diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Makefile | 1 | ||||
| -rw-r--r-- | mm/balloon_compaction.c | 69 | ||||
| -rw-r--r-- | mm/compaction.c | 11 | ||||
| -rw-r--r-- | mm/hmm.c | 10 | ||||
| -rw-r--r-- | mm/kmemleak.c | 2 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 2 | ||||
| -rw-r--r-- | mm/memremap.c | 411 | ||||
| -rw-r--r-- | mm/migrate.c | 21 | ||||
| -rw-r--r-- | mm/slub.c | 8 | ||||
| -rw-r--r-- | mm/vmalloc.c | 9 | ||||
| -rw-r--r-- | mm/vmscan.c | 9 |
11 files changed, 498 insertions, 55 deletions
diff --git a/mm/Makefile b/mm/Makefile index 338e528ad436..d0b295c3b764 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -102,5 +102,6 @@ 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-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_HMM_MIRROR) += hmm.o obj-$(CONFIG_MEMFD_CREATE) += memfd.o diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index 83a7b614061f..798275a51887 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -21,7 +21,6 @@ static void balloon_page_enqueue_one(struct balloon_dev_info *b_dev_info, * memory corruption is possible and we should stop execution. */ BUG_ON(!trylock_page(page)); - list_del(&page->lru); balloon_page_insert(b_dev_info, page); unlock_page(page); __count_vm_event(BALLOON_INFLATE); @@ -33,8 +32,8 @@ static void balloon_page_enqueue_one(struct balloon_dev_info *b_dev_info, * @b_dev_info: balloon device descriptor where we will insert a new page to * @pages: pages to enqueue - allocated using balloon_page_alloc. * - * Driver must call it to properly enqueue a balloon pages before definitively - * removing it from the guest system. + * Driver must call this function to properly enqueue balloon pages before + * definitively removing them from the guest system. * * Return: number of pages that were enqueued. */ @@ -47,6 +46,7 @@ size_t balloon_page_list_enqueue(struct balloon_dev_info *b_dev_info, spin_lock_irqsave(&b_dev_info->pages_lock, flags); list_for_each_entry_safe(page, tmp, pages, lru) { + list_del(&page->lru); balloon_page_enqueue_one(b_dev_info, page); n_pages++; } @@ -63,12 +63,13 @@ EXPORT_SYMBOL_GPL(balloon_page_list_enqueue); * @n_req_pages: number of requested pages. * * Driver must call this function to properly de-allocate a previous enlisted - * balloon pages before definetively releasing it back to the guest system. + * balloon pages before definitively releasing it back to the guest system. * This function tries to remove @n_req_pages from the ballooned pages and * return them to the caller in the @pages list. * - * Note that this function may fail to dequeue some pages temporarily empty due - * to compaction isolated pages. + * Note that this function may fail to dequeue some pages even if the balloon + * isn't empty - since the page list can be temporarily empty due to compaction + * of isolated pages. * * Return: number of pages that were added to the @pages list. */ @@ -112,12 +113,13 @@ EXPORT_SYMBOL_GPL(balloon_page_list_dequeue); /* * balloon_page_alloc - allocates a new page for insertion into the balloon - * page list. + * page list. + * + * Driver must call this function to properly allocate a new balloon page. + * Driver must call balloon_page_enqueue before definitively removing the page + * from the guest system. * - * Driver must call it to properly allocate a new enlisted balloon page. - * Driver must call balloon_page_enqueue before definitively removing it from - * the guest system. This function returns the page address for the recently - * allocated page or NULL in the case we fail to allocate a new page this turn. + * Return: struct page for the allocated page or NULL on allocation failure. */ struct page *balloon_page_alloc(void) { @@ -128,15 +130,17 @@ struct page *balloon_page_alloc(void) EXPORT_SYMBOL_GPL(balloon_page_alloc); /* - * balloon_page_enqueue - allocates a new page and inserts it into the balloon - * page list. - * @b_dev_info: balloon device descriptor where we will insert a new page to + * balloon_page_enqueue - inserts a new page into the balloon page list. + * + * @b_dev_info: balloon device descriptor where we will insert a new page * @page: new page to enqueue - allocated using balloon_page_alloc. * - * Driver must