigned long pfn_first; - unsigned long pfn_last; - struct resource *resource; - struct device *device; - struct dev_pagemap pagemap; - const struct hmm_devmem_ops *ops; - struct percpu_ref ref; - dev_page_fault_t page_fault; -}; - -/* - * To add (hotplug) device memory, HMM assumes that there is no real resource - * that reserves a range in the physical address space (this is intended to be - * use by unaddressable device memory). It will reserve a physical range big - * enough and allocate struct page for it. - * - * The device driver can wrap the hmm_devmem struct inside a private device - * driver struct. - */ -struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, - struct device *device, - unsigned long size); -struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops, - struct device *device, - struct resource *res); - -/* - * hmm_devmem_page_set_drvdata - set per-page driver data field - * - * @page: pointer to struct page - * @data: driver data value to set - * - * Because page can not be on lru we have an unsigned long that driver can use - * to store a per page field. This just a simple helper to do that. - */ -static inline void hmm_devmem_page_set_drvdata(struct page *page, - unsigned long data) -{ - page->hmm_data = data; -} - -/* - * hmm_devmem_page_get_drvdata - get per page driver data field - * - * @page: pointer to struct page - * Return: driver data value - */ -static inline unsigned long hmm_devmem_page_get_drvdata(const struct page *page) -{ - return page->hmm_data; -} - - -/* - * struct hmm_device - fake device to hang device memory onto - * - * @device: device struct - * @minor: device minor number - */ -struct hmm_device { - struct device device; - unsigned int minor; -}; - -/* - * A device driver that wants to handle multiple devices memory through a - * single fake device can use hmm_device to do so. This is purely a helper and - * it is not strictly needed, in order to make use of any HMM functionality. - */ -struct hmm_device *hmm_device_new(void *drvdata); -void hmm_device_put(struct hmm_device *hmm_device); -#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ -#else /* IS_ENABLED(CONFIG_HMM) */ -static inline void hmm_mm_destroy(struct mm_struct *mm) {} -static inline void hmm_mm_init(struct mm_struct *mm) {} -#endif /* IS_ENABLED(CONFIG_HMM) */ - #endif /* LINUX_HMM_H */ diff --git a/include/linux/ioport.h b/include/linux/ioport.h index da0ebaec25f0..a02b290ca08a 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -132,7 +132,6 @@ enum { IORES_DESC_PERSISTENT_MEMORY = 4, IORES_DESC_PERSISTENT_MEMORY_LEGACY = 5, IORES_DESC_DEVICE_PRIVATE_MEMORY = 6, - IORES_DESC_DEVICE_PUBLIC_MEMORY = 7, }; /* helpers to define resources */ @@ -286,6 +285,8 @@ static inline bool resource_overlaps(struct resource *r1, struct resource *r2) return (r1->start <= r2->end && r1->end >= r2->start); } +struct resource *devm_request_free_mem_region(struct device *dev, + struct resource *base, unsigned long size); #endif /* __ASSEMBLY__ */ #endif /* _LINUX_IOPORT_H */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 1732dea030b2..f8a5b2a19945 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -37,13 +37,6 @@ struct vmem_altmap { * A more complete discussion of unaddressable memory may be found in * include/linux/hmm.h and Documentation/vm/hmm.rst. * - * MEMORY_DEVICE_PUBLIC: - * Device memory that is cache coherent from device and CPU point of view. This - * is use on platform that have an advance system bus (like CAPI or CCIX). A - * driver can hotplug the device memory using ZONE_DEVICE and with that memory - * type. Any page of a process can be migrated to such memory. However no one - * should be allow to pin such memory so that it can always be evicted. - * * MEMORY_DEVICE_FS_DAX: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. In support of coordinating page @@ -52,54 +45,84 @@ struct vmem_altmap { * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). * + * MEMORY_DEVICE_DEVDAX: + * Host memory that has similar access semantics as System RAM i.e. DMA + * coherent and supports page pinning. In contrast to + * MEMORY_DEVICE_FS_DAX, this memory is access via a device-dax + * character device. + * * MEMORY_DEVICE_PCI_P2PDMA: * Device memory residing in a PCI BAR intended for use with Peer-to-Peer * transactions. */ enum memory_type { + /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1, - MEMORY_DEVICE_PUBLIC, MEMORY_DEVICE_FS_DAX, + MEMORY_DEVICE_DEVDAX, MEMORY_DEVICE_PCI_P2PDMA, }; -/* - * Additional notes about MEMORY_DEVICE_PRIVATE may be found in - * include/linux/hmm.h and Documentation/vm/hmm.rst. There is also a brief - * explanation in include/linux/memory_hotplug.h. - * - * The page_free() callback is called once the page refcount reaches 1 - * (ZONE_DEVICE pages never reach 0 refcount unless there is a refcount bug. - * This allows the device driver to implement its own memory management.) - */ -typedef void (*dev_page_free_t)(struct page *page, void *data); +struct dev_pagemap_ops { + /* + * Called once the page refcount reaches 1. (ZONE_DEVICE pages never + * reach 0 refcount unless there is a refcount bug. This allows the + * device driver to implement its own memory management.) + */ + void (*page_free)(struct page *page); + + /* + * Transition the refcount in struct dev_pagemap to the dead state. + */ + void (*kill)(struct dev_pagemap *pgmap); + + /* + * Wait for refcount in struct dev_pagemap to be idle and reap it. + */ + void (*cleanup)(struct dev_pagemap *pgmap); + + /* + * Used for