diff options
Diffstat (limited to '')
| -rw-r--r-- | mm/hugetlb.c | 4764 |
1 files changed, 3655 insertions, 1109 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c index dd8737a94bec..e48f8ef45b17 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -19,6 +19,7 @@ #include <linux/memblock.h> #include <linux/sysfs.h> #include <linux/slab.h> +#include <linux/sched/mm.h> #include <linux/mmdebug.h> #include <linux/sched/signal.h> #include <linux/rmap.h> @@ -28,35 +29,52 @@ #include <linux/jhash.h> #include <linux/numa.h> #include <linux/llist.h> +#include <linux/cma.h> +#include <linux/migrate.h> +#include <linux/nospec.h> +#include <linux/delayacct.h> +#include <linux/memory.h> #include <asm/page.h> -#include <asm/pgtable.h> +#include <asm/pgalloc.h> #include <asm/tlb.h> #include <linux/io.h> #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> #include <linux/node.h> -#include <linux/userfaultfd_k.h> #include <linux/page_owner.h> #include "internal.h" +#include "hugetlb_vmemmap.h" int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; -/* - * Minimum page order among possible hugepage sizes, set to a proper value - * at boot time. - */ -static unsigned int minimum_order __read_mostly = UINT_MAX; + +#ifdef CONFIG_CMA +static struct cma *hugetlb_cma[MAX_NUMNODES]; +static unsigned long hugetlb_cma_size_in_node[MAX_NUMNODES] __initdata; +static bool hugetlb_cma_page(struct page *page, unsigned int order) +{ + return cma_pages_valid(hugetlb_cma[page_to_nid(page)], page, + 1 << order); +} +#else +static bool hugetlb_cma_page(struct page *page, unsigned int order) +{ + return false; +} +#endif +static unsigned long hugetlb_cma_size __initdata; __initdata LIST_HEAD(huge_boot_pages); /* for command line parsing */ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; -static unsigned long __initdata default_hstate_size; static bool __initdata parsed_valid_hugepagesz = true; +static bool __initdata parsed_default_hugepagesz; +static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata; /* * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, @@ -73,17 +91,31 @@ struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp; /* Forward declaration */ static int hugetlb_acct_memory(struct hstate *h, long delta); +static void hugetlb_vma_lock_free(struct vm_area_struct *vma); +static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma); +static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma); -static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) +static inline bool subpool_is_free(struct hugepage_subpool *spool) { - bool free = (spool->count == 0) && (spool->used_hpages == 0); + if (spool->count) + return false; + if (spool->max_hpages != -1) + return spool->used_hpages == 0; + if (spool->min_hpages != -1) + return spool->rsv_hpages == spool->min_hpages; + + return true; +} - spin_unlock(&spool->lock); +static inline void unlock_or_release_subpool(struct hugepage_subpool *spool, + unsigned long irq_flags) +{ + spin_unlock_irqrestore(&spool->lock, irq_flags); /* If no pages are used, and no other handles to the subpool - * remain, give up any reservations mased on minimum size and + * remain, give up any reservations based on minimum size and * free the subpool */ - if (free) { + if (subpool_is_free(spool)) { if (spool->min_hpages != -1) hugetlb_acct_memory(spool->hstate, -spool->min_hpages); @@ -117,19 +149,21 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, void hugepage_put_subpool(struct hugepage_subpool *spool) { - spin_lock(&spool->lock); + unsigned long flags; + + spin_lock_irqsave(&spool->lock, flags); BUG_ON(!spool->count); spool->count--; - unlock_or_release_subpool(spool); + unlock_or_release_subpool(spool, flags); } /* * Subpool accounting for allocating and reserving pages. * Return -ENOMEM if there are not enough resources to satisfy the - * the request. Otherwise, return the number of pages by which the + * request. Otherwise, return the number of pages by which the * global pools must be adjusted (upward). The returned value may * only be different than the passed value (delta) in the case where - * a subpool minimum size must be manitained. + * a subpool minimum size must be maintained. */ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, long delta) @@ -139,7 +173,7 @@ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, if (!spool) return ret; - spin_lock(&spool->lock); + spin_lock_irq(&spool->lock); if (spool->max_hpages != -1) { /* maximum size accounting */ if ((spool->used_hpages + delta) <= spool->max_hpages) @@ -166,7 +200,7 @@ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, } unlock_ret: - spin_unlock(&spool->lock); + spin_unlock_irq(&spool->lock); return ret; } @@ -180,11 +214,12 @@ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; + unsigned long flags; if (!spool) return delta; - spin_lock(&spool->lock); + spin_lock_irqsave(&spool->lock, flags); if (spool->max_hpages != -1) /* maximum size accounting */ spool->used_hpages -= delta; @@ -205,7 +240,7 @@ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, * If hugetlbfs_put_super couldn't free spool due to an outstanding * quota reference, free it now. */ - unlock_or_release_subpool(spool); + unlock_or_release_subpool(spool, flags); return ret; } @@ -220,134 +255,322 @@ static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) return subpool_inode(file_inode(vma->vm_file)); } -/* - * Region tracking -- allows tracking of reservations and instantiated pages - * across the pages in a mapping. - * - * The region data structures are embedded into a resv_map and protected - * by a resv_map's lock. The set of regions within the resv_map represent - * reservations for huge pages, or huge pages that have already been - * instantiated within the map. The from and to elements are huge page - * indicies into the associated mapping. from indicates the starting index - * of the region. to represents the first index past the end of the region. - * - * For example, a file region structure with from == 0 and to == 4 represents - * four huge pages in a mapping. It is important to note that the to element - * represents the first element past the end of the region. This is used in - * arithmetic as 4(to) - 0(from) = 4 huge pages in the region. - * - * Interval notation of the form [from, to) will be used to indicate that - * the endpoint from is inclusive and to is exclusive. +/* Helper that removes a struct file_region from the resv_map cache and returns + * it for use. */ -struct file_region { - struct list_head link; - long from; - long to; -}; +static struct file_region * +get_file_region_entry_from_cache(struct resv_map *resv, long from, long to) +{ + struct file_region *nrg; + + VM_BUG_ON(resv->region_cache_count <= 0); + + resv->region_cache_count--; + nrg = list_first_entry(&resv->region_cache, struct file_region, link); + list_del(&nrg->link); + + nrg->from = from; + nrg->to = to; + + return nrg; +} + +static void copy_hugetlb_cgroup_uncharge_info(struct file_region *nrg, + struct file_region *rg) +{ +#ifdef CONFIG_CGROUP_HUGETLB + nrg->reservation_counter = rg->reservation_counter; + nrg->css = rg->css; + if (rg->css) + css_get(rg->css); +#endif +} + +/* Helper that records hugetlb_cgroup uncharge info. */ +static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg, + struct hstate *h, + struct resv_map *resv, + struct file_region *nrg) +{ +#ifdef CONFIG_CGROUP_HUGETLB + if (h_cg) { + nrg->reservation_counter = + &h_cg->rsvd_hugepage[hstate_index(h)]; + nrg->css = &h_cg->css; + /* + * The caller will hold exactly one h_cg->css reference for the + * whole contiguous reservation region. But this area might be + * scattered when there are already some file_regions reside in + * it. As a result, many file_regions may share only one css + * reference. In order to ensure that one file_region must hold + * exactly one h_cg->css reference, we should do css_get for + * each file_region and leave the reference held by caller + * untouched. + */ + css_get(&h_cg->css); + if (!resv->pages_per_hpage) + resv->pages_per_hpage = pages_per_huge_page(h); + /* pages_per_hpage should be the same for all entries in + * a resv_map. + */ + VM_BUG_ON(resv->pages_per_hpage != pages_per_huge_page(h)); + } else { + nrg->reservation_counter = NULL; + nrg->css = NULL; + } +#endif +} + +static void put_uncharge_info(struct