call it to properly enqueue a new allocated balloon page - * before definitively removing it from the guest system. - * This function returns the page address for the recently enqueued page or - * NULL in the case we fail to allocate a new page this turn. + * Drivers must call this function to properly enqueue a new allocated balloon + * page before definitively removing the page from the guest system. + * + * Drivers must not call balloon_page_enqueue on pages that have been pushed to + * a list with balloon_page_push before removing them with balloon_page_pop. To + * enqueue a list of pages, use balloon_page_list_enqueue instead. */ void balloon_page_enqueue(struct balloon_dev_info *b_dev_info, struct page *page) @@ -151,14 +155,23 @@ EXPORT_SYMBOL_GPL(balloon_page_enqueue); /* * balloon_page_dequeue - removes a page from balloon's page list and returns - * the its address to allow the driver release the page. + * its address to allow the driver to release the page. * @b_dev_info: balloon device decriptor where we will grab a page from. * - * Driver must call it to properly de-allocate a previous enlisted balloon page - * before definetively releasing it back to the guest system. - * This function returns the page address for the recently dequeued page or - * NULL in the case we find balloon's page list temporarily empty due to - * compaction isolated pages. + * Driver must call this function to properly dequeue a previously enqueued page + * before definitively releasing it back to the guest system. + * + * Caller must perform its own accounting to ensure that this + * function is called only if some pages are actually enqueued. + * + * Note that this function may fail to dequeue some pages even if there are + * some enqueued pages - since the page list can be temporarily empty due to + * the compaction of isolated pages. + * + * TODO: remove the caller accounting requirements, and allow caller to wait + * until all pages can be dequeued. + * + * Return: struct page for the dequeued page, or NULL if no page was dequeued. */ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info) { @@ -171,9 +184,9 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info) if (n_pages != 1) { /* * If we are unable to dequeue a balloon page because the page - * list is empty and there is no isolated pages, then something + * list is empty and there are no isolated pages, then something * went out of track and some balloon pages are lost. - * BUG() here, otherwise the balloon driver may get stuck into + * BUG() here, otherwise the balloon driver may get stuck in * an infinite loop while attempting to release all its pages. */ spin_lock_irqsave(&b_dev_info->pages_lock, flags); @@ -224,8 +237,8 @@ int balloon_page_migrate(struct address_space *mapping, /* * We can not easily support the no copy case here so ignore it as it - * is unlikely to be use with ballon pages. See include/linux/hmm.h for - * user of the MIGRATE_SYNC_NO_COPY mode. + * is unlikely to be used with balloon pages. See include/linux/hmm.h + * for a user of the MIGRATE_SYNC_NO_COPY mode. */ if (mode == MIGRATE_SYNC_NO_COPY) return -EINVAL; diff --git a/mm/compaction.c b/mm/compaction.c index 9e1b9acb116b..952dc2fb24e5 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -842,13 +842,15 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, /* * Periodically drop the lock (if held) regardless of its - * contention, to give chance to IRQs. Abort async compaction - * if contended. + * contention, to give chance to IRQs. Abort completely if + * a fatal signal is pending. */ if (!(low_pfn % SWAP_CLUSTER_MAX) && compact_unlock_should_abort(&pgdat->lru_lock, - flags, &locked, cc)) - break; + flags, &locked, cc)) { + low_pfn = 0; + goto fatal_pending; + } if (!pfn_valid_within(low_pfn)) goto isolate_fail; @@ -1060,6 +1062,7 @@ isolate_abort: trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn, nr_scanned, nr_isolated); +fatal_pending: cc->total_migrate_scanned += nr_scanned; if (nr_isolated) count_compact_events(COMPACTISOLATED, nr_isolated); @@ -946,7 +946,7 @@ EXPORT_SYMBOL(hmm_range_unregister); * @range: range * Return: -EINVAL if invalid argument, -ENOMEM out of memory, -EPERM invalid * permission (for instance