private (un-addressable) device memory only. Must migrate + * the page back to a CPU accessible page. + */ + vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); +}; + +#define PGMAP_ALTMAP_VALID (1 << 0) /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings - * @page_free: free page callback when page refcount reaches 1 * @altmap: pre-allocated/reserved memory for vmemmap allocations * @res: physical address range covered by @ref * @ref: reference count that pins the devm_memremap_pages() mapping - * @kill: callback to transition @ref to the dead state - * @cleanup: callback to wait for @ref to be idle and reap it + * @internal_ref: internal reference if @ref is not provided by the caller + * @done: completion for @internal_ref * @dev: host device of the mapping for debug * @data: private data pointer for page_free() * @type: memory type: see MEMORY_* in memory_hotplug.h + * @flags: PGMAP_* flags to specify defailed behavior + * @ops: method table */ struct dev_pagemap { - dev_page_free_t page_free; struct vmem_altmap altmap; - bool altmap_valid; struct resource res; struct percpu_ref *ref; - void (*kill)(struct percpu_ref *ref); - void (*cleanup)(struct percpu_ref *ref); + struct percpu_ref internal_ref; + struct completion done; struct device *dev; - void *data; enum memory_type type; + unsigned int flags; u64 pci_p2pdma_bus_offset; + const struct dev_pagemap_ops *ops; }; +static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) +{ + if (pgmap->flags & PGMAP_ALTMAP_VALID) + return &pgmap->altmap; + return NULL; +} + #ifdef CONFIG_ZONE_DEVICE void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap); diff --git a/include/linux/mm.h b/include/linux/mm.h index dd0b5f4e1e45..2425f4167ec2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -932,8 +932,6 @@ static inline bool is_zone_device_page(const struct page *page) #endif #ifdef CONFIG_DEV_PAGEMAP_OPS -void dev_pagemap_get_ops(void); -void dev_pagemap_put_ops(void); void __put_devmap_managed_page(struct page *page); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); static inline bool put_devmap_managed_page(struct page *page) @@ -944,7 +942,6 @@ static inline bool put_devmap_managed_page(struct page *page) return false; switch (page->pgmap->type) { case MEMORY_DEVICE_PRIVATE: - case MEMORY_DEVICE_PUBLIC: case MEMORY_DEVICE_FS_DAX: __put_devmap_managed_page(page); return true; @@ -960,12 +957,6 @@ static inline bool is_device_private_page(const struct page *page) page->pgmap->type == MEMORY_DEVICE_PRIVATE; } -static inline bool is_device_public_page(const struct page *page) -{ - return is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PUBLIC; -} - #ifdef CONFIG_PCI_P2PDMA static inline bool is_pci_p2pdma_page(const struct page *page) { @@ -980,14 +971,6 @@ static inline bool is_pci_p2pdma_page(const struct page *page) #endif /* CONFIG_PCI_P2PDMA */ #else /* CONFIG_DEV_PAGEMAP_OPS */ -static inline void dev_pagemap_get_ops(void) -{ -} - -static inline void dev_pagemap_put_ops(void) -{ -} - static inline bool put_devmap_managed_page(struct page *page) { return false; @@ -998,11 +981,6 @@ static inline bool is_device_private_page(const struct page *page) return false; } -static inline bool is_device_public_page(const struct page *page) -{ - return false; -} - static inline bool is_pci_p2pdma_page(const struct page *page) { return false; @@ -1431,10 +1409,8 @@ struct zap_details { pgoff_t last_index; /* Highest page->index to unmap */ }; -struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, - pte_t pte, bool with_public_device); -#define vm_normal_page(vma, addr, pte) _vm_normal_page(vma, addr, pte, false) - +struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8ec38b11b361..8d37182f8dbe 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -158,7 +158,7 @@ struct page { struct { /* ZONE_DEVICE pages */ /** @pgmap: Points to the hosting device page map. */ struct dev_pagemap *pgmap; - unsigned long hmm_data; + void *zone_device_data; unsigned long _zd_pad_1; /* uses mapping */ }; @@ -501,7 +501,7 @@ struct mm_struct { #endif struct work_struct async_put_work; -#if IS_ENABLED(CONFIG_HMM) +#ifdef CONFIG_HMM_MIRROR /* HMM needs to track a few things per mm */ struct hmm *hmm; #endif diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 4d961668e5fc..15bdb6fe71e5 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -129,12 +129,6 @@ static inline struct page *device_private_entry_to_page(swp_entry_t entry) { return pfn_to_page(swp_offset(entry)); } - -vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, - unsigned long addr, - swp_entry_t entry, - unsigned int flags, - pmd_t *pmdp); #else /* CONFIG_DEVICE_PRIVATE */ static inline swp_entry_t make_device_private_entry(struct page *page, bool write) { @@ -164,15 +158,6 @@ static inline struct page *device_private_entry_to_page(swp_entry_t entry) { return NULL; } - -static inline vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, - unsigned long addr, - swp_entry_t entry, - unsigned int flags, - pmd_t *pmdp) -{ - return VM_FAULT_SIGBUS; -} #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION diff --git a/kernel/memremap.c b/kernel/memremap.c index 6e1970719dc2..bea6f887adad 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -11,41 +11,39 @@ #include <linux/types.h> #include <linux/wait_bit.h> #include <linux/xarray.h> -#include <linux/hmm.h> static DEFINE_XARRAY(pgmap_array); #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) #define SECTION_SIZE (1UL << PA_SECTION_SHIFT) -#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) -vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, - unsigned long addr, - swp_entry_t entry, - unsigned int flags, - pmd_t *pmdp) +#ifdef CONFIG_DEV_PAGEMAP_OPS +DEFINE_STATIC_KEY_FALSE(devmap_managed_key); +EXPORT_SYMBOL(devmap_managed_key); +static atomic_t devmap_managed_enable; + +static void devmap_managed_enable_put(void *data) { - struct page *page = device_private_entry_to_page(entry); - struct hmm_devmem *devmem; + if (atomic_dec_and_test(&devmap_managed_enable)) + static_branch_disable(&devmap_managed_key); +} - devmem = container_of(page->pgmap, typeof(*devmem), pagemap); +static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap) +{ + if (!pgmap->ops || !pgmap->ops->page_free) { + WARN(1, "Missing page_free method\n"); + return -EINVAL; + } - /* - * The page_fault() callback must migrate page back to system memory - * so that CPU can access it. This might fail for various reasons - * (device issue, device was unsafely unplugged, ...). When such - * error conditions happen, the callback must return VM_FAULT_SIGBUS. - * - * Note that because memory cgroup charges are accounted to the device - * memory, this should never fail because of memory restrictions (but - * allocation of regular system page might still fail because we are - * out of memory). - * - * There is a more in-depth description of what that callback can and - * cannot do, in include/linux/memremap.h - */ - return devmem->page_fault(vma, addr, page, flags, pmdp); + if (atomic_inc_return(&devmap_managed_enable) == 1) + static_branch_enable(&devmap_managed_key); + return devm_add_action_or_reset(dev, devmap_managed_enable_put, NULL); } -#endif /* CONFIG_DEVICE_PRIVATE */ +#else +static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap) +{ + return -EINVAL; +} +#endif /* CONFIG_DEV_PAGEMAP_OPS */ static void pgmap_array_delete(struct resource *res) { @@ -56,14 +54,8 @@ static void pgmap_array_delete(struct resource *res) static unsigned long pfn_first(struct dev_pagemap *pgmap) { - const struct resource *res = &pgmap->res; - struct vmem_altmap *altmap = &pgmap->altmap; - unsigned long pfn; - - pfn = res->start >> PAGE_SHIFT; - if (pgmap->altmap_valid) - pfn += vmem_altmap_offset(altmap); - return pfn; + return (pgmap->res.start >> PAGE_SHIFT) + + vmem_altmap_offset(pgmap_altmap(pgmap)); } static unsigned long pfn_end(struct dev_pagemap *pgmap) @@ -83,6 +75,24 @@ static unsigned long pfn_next(unsigned long pfn) #define for_each_device_pfn(pfn, map) \ for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn)) +static void dev_pagemap_kill(struct dev_pagemap *pgmap) +{ + if (pgmap->ops && pgmap->ops->kill) + pgmap->ops->kill(pgmap); + else + percpu_ref_kill(pgmap->ref); +} + +static void dev_pagemap_cleanup(struct dev_pagemap *pgmap) +{ + if (pgmap->ops && pgmap->ops->cleanup) { + pgmap->ops->cleanup(pgmap); + } else { + wait_for_completion(&pgmap->done); + percpu_ref_exit(pgmap->ref); + } +} + static void devm_memremap_pages_release(void *data) { struct dev_pagemap *pgmap = data; @@ -92,10 +102,10 @@ static void devm_memremap_pages_release(void *data) unsigned long pfn; int nid; - pgmap->kill(pgmap->ref); + dev_pagemap_kill(pgmap); for_each_device_pfn(pfn, pgmap) put_page(pfn_to_page(pfn)); - pgmap->cleanup(pgmap->ref); + dev_pagemap_cleanup(pgmap); /* pages are dead and unused, undo the arch mapping */ align_start = res->start & ~(SECTION_SIZE - 1); @@ -111,7 +121,7 @@ static void devm_memremap_pages_release(void *data) align_size >> PAGE_SHIFT, NULL); } else { arch_remove_memory(nid, align_start, align_size, - pgmap->altmap_valid ? &pgmap->altmap : NULL); + pgmap_altmap(pgmap)); kasan_remove_zero_shadow(__va(align_start), align_size); } mem_hotplug_done(); @@ -122,20 +132,29 @@ static void devm_memremap_pages_release(void *data) "%s: failed to free all reserved pages\n", __func__); } +static void dev_pagemap_percpu_release(struct percpu_ref *ref) +{ + struct dev_pagemap *pgmap = + container_of(ref, struct dev_pagemap, internal_ref); + + complete(&pgmap->done); +} + /** * devm_memremap_pages - remap and provide memmap backing for the given resource * @dev: hosting device for @res * @pgmap: pointer to a struct dev_pagemap * * Notes: - * 1/ At a minimum the res, ref and type members of @pgmap must be initialized + * 1/ At a minimum the res and type members of @pgmap must be initialized * by the caller before passing it to this function * - * 2/ The altmap field may optionally be initialized, in which case altmap_valid - * must be set to true + * 2/ The altmap field may optionally be initialized, in which case + * PGMAP_ALTMAP_VALID must be set in pgmap->flags. * - * 3/ pgmap->ref must be 'live' on entry and will be killed and reaped - * at devm_memremap_pages_release() time, or if this routine fails. + * 3/ The ref field may optionally be provided, in which pgmap->ref must be + * 'live' on entry and will be killed and reaped at + * devm_memremap_pages_release() time, or if this routine fails. * * 4/ res is expected to be a host memory range that could feasibly be * treated as a "System RAM" range, i.e. not a device mmio range, but @@ -144,22 +163,66 @@ static void devm_memremap_pages_release(void *data) void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { resource_size_t align_start, align_size, align_end; - struct vmem_altmap *altmap = pgmap->altmap_valid ? - &pgmap->altmap : NULL; struct resource *res = &pgmap->res; struct dev_pagemap *conflict_pgmap; struct mhp_restrictions restrictions = { /* * We do not