From: Dan Williams <dan.j.williams@xxxxxxxxx> Subject: mm/memremap_pages: support multiple ranges per invocation In support of device-dax growing the ability to front physically dis-contiguous ranges of memory, update devm_memremap_pages() to track multiple ranges with a single reference counter and devm instance. Convert all [devm_]memremap_pages() users to specify the number of ranges they are mapping in their 'struct dev_pagemap' instance. Link: https://lkml.kernel.org/r/159643103789.4062302.18426128170217903785.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Link: https://lkml.kernel.org/r/160106116293.30709.13350662794915396198.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx> Cc: Paul Mackerras <paulus@xxxxxxxxxx> Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx> Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx> Cc: Vishal Verma <vishal.l.verma@xxxxxxxxx> Cc: Vivek Goyal <vgoyal@xxxxxxxxxx> Cc: Dave Jiang <dave.jiang@xxxxxxxxx> Cc: Ben Skeggs <bskeggs@xxxxxxxxxx> Cc: David Airlie <airlied@xxxxxxxx> Cc: Daniel Vetter <daniel@xxxxxxxx> Cc: Ira Weiny <ira.weiny@xxxxxxxxx> Cc: Bjorn Helgaas <bhelgaas@xxxxxxxxxx> Cc: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx> Cc: Juergen Gross <jgross@xxxxxxxx> Cc: Stefano Stabellini <sstabellini@xxxxxxxxxx> Cc: "Jérôme Glisse" <jglisse@xxxxxxxxx Cc: Andy Lutomirski <luto@xxxxxxxxxx> Cc: Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx> Cc: Ard Biesheuvel <ardb@xxxxxxxxxx> Cc: Borislav Petkov <bp@xxxxxxxxx> Cc: Brice Goglin <Brice.Goglin@xxxxxxxx> Cc: Catalin Marinas <catalin.marinas@xxxxxxx> Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx> Cc: David Hildenbrand <david@xxxxxxxxxx> Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> Cc: "H. Peter Anvin" <hpa@xxxxxxxxx> Cc: Hulk Robot <hulkci@xxxxxxxxxx> Cc: Ingo Molnar <mingo@xxxxxxxxxx> Cc: Jason Gunthorpe <jgg@xxxxxxxxxxxx> Cc: Jason Yan <yanaijie@xxxxxxxxxx> Cc: Jeff Moyer <jmoyer@xxxxxxxxxx> Cc: "Jérôme Glisse" <jglisse@xxxxxxxxxx> Cc: Jia He <justin.he@xxxxxxx> Cc: Joao Martins <joao.m.martins@xxxxxxxxxx> Cc: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx> Cc: kernel test robot <lkp@xxxxxxxxx> Cc: Mike Rapoport <rppt@xxxxxxxxxxxxx> Cc: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@xxxxxxxxx> Cc: Randy Dunlap <rdunlap@xxxxxxxxxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: Tom Lendacky <thomas.lendacky@xxxxxxx> Cc: Wei Yang <richard.weiyang@xxxxxxxxxxxxxxxxx> Cc: Will Deacon <will@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- arch/powerpc/kvm/book3s_hv_uvmem.c | 1 drivers/dax/device.c | 1 drivers/gpu/drm/nouveau/nouveau_dmem.c | 1 drivers/nvdimm/pfn_devs.c | 1 drivers/nvdimm/pmem.c | 1 drivers/pci/p2pdma.c | 1 drivers/xen/unpopulated-alloc.c | 1 include/linux/memremap.h | 10 lib/test_hmm.c | 1 mm/memremap.c | 258 +++++++++++++---------- 10 files changed, 166 insertions(+), 110 deletions(-) --- a/arch/powerpc/kvm/book3s_hv_uvmem.c~mm-memremap_pages-support-multiple-ranges-per-invocation +++ a/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -1172,6 +1172,7 @@ int kvmppc_uvmem_init(void) kvmppc_uvmem_pgmap.type = MEMORY_DEVICE_PRIVATE; kvmppc_uvmem_pgmap.range.start = res->start; kvmppc_uvmem_pgmap.range.end = res->end; + kvmppc_uvmem_pgmap.nr_range = 1; kvmppc_uvmem_pgmap.ops = &kvmppc_uvmem_ops; /* just one global instance: */ kvmppc_uvmem_pgmap.owner = &kvmppc_uvmem_pgmap; --- a/drivers/dax/device.c~mm-memremap_pages-support-multiple-ranges-per-invocation +++ a/drivers/dax/device.c @@ -417,6 +417,7 @@ int dev_dax_probe(struct dev_dax *dev_da if (!pgmap) return -ENOMEM; pgmap->range = *range; + pgmap->nr_range = 1; } pgmap->type = MEMORY_DEVICE_GENERIC; addr = devm_memremap_pages(dev, pgmap); --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c~mm-memremap_pages-support-multiple-ranges-per-invocation +++ a/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -251,6 +251,7 @@ nouveau_dmem_chunk_alloc(struct nouveau_ chunk->pagemap.type = MEMORY_DEVICE_PRIVATE; chunk->pagemap.range.start = res->start; chunk->pagemap.range.end = res->end; + chunk->pagemap.nr_range = 1; chunk->pagemap.ops = &nouveau_dmem_pagemap_ops; chunk->pagemap.owner = drm->dev; --- a/drivers/nvdimm/pfn_devs.c~mm-memremap_pages-support-multiple-ranges-per-invocation +++ a/drivers/nvdimm/pfn_devs.c @@ -693,6 +693,7 @@ static int __nvdimm_setup_pfn(struct nd_ .start = nsio->res.start + start_pad, .end = nsio->res.end - end_trunc, }; + pgmap->nr_range = 1; if (nd_pfn->mode == PFN_MODE_RAM) { if (offset < reserve) return -EINVAL; --- a/drivers/nvdimm/pmem.c~mm-memremap_pages-support-multiple-ranges-per-invocation +++ a/drivers/nvdimm/pmem.c @@ -441,6 +441,7 @@ static int pmem_attach_disk(struct devic } else if (pmem_should_map_pages(dev)) { pmem->pgmap.range.start = res->start; pmem->pgmap.range.end = res->end; + pmem->pgmap.nr_range = 1; pmem->pgmap.type = MEMORY_DEVICE_FS_DAX; pmem->pgmap.ops = &fsdax_pagemap_ops; addr = devm_memremap_pages(dev, &pmem->pgmap); --- a/drivers/pci/p2pdma.c~mm-memremap_pages-support-multiple-ranges-per-invocation +++ a/drivers/pci/p2pdma.c @@ -187,6 +187,7 @@ int pci_p2pdma_add_resource(struct pci_d pgmap = &p2p_pgmap->pgmap; pgmap->range.start = pci_resource_start(pdev, bar) + offset; pgmap->range.end = pgmap->range.start + size - 1; + pgmap->nr_range = 1; pgmap->type = MEMORY_DEVICE_PCI_P2PDMA; p2p_pgmap->provider = pdev; --- a/drivers/xen/unpopulated-alloc.c~mm-memremap_pages-support-multiple-ranges-per-invocation +++ a/drivers/xen/unpopulated-alloc.c @@ -47,6 +47,7 @@ static int fill_list(unsigned int nr_pag .start = res->start, .end = res->end, }; + pgmap->nr_range = 1; pgmap->owner = res; #ifdef CONFIG_XEN_HAVE_PVMMU --- a/include/linux/memremap.h~mm-memremap_pages-support-multiple-ranges-per-invocation +++ a/include/linux/memremap.h @@ -94,7 +94,6 @@ struct dev_pagemap_ops { /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations - * @range: physical address range covered by @ref * @ref: reference count that pins the devm_memremap_pages() mapping * @internal_ref: internal reference if @ref is not provided by the caller * @done: completion for @internal_ref @@ -104,10 +103,12 @@ struct dev_pagemap_ops { * @owner: an opaque pointer identifying the entity that manages this * instance. Used by various helpers to make sure that no * foreign ZONE_DEVICE memory is accessed. + * @nr_range: number of ranges to be mapped + * @range: range to be mapped when nr_range == 1 + * @ranges: array of ranges to be mapped when nr_range > 1 */ struct dev_pagemap { struct vmem_altmap altmap; - struct range range; struct percpu_ref *ref; struct percpu_ref internal_ref; struct completion done; @@ -115,6 +116,11 @@ struct dev_pagemap { unsigned int flags; const struct dev_pagemap_ops *ops; void *owner; + int nr_range; + union { + struct range range; + struct range ranges[0]; + }; }; static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) --- a/lib/test_hmm.c~mm-memremap_pages-support-multiple-ranges-per-invocation +++ a/lib/test_hmm.c @@ -472,6 +472,7 @@ static bool dmirror_allocate_chunk(struc devmem->pagemap.type = MEMORY_DEVICE_PRIVATE; devmem->pagemap.range.start = res->start; devmem->pagemap.range.end = res->end; + devmem->pagemap.nr_range = 1; devmem->pagemap.ops = &dmirror_devmem_ops; devmem->pagemap.owner = mdevice; --- a/mm/memremap.c~mm-memremap_pages-support-multiple-ranges-per-invocation +++ a/mm/memremap.c @@ -77,15 +77,19 @@ static void pgmap_array_delete(struct ra synchronize_rcu(); } -static unsigned long pfn_first(struct dev_pagemap *pgmap) +static unsigned long pfn_first(struct dev_pagemap *pgmap, int range_id) { - return