asking for write and range is read only), - * -EAGAIN if you need to retry, -EFAULT invalid (ie either no valid + * -EBUSY if you need to retry, -EFAULT invalid (ie either no valid * vma or it is illegal to access that range), number of valid pages * in range->pfns[] (from range start address). * @@ -967,7 +967,7 @@ long hmm_range_snapshot(struct hmm_range *range) do { /* If range is no longer valid force retry. */ if (!range->valid) - return -EAGAIN; + return -EBUSY; vma = find_vma(hmm->mm, start); if (vma == NULL || (vma->vm_flags & device_vma)) @@ -1062,10 +1062,8 @@ long hmm_range_fault(struct hmm_range *range, bool block) do { /* If range is no longer valid force retry. */ - if (!range->valid) { - up_read(&hmm->mm->mmap_sem); - return -EAGAIN; - } + if (!range->valid) + return -EBUSY; vma = find_vma(hmm->mm, start); if (vma == NULL || (vma->vm_flags & device_vma)) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index dbbd518fb6b3..6e9e8cca663e 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -114,7 +114,7 @@ /* GFP bitmask for kmemleak internal allocations */ #define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \ __GFP_NORETRY | __GFP_NOMEMALLOC | \ - __GFP_NOWARN | __GFP_NOFAIL) + __GFP_NOWARN) /* scanning area inside a memory block */ struct kmemleak_scan_area { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 2a9bbddb0e55..c73f09913165 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -132,7 +132,6 @@ static void release_memory_resource(struct resource *res) return; release_resource(res); kfree(res); - return; } #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE @@ -979,7 +978,6 @@ static void rollback_node_hotadd(int nid) arch_refresh_nodedata(nid, NULL); free_percpu(pgdat->per_cpu_nodestats); arch_free_nodedata(pgdat); - return; } diff --git a/mm/memremap.c b/mm/memremap.c new file mode 100644 index 000000000000..86432650f829 --- /dev/null +++ b/mm/memremap.c @@ -0,0 +1,411 @@ +/* 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/pfn_t.h> +#include <linux/swap.h> +#include <linux/swapops.h> +#include <linux/types.h> +#include <linux/wait_bit.h> +#include <linux/xarray.h> + +static DEFINE_XARRAY(pgmap_array); +#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) +#define SECTION_SIZE (1UL << PA_SECTION_SHIFT) + +#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) +{ + if (atomic_dec_and_test(&devmap_managed_enable)) + static_branch_disable(&devmap_managed_key); +} + +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; + } + + 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); +} +#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) +{ + xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end), + NULL, GFP_KERNEL); + synchronize_rcu(); +} + +static unsigned long pfn_first(struct dev_pagemap *pgmap) +{ + return PHYS_PFN(pgmap->res.start) + + vmem_altmap_offset(pgmap_altmap(pgmap)); +} + +static unsigned long pfn_end(struct dev_pagemap *pgmap) +{ + const struct resource *res = &pgmap->res; + + return (res->start + resource_size(res)) >> PAGE_SHIFT; +} + +static unsigned long pfn_next(unsigned long pfn) +{ + if (pfn % 1024 == 0) + cond_resched(); + return pfn + 1; +} + +#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); + } + /* + * 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; +} + +static void devm_memremap_pages_release(void *data) +{ + struct dev_pagemap *pgmap = data; + struct device *dev = pgmap->dev; + struct resource *res = &pgmap->res; + 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); + + /* pages are dead and unused, undo the arch mapping */ + nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start))); + + mem_hotplug_begin(); + if (pgmap->type == MEMORY_DEVICE_PRIVATE) { + pfn = PHYS_PFN(res->start); + __remove_pages(page_zone(pfn_to_page(pfn)), pfn, + PHYS_PFN(resource_size(res)), NULL); + } else { + arch_remove_memory(nid, res->start, resource_size(res), + pgmap_altmap(pgmap)); + kasan_remove_zero_shadow(__va(res->start), resource_size(res)); + } + mem_hotplug_done(); + + untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res)); + pgmap_array_delete(res); + dev_WARN_ONCE(dev, pgmap->altmap.alloc, + "%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 