want any optional features only our own memmap */ - .altmap = altmap, + .altmap = pgmap_altmap(pgmap), }; pgprot_t pgprot = PAGE_KERNEL; int error, nid, is_ram; + bool need_devmap_managed = true; + + switch (pgmap->type) { + case MEMORY_DEVICE_PRIVATE: + if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) { + WARN(1, "Device private memory not supported\n"); + return ERR_PTR(-EINVAL); + } + if (!pgmap->ops || !pgmap->ops->migrate_to_ram) { + WARN(1, "Missing migrate_to_ram method\n"); + return ERR_PTR(-EINVAL); + } + break; + case MEMORY_DEVICE_FS_DAX: + if (!IS_ENABLED(CONFIG_ZONE_DEVICE) || + IS_ENABLED(CONFIG_FS_DAX_LIMITED)) { + WARN(1, "File system DAX not supported\n"); + return ERR_PTR(-EINVAL); + } + break; + case MEMORY_DEVICE_DEVDAX: + case MEMORY_DEVICE_PCI_P2PDMA: + need_devmap_managed = false; + break; + default: + WARN(1, "Invalid pgmap type %d\n", pgmap->type); + break; + } + + if (!pgmap->ref) { + if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup)) + return ERR_PTR(-EINVAL); + + init_completion(&pgmap->done); + error = percpu_ref_init(&pgmap->internal_ref, + dev_pagemap_percpu_release, 0, GFP_KERNEL); + if (error) + return ERR_PTR(error); + pgmap->ref = &pgmap->internal_ref; + } else { + if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) { + WARN(1, "Missing reference count teardown definition\n"); + return ERR_PTR(-EINVAL); + } + } - if (!pgmap->ref || !pgmap->kill || !pgmap->cleanup) { - WARN(1, "Missing reference count teardown definition\n"); - return ERR_PTR(-EINVAL); + if (need_devmap_managed) { + error = devmap_managed_enable_get(dev, pgmap); + if (error) + return ERR_PTR(error); } align_start = res->start & ~(SECTION_SIZE - 1); @@ -241,7 +304,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE]; move_pfn_range_to_zone(zone, align_start >> PAGE_SHIFT, - align_size >> PAGE_SHIFT, altmap); + align_size >> PAGE_SHIFT, pgmap_altmap(pgmap)); } mem_hotplug_done(); @@ -271,9 +334,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) err_pfn_remap: pgmap_array_delete(res); err_array: - pgmap->kill(pgmap->ref); - pgmap->cleanup(pgmap->ref); - + dev_pagemap_kill(pgmap); + dev_pagemap_cleanup(pgmap); return ERR_PTR(error); } EXPORT_SYMBOL_GPL(devm_memremap_pages); @@ -287,7 +349,9 @@ EXPORT_SYMBOL_GPL(devm_memunmap_pages); unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) { /* number of pfns from base where pfn_to_page() is valid */ - return altmap->reserve + altmap->free; + if (altmap) + return altmap->reserve + altmap->free; + return 0; } void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) @@ -329,28 +393,6 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, EXPORT_SYMBOL_GPL(get_dev_pagemap); #ifdef CONFIG_DEV_PAGEMAP_OPS -DEFINE_STATIC_KEY_FALSE(devmap_managed_key); -EXPORT_SYMBOL(devmap_managed_key); -static atomic_t devmap_enable; - -/* - * Toggle the static key for ->page_free() callbacks when dev_pagemap - * pages go idle. - */ -void dev_pagemap_get_ops(void) -{ - if (atomic_inc_return(&devmap_enable) == 1) - static_branch_enable(&devmap_managed_key); -} -EXPORT_SYMBOL_GPL(dev_pagemap_get_ops); - -void dev_pagemap_put_ops(void) -{ - if (atomic_dec_and_test(&devmap_enable)) - static_branch_disable(&devmap_managed_key); -} -EXPORT_SYMBOL_GPL(dev_pagemap_put_ops); - void __put_devmap_managed_page(struct page *page) { int count = page_ref_dec_return(page); @@ -366,7 +408,7 @@ void __put_devmap_managed_page(struct page *page) mem_cgroup_uncharge(page); - page->pgmap->page_free(page, page->pgmap->data); + page->pgmap->ops->page_free(page); } else if (!count) __put_page(page); } diff --git a/kernel/resource.c b/kernel/resource.c index 158f04ec1d4f..d22423e85cf8 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1628,6 +1628,45 @@ void resource_list_free(struct list_head *head) } EXPORT_SYMBOL(resource_list_free); +#ifdef CONFIG_DEVICE_PRIVATE +/** + * devm_request_free_mem_region - find free region for device private memory + * + * @dev: device struct to bind the resource to + * @size: size in bytes of the device memory to add + * @base: resource tree to look in + * + * This function tries to find an empty range of physical address big enough to + * contain the new resource, so that it can later be hotplugged as ZONE_DEVICE + * memory, which in turn allocates struct pages. + */ +struct resource *devm_request_free_mem_region(struct device *dev, + struct resource *base, unsigned long size) +{ + resource_size_t end, addr; + struct resource *res; + + size = ALIGN(size, 1UL << PA_SECTION_SHIFT); + end = min_t(unsigned long, base->end, (1UL << MAX_PHYSMEM_BITS) - 1); + addr = end - size + 1UL; + + for (; addr > size && addr >= base->start; addr -= size) { + if (region_intersects(addr, size, 0, IORES_DESC_NONE) != + REGION_DISJOINT) + continue; + + res = devm_request_mem_region(dev, addr, size, dev_name(dev)); + if (!res) + return ERR_PTR(-ENOMEM); + res->desc = IORES_DESC_DEVICE_PRIVATE_MEMORY; + return res; + } + + return ERR_PTR(-ERANGE); +} +EXPORT_SYMBOL_GPL(devm_request_free_mem_region); +#endif /* CONFIG_DEVICE_PRIVATE */ + static int __init strict_iomem(char *str) { if (strstr(str, "relaxed")) diff --git a/mm/Kconfig b/mm/Kconfig index f0c76ba47695..40cf0562412d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -669,47 +669,17 @@ config ZONE_DEVICE If FS_DAX is enabled, then say Y. -config ARCH_HAS_HMM_MIRROR - bool - default y - depends on (X86_64 || PPC64) - depends on MMU && 64BIT - -config ARCH_HAS_HMM_DEVICE - bool - default y - depends on (X86_64 || PPC64) - depends on