file_region *rg) +{ +#ifdef CONFIG_CGROUP_HUGETLB + if (rg->css) + css_put(rg->css); +#endif +} + +static bool has_same_uncharge_info(struct file_region *rg, + struct file_region *org) +{ +#ifdef CONFIG_CGROUP_HUGETLB + return rg->reservation_counter == org->reservation_counter && + rg->css == org->css; + +#else + return true; +#endif +} + +static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) +{ + struct file_region *nrg, *prg; -/* Must be called with resv->lock held. Calling this with count_only == true - * will count the number of pages to be added but will not modify the linked - * list. + prg = list_prev_entry(rg, link); + if (&prg->link != &resv->regions && prg->to == rg->from && + has_same_uncharge_info(prg, rg)) { + prg->to = rg->to; + + list_del(&rg->link); + put_uncharge_info(rg); + kfree(rg); + + rg = prg; + } + + nrg = list_next_entry(rg, link); + if (&nrg->link != &resv->regions && nrg->from == rg->to && + has_same_uncharge_info(nrg, rg)) { + nrg->from = rg->from; + + list_del(&rg->link); + put_uncharge_info(rg); + kfree(rg); + } +} + +static inline long +hugetlb_resv_map_add(struct resv_map *map, struct list_head *rg, long from, + long to, struct hstate *h, struct hugetlb_cgroup *cg, + long *regions_needed) +{ + struct file_region *nrg; + + if (!regions_needed) { + nrg = get_file_region_entry_from_cache(map, from, to); + record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg); + list_add(&nrg->link, rg); + coalesce_file_region(map, nrg); + } else + *regions_needed += 1; + + return to - from; +} + +/* + * Must be called with resv->lock held. + * + * Calling this with regions_needed != NULL will count the number of pages + * to be added but will not modify the linked list. And regions_needed will + * indicate the number of file_regions needed in the cache to carry out to add + * the regions for this range. */ static long add_reservation_in_range(struct resv_map *resv, long f, long t, - bool count_only) + struct hugetlb_cgroup *h_cg, + struct hstate *h, long *regions_needed) { - long chg = 0; + long add = 0; struct list_head *head = &resv->regions; - struct file_region *rg = NULL, *trg = NULL, *nrg = NULL; + long last_accounted_offset = f; + struct file_region *iter, *trg = NULL; + struct list_head *rg = NULL; + + if (regions_needed) + *regions_needed = 0; + + /* In this loop, we essentially handle an entry for the range + * [last_accounted_offset, iter->from), at every iteration, with some + * bounds checking. + */ + list_for_each_entry_safe(iter, trg, head, link) { + /* Skip irrelevant regions that start before our range. */ + if (iter->from < f) { + /* If this region ends after the last accounted offset, + * then we need to update last_accounted_offset. + */ + if (iter->to > last_accounted_offset) + last_accounted_offset = iter->to; + continue; + } - /* Locate the region we are before or in. */ - list_for_each_entry(rg, head, link) - if (f <= rg->to) + /* When we find a region that starts beyond our range, we've + * finished. + */ + if (iter->from >= t) { + rg = iter->link.prev; break; + } - /* Round our left edge to the current segment if it encloses us. */ - if (f > rg->from) - f = rg->from; + /* Add an entry for last_accounted_offset -> iter->from, and + * update last_accounted_offset. + */ + if (iter->from > last_accounted_offset) + add += hugetlb_resv_map_add(resv, iter->link.prev, + last_accounted_offset, + iter->from, h, h_cg, + regions_needed); - chg = t - f; + last_accounted_offset = iter->to; + } - /* Check for and consume any regions we now overlap with. */ - nrg = rg; - list_for_each_entry_safe(rg, trg, rg->link.prev, link) { - if (&rg->link == head) - break; - if (rg->from > t) - break; + /* Handle the case where our range extends beyond + * last_accounted_offset. + */ + if (!rg) + rg = head->prev; + if (last_accounted_offset < t) + add += hugetlb_resv_map_add(resv, rg, last_accounted_offset, + t, h, h_cg, regions_needed); + + return add; +} - /* We overlap with this area, if it extends further than - * us then we must extend ourselves. Account for its - * existing reservation. +/* Must be called with resv->lock acquired. Will drop lock to allocate entries. + */ +static int allocate_file_region_entries(struct resv_map *resv, + int regions_needed) + __must_hold(&resv->lock) +{ + LIST_HEAD(allocated_regions); + int to_allocate = 0, i = 0; + struct file_region *trg = NULL, *rg = NULL; + + VM_BUG_ON(regions_needed < 0); + + /* + * Check for sufficient descriptors in the cache to accommodate + * the number of in progress add operations plus regions_needed. + * + * This is a while loop because when we drop the lock, some other call + * to region_add or region_del may have consumed some region_entries, + * so we keep looping here until we finally have enough entries for + * (adds_in_progress + regions_needed). + */ + while (resv->region_cache_count < + (resv->adds_in_progress + regions_needed)) { + to_allocate = resv->adds_in_progress + regions_needed - + resv->region_cache_count; + + /* At this point, we should have enough entries in the cache + * for all the existing adds_in_progress. We should only be + * needing to allocate for regions_needed. */ - if (rg->to > t) { - chg += rg->to - t; - t = rg->to; - } - chg -= rg->to - rg->from; + VM_BUG_ON(resv->region_cache_count < resv->adds_in_progress); - if (!count_only && rg != nrg) { - list_del(&rg->link); - kfree(rg); + spin_unlock(&resv->lock); + for (i = 0; i < to_allocate; i++) { + trg = kmalloc(sizeof(*trg), GFP_KERNEL); + if (!trg) + goto out_of_memory; + list_add(&trg->link, &allocated_regions); } - } - if (!count_only) { - nrg->from = f; - nrg->to = t; + spin_lock(&resv->lock); + + list_splice(&allocated_regions, &resv->region_cache); + resv->region_cache_count += to_allocate; } - return chg; + return 0; + +out_of_memory: + list_for_each_entry_safe(rg, trg, &allocated_regions, link) { + list_del(&rg->link); + kfree(rg); + } + return -ENOMEM; } /* * Add the huge page range represented by [f, t) to the reserve - * map. Existing regions will be expanded to accommodate the specified - * range, or a region will be taken from the cache. Sufficient regions - * must exist in the cache due to the previous call to region_chg with - * the same range. + * map. Regions will be taken from the cache to fill in this range. + * Sufficient regions should exist in the cache due to the previous + * call to region_chg with the same range, but in some cases the cache will not + * have sufficient entries due to races with other code doing region_add or + * region_del. The extra needed entries will be allocated. + * + * regions_needed is the out value provided by a previous call to region_chg. * - * Return the number of new huge pages added to the map. This - * number is greater than or equal to zero. + * Return the number of new huge pages added to the map. This number is greater + * than or equal to zero. If file_region entries needed to be allocated for + * this operation and we were not able to allocate, it returns -ENOMEM. + * region_add of regions of length 1 never allocate file_regions and cannot + * fail; region_chg will always allocate at least 1 entry and a region_add for + * 1 page will only require at most 1 entry. */ -static long region_add(struct resv_map *resv, long f, long t) +static long region_add(struct resv_map *resv, long f, long t, + long in_regions_needed, struct hstate *h, + struct hugetlb_cgroup *h_cg) { - struct list_head *head = &resv->regions; - struct file_region *rg, *nrg; - long add = 0; + long add = 0, actual_regions_needed = 0; spin_lock(&resv->lock); - /* Locate the region we are either in or before. */ - list_for_each_entry(rg, head, link) - if (f <= rg->to) - break; +retry: + + /* Count how many regions are actually needed to execute this add. */ + add_reservation_in_range(resv, f, t, NULL, NULL, + &actual_regions_needed); /* - * If no region exists which can be expanded to include the - * specified range, pull a region descriptor from the cache - * and use it for this range. + * Check for sufficient descriptors in the cache to accommodate + * this add operation. Note that actual_regions_needed may be greater + * than in_regions_needed, as the resv_map may have been modified since + * the region_chg call. In this case, we need to make sure that we + * allocate extra entries, such that we have enough