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 + * PGMAP_ALTMAP_VALID must be set in pgmap->flags. + * + * 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 + * this is not enforced. + */ +void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) +{ + 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 = 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 (need_devmap_managed) { + error = devmap_managed_enable_get(dev, pgmap); + if (error) + return ERR_PTR(error); + } + + conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL); + if (conflict_pgmap) { + dev_WARN(dev, "Conflicting mapping in same section\n"); + put_dev_pagemap(conflict_pgmap); + error = -ENOMEM; + goto err_array; + } + + conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL); + if (conflict_pgmap) { + dev_WARN(dev, "Conflicting mapping in same section\n"); + put_dev_pagemap(conflict_pgmap); + error = -ENOMEM; + goto err_array; + } + + is_ram = region_intersects(res->start, resource_size(res), + IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); + + if (is_ram != REGION_DISJOINT) { + WARN_ONCE(1, "%s attempted on %s region %pr\n", __func__, + is_ram == REGION_MIXED ? "mixed" : "ram", res); + error = -ENXIO; + goto err_array; + } + + pgmap->dev = dev; + + error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start), + PHYS_PFN(res->end), pgmap, GFP_KERNEL)); + if (error) + goto err_array; + + nid = dev_to_node(dev); + if (nid < 0) + nid = numa_mem_id(); + + error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(res->start), 0, + resource_size(res)); + if (error) + goto err_pfn_remap; + + mem_hotplug_begin(); + + /* + * For device private memory we call add_pages() as we only need to + * allocate and initialize struct page for the device memory. More- + * over the device memory is un-accessible thus we do not want to + * create a linear mapping for the memory like arch_add_memory() + * would do. + * + * For all other device memory types, which are accessible by + * the CPU, we do want the linear mapping and thus use + * arch_add_memory(). + */ + if (pgmap->type == MEMORY_DEVICE_PRIVATE) { + error = add_pages(nid, PHYS_PFN(res->start), + PHYS_PFN(resource_size(res)), &restrictions); + } else { + error = kasan_add_zero_shadow(__va(res->start), resource_size(res)); + if (error) { + mem_hotplug_done(); + goto err_kasan; + } + + error = arch_add_memory(nid, res->start, resource_size(res), + &restrictions); + } + + if (!error) { + struct zone *zone; + + zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE]; + move_pfn_range_to_zone(zone, PHYS_PFN(res->start), + PHYS_PFN(resource_size(res)), restrictions.altmap); + } + + mem_hotplug_done(); + if (error) + goto err_add_memory; + + /* + * Initialization of the pages has been deferred until now in order + * to allow us to do the work while not holding the hotplug lock. + */ + memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], + PHYS_PFN(res->start), + PHYS_PFN(resource_size(res)), pgmap); + percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap)); + + error = devm_add_action_or_reset(dev, devm_memremap_pages_release, + pgmap); + if (error) + return ERR_PTR(error); + + return __va(res->start); + + err_add_memory: + kasan_remove_zero_shadow(__va(res->start), resource_size(res)); + err_kasan: + untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res)); + err_pfn_remap: + pgmap_array_delete(res); + err_array: + dev_pagemap_kill(pgmap); + dev_pagemap_cleanup(pgmap); + return ERR_PTR(error); +} +EXPORT_SYMBOL_GPL(devm_memremap_pages); + +void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap) +{ + devm_release_action(dev, devm_memremap_pages_release, 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 + * @pgmap: optional known pgmap that already has a reference + * + * If @pgmap is non-NULL and covers @pfn it will be returned as-is. If @pgmap + * is non-NULL but does not cover @pfn the reference to it will be released. + */ +struct dev_pagemap *get_dev_pagemap(unsigned long pfn, + struct dev_pagemap *pgmap) +{ + resource_size_t phys = PFN_PHYS(pfn); + + /* + * In the cached case we're already holding a live reference. + */ + if (pgmap) { + if (phys >= pgmap->res.start && phys <= pgmap->res.end) + return