PHYS_PFN(pgmap->range.start) + - vmem_altmap_offset(pgmap_altmap(pgmap)); + struct range *range = &pgmap->ranges[range_id]; + unsigned long pfn = PHYS_PFN(range->start); + + if (range_id) + return pfn; + return pfn + vmem_altmap_offset(pgmap_altmap(pgmap)); } -static unsigned long pfn_end(struct dev_pagemap *pgmap) +static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id) { - const struct range *range = &pgmap->range; + const struct range *range = &pgmap->ranges[range_id]; return (range->start + range_len(range)) >> PAGE_SHIFT; } @@ -97,8 +101,8 @@ static unsigned long pfn_next(unsigned l return pfn + 1; } -#define for_each_device_pfn(pfn, map) \ - for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn)) +#define for_each_device_pfn(pfn, map, i) \ + for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); pfn = pfn_next(pfn)) static void dev_pagemap_kill(struct dev_pagemap *pgmap) { @@ -124,20 +128,14 @@ static void dev_pagemap_cleanup(struct d pgmap->ref = NULL; } -void memunmap_pages(struct dev_pagemap *pgmap) +static void pageunmap_range(struct dev_pagemap *pgmap, int range_id) { - struct range *range = &pgmap->range; + struct range *range = &pgmap->ranges[range_id]; struct page *first_page; - unsigned long pfn; int nid; - dev_pagemap_kill(pgmap); - for_each_device_pfn(pfn, pgmap) - put_page(pfn_to_page(pfn)); - dev_pagemap_cleanup(pgmap); - /* make sure to access a memmap that was actually initialized */ - first_page = pfn_to_page(pfn_first(pgmap)); + first_page = pfn_to_page(pfn_first(pgmap, range_id)); /* pages are dead and unused, undo the arch mapping */ nid = page_to_nid(first_page); @@ -157,6 +155,22 @@ void memunmap_pages(struct dev_pagemap * untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range)); pgmap_array_delete(range); +} + +void memunmap_pages(struct dev_pagemap *pgmap) +{ + unsigned long pfn; + int i; + + dev_pagemap_kill(pgmap); + for (i = 0; i < pgmap->nr_range; i++) + for_each_device_pfn(pfn, pgmap, i) + put_page(pfn_to_page(pfn)); + dev_pagemap_cleanup(pgmap); + + for (i = 0; i < pgmap->nr_range; i++) + pageunmap_range(pgmap, i); + WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n"); devmap_managed_enable_put(); } @@ -175,96 +189,29 @@ static void dev_pagemap_percpu_release(s complete(&pgmap->done); } -/* - * Not device managed version of dev_memremap_pages, undone by - * memunmap_pages(). Please use dev_memremap_pages if you have a struct - * device available. - */ -void *memremap_pages(struct dev_pagemap *pgmap, int nid) +static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, + int range_id, int nid) { - struct range *range = &pgmap->range; + struct range *range = &pgmap->ranges[range_id]; struct dev_pagemap *conflict_pgmap; - struct mhp_params params = { - /* - * We do not want any optional features only our own memmap - */ - .altmap = pgmap_altmap(pgmap), - .pgprot = PAGE_KERNEL, - }; int error, 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); - } - if (!pgmap->owner) { - WARN(1, "Missing owner\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_GENERIC: - need_devmap_managed = false; - break; - case MEMORY_DEVICE_PCI_P2PDMA: - params.pgprot = pgprot_noncached(params.pgprot); - 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 (need_devmap_managed) { - error = devmap_managed_enable_get(pgmap); - if (error) - return ERR_PTR(error); - } + if (WARN_ONCE(pgmap_altmap(pgmap) && range_id > 0, + "altmap not supported for multiple ranges\n")) + return -EINVAL; conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->start), NULL); if (conflict_pgmap) { WARN(1, "Conflicting mapping in same section\n"); put_dev_pagemap(conflict_pgmap); - error = -ENOMEM; - goto err_array; + return -ENOMEM; } conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->end), NULL); if (conflict_pgmap) { WARN(1, "Conflicting mapping in same