for all the + * existing adds_in_progress, plus the excess needed for this + * operation. */ - if (&rg->link == head || t < rg->from) { - VM_BUG_ON(resv->region_cache_count <= 0); - - resv->region_cache_count--; - nrg = list_first_entry(&resv->region_cache, struct file_region, - link); - list_del(&nrg->link); + if (actual_regions_needed > in_regions_needed && + resv->region_cache_count < + resv->adds_in_progress + + (actual_regions_needed - in_regions_needed)) { + /* region_add operation of range 1 should never need to + * allocate file_region entries. + */ + VM_BUG_ON(t - f <= 1); - nrg->from = f; - nrg->to = t; - list_add(&nrg->link, rg->link.prev); + if (allocate_file_region_entries( + resv, actual_regions_needed - in_regions_needed)) { + return -ENOMEM; + } - add += t - f; - goto out_locked; + goto retry; } - add = add_reservation_in_range(resv, f, t, false); + add = add_reservation_in_range(resv, f, t, h_cg, h, NULL); + + resv->adds_in_progress -= in_regions_needed; -out_locked: - resv->adds_in_progress--; spin_unlock(&resv->lock); - VM_BUG_ON(add < 0); return add; } @@ -358,46 +581,37 @@ out_locked: * call to region_add that will actually modify the reserve * map to add the specified range [f, t). region_chg does * not change the number of huge pages represented by the - * map. A new file_region structure is added to the cache - * as a placeholder, so that the subsequent region_add - * call will have all the regions it needs and will not fail. + * map. A number of new file_region structures is added to the cache as a + * placeholder, for the subsequent region_add call to use. At least 1 + * file_region structure is added. + * + * out_regions_needed is the number of regions added to the + * resv->adds_in_progress. This value needs to be provided to a follow up call + * to region_add or region_abort for proper accounting. * * Returns the number of huge pages that need to be added to the existing * reservation map for the range [f, t). This number is greater or equal to * zero. -ENOMEM is returned if a new file_region structure or cache entry * is needed and can not be allocated. */ -static long region_chg(struct resv_map *resv, long f, long t) +static long region_chg(struct resv_map *resv, long f, long t, + long *out_regions_needed) { long chg = 0; spin_lock(&resv->lock); -retry_locked: - resv->adds_in_progress++; - /* - * Check for sufficient descriptors in the cache to accommodate - * the number of in progress add operations. - */ - if (resv->adds_in_progress > resv->region_cache_count) { - struct file_region *trg; + /* Count how many hugepages in this range are NOT represented. */ + chg = add_reservation_in_range(resv, f, t, NULL, NULL, + out_regions_needed); - VM_BUG_ON(resv->adds_in_progress - resv->region_cache_count > 1); - /* Must drop lock to allocate a new descriptor. */ - resv->adds_in_progress--; - spin_unlock(&resv->lock); + if (*out_regions_needed == 0) + *out_regions_needed = 1; - trg = kmalloc(sizeof(*trg), GFP_KERNEL); - if (!trg) - return -ENOMEM; - - spin_lock(&resv->lock); - list_add(&trg->link, &resv->region_cache); - resv->region_cache_count++; - goto retry_locked; - } + if (allocate_file_region_entries(resv, *out_regions_needed)) + return -ENOMEM; - chg = add_reservation_in_range(resv, f, t, true); + resv->adds_in_progress += *out_regions_needed; spin_unlock(&resv->lock); return chg; @@ -408,17 +622,20 @@ retry_locked: * of the resv_map keeps track of the operations in progress between * calls to region_chg and region_add. Operations are sometimes * aborted after the call to region_chg. In such cases, region_abort - * is called to decrement the adds_in_progress counter. + * is called to decrement the adds_in_progress counter. regions_needed + * is the value returned by the region_chg call, it is used to decrement + * the adds_in_progress counter. * * NOTE: The range arguments [f, t) are not needed or used in this * routine. They are kept to make reading the calling code easier as * arguments will match the associated region_chg call. */ -static void region_abort(struct resv_map *resv, long f, long t) +static void region_abort(struct resv_map *resv, long f, long t, + long regions_needed) { spin_lock(&resv->lock); VM_BUG_ON(!resv->region_cache_count); - resv->adds_in_progress--; + resv->adds_in_progress -= regions_needed; spin_unlock(&resv->lock); } @@ -482,10 +699,15 @@ retry: } del += t - f; + hugetlb_cgroup_uncharge_file_region( + resv, rg, t - f, false); /* New entry for end of split region */ nrg->from = t; nrg->to = rg->to; + + copy_hugetlb_cgroup_uncharge_info(nrg, rg); + INIT_LIST_HEAD(&nrg->link); /* Original entry is trimmed */ @@ -498,15 +720,23 @@ retry: if (f <= rg->from && t >= rg->to) { /* Remove entire region */ del += rg->to - rg->from; + hugetlb_cgroup_uncharge_file_region(resv, rg, + rg->to - rg->from, true); list_del(&rg->link); kfree(rg); continue; } if (f <= rg->from) { /* Trim beginning of region */ + hugetlb_cgroup_uncharge_file_region(resv, rg, + t - rg->from, false); + del += t - rg->from; rg->from = t; } else { /* Trim end of region */ + hugetlb_cgroup_uncharge_file_region(resv, rg, + rg->to - f, false); + del += rg->to - f; rg->to = f; } @@ -530,13 +760,20 @@ void hugetlb_fix_reserve_counts(struct inode *inode) { struct hugepage_subpool *spool = subpool_inode(inode); long rsv_adjust; + bool reserved = false; rsv_adjust = hugepage_subpool_get_pages(spool, 1); - if (rsv_adjust) { + if (rsv_adjust > 0) { struct hstate *h = hstate_inode(inode); - hugetlb_acct_memory(h, 1); + if (!hugetlb_acct_memory(h, 1)) + reserved = true; + } else if (!rsv_adjust) { + reserved = true; } + + if (!reserved) + pr_warn("hugetlb: Huge Page Reserved count may go negative.\n"); } /* @@ -625,7 +862,7 @@ __weak unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) * faults in a MAP_PRIVATE mapping. Only the process that called mmap() * is guaranteed to have their future faults succeed. * - * With the exception of reset_vma_resv_huge_pages() which is called at fork(), + * With the exception of hugetlb_dup_vma_private() which is called at fork(), * the reserve counters are updated with the hugetlb_lock held. It is safe * to reset the VMA at fork() time as it is not in use yet and there is no * chance of the global counters getting corrupted as a result of the values. @@ -650,6 +887,25 @@ static void set_vma_private_data(struct vm_area_struct *vma, vma->vm_private_data = (void *)value; } +static void +resv_map_set_hugetlb_cgroup_uncharge_info(struct resv_map *resv_map, + struct hugetlb_cgroup *h_cg, + struct hstate *h) +{ +#ifdef CONFIG_CGROUP_HUGETLB + if (!h_cg || !h) { + resv_map->reservation_counter = NULL; + resv_map->pages_per_hpage = 0; + resv_map->css = NULL; + } else { + resv_map->reservation_counter = + &h_cg->rsvd_hugepage[hstate_index(h)]; + resv_map->pages_per_hpage = pages_per_huge_page(h); + resv_map->css = &h_cg->css; + } +#endif +} + struct resv_map *resv_map_alloc(void) { struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL); @@ -666,6 +922,13 @@ struct resv_map *resv_map_alloc(void) INIT_LIST_HEAD(&resv_map->regions); resv_map->adds_in_progress = 0; + /* + * Initialize these to 0. On shared mappings, 0's here indicate these + * fields don't do cgroup accounting. On private mappings, these will be + * re-initialized to the proper values, to indicate that hugetlb cgroup + * reservations are to be un-charged from here. + */ + resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, NULL, NULL); INIT_LIST_HEAD(&resv_map->region_cache); list_add(&rg->link, &resv_map->region_cache); @@ -746,12 +1009,59 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) return (get_vma_private_data(vma) & flag) != 0; } -/* Reset counters to 0 and clear all HPAGE_RESV_* flags */ -void reset_vma_resv_huge_pages(struct vm_area_struct *vma) +void hugetlb_dup_vma_private(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); - if (!