diff options
Diffstat (limited to 'mm/memremap.c')
| -rw-r--r-- | mm/memremap.c | 274 |
1 files changed, 140 insertions, 134 deletions
diff --git a/mm/memremap.c b/mm/memremap.c index 198083453182..9e9fb1972fff 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -1,17 +1,19 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +// SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2015 Intel Corporation. All rights reserved. */ #include <linux/device.h> #include <linux/io.h> #include <linux/kasan.h> #include <linux/memory_hotplug.h> -#include <linux/mm.h> +#include <linux/memremap.h> #include <linux/pfn_t.h> #include <linux/swap.h> +#include <linux/mm.h> #include <linux/mmzone.h> #include <linux/swapops.h> #include <linux/types.h> #include <linux/wait_bit.h> #include <linux/xarray.h> +#include "internal.h" static DEFINE_XARRAY(pgmap_array); @@ -37,35 +39,29 @@ unsigned long memremap_compat_align(void) EXPORT_SYMBOL_GPL(memremap_compat_align); #endif -#ifdef CONFIG_DEV_PAGEMAP_OPS +#ifdef CONFIG_FS_DAX DEFINE_STATIC_KEY_FALSE(devmap_managed_key); EXPORT_SYMBOL(devmap_managed_key); -static void devmap_managed_enable_put(void) +static void devmap_managed_enable_put(struct dev_pagemap *pgmap) { - static_branch_dec(&devmap_managed_key); + if (pgmap->type == MEMORY_DEVICE_FS_DAX) + static_branch_dec(&devmap_managed_key); } -static int devmap_managed_enable_get(struct dev_pagemap *pgmap) +static void devmap_managed_enable_get(struct dev_pagemap *pgmap) { - if (pgmap->type == MEMORY_DEVICE_PRIVATE && - (!pgmap->ops || !pgmap->ops->page_free)) { - WARN(1, "Missing page_free method\n"); - return -EINVAL; - } - - static_branch_inc(&devmap_managed_key); - return 0; + if (pgmap->type == MEMORY_DEVICE_FS_DAX) + static_branch_inc(&devmap_managed_key); } #else -static int devmap_managed_enable_get(struct dev_pagemap *pgmap) +static void devmap_managed_enable_get(struct dev_pagemap *pgmap) { - return -EINVAL; } -static void devmap_managed_enable_put(void) +static void devmap_managed_enable_put(struct dev_pagemap *pgmap) { } -#endif /* CONFIG_DEV_PAGEMAP_OPS */ +#endif /* CONFIG_FS_DAX */ static void pgmap_array_delete(struct range *range) { @@ -84,59 +80,43 @@ static unsigned long pfn_first(struct dev_pagemap *pgmap, int range_id) return pfn + vmem_altmap_offset(pgmap_altmap(pgmap)); } -static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id) +bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) { - const struct range *range = &pgmap->ranges[range_id]; + int i; - return (range->start + range_len(range)) >> PAGE_SHIFT; -} + for (i = 0; i < pgmap->nr_range; i++) { + struct range *range = &pgmap->ranges[i]; -static unsigned long pfn_next(unsigned long pfn) -{ - if (pfn % 1024 == 0) - cond_resched(); - return pfn + 1; -} + if (pfn >= PHYS_PFN(range->start) && + pfn <= PHYS_PFN(range->end)) + return pfn >= pfn_first(pgmap, i); + } -#define for_each_device_pfn(pfn, map, i) \ - for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); pfn = pfn_next(pfn)) + return false; +} -static void dev_pagemap_kill(struct dev_pagemap *pgmap) +static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id) { - if (pgmap->ops && pgmap->ops->kill) - pgmap->ops->kill(pgmap); - else - percpu_ref_kill(pgmap->ref); + const struct range *range = &pgmap->ranges[range_id]; + + return (range->start + range_len(range)) >> PAGE_SHIFT; } -static void dev_pagemap_cleanup(struct dev_pagemap *pgmap) +static unsigned long pfn_len(struct dev_pagemap *pgmap, unsigned long range_id) { - if (pgmap->ops && pgmap->ops->cleanup) { - pgmap->ops->cleanup(pgmap); - } else { - wait_for_completion(&pgmap->done); - percpu_ref_exit(pgmap->ref); - } - /* - * Undo the pgmap ref assignment for the internal case as the - * caller may re-enable the same pgmap. - */ - if (pgmap->ref == &pgmap->internal_ref) - pgmap->ref = NULL; + return (pfn_end(pgmap, range_id) - + pfn_first(pgmap, range_id)) >> pgmap->vmemmap_shift; } static void pageunmap_range(struct dev_pagemap *pgmap, int range_id) { struct range *range = &pgmap->ranges[range_id]; struct page *first_page; - int nid; /* make sure to access a memmap that was actually initialized */ 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); - mem_hotplug_begin(); remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(range->start), PHYS_PFN(range_len(range))); @@ -144,32 +124,34 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id) __remove_pages(PHYS_PFN(range->start), PHYS_PFN(range_len(range)), NULL); } else { - arch_remove_memory(nid, range->start, range_len(range), + arch_remove_memory(range->start, range_len(range), pgmap_altmap(pgmap)); kasan_remove_zero_shadow(__va(range->start), range_len(range)); } mem_hotplug_done(); - untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range)); + untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range), true); 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); + percpu_ref_kill(&pgmap->ref); + if (pgmap->type != MEMORY_DEVICE_PRIVATE && + pgmap->type != MEMORY_DEVICE_COHERENT) + for (i = 0; i < pgmap->nr_range; i++) + percpu_ref_put_many(&pgmap->ref, pfn_len(pgmap, i)); + + wait_for_completion(&pgmap->done); for (i = 0; i < pgmap->nr_range; i++) pageunmap_range(pgmap, i); + percpu_ref_exit(&pgmap->ref); WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n"); - devmap_managed_enable_put(); + devmap_managed_enable_put(pgmap); } EXPORT_SYMBOL_GPL(memunmap_pages); @@ -180,8 +162,7 @@ static void devm_memremap_pages_release(void *data) static void dev_pagemap_percpu_release(struct percpu_ref *ref) { - struct dev_pagemap *pgmap = - container_of(ref, struct dev_pagemap, internal_ref); + struct dev_pagemap *pgmap = container_of(ref, struct dev_pagemap, ref); complete(&pgmap->done); } @@ -189,6 +170,7 @@ static void dev_pagemap_percpu_release(struct percpu_ref *ref) static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, int range_id, int nid) { + const bool is_private = pgmap->type == MEMORY_DEVICE_PRIVATE; struct range *range = &pgmap->ranges[range_id]; struct dev_pagemap *conflict_pgmap; int error, is_ram; @@ -234,6 +216,11 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, if (error) goto err_pfn_remap; + if (!mhp_range_allowed(range->start, range_len(range), !is_private)) { + error = -EINVAL; + goto err_kasan; + } + mem_hotplug_begin(); /* @@ -247,7 +234,7 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, * the CPU, we do want the linear mapping and thus use * arch_add_memory(). */ - if (pgmap->type == MEMORY_DEVICE_PRIVATE) { + if (is_private) { error = add_pages(nid, PHYS_PFN(range->start), PHYS_PFN(range_len(range)), params); } else { @@ -266,7 +253,8 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, 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, + MIGRATE_MOVABLE); } mem_hotplug_done(); @@ -280,14 +268,16 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, 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, range_id) - - pfn_first(pgmap, range_id)); + if (pgmap->type != MEMORY_DEVICE_PRIVATE && + pgmap->type != MEMORY_DEVICE_COHERENT) + percpu_ref_get_many(&pgmap->ref, pfn_len(pgmap, range_id)); return 0; err_add_memory: - kasan_remove_zero_shadow(__va(range->start), range_len(range)); + if (!is_private) + kasan_remove_zero_shadow(__va(range->start), range_len(range)); err_kasan: - untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range)); + untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range), true); err_pfn_remap: pgmap_array_delete(range); return error; @@ -295,18 +285,18 @@ err_pfn_remap: /* - * Not device managed version of dev_memremap_pages, undone by - * memunmap_pages(). Please use dev_memremap_pages if you have a struct + * Not device managed version of devm_memremap_pages, undone by + * memunmap_pages(). Please use devm_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), + .pgmap = 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")) @@ -322,52 +312,49 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) WARN(1, "Missing migrate_to_ram method\n"); return ERR_PTR(-EINVAL); } + if (!pgmap->ops->page_free) { + WARN(1, "Missing page_free method\n"); + return ERR_PTR(-EINVAL); + } + if (!pgmap->owner) { + WARN(1, "Missing owner\n"); + return ERR_PTR(-EINVAL); + } + break; + case MEMORY_DEVICE_COHERENT: + if (!pgmap->ops->page_free) { + WARN(1, "Missing page_free 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)) { + if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) { WARN(1, "File system DAX not supported\n"); return ERR_PTR(-EINVAL); } + params.pgprot = pgprot_decrypted(params.pgprot); 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->ref, dev_pagemap_percpu_release, 0, + GFP_KERNEL); + if (error) + return ERR_PTR(error); - 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); - } + devmap_managed_enable_get(pgmap); /* * Clear the pgmap nr_range as it will be incremented for each @@ -399,7 +386,7 @@ EXPORT_SYMBOL_GPL(memremap_pages); * @pgmap: pointer to a struct dev_pagemap * * Notes: - * 1/ At a minimum the res and type members of @pgmap must be initialized + * 1/ At a minimum the range 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 @@ -436,19 +423,6 @@ void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap) } 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 */ - if (altmap) - return altmap->reserve + altmap->free; - return 0; -} - -void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) -{ - altmap->alloc -= nr_pfns; -} - /** * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn * @pfn: page frame number to lookup page_map @@ -474,7 +448,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, /* fall back to slow path lookup */ rcu_read_lock(); pgmap = xa_load(&pgmap_array, PHYS_PFN(phys)); - if (pgmap && !percpu_ref_tryget_live(pgmap->ref)) + if (pgmap && !percpu_ref_tryget_live_rcu(&pgmap->ref)) pgmap = NULL; rcu_read_unlock(); @@ -482,35 +456,28 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, } EXPORT_SYMBOL_GPL(get_dev_pagemap); -#ifdef CONFIG_DEV_PAGEMAP_OPS -void free_devmap_managed_page(struct page *page) +void free_zone_device_page(struct page *page) { - /* notify page idle for dax */ - if (!is_device_private_page(page)) { - wake_up_var(&page->_refcount); + if (WARN_ON_ONCE(!page->pgmap->ops || !page->pgmap->ops->page_free)) return; - } - __ClearPageWaiters(page); + mem_cgroup_uncharge(page_folio(page)); - mem_cgroup_uncharge(page); + /* + * Note: we don't expect anonymous compound pages yet. Once supported + * and we could PTE-map them similar to THP, we'd have to clear + * PG_anon_exclusive on all tail pages. + */ + VM_BUG_ON_PAGE(PageAnon(page) && PageCompound(page), page); + if (PageAnon(page)) + __ClearPageAnonExclusive(page); /* - * When a device_private page is freed, the page->mapping field + * When a device managed page is freed, the folio->mapping field * may still contain a (stale) mapping value. For example, the - * lower bits of page->mapping may still identify the page as an - * anonymous page. Ultimately, this entire field is just stale - * and wrong, and it will cause errors if not cleared. One - * example is: - * - * migrate_vma_pages() - * migrate_vma_insert_page() - * page_add_new_anon_rmap() - * __page_set_anon_rmap() - * ...checks page->mapping, via PageAnon(page) call, - * and incorrectly concludes that the page is an - * anonymous page. Therefore, it incorrectly, - * silently fails to set up the new anon rmap. + * lower bits of folio->mapping may still identify the folio as an + * anonymous folio. Ultimately, this entire field is just stale + * and wrong, and it will cause errors if not cleared. * * For other types of ZONE_DEVICE pages, migration is either * handled differently or not done at all, so there is no need @@ -518,5 +485,44 @@ void free_devmap_managed_page(struct page *page) */ page->mapping = NULL; page->pgmap->ops->page_free(page); + + if (page->pgmap->type != MEMORY_DEVICE_PRIVATE && + page->pgmap->type != MEMORY_DEVICE_COHERENT) + /* + * Reset the page count to 1 to prepare for handing out the page + * again. + */ + set_page_count(page, 1); + else + put_dev_pagemap(page->pgmap); +} + +void zone_device_page_init(struct page *page) +{ + /* + * Drivers shouldn't be allocating pages after calling + * memunmap_pages(). + */ + WARN_ON_ONCE(!percpu_ref_tryget_live(&page->pgmap->ref)); + set_page_count(page, 1); + lock_page(page); +} +EXPORT_SYMBOL_GPL(zone_device_page_init); + +#ifdef CONFIG_FS_DAX +bool __put_devmap_managed_page_refs(struct page *page, int refs) +{ + if (page->pgmap->type != MEMORY_DEVICE_FS_DAX) + return false; + + /* + * fsdax page refcounts are 1-based, rather than 0-based: if + * refcount is 1, then the page is free and the refcount is + * stable because nobody holds a reference on the page. + */ + if (page_ref_sub_return(page, refs) == 1) + wake_up_var(&page->_refcount); + return true; } -#endif /* CONFIG_DEV_PAGEMAP_OPS */ +EXPORT_SYMBOL(__put_devmap_managed_page_refs); +#endif /* CONFIG_FS_DAX */ |