section\n"); put_dev_pagemap(conflict_pgmap); - error = -ENOMEM; - goto err_array; + return -ENOMEM; } is_ram = region_intersects(range->start, range_len(range), @@ -274,19 +221,18 @@ void *memremap_pages(struct dev_pagemap WARN_ONCE(1, "attempted on %s region %#llx-%#llx\n", is_ram == REGION_MIXED ? "mixed" : "ram", range->start, range->end); - error = -ENXIO; - goto err_array; + return -ENXIO; } error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(range->start), PHYS_PFN(range->end), pgmap, GFP_KERNEL)); if (error) - goto err_array; + return error; if (nid < 0) nid = numa_mem_id(); - error = track_pfn_remap(NULL, ¶ms.pgprot, PHYS_PFN(range->start), 0, + error = track_pfn_remap(NULL, ¶ms->pgprot, PHYS_PFN(range->start), 0, range_len(range)); if (error) goto err_pfn_remap; @@ -306,7 +252,7 @@ void *memremap_pages(struct dev_pagemap */ if (pgmap->type == MEMORY_DEVICE_PRIVATE) { error = add_pages(nid, PHYS_PFN(range->start), - PHYS_PFN(range_len(range)), ¶ms); + PHYS_PFN(range_len(range)), params); } else { error = kasan_add_zero_shadow(__va(range->start), range_len(range)); if (error) { @@ -315,7 +261,7 @@ void *memremap_pages(struct dev_pagemap } error = arch_add_memory(nid, range->start, range_len(range), - ¶ms); + params); } if (!error) { @@ -323,7 +269,7 @@ void *memremap_pages(struct dev_pagemap zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE]; move_pfn_range_to_zone(zone, PHYS_PFN(range->start), - PHYS_PFN(range_len(range)), params.altmap); + PHYS_PFN(range_len(range)), params->altmap); } mem_hotplug_done(); @@ -337,20 +283,116 @@ void *memremap_pages(struct dev_pagemap memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], PHYS_PFN(range->start), PHYS_PFN(range_len(range)), pgmap); - percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap)); - return __va(range->start); + percpu_ref_get_many(pgmap->ref, pfn_end(pgmap, range_id) + - pfn_first(pgmap, range_id)); + return 0; - err_add_memory: +err_add_memory: kasan_remove_zero_shadow(__va(range->start), range_len(range)); - err_kasan: +err_kasan: untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range)); - err_pfn_remap: +err_pfn_remap: pgmap_array_delete(range); - err_array: - dev_pagemap_kill(pgmap); - dev_pagemap_cleanup(pgmap); - devmap_managed_enable_put(); - return ERR_PTR(error); + return error; +} + + +/* + * Not device managed version of dev_memremap_pages, undone by + * memunmap_pages(). Please use dev_memremap_pages if you have a struct + * device available. + */ +void *memremap_pages(struct dev_pagemap *pgmap, int nid) +{ + struct mhp_params params = { + .altmap = pgmap_altmap(pgmap), + .pgprot = PAGE_KERNEL, + }; + const int nr_range = pgmap->nr_range; + bool need_devmap_managed = true; + int error, i; + + if (WARN_ONCE(!nr_range, "nr_range must be specified\n")) + return ERR_PTR(-EINVAL); + + 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); + } + if (!pgmap->owner) { + WARN(1, "Missing owner\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_GENERIC: + need_devmap_managed = false; + break; + case MEMORY_DEVICE_PCI_P2PDMA: + params.pgprot = pgprot_noncached(params.pgprot); + 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 (need_devmap_managed) { + error = devmap_managed_enable_get(pgmap); + if (error) + return ERR_PTR(error); + } + + /* + * Clear the pgmap nr_range as it will be incremented for each + * successfully processed range. This communicates how many + * regions to unwind in the abort case. + */ + pgmap->nr_range = 0; + error = 0; + for (i = 0; i < nr_range; i++) { + error = pagemap_range(pgmap, ¶ms, i, nid); + if (error) + break; + pgmap->nr_range++; + } + + if (i < nr_range) { + memunmap_pages(pgmap); + pgmap->nr_range = nr_range; + return ERR_PTR(error); + } + + return __va(pgmap->ranges[0].start); } EXPORT_SYMBOL_GPL(memremap_pages); _