(vma->vm_flags & VM_MAYSHARE)) - vma->vm_private_data = (void *)0; + /* + * Clear vm_private_data + * - For shared mappings this is a per-vma semaphore that may be + * allocated in a subsequent call to hugetlb_vm_op_open. + * Before clearing, make sure pointer is not associated with vma + * as this will leak the structure. This is the case when called + * via clear_vma_resv_huge_pages() and hugetlb_vm_op_open has already + * been called to allocate a new structure. + * - For MAP_PRIVATE mappings, this is the reserve map which does + * not apply to children. Faults generated by the children are + * not guaranteed to succeed, even if read-only. + */ + if (vma->vm_flags & VM_MAYSHARE) { + struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; + + if (vma_lock && vma_lock->vma != vma) + vma->vm_private_data = NULL; + } else + vma->vm_private_data = NULL; +} + +/* + * Reset and decrement one ref on hugepage private reservation. + * Called with mm->mmap_sem writer semaphore held. + * This function should be only used by move_vma() and operate on + * same sized vma. It should never come here with last ref on the + * reservation. + */ +void clear_vma_resv_huge_pages(struct vm_area_struct *vma) +{ + /* + * Clear the old hugetlb private page reservation. + * It has already been transferred to new_vma. + * + * During a mremap() operation of a hugetlb vma we call move_vma() + * which copies vma into new_vma and unmaps vma. After the copy + * operation both new_vma and vma share a reference to the resv_map + * struct, and at that point vma is about to be unmapped. We don't + * want to return the reservation to the pool at unmap of vma because + * the reservation still lives on in new_vma, so simply decrement the + * ref here and remove the resv_map reference from this vma. + */ + struct resv_map *reservations = vma_resv_map(vma); + + if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + resv_map_put_hugetlb_cgroup_uncharge_info(reservations); + kref_put(&reservations->refs, resv_map_release); + } + + hugetlb_dup_vma_private(vma); } /* Returns true if the VMA has associated reserve pages */ @@ -779,7 +1089,7 @@ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) * We know VM_NORESERVE is not set. Therefore, there SHOULD * be a region map for all pages. The only situation where * there is no region map is if a hole was punched via - * fallocate. In this case, there really are no reverves to + * fallocate. In this case, there really are no reserves to * use. This situation is indicated if chg != 0. */ if (chg) @@ -820,29 +1130,38 @@ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) static void enqueue_huge_page(struct hstate *h, struct page *page) { int nid = page_to_nid(page); + + lockdep_assert_held(&hugetlb_lock); + VM_BUG_ON_PAGE(page_count(page), page); + list_move(&page->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; + SetHPageFreed(page); } static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) { struct page *page; + bool pin = !!(current->flags & PF_MEMALLOC_PIN); - list_for_each_entry(page, &h->hugepage_freelists[nid], lru) - if (!PageHWPoison(page)) - break; - /* - * if 'non-isolated free hugepage' not found on the list, - * the allocation fails. - */ - if (&h->hugepage_freelists[nid] == &page->lru) - return NULL; - list_move(&page->lru, &h->hugepage_activelist); - set_page_refcounted(page); - h->free_huge_pages--; - h->free_huge_pages_node[nid]--; - return page; + lockdep_assert_held(&hugetlb_lock); + list_for_each_entry(page, &h->hugepage_freelists[nid], lru) { + if (pin && !is_longterm_pinnable_page(page)) + continue; + + if (PageHWPoison(page)) + continue; + + list_move(&page->lru, &h->hugepage_activelist); + set_page_refcounted(page); + ClearHPageFreed(page); + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; + return page; + } + + return NULL; } static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid, @@ -881,13 +1200,9 @@ retry_cpuset: return NULL; } -/* Movability of hugepages depends on migration support. */ -static inline gfp_t htlb_alloc_mask(struct hstate *h) +static unsigned long available_huge_pages(struct hstate *h) { - if (hugepage_movable_supported(h)) - return GFP_HIGHUSER_MOVABLE; - else - return GFP_HIGHUSER; + return h->free_huge_pages - h->resv_huge_pages; } static struct page *dequeue_huge_page_vma(struct hstate *h, @@ -895,7 +1210,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, unsigned long address, int avoid_reserve, long chg) { - struct page *page; + struct page *page = NULL; struct mempolicy *mpol; gfp_t gfp_mask; nodemask_t *nodemask; @@ -906,19 +1221,28 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, * have no page reserves. This check ensures that reservations are * not "stolen". The child may still get SIGKILLed */ - if (!vma_has_reserves(vma, chg) && - h->free_huge_pages - h->resv_huge_pages == 0) + if (!vma_has_reserves(vma, chg) && !available_huge_pages(h)) goto err; /* If reserves cannot be used, ensure enough pages are in the pool */ - if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0) + if (avoid_reserve && !available_huge_pages(h)) goto err; gfp_mask = htlb_alloc_mask(h); nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); - page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask); + + if (mpol_is_preferred_many(mpol)) { + page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask); + + /* Fallback to all nodes if page==NULL */ + nodemask = NULL; + } + + if (!page) + page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask); + if (page && !avoid_reserve && vma_has_reserves(vma, chg)) { - SetPagePrivate(page); + SetHPageRestoreReserve(page); h->resv_huge_pages--; } @@ -971,7 +1295,7 @@ static int hstate_next_node_to_alloc(struct hstate *h, } /* - * helper for free_pool_huge_page() - return the previously saved + * helper for remove_pool_huge_page() - return the previously saved * node ["this node"] from which to free a huge page. Advance the * next node id whether or not we find a free huge page to free so * that the next attempt to free addresses the next node. @@ -1000,26 +1324,56 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE -static void destroy_compound_gigantic_page(struct page *page, - unsigned int order) +/* used to demote non-gigantic_huge pages as well */ +static void __destroy_compound_gigantic_page(struct page *page, + unsigned int order, bool demote) { int i; int nr_pages = 1 << order; - struct page *p = page + 1; + struct page *p; atomic_set(compound_mapcount_ptr(page), 0); - for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { + atomic_set(compound_pincount_ptr(page), 0); + + for (i = 1; i < nr_pages; i++) { + p = nth_page(page, i); + p->mapping = NULL; clear_compound_head(p); - set_page_refcounted(p); + if (!demote) + set_page_refcounted(p); } set_compound_order(page, 0); +#ifdef CONFIG_64BIT + page[1].compound_nr = 0; +#endif __ClearPageHead(page); } +static void destroy_compound_hugetlb_page_for_demote(struct page *page, + unsigned int order) +{ + __destroy_compound_gigantic_page(page, order, true); +} + +#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE +static void destroy_compound_gigantic_page(struct page *page, + unsigned int order) +{ + __destroy_compound_gigantic_page(page, order, false); +} + static void free_gigantic_page(struct page *page, unsigned int order) { + /* + * If the page isn't allocated using the cma allocator, + * cma_release() returns false. + */ +#ifdef CONFIG_CMA + if (cma_release(hugetlb_cma[page_to_nid(page)], page, 1 << order)) + return; +#endif + free_contig_range(page_to_pfn(page), 1 << order); } @@ -1027,13 +1381,39 @@ static void free_gigantic_page(struct page *page, unsigned int order) static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { - unsigned long nr_pages = 1UL << huge_page_order(h); + unsigned long nr_pages = pages_per_huge_page(h); + if (nid == NUMA_NO_NODE) + nid = numa_mem_id(); + +#ifdef CONFIG_CMA + { + struct page *page; + int node; + + if (hugetlb_cma[nid]) { + page = cma_alloc(hugetlb_cma[nid], nr_pages, + huge_page_order(h), true); + if (page) + return page; + } + + if (!