MEMORY_HOTPLUG - depends on MEMORY_HOTREMOVE - depends on SPARSEMEM_VMEMMAP - depends on ARCH_HAS_ZONE_DEVICE - select XARRAY_MULTI - -config ARCH_HAS_HMM - bool - default y - depends on (X86_64 || PPC64) - depends on ZONE_DEVICE - depends on MMU && 64BIT - depends on MEMORY_HOTPLUG - depends on MEMORY_HOTREMOVE - depends on SPARSEMEM_VMEMMAP - config MIGRATE_VMA_HELPER bool config DEV_PAGEMAP_OPS bool -config HMM - bool - select MMU_NOTIFIER - select MIGRATE_VMA_HELPER - config HMM_MIRROR bool "HMM mirror CPU page table into a device page table" - depends on ARCH_HAS_HMM - select HMM + depends on (X86_64 || PPC64) + depends on MMU && 64BIT + select MMU_NOTIFIER help Select HMM_MIRROR if you want to mirror range of the CPU page table of a process into a device page table. Here, mirror means "keep synchronized". @@ -719,8 +689,7 @@ config HMM_MIRROR config DEVICE_PRIVATE bool "Unaddressable device memory (GPU memory, ...)" - depends on ARCH_HAS_HMM - select HMM + depends on ZONE_DEVICE select DEV_PAGEMAP_OPS help @@ -728,17 +697,6 @@ config DEVICE_PRIVATE memory; i.e., memory that is only accessible from the device (or group of devices). You likely also want to select HMM_MIRROR. -config DEVICE_PUBLIC - bool "Addressable device memory (like GPU memory)" - depends on ARCH_HAS_HMM - select HMM - select DEV_PAGEMAP_OPS - - help - Allows creation of struct pages to represent addressable device - memory; i.e., memory that is accessible from both the device and - the CPU - config FRAME_VECTOR bool diff --git a/mm/Makefile b/mm/Makefile index ac5e5ba78874..91c99040065c 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -102,5 +102,5 @@ obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o -obj-$(CONFIG_HMM) += hmm.o +obj-$(CONFIG_HMM_MIRROR) += hmm.o obj-$(CONFIG_MEMFD_CREATE) += memfd.o @@ -605,13 +605,6 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(*pte))) goto unmap; *page = pte_page(*pte); - - /* - * This should never happen (a device public page in the gate - * area). - */ - if (is_device_public_page(*page)) - goto unmap; } if (unlikely(!try_get_page(*page))) { ret = -ENOMEM; @@ -26,9 +26,6 @@ #include <linux/mmu_notifier.h> #include <linux/memory_hotplug.h> -#define PA_SECTION_SIZE (1UL << PA_SECTION_SHIFT) - -#if IS_ENABLED(CONFIG_HMM_MIRROR) static const struct mmu_notifier_ops hmm_mmu_notifier_ops; /** @@ -1287,284 +1284,3 @@ long hmm_range_dma_unmap(struct hmm_range *range, return cpages; } EXPORT_SYMBOL(hmm_range_dma_unmap); -#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ - - -#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC) -struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma, - unsigned long addr) -{ - struct page *page; - - page = alloc_page_vma(GFP_HIGHUSER, vma, addr); - if (!page) - return NULL; - lock_page(page); - return page; -} -EXPORT_SYMBOL(hmm_vma_alloc_locked_page); - - -static void hmm_devmem_ref_release(struct percpu_ref *ref) -{ - struct hmm_devmem *devmem; - - devmem = container_of(ref, struct hmm_devmem, ref); - complete(&devmem->completion); -} - -static void hmm_devmem_ref_exit(struct percpu_ref *ref) -{ - struct hmm_devmem *devmem; - - devmem = container_of(ref, struct hmm_devmem, ref); - wait_for_completion(&devmem->completion); - percpu_ref_exit(ref); -} - -static void hmm_devmem_ref_kill(struct percpu_ref *ref) -{ - percpu_ref_kill(ref); -} - -static vm_fault_t hmm_devmem_fault(struct vm_area_struct *vma, - unsigned long addr, - const struct page *page, - unsigned int flags, - pmd_t *pmdp) -{ - struct hmm_devmem *devmem = page->pgmap->data; - - return devmem->ops->fault(devmem, vma, addr, page, flags, pmdp); -} - -static void hmm_devmem_free(struct page *page, void *data) -{ - struct hmm_devmem *devmem = data; - - page->mapping = NULL; - - devmem->ops->free(devmem, page); -} - -/* - * hmm_devmem_add() - hotplug ZONE_DEVICE memory for device memory - * - * @ops: memory event device driver callback (see struct hmm_devmem_ops) - * @device: device struct to bind the resource too - * @size: size in bytes of the device memory to add - * Return: pointer to new hmm_devmem struct ERR_PTR otherwise - * - * This function first finds an empty range of physical address big enough to - * contain the new resource, and then hotplugs it as ZONE_DEVICE memory, which - * in turn allocates struct pages. It does not do anything beyond that; all - * events affecting the memory will go through the various callbacks provided - * by hmm_devmem_ops struct. - * - * Device driver should call this function during device initialization and - * is then responsible of memory management. HMM only provides helpers. - */ -struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, - struct device *device, - unsigned long size) -{ - struct hmm_devmem *devmem; - resource_size_t addr; - void *result; - int ret; - - dev_pagemap_get_ops(); - - devmem = devm_kzalloc(device, sizeof(*devmem), GFP_KERNEL); - if (!devmem) - return ERR_PTR(-ENOMEM); - - init_completion(&devmem->completion); - devmem->pfn_first = -1UL; - devmem->pfn_last = -1UL; - devmem->resource = NULL; - devmem->device = device; - devmem->ops = ops; - - ret = percpu_ref_init(&devmem->ref, &hmm_devmem_ref_release, - 0, GFP_KERNEL); - if (ret) - return ERR_PTR(ret); - - size = ALIGN(size, PA_SECTION_SIZE); - addr = min((unsigned long)iomem_resource.end, - (1UL << MAX_PHYSMEM_BITS) - 1); - addr = addr - size + 1UL; - - /* - * FIXME add a new helper to quickly walk resource tree and find free - * range - * - * FIXME what about ioport_resource resource ? - */ - for (; addr > size && addr >= iomem_resource.start; addr -= size) { - ret = region_intersects(addr, size, 0, IORES_DESC_NONE); - if (ret != REGION_DISJOINT) - continue; - - devmem->resource = devm_request_mem_region(device, addr, size, - dev_name(device)); - if (!devmem->resource) - return ERR_PTR(-ENOMEM); - break; - } - if (!devmem->resource) - return ERR_PTR(-ERANGE); - - devmem->resource->desc = IORES_DESC_DEVICE_PRIVATE_MEMORY; - devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT; - devmem->pfn_last = devmem->pfn_first + - (resource_size(devmem->resource) >> PAGE_SHIFT); - devmem->page_fault = hmm_devmem_fault; - - devmem->pagemap.type = MEMORY_DEVICE_PRIVATE; - devmem->pagemap.res = *devmem->resource; - devmem->pagemap.page_free = hmm_devmem_free; - devmem->pagemap.altmap_valid = false; - devmem->pagemap.ref = &devmem->ref; - devmem->pagemap.data = devmem; - devmem->pagemap.kill = hmm_devmem_ref_kill; - devmem->pagemap.cleanup = hmm_devmem_ref_exit; - - result = devm_memremap_pages(devmem->device, &devmem->pagemap); - if (IS_ERR(result)) - return result; - return devmem; -} -EXPORT_SYMBOL_GPL(hmm_devmem_add); - -struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops, - struct device *device, - struct resource *res) -{ - struct hmm_devmem *devmem; - void *result; - int ret; - - if (res->desc != IORES_DESC_DEVICE_PUBLIC_MEMORY) - return ERR_PTR(-EINVAL); - - dev_pagemap_get_ops(); - - devmem = devm_kzalloc(device, sizeof(*devmem), GFP_KERNEL); - if (!devmem) - return ERR_PTR(-ENOMEM); - - init_completion(&devmem->completion); - devmem->pfn_first = -1UL; - devmem->pfn_last = -1UL; - devmem->resource = res; - devmem->device = device; - devmem->ops = ops; - - ret = percpu_ref_init(&devmem->ref, &hmm_devmem_ref_release, - 0, GFP_KERNEL); - if (ret) - return ERR_PTR(ret); - - devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT; - devmem->pfn_last = devmem->pfn_first + - (resource_size(devmem->resource) >> PAGE_SHIFT); - devmem->page_fault = hmm_devmem_fault; - - devmem->pagemap.type = MEMORY_DEVICE_PUBLIC; - devmem->pagemap.res = *devmem->resource; - devmem->pagemap.page_free = hmm_devmem_free; - devmem->pagemap.altmap_valid = false; - devmem->pagemap.ref = &devmem->ref; - devmem->pagemap.data = devmem; - devmem->pagemap.kill = hmm_devmem_ref_kill; - devmem->pagemap.cleanup = hmm_devmem_ref_exit; - - result = devm_memremap_pages(devmem->device, &devmem->pagemap); - if (IS_ERR(result)) - return result; - return devmem; -} -EXPORT_SYMBOL_GPL(hmm_devmem_add_resource); - -/* - * A device driver that wants to handle multiple devices memory through a - * single fake device can use hmm_device to do so. This is purely a helper - * and it is not needed to make use of any HMM functionality. - */ -#define HMM_DEVICE_MAX 256 - -static DECLARE_BITMAP(hmm_device_mask, HMM_DEVICE_MAX); -static DEFINE_SPINLOCK(hmm_device_lock); -static struct class *hmm_device_class; -static dev_t hmm_device_devt; - -static void hmm_device_release(struct device *device) -{ - struct hmm_device *hmm_device; - - hmm_device = container_of(device, struct hmm_device, device); - spin_lock(&hmm_device_lock); - clear_bit(hmm_device->minor, hmm_device_mask); - spin_unlock(&hmm_device_lock); - - kfree(hmm_device); -} - -struct hmm_device *hmm_device_new(void *drvdata) -{ - struct hmm_device *hmm_device; - - hmm_device = kzalloc(sizeof(*hmm_device), GFP_KERNEL); - if (!hmm_device) - return ERR_PTR(-ENOMEM); - - spin_lock(&hmm_device_lock); - hmm_device->minor = find_first_zero_bit(hmm_device_mask, HMM_DEVICE_MAX); - if (hmm_device->minor >= HMM_DEVICE_MAX) { - spin_unlock(&hmm_device_lock); - kfree(hmm_device); - return ERR_PTR(-EBUSY); - } - set_bit(hmm_device->minor, hmm_device_mask); - spin_unlock(&hmm_device_lock); - - dev_set_name(&hmm_device->device, "hmm_device%d", hmm_device->minor); - hmm_device->device.devt = MKDEV(MAJOR(hmm_device_devt), - hmm_device->minor); - hmm_device->device.release = hmm_device_release; - dev_set_drvdata(&hmm_device->device, drvdata); - hmm_device->device.class = hmm_device_class; - device_initialize(&hmm_device->device); - - return hmm_device; -} -EXPORT_SYMBOL(hmm_device_new); - -void hmm_device_put(struct hmm_device *hmm_device) -{ - put_device(&hmm_device->device); -} -EXPORT_SYMBOL(hmm_device_put); - -static int __init hmm_init(void) -{ - int ret; - - ret = alloc_chrdev_region(&hmm_device_devt, 0, - HMM_DEVICE_MAX, - "hmm_device"); - if (ret) - return ret; - - hmm_device_class = class_create(THIS_MODULE, "hmm_device"); - if (IS_ERR(hmm_device_class)) { - unregister_chrdev_region(hmm_device_devt, HMM_DEVICE_MAX); - return PTR_ERR(hmm_device_class); - } - return 0; -} - -device_initcall(hmm_init); -#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ diff --git a/mm/madvise.c b/mm/madvise.c index 628022e674a7..968df3aa069f 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -354,7 +354,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, continue; } - page = _vm_normal_page(vma, addr, ptent, true); + page = vm_normal_page(vma, addr, ptent); if (!page) continue; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ba9138a4a1de..d2a6454fa0bd 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4793,7 +4793,7 @@ enum mc_target_type { static struct page *mc_handle_present_pte(struct vm_area_struct *vma, unsigned long addr, pte_t ptent) { - struct page *page = _vm_normal_page(vma, addr, ptent, true); + struct page *page = vm_normal_page(vma, addr, ptent); if (!page || !page_mapped(page)) return NULL; @@ -4994,8 +4994,8 @@ out: * 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a * target for charge migration. if @target is not NULL, the entry is stored * in target->ent. - * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is MEMORY_DEVICE_PUBLIC - * or MEMORY_DEVICE_PRIVATE (so ZONE_DEVICE page and thus not on the lru). + * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is MEMORY_DEVICE_PRIVATE + * (so ZONE_DEVICE page and thus not on the lru). * For now we such page is charge like a regular page would be as for all * intent and purposes it is just special memory taking the place of a * regular page. @@ -5029,8 +5029,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, */ if (page->mem_cgroup == mc.from) { ret = MC_TARGET_PAGE; - if (is_device_private_page(page) || - is_device_public_page(page)) + if (is_device_private_page(page)) ret = MC_TARGET_DEVICE; if (target) target->page = page; @@ -5101,8 +5100,8 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, if (ptl) { /* * Note their can not be MC_TARGET_DEVICE for now as we do not - * support transparent huge page with MEMORY_DEVICE_PUBLIC or - * MEMORY_DEVICE_PRIVATE but this might change. + * support transparent huge page with MEMORY_DEVICE_PRIVATE but + * this might change. */ if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE) mc.precharge += HPAGE_PMD_NR; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index d9cc6606f409..31e7c7b424a1 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1177,16 +1177,12 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, goto unlock; } - switch (pgmap->type) { - case MEMORY_DEVICE_PRIVATE: - case MEMORY_DEVICE_PUBLIC: + if (pgmap->type == MEMORY_DEVICE_PRIVATE) { /* * TODO: Handle HMM pages which may need coordination * with device-side memory. */ goto unlock; - default: - break; } /* diff --git a/mm/memory.c b/mm/memory.c index ddf20bd0c317..d437ccdb210c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -571,8 +571,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, * PFNMAP mappings in order to support COWable mappings. * */ -struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, - pte_t pte, bool with_public_device) +struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte) { unsigned long pfn = pte_pfn(pte); @@ -585,29 +585,6 @@ struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, return NULL; if (is_zero_pfn(pfn)) return NULL; - - /* - * Device public pages are special pages (they are ZONE_DEVICE - * pages but different from persistent memory). They behave - * allmost like normal pages. The difference is that they are - * not on the lru and thus should never be involve with any- - * thing that involve lru manipulation (mlock, numa balancing, - * ...). - * - * This is why we still want to return NULL for such page from - * vm_normal_page() so that we do not have to special case all - * call site of vm_normal_page(). - */ - if (likely(pfn <= highest_memmap_pfn)) { - struct page *page = pfn_to_page(pfn); - - if (is_device_public_page(page)) { - if (with_public_device) - return page; - return NULL; - } - } - if (pte_devmap(pte)) return NULL; @@ -797,17 +774,6 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, rss[mm_counter(page)]++; } else if (pte_devmap(pte)) { page = pte_page(pte); - - /* - * Cache coherent device memory behave like regular page and - * not like persistent memory page. For more informations see - * MEMORY_DEVICE_CACHE_COHERENT in memory_hotplug.h - */ - if (is_device_public_page(page)) { - get_page(page); - page_dup_rmap(page, false); - rss[mm_counter(page)]++; - } } out_set_pte: @@ -1063,7 +1029,7 @@ again: if (pte_present(ptent)) { struct page *page; - page = _vm_normal_page(vma, addr, ptent, true); + page = vm_normal_page(vma, addr, ptent); if (unlikely(details) && page) { /* * unmap_shared_mapping_pages() wants to @@ -2782,13 +2748,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) migration_entry_wait(vma->vm_mm, vmf->pmd, vmf->address); } else if (is_device_private_entry(entry)) { - /* - * For un-addressable device memory we call the pgmap - * fault handler callback. The callback must migrate - * the page back to some CPU accessible page. - */ - ret = device_private_entry_fault(vma, vmf->address, entry, - vmf->flags, vmf->pmd); + vmf->page = device_private_entry_to_page(entry); + ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; } else { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index e096c987d261..6166ba5a15f3 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -557,10 +557,8 @@ void __remove_pages(struct zone *zone, unsigned long phys_start_pfn, int sections_to_remove; /* In the ZONE_DEVICE case device driver owns the memory region */ - if (is_dev_zone(zone)) { - if (altmap) - map_offset = vmem_altmap_offset(altmap); - } + if (is_dev_zone(zone)) + map_offset = vmem_altmap_offset(altmap); clear_zone_contiguous(zone); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index fdcb73536319..f48693f75b37 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2098,6 +2098,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, out: return page; } +EXPORT_SYMBOL(alloc_pages_vma); /** * alloc_pages_current - Allocate pages. diff --git a/mm/migrate.c b/mm/migrate.c index f2ecc2855a12..78d45e184457 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -246,8 +246,6 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, if (is_device_private_page(new)) { entry = make_device_private_entry(new, pte_write(pte)); pte = swp_entry_to_pte(entry); - } else if (is_device_public_page(new)) { - pte = pte_mkdevmap(pte); } } @@ -381,7 +379,6 @@ static int expected_page_refs(struct address_space *mapping, struct page *page) * ZONE_DEVICE pages. */ expected_count += is_device_private_page(page); - expected_count += is_device_public_page(page); if (mapping) expected_count += hpage_nr_pages(page) + page_has_private(page); @@ -994,10 +991,7 @@ static int move_to_new_page(struct page *newpage, struct page *page, if (!PageMappingFlags(page)) page->mapping = NULL; - if (unlikely(is_zone_device_page(newpage))) { - if (is_device_public_page(newpage)) - flush_dcache_page(newpage); - } else + if (likely(!is_zone_device_page(newpage))) flush_dcache_page(newpage); } @@ -2265,7 +2259,7 @@ again: pfn = 0; goto next; } - page = _vm_normal_page(migrate->vma, addr, pte, true); + page = vm_normal_page(migrate->vma, addr, pte); mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE; mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0; } @@ -2406,16 +2400,7 @@ static bool migrate_vma_check_page(struct page *page) * FIXME proper solution is to rework migration_entry_wait() so * it does not need to take a reference on page. */ - if (is_device_private_page(page)) - return true; - - /* - * Only allow device public page to be migrated and account for - * the extra reference count imply by ZONE_DEVICE pages. - */ - if (!is_device_public_page(page)) - return false; - extra++; + return is_device_private_page(page); } /* For file back page */ @@ -2665,11 +2650,6 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE); entry = swp_entry_to_pte(swp_entry); - } else if (is_device_public_page(page)) { - entry = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot))); - if (vma->vm_flags & VM_WRITE) - entry = pte_mkwrite(pte_mkdirty(entry)); - entry = pte_mkdevmap(entry); } } else { entry = mk_pte(page, vma->vm_page_prot); @@ -2789,7 +2769,7 @@ static void migrate_vma_pages(struct migrate_vma *migrate) migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; continue; } - } else if (!is_device_public_page(newpage)) { + } else { /* * Other types of ZONE_DEVICE page are not * supported. diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d66bc8abe0af..c0e031c52db5 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5853,6 +5853,7 @@ void __ref memmap_init_zone_device(struct zone *zone, { unsigned long pfn, end_pfn = start_pfn + size; struct pglist_data *pgdat = zone->zone_pgdat; + struct vmem_altmap *altmap = pgmap_altmap(pgmap); unsigned long zone_idx = zone_idx(zone); unsigned long start = jiffies; int nid = pgdat->node_id; @@ -5865,9 +5866,7 @@ void __ref memmap_init_zone_device(struct zone *zone, * of the pages reserved for the memmap, so we can just jump to * the end of that region and start processing the device pages. */ - if (pgmap->altmap_valid) { - struct vmem_altmap *altmap = &pgmap->altmap; - + if (altmap) { start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); size = end_pfn - start_pfn; } @@ -5887,12 +5886,12 @@ void __ref memmap_init_zone_device(struct zone *zone, __SetPageReserved(page); /* - * ZONE_DEVICE pages union ->lru with a ->pgmap back - * pointer and hmm_data. It is a bug if a ZONE_DEVICE - * page is ever freed or placed on a driver-private list. + * ZONE_DEVICE pages union ->lru with a ->pgmap back pointer + * and zone_device_data. It is a bug if a ZONE_DEVICE page is + * ever freed or placed on a driver-private list. */ page->pgmap = pgmap; - page->hmm_data = 0; + page->zone_device_data = NULL; /* * Mark the block movable so that blocks are reserved for diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 076df22e4bda..cd040b5abffe 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -100,25 +100,60 @@ static void nfit_test_kill(void *_pgmap) { struct dev_pagemap *pgmap = _pgmap; - WARN_ON(!pgmap || !pgmap->ref || !pgmap->kill || !pgmap->cleanup); - pgmap->kill(pgmap->ref); - pgmap->cleanup(pgmap->ref); + WARN_ON(!pgmap || !pgmap->ref); + + if (pgmap->ops && pgmap->ops->kill) + pgmap->ops->kill(pgmap); + else + percpu_ref_kill(pgmap->ref); + + if (pgmap->ops && pgmap->ops->cleanup) { + pgmap->ops->cleanup(pgmap); + } else { + wait_for_completion(&pgmap->done); + percpu_ref_exit(pgmap->ref); + } +} + +static void dev_pagemap_percpu_release(struct percpu_ref *ref) +{ + struct dev_pagemap *pgmap = + container_of(ref, struct dev_pagemap, internal_ref); + + complete(&pgmap->done); } void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { + int error; resource_size_t offset = pgmap->res.start; struct nfit_test_resource *nfit_res = get_nfit_res(offset); - if (nfit_res) { - int rc; - - rc = devm_add_action_or_reset(dev, nfit_test_kill, pgmap); - if (rc) - return ERR_PTR(rc); - return nfit_res->buf + offset - nfit_res->res.start; + if (!nfit_res) + return devm_memremap_pages(dev, pgmap); + + pgmap->dev = dev; + if (!pgmap->ref) { + if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup)) + return ERR_PTR(-EINVAL); + + init_completion(&pgmap->done); + error = percpu_ref_init(&pgmap->internal_ref, + dev_pagemap_percpu_release, 0, GFP_KERNEL); + if (error) + return ERR_PTR(error); + pgmap->ref = &pgmap->internal_ref; + } else { + if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) { + WARN(1, "Missing reference count teardown definition\n"); + return ERR_PTR(-EINVAL); + } } - return devm_memremap_pages(dev, pgmap); + + error = devm_add_action_or_reset(dev, nfit_test_kill, pgmap); + if (error) + return ERR_PTR(error); + return nfit_res->buf + offset - nfit_res->res.start; } EXPORT_SYMBOL_GPL(__wrap_devm_memremap_pages); |