pgmap; + put_dev_pagemap(pgmap); + } + + /* 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)) + pgmap = NULL; + rcu_read_unlock(); + + return pgmap; +} +EXPORT_SYMBOL_GPL(get_dev_pagemap); + +#ifdef CONFIG_DEV_PAGEMAP_OPS +void __put_devmap_managed_page(struct page *page) +{ + int count = page_ref_dec_return(page); + + /* + * If refcount is 1 then page is freed and refcount is stable as nobody + * holds a reference on the page. + */ + if (count == 1) { + /* Clear Active bit in case of parallel mark_page_accessed */ + __ClearPageActive(page); + __ClearPageWaiters(page); + + mem_cgroup_uncharge(page); + + page->pgmap->ops->page_free(page); + } else if (!count) + __put_page(page); +} +EXPORT_SYMBOL(__put_devmap_managed_page); +#endif /* CONFIG_DEV_PAGEMAP_OPS */ diff --git a/mm/migrate.c b/mm/migrate.c index 8992741f10aa..a42858d8e00b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -767,12 +767,12 @@ recheck_buffers: } bh = bh->b_this_page; } while (bh != head); - spin_unlock(&mapping->private_lock); if (busy) { if (invalidated) { rc = -EAGAIN; goto unlock_buffers; } + spin_unlock(&mapping->private_lock); invalidate_bh_lrus(); invalidated = true; goto recheck_buffers; @@ -805,6 +805,8 @@ recheck_buffers: rc = MIGRATEPAGE_SUCCESS; unlock_buffers: + if (check_refs) + spin_unlock(&mapping->private_lock); bh = head; do { unlock_buffer(bh); @@ -2338,16 +2340,13 @@ next: static void migrate_vma_collect(struct migrate_vma *migrate) { struct mmu_notifier_range range; - struct mm_walk mm_walk; - - mm_walk.pmd_entry = migrate_vma_collect_pmd; - mm_walk.pte_entry = NULL; - mm_walk.pte_hole = migrate_vma_collect_hole; - mm_walk.hugetlb_entry = NULL; - mm_walk.test_walk = NULL; - mm_walk.vma = migrate->vma; - mm_walk.mm = migrate->vma->vm_mm; - mm_walk.private = migrate; + struct mm_walk mm_walk = { + .pmd_entry = migrate_vma_collect_pmd, + .pte_hole = migrate_vma_collect_hole, + .vma = migrate->vma, + .mm = migrate->vma->vm_mm, + .private = migrate, + }; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm_walk.mm, migrate->start, diff --git a/mm/slub.c b/mm/slub.c index e6c030e47364..8834563cdb4b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1432,7 +1432,9 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, void *old_tail = *tail ? *tail : *head; int rsize; - if (slab_want_init_on_free(s)) + if (slab_want_init_on_free(s)) { + void *p = NULL; + do { object = next; next = get_freepointer(s, object); @@ -1445,8 +1447,10 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, : 0; memset((char *)object + s->inuse, 0, s->size - s->inuse - rsize); - set_freepointer(s, object, next); + set_freepointer(s, object, p); + p = object; } while (object != old_tail); + } /* * Compiler cannot detect this function can be removed if slab_free_hook() diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 4fa8d84599b0..e0fc963acc41 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1259,6 +1259,12 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) return false; /* + * First make sure the mappings are removed from all page-tables + * before they are freed. + */ + vmalloc_sync_all(); + + /* * TODO: to calculate a flush range without looping. * The list can be up to lazy_max_pages() elements. */ @@ -3038,6 +3044,9 @@ EXPORT_SYMBOL(remap_vmalloc_range); /* * Implement a stub for vmalloc_sync_all() if the architecture chose not to * have one. + * + * The purpose of this function is to make sure the vmalloc area + * mappings are identical in all page-tables in the system. */ void __weak vmalloc_sync_all(void) { diff --git a/mm/vmscan.c b/mm/vmscan.c index 44df66a98f2a..dbdc46a84f63 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -699,7 +699,14 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, unsigned long ret, freed = 0; struct shrinker *shrinker; - if (!mem_cgroup_is_root(memcg)) + /* + * The root memcg might be allocated even though memcg is disabled + * via "cgroup_disable=memory" boot parameter. This could make + * mem_cgroup_is_root() return false, then just run memcg slab + * shrink, but skip global shrink. This may result in premature + * oom. + */ + if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); if (!down_read_trylock(&shrinker_rwsem)) |