(gfp_mask & __GFP_THISNODE)) { + for_each_node_mask(node, *nodemask) { + if (node == nid || !hugetlb_cma[node]) + continue; + + page = cma_alloc(hugetlb_cma[node], nr_pages, + huge_page_order(h), true); + if (page) + return page; + } + } + } +#endif return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); } -static void prep_new_huge_page(struct hstate *h, struct page *page, int nid); -static void prep_compound_gigantic_page(struct page *page, unsigned int order); #else /* !CONFIG_CONTIG_ALLOC */ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) @@ -1053,25 +1433,175 @@ static inline void destroy_compound_gigantic_page(struct page *page, unsigned int order) { } #endif -static void update_and_free_page(struct hstate *h, struct page *page) +/* + * Remove hugetlb page from lists, and update dtor so that page appears + * as just a compound page. + * + * A reference is held on the page, except in the case of demote. + * + * Must be called with hugetlb lock held. + */ +static void __remove_hugetlb_page(struct hstate *h, struct page *page, + bool adjust_surplus, + bool demote) { - int i; + int nid = page_to_nid(page); + + VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page); + VM_BUG_ON_PAGE(hugetlb_cgroup_from_page_rsvd(page), page); + lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; + list_del(&page->lru); + + if (HPageFreed(page)) { + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; + } + if (adjust_surplus) { + h->surplus_huge_pages--; + h->surplus_huge_pages_node[nid]--; + } + + /* + * Very subtle + * + * For non-gigantic pages set the destructor to the normal compound + * page dtor. This is needed in case someone takes an additional + * temporary ref to the page, and freeing is delayed until they drop + * their reference. + * + * For gigantic pages set the destructor to the null dtor. This + * destructor will never be called. Before freeing the gigantic + * page destroy_compound_gigantic_page will turn the compound page + * into a simple group of pages. After this the destructor does not + * apply. + * + * This handles the case where more than one ref is held when and + * after update_and_free_page is called. + * + * In the case of demote we do not ref count the page as it will soon + * be turned into a page of smaller size. + */ + if (!demote) + set_page_refcounted(page); + if (hstate_is_gigantic(h)) + set_compound_page_dtor(page, NULL_COMPOUND_DTOR); + else + set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); + h->nr_huge_pages--; - h->nr_huge_pages_node[page_to_nid(page)]--; + h->nr_huge_pages_node[nid]--; +} + +static void remove_hugetlb_page(struct hstate *h, struct page *page, + bool adjust_surplus) +{ + __remove_hugetlb_page(h, page, adjust_surplus, false); +} + +static void remove_hugetlb_page_for_demote(struct hstate *h, struct page *page, + bool adjust_surplus) +{ + __remove_hugetlb_page(h, page, adjust_surplus, true); +} + +static void add_hugetlb_page(struct hstate *h, struct page *page, + bool adjust_surplus) +{ + int zeroed; + int nid = page_to_nid(page); + + VM_BUG_ON_PAGE(!HPageVmemmapOptimized(page), page); + + lockdep_assert_held(&hugetlb_lock); + + INIT_LIST_HEAD(&page->lru); + h->nr_huge_pages++; + h->nr_huge_pages_node[nid]++; + + if (adjust_surplus) { + h->surplus_huge_pages++; + h->surplus_huge_pages_node[nid]++; + } + + set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); + set_page_private(page, 0); + /* + * We have to set HPageVmemmapOptimized again as above + * set_page_private(page, 0) cleared it. + */ + SetHPageVmemmapOptimized(page); + + /* + * This page is about to be managed by the hugetlb allocator and + * should have no users. Drop our reference, and check for others + * just in case. + */ + zeroed = put_page_testzero(page); + if (!zeroed) + /* + * It is VERY unlikely soneone else has taken a ref on + * the page. In this case, we simply return as the + * hugetlb destructor (free_huge_page) will be called + * when this other ref is dropped. + */ + return; + + arch_clear_hugepage_flags(page); + enqueue_huge_page(h, page); +} + +static void __update_and_free_page(struct hstate *h, struct page *page) +{ + int i; + struct page *subpage; + + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) + return; + + /* + * If we don't know which subpages are hwpoisoned, we can't free + * the hugepage, so it's leaked intentionally. + */ + if (HPageRawHwpUnreliable(page)) + return; + + if (hugetlb_vmemmap_restore(h, page)) { + spin_lock_irq(&hugetlb_lock); + /* + * If we cannot allocate vmemmap pages, just refuse to free the + * page and put the page back on the hugetlb free list and treat + * as a surplus page. + */ + add_hugetlb_page(h, page, true); + spin_unlock_irq(&hugetlb_lock); + return; + } + + /* + * Move PageHWPoison flag from head page to the raw error pages, + * which makes any healthy subpages reusable. + */ + if (unlikely(PageHWPoison(page))) + hugetlb_clear_page_hwpoison(page); + for (i = 0; i < pages_per_huge_page(h); i++) { - page[i].flags &= ~(1 << PG_locked | 1 << PG_error | + subpage = nth_page(page, i); + subpage->flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced | 1 << PG_dirty | 1 << PG_active | 1 << PG_private | 1 << PG_writeback); } - VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page); - set_compound_page_dtor(page, NULL_COMPOUND_DTOR); - set_page_refcounted(page); - if (hstate_is_gigantic(h)) { + + /* + * Non-gigantic pages demoted from CMA allocated gigantic pages + * need to be given back to CMA in free_gigantic_page. + */ + if (hstate_is_gigantic(h) || + hugetlb_cma_page(page, huge_page_order(h))) { destroy_compound_gigantic_page(page, huge_page_order(h)); free_gigantic_page(page, huge_page_order(h)); } else { @@ -1079,65 +1609,95 @@ static void update_and_free_page(struct hstate *h, struct page *page) } } -struct hstate *size_to_hstate(unsigned long size) -{ - struct hstate *h; - - for_each_hstate(h) { - if (huge_page_size(h) == size) - return h; - } - return NULL; -} - /* - * Test to determine whether the hugepage is "active/in-use" (i.e. being linked - * to hstate->hugepage_activelist.) + * As update_and_free_page() can be called under any context, so we cannot + * use GFP_KERNEL to allocate vmemmap pages. However, we can defer the + * actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate + * the vmemmap pages. * - * This function can be called for tail pages, but never returns true for them. + * free_hpage_workfn() locklessly retrieves the linked list of pages to be + * freed and frees them one-by-one. As the page->mapping pointer is going + * to be cleared in free_hpage_workfn() anyway, it is reused as the llist_node + * structure of a lockless linked list of huge pages to be freed. */ -bool page_huge_active(struct page *page) -{ - VM_BUG_ON_PAGE(!PageHuge(page), page); - return PageHead(page) && PagePrivate(&page[1]); -} +static LLIST_HEAD(hpage_freelist); -/* never called for tail page */ -static void set_page_huge_active(struct page *page) +static void free_hpage_workfn(struct work_struct *work) { - VM_BUG_ON_PAGE(!PageHeadHuge(page), page); - SetPagePrivate(&page[1]); + struct llist_node *node; + + node = llist_del_all(&hpage_freelist); + + while (node) { + struct page *page; + struct hstate *h; + + page = container_of((struct address_space **)node, + struct page, mapping); + node = node->next; + page->mapping = NULL; + /* + * The VM_BUG_ON_PAGE(!PageHuge(page), page) in page_hstate() + * is going to trigger because a previous call to + * remove_hugetlb_page() will set_compound_page_dtor(page, + * NULL_COMPOUND_DTOR), so do not use page_hstate() directly. + */ + h = size_to_hstate(page_size(page)); + + __update_and_free_page(h, page); + + cond_resched(); + } } +static DECLARE_WORK(free_hpage_work, free_hpage_workfn); -static void clear_page_huge_active(struct page *page) +static inline void flush_free_hpage_work(struct hstate *h) { - VM_BUG_ON_PAGE(!PageHeadHuge(page), page); - ClearPagePrivate(&page[1]); + if (hugetlb_vmemmap_optimizable(h)) + flush_work(&free_hpage_work); } -/* - * Internal hugetlb specific page flag. Do not use outside of the hugetlb - * code - */ -static inline bool PageHugeTemporary(struct page *page) +static void update_and_free_page(struct hstate *h, struct page *page, + bool atomic) { - if (!PageHuge(page)) - return false; + if (!HPageVmemmapOptimized(page) || !atomic) { + __update_and_free_page(h, page); + return; + } - return (unsigned long)page[2].mapping == -1U; + /* + * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap pages. + * + * Only call schedule_work() if hpage_freelist is previously + * empty. Otherwise, schedule_work() had been called but the workfn + * hasn't retrieved the list yet. + */ + if (llist_add((struct llist_node *)&page->mapping, &hpage_freelist)) + schedule_work(&free_hpage_work); } -static inline void SetPageHugeTemporary(struct page *page) +static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list) { - page[2].mapping = (void *)-1U; + struct page *page, *t_page; + + list_for_each_entry_safe(page, t_page, list, lru) { + update_and_free_page(h, page, false); + cond_resched(); + } } -static inline void ClearPageHugeTemporary(struct page *page) +struct hstate *size_to_hstate(unsigned long size) { - page[2].mapping = NULL; + struct hstate *h; + + for_each_hstate(h) { + if (huge_page_size(h) == size) + return h; + } + return NULL; } -static void __free_huge_page(struct page *page) +void free_huge_page(struct page *page) { /* * Can't pass hstate in here because it is called from the @@ -1145,24 +1705,26 @@ static void __free_huge_page(struct page *page) */ struct hstate *h = page_hstate(page); int nid = page_to_nid(page); - struct hugepage_subpool *spool = - (struct hugepage_subpool *)page_private(page); + struct hugepage_subpool *spool = hugetlb_page_subpool(page); bool restore_reserve; + unsigned long flags; VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(page_mapcount(page), page); - set_page_private(page, 0); + hugetlb_set_page_subpool(page, NULL); + if (PageAnon(page)) + __ClearPageAnonExclusive(page); page->mapping = NULL; - restore_reserve = PagePrivate(page); - ClearPagePrivate(page); + restore_reserve = HPageRestoreReserve(page); + ClearHPageRestoreReserve(page); /* - * If PagePrivate() was set on page, page allocation consumed a + * If HPageRestoreReserve was set on page, page allocation consumed a * reservation. If the page was associated with a subpool, there * would have been a page reserved in the subpool before allocation * via hugepage_subpool_get_pages(). Since we are 'restoring' the - * reservtion, do not call hugepage_subpool_put_pages() as this will + * reservation, do not call hugepage_subpool_put_pages() as this will * remove the reserved page from the subpool. */ if (!restore_reserve) { @@ -1176,105 +1738,77 @@ static void __free_huge_page(struct page *page) restore_reserve = true; } - spin_lock(&hugetlb_lock); - clear_page_huge_active(page); + spin_lock_irqsave(&hugetlb_lock, flags); + ClearHPageMigratable(page); hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h), page); + hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), + pages_per_huge_page(h), page); if (restore_reserve) h->resv_huge_pages++; - if (PageHugeTemporary(page)) { - list_del(&page->lru); - ClearPageHugeTemporary(page); - update_and_free_page(h, page); + if (HPageTemporary(page)) { + remove_hugetlb_page(h, page, false); + spin_unlock_irqrestore(&hugetlb_lock, flags); + update_and_free_page(h, page, true); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ - list_del(&page->lru); - update_and_free_page(h, page); - h->surplus_huge_pages--; - h->surplus_huge_pages_node[nid]--; + remove_hugetlb_page(h, page, true); + spin_unlock_irqrestore(&hugetlb_lock, flags); + update_and_free_page(h, page, true); } else { arch_clear_hugepage_flags(page); enqueue_huge_page(h, page); + spin_unlock_irqrestore(&hugetlb_lock, flags); } - spin_unlock(&hugetlb_lock); } /* - * As free_huge_page() can be called from a non-task context, we have - * to defer the actual freeing in a workqueue to prevent potential - * hugetlb_lock deadlock. - * - * free_hpage_workfn() locklessly retrieves the linked list of pages to - * be freed and frees them one-by-one. As the page->mapping pointer is - * going to be cleared in __free_huge_page() anyway, it is reused as the - * llist_node structure of a lockless linked list of huge pages to be freed. + * Must be called with the hugetlb lock held */ -static LLIST_HEAD(hpage_freelist); - -static void free_hpage_workfn(struct work_struct *work) +static void __prep_account_new_huge_page(struct hstate *h, int nid) { - struct llist_node *node; - struct page *page; - - node = llist_del_all(&hpage_freelist); - - while (node) { - page = container_of((struct address_space **)node, - struct page, mapping); - node = node->next; - __free_huge_page(page); - } + lockdep_assert_held(&hugetlb_lock); + h->nr_huge_pages++; + h->nr_huge_pages_node[nid]++; } -static DECLARE_WORK(free_hpage_work, free_hpage_workfn); -void free_huge_page(struct page *page) +static void __prep_new_huge_page(struct hstate *h, struct page *page) { - /* - * Defer freeing if in non-task context to avoid hugetlb_lock deadlock. - */ - if (!in_task()) { - /* - * Only call schedule_work() if hpage_freelist is previously - * empty. Otherwise, schedule_work() had been called but the - * workfn hasn't retrieved the list yet. - */ - if (llist_add((struct llist_node *)&page->mapping, - &hpage_freelist)) - schedule_work(&free_hpage_work); - return; - } - - __free_huge_page(page); + hugetlb_vmemmap_optimize(h, page); + INIT_LIST_HEAD(&page->lru); + set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); + hugetlb_set_page_subpool(page, NULL); + set_hugetlb_cgroup(page, NULL); + set_hugetlb_cgroup_rsvd(page, NULL); } static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { - INIT_LIST_HEAD(&page->lru); - set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); - spin_lock(&hugetlb_lock); - set_hugetlb_cgroup(page, NULL); - h->nr_huge_pages++; - h->nr_huge_pages_node[nid]++; - spin_unlock(&hugetlb_lock); + __prep_new_huge_page(h, page); + spin_lock_irq(&hugetlb_lock); + __prep_account_new_huge_page(h, nid); + spin_unlock_irq(&hugetlb_lock); } -static void prep_compound_gigantic_page(struct page *page, unsigned int order) +static bool __prep_compound_gigantic_page(struct page *page, unsigned int order, + bool demote) { - int i; + int i, j; int nr_pages = 1 << order; - struct page *p = page + 1; + struct page *p; /* we rely on prep_new_huge_page to set the destructor */ set_compound_order(page, order); - __ClearPageReserved(page); __SetPageHead(page); - for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { + for (i = 0; i < nr_pages; i++) { + p = nth_page(page, i); + /* * For gigantic hugepages allocated through bootmem at * boot, it's safer to be consistent with the not-gigantic * hugepages and clear the PG_reserved bit from all tail pages - * too. Otherwse drivers using get_user_pages() to access tail + * too. Otherwise drivers using get_user_pages() to access tail * pages may get the reference counting wrong if they see * PG_reserved set on a tail page (despite the head page not * having PG_reserved set). Enforcing this consistency between @@ -1283,10 +1817,68 @@ static void prep_compound_gigantic_page(struct page *page, unsigned int order) * after get_user_pages(). */ __ClearPageReserved(p); - set_page_count(p, 0); - set_compound_head(p, page); + /* + * Subtle and very unlikely + * + * Gigantic 'page allocators' such as memblock or cma will + * return a set of pages with each page ref counted. We need + * to turn this set of pages into a compound page with tail + * page ref counts set to zero. Code such as speculative page + * cache adding could take a ref on a 'to be' tail page. + * We need to respect any increased ref count, and only set + * the ref count to zero if count is currently 1. If count + * is not 1, we return an error. An error return indicates + * the set of pages can not be converted to a gigantic page. + * The caller who allocated the pages should then discard the + * pages using the appropriate free interface. + * + * In the case of demote, the ref count will be zero. + */ + if (!demote) { + if (!page_ref_freeze(p, 1)) { + pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n"); + goto out_error; + } + } else { + VM_BUG_ON_PAGE(page_count(p), p); + } + if (i != 0) + set_compound_head(p, page); } atomic_set(compound_mapcount_ptr(page), -1); + atomic_set(compound_pincount_ptr(page), 0); + return true; + +out_error: + /* undo page modifications made above */ + for (j = 0; j < i; j++) { + p = nth_page(page, j); + if (j != 0) + clear_compound_head(p); + set_page_refcounted(p); + } + /* need to clear PG_reserved on remaining tail pages */ + for (; j < nr_pages; j++) { + p = nth_page(page, j); + __ClearPageReserved(p); + } + set_compound_order(page, 0); +#ifdef CONFIG_64BIT + page[1].compound_nr = 0; +#endif + __ClearPageHead(page); + return false; +} + +static bool prep_compound_gigantic_page(struct page *page, unsigned int order) +{ + return __prep_compound_gigantic_page(page, order, false); +} + +static bool prep_compound_gigantic_page_for_demote(struct page *page, + unsigned int order) +{ + return __prep_compound_gigantic_page(page, order, true); } /* @@ -1313,18 +1905,36 @@ int PageHeadHuge(struct page *page_head) if (!PageHead(page_head)) return 0; - return get_compound_page_dtor(page_head) == free_huge_page; + return page_head[1].compound_dtor == HUGETLB_PAGE_DTOR; } +EXPORT_SYMBOL_GPL(PageHeadHuge); -pgoff_t __basepage_index(struct page *page) +/* + * Find and lock address space (mapping) in write mode. + * + * Upon entry, the page is locked which means that page_mapping() is + * stable. Due to locking order, we can only trylock_write. If we can + * not get the lock, simply return NULL to caller. + */ +struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) +{ + struct address_space *mapping = page_mapping(hpage); + + if (!mapping) + return mapping; + + if (i_mmap_trylock_write(mapping)) + return mapping; + + return NULL; +} + +pgoff_t hugetlb_basepage_index(struct page *page) { struct page *page_head = compound_head(page); pgoff_t index = page_index(page_head); unsigned long compound_idx; - if (!PageHuge(page_head)) - return page_index(page); - if (compound_order(page_head) >= MAX_ORDER) compound_idx = page_to_pfn(page) - page_to_pfn(page_head); else @@ -1340,6 +1950,7 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int order = huge_page_order(h); struct page *page; bool alloc_try_hard = true; + bool retry = true; /* * By default we always try hard to allocate the page with @@ -1355,7 +1966,21 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, gfp_mask |= __GFP_RETRY_MAYFAIL; if (nid == NUMA_NO_NODE) nid = numa_mem_id(); - page = __alloc_pages_nodemask(gfp_mask, order, nid, nmask); +retry: + page = __alloc_pages(gfp_mask, order, nid, nmask); + + /* Freeze head page */ + if (page && !page_ref_freeze(page, 1)) { + __free_pages(page, order); + if (retry) { /* retry once */ + retry = false; + goto retry; + } + /* WOW! twice in a row. */ + pr_warn("HugeTLB head page unexpected inflated ref count\n"); + page = NULL; + } + if (page) __count_vm_event(HTLB_BUDDY_PGALLOC); else @@ -1383,13 +2008,18 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, /* * Common helper to allocate a fresh hugetlb page. All specific allocators * should use this function to get new hugetlb pages + * + * Note that returned page is 'frozen': ref count of head page and all tail + * pages is zero. */ static struct page *alloc_fresh_huge_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct page *page; + bool retry = false; +retry: if (hstate_is_gigantic(h)) page = alloc_gigantic_page(h, gfp_mask, nid, nmask); else @@ -1398,8 +2028,20 @@ static struct page *alloc_fresh_huge_page(struct hstate *h, if (!page) return NULL; - if (hstate_is_gigantic(h)) - prep_compound_gigantic_page(page, huge_page_order(h)); + if (hstate_is_gigantic(h)) { + if (!prep_compound_gigantic_page(page, huge_page_order(h))) { + /* + * Rare failure to convert pages to compound page. + * Free pages and try again - ONCE! + */ + free_gigantic_page(page, huge_page_order(h)); + if (!retry) { + retry = true; + goto retry; + } + return NULL; + } + } prep_new_huge_page(h, page, page_to_nid(page)); return page; @@ -1426,23 +2068,26 @@ static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, if (!page) return 0; - put_page(page); /* free it into the hugepage allocator */ + free_huge_page(page); /* free it into the hugepage allocator */ return 1; } /* - * Free huge page from pool from next node to free. - * Attempt to keep persistent huge pages more or less - * balanced over allowed nodes. + * Remove huge page from pool from next node to free. Attempt to keep + * persistent huge pages more or less balanced over allowed nodes. + * This routine only 'removes' the hugetlb page. The caller must make + * an additional call to free the page to low level allocators. * Called with hugetlb_lock locked. */ -static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, - bool acct_surplus) +static struct page *remove_pool_huge_page(struct hstate *h, + nodemask_t *nodes_allowed, + bool acct_surplus) { int nr_nodes, node; - int ret = 0; + struct page *page = NULL; + lockdep_assert_held(&hugetlb_lock); for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { /* * If we're returning unused surplus pages, only examine @@ -1450,23 +2095,14 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, */ if ((!acct_surplus || h->surplus_huge_pages_node[node]) && !list_empty(&h->hugepage_freelists[node])) { - struct page *page = - list_entry(h->hugepage_freelists[node].next, + page = list_entry(h->hugepage_freelists[node].next, struct page, lru); - list_del(&page->lru); - h->free_huge_pages--; - h->free_huge_pages_node[node]--; - if (acct_surplus) { - h->surplus_huge_pages--; - h->surplus_huge_pages_node[node]--; - } - update_and_free_page(h, page); - ret = 1; + remove_hugetlb_page(h, page, acct_surplus); break; } } - return ret; + return page; } /* @@ -1474,20 +2110,25 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, * nothing for in-use hugepages and non-hugepages. * This function returns values like below: * - * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use - * (allocated or reserved.) - * 0: successfully dissolved free hugepages or the page is not a - * hugepage (considered as already dissolved) + * -ENOMEM: failed to allocate vmemmap pages to free the freed hugepages + * when the system is under memory pressure and the feature of + * freeing unused vmemmap pages associated with each hugetlb page + * is enabled. + * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use + * (allocated or reserved.) + * 0: successfully dissolved free hugepages or the page is not a + * hugepage (considered as already dissolved) */ int dissolve_free_huge_page(struct page *page) { int rc = -EBUSY; +retry: /* Not to disrupt normal path by vainly holding hugetlb_lock */ if (!PageHuge(page)) return 0; - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); if (!PageHuge(page)) { rc = 0; goto out; @@ -1496,26 +2137,54 @@ int dissolve_free_huge_page(struct page *page) if (!page_count(page)) { struct page *head = compound_head(page); struct hstate *h = page_hstate(head); - int nid = page_to_nid(head); - if (h->free_huge_pages - h->resv_huge_pages == 0) + if (!available_huge_pages(h)) goto out; + /* - * Move PageHWPoison flag from head page to the raw error page, - * which makes any subpages rather than the error page reusable. + * We should make sure that the page is already on the free list + * when it is dissolved. */ - if (PageHWPoison(head) && page != head) { - SetPageHWPoison(page); - ClearPageHWPoison(head); + if (unlikely(!HPageFreed(head))) { + spin_unlock_irq(&hugetlb_lock); + cond_resched(); + + /* + * Theoretically, we should return -EBUSY when we + * encounter this race. In fact, we have a chance + * to successfully dissolve the page if we do a + * retry. Because the race window is quite small. + * If we seize this opportunity, it is an optimization + * for increasing the success rate of dissolving page. + */ + goto retry; } - list_del(&head->lru); - h->free_huge_pages--; - h->free_huge_pages_node[nid]--; + + remove_hugetlb_page(h, head, false); h->max_huge_pages--; - update_and_free_page(h, head); - rc = 0; + spin_unlock_irq(&hugetlb_lock); + + /* + * Normally update_and_free_page will allocate required vmemmmap + * before freeing the page. update_and_free_page will fail to + * free the page if it can not allocate required vmemmap. We + * need to adjust max_huge_pages if the page is not freed. + * Attempt to allocate vmemmmap here so that we can take + * appropriate action on failure. + */ + rc = hugetlb_vmemmap_restore(h, head); + if (!rc) { + update_and_free_page(h, head, false); + } else { + spin_lock_irq(&hugetlb_lock); + add_hugetlb_page(h, head, false); + h->max_huge_pages++; + spin_unlock_irq(&hugetlb_lock); + } + + return rc; } out: - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); return rc; } @@ -1532,11 +2201,17 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) unsigned long pfn; struct page *page; int rc = 0; + unsigned int order; + struct hstate *h; if (!hugepages_supported()) return rc; - for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) { + order = huge_page_order(&default_hstate); + for_each_hstate(h) + order = min(order, huge_page_order(h)); + + for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) { page = pfn_to_page(pfn); rc = dissolve_free_huge_page(page); if (rc) @@ -1550,23 +2225,23 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) * Allocates a fresh surplus page from the page allocator. */ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, - int nid, nodemask_t *nmask) + int nid, nodemask_t *nmask) { struct page *page = NULL; if (hstate_is_gigantic(h)) return NULL; - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) goto out_unlock; - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL); if (!page) return NULL; - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); /* * We could have raced with the pool size change. * Double check that and simply deallocate the new page @@ -1575,22 +2250,22 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, * codeflow */ if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { - SetPageHugeTemporary(page); - spin_unlock(&hugetlb_lock); - put_page(page); + SetHPageTemporary(page); + spin_unlock_irq(&hugetlb_lock); + free_huge_page(page); return NULL; - } else { - h->surplus_huge_pages++; - h->surplus_huge_pages_node[page_to_nid(page)]++; } + h->surplus_huge_pages++; + h->surplus_huge_pages_node[page_to_nid(page)]++; + out_unlock: - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); return page; } -struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, +static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct page *page; @@ -1602,11 +2277,14 @@ struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, if (!page) return NULL; + /* fresh huge pages are frozen */ + set_page_refcounted(page); + /* * We do not account these pages as surplus because they are only * temporary and will be released properly on the last reference */ - SetPageHugeTemporary(page); + SetHPageTemporary(page); return page; } @@ -1618,56 +2296,44 @@ static struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { - struct page *page; + struct page *page = NULL; struct mempolicy *mpol; gfp_t gfp_mask = htlb_alloc_mask(h); int nid; nodemask_t *nodemask; nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask); - page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask); - mpol_cond_put(mpol); - - return page; -} + if (mpol_is_preferred_many(mpol)) { + gfp_t gfp = gfp_mask | __GFP_NOWARN; -/* page migration callback function */ -struct page *alloc_huge_page_node(struct hstate *h, int nid) -{ - gfp_t gfp_mask = htlb_alloc_mask(h); - struct page *page = NULL; - - if (nid != NUMA_NO_NODE) - gfp_mask |= __GFP_THISNODE; + gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); + page = alloc_surplus_huge_page(h, gfp, nid, nodemask); - spin_lock(&hugetlb_lock); - if (h->free_huge_pages - h->resv_huge_pages > 0) - page = dequeue_huge_page_nodemask(h, gfp_mask, nid, NULL); - spin_unlock(&hugetlb_lock); + /* Fallback to all nodes if page==NULL */ + nodemask = NULL; + } if (!page) - page = alloc_migrate_huge_page(h, gfp_mask, nid, NULL); - + page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask); + mpol_cond_put(mpol); return page; } /* page migration callback function */ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, - nodemask_t *nmask) + nodemask_t *nmask, gfp_t gfp_mask) { - gfp_t gfp_mask = htlb_alloc_mask(h); - - spin_lock(&hugetlb_lock); - if (h->free_huge_pages - h->resv_huge_pages > 0) { + spin_lock_irq(&hugetlb_lock); + if (available_huge_pages(h)) { struct page *page; page = dequeue_huge_page_nodemask(h, gfp_mask, preferred_nid, nmask); if (page) { - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); return page; } } - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); return alloc_migrate_huge_page(h, gfp_mask, preferred_nid, nmask); } @@ -1684,7 +2350,7 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, gfp_mask = htlb_alloc_mask(h); node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); - page = alloc_huge_page_nodemask(h, node, nodemask); + page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask); mpol_cond_put(mpol); return page; @@ -1694,14 +2360,17 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, * Increase the hugetlb pool such that it can accommodate a reservation * of size 'delta'. */ -static int gather_surplus_pages(struct hstate *h, int delta) +static int gather_surplus_pages(struct hstate *h, long delta) + __must_hold(&hugetlb_lock) { - struct list_head surplus_list; + LIST_HEAD(surplus_list); struct page *page, *tmp; - int ret, i; - int needed, allocated; + int ret; + long i; + long needed, allocated; bool alloc_ok = true; + lockdep_assert_held(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { h->resv_huge_pages += delta; @@ -1709,11 +2378,10 @@ static int gather_surplus_pages(struct hstate *h, int delta) } allocated = 0; - INIT_LIST_HEAD(&surplus_list); ret = -ENOMEM; retry: - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); for (i = 0; i < needed; i++) { page = alloc_surplus_huge_page(h, htlb_alloc_mask(h), NUMA_NO_NODE, NULL); @@ -1730,7 +2398,7 @@ retry: * After retaking hugetlb_lock, we need to recalculate 'needed' * because either resv_huge_pages or free_huge_pages may have changed. */ - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - (h->free_huge_pages + allocated); if (needed > 0) { @@ -1759,21 +2427,19 @@ retry: list_for_each_entry_safe(page, tmp, &surplus_list, lru) { if ((--needed) < 0) break; - /* - * This page is now managed by the hugetlb allocator and has - * no users -- drop the buddy allocator's reference. - */ - put_page_testzero(page); - VM_BUG_ON_PAGE(page_count(page), page); + /* Add the page to the hugetlb allocator */ enqueue_huge_page(h, page); } free: - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); - /* Free unnecessary surplus pages to the buddy allocator */ + /* + * Free unnecessary surplus pages to the buddy allocator. + * Pages have no ref count, call free_huge_page directly. + */ list_for_each_entry_safe(page, tmp, &surplus_list, lru) - put_page(page); - spin_lock(&hugetlb_lock); + free_huge_page(page); + spin_lock_irq(&hugetlb_lock); return ret; } @@ -1785,20 +2451,19 @@ free: * to the associated reservation map. * 2) Free any unused surplus pages that may have been allocated to satisfy * the reservation. As many as unused_resv_pages may be freed. - * - * Called with hugetlb_lock held. However, the lock could be dropped (and - * reacquired) during calls to cond_resched_lock. Whenever dropping the lock, - * we must make sure nobody else can claim pages we are in the process of - * freeing. Do this by ensuring resv_huge_page always is greater than the - * number of huge pages we plan to free when dropping the lock. */ static void return_unused_surplus_pages(struct hstate *h, unsigned long unused_resv_pages) { unsigned long nr_pages; + struct page *page; + LIST_HEAD(page_list); - /* Cannot return gigantic pages currently */ - if (hstate_is_gigantic(h)) + lockdep_assert_held(&hugetlb_lock); + /* Uncommit the reservation */ + h->resv_huge_pages -= unused_resv_pages; + + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) goto out; /* @@ -1812,24 +2477,21 @@ static void return_unused_surplus_pages(struct hstate *h, * evenly across all nodes with memory. Iterate across these nodes * until we can no longer free unreserved surplus pages. This occurs * when the nodes with surplus pages have no free pages. - * free_pool_huge_page() will balance the the freed pages across the + * remove_pool_huge_page() will balance the freed pages across the * on-line nodes with memory and will handle the hstate accounting. - * - * Note that we decrement resv_huge_pages as we free the pages. If - * we drop the lock, resv_huge_pages will still be sufficiently large - * to cover subsequent pages we may free. */ while (nr_pages--) { - h->resv_huge_pages--; - unused_resv_pages--; - if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1)) + page = remove_pool_huge_page(h, &node_states[N_MEMORY], 1); + if (!page) goto out; - cond_resched_lock(&hugetlb_lock); + + list_add(&page->lru, &page_list); } out: - /* Fully uncommit the reservation */ - h->resv_huge_pages -= unused_resv_pages; + spin_unlock_irq(&hugetlb_lock); + update_and_free_pages_bulk(h, &page_list); + spin_lock_irq(&hugetlb_lock); } @@ -1856,12 +2518,18 @@ out: * be restored when a newly allocated huge page must be freed. It is * to be called after calling vma_needs_reservation to determine if a * reservation exists. + * + * vma_del_reservation is used in error paths where an entry in the reserve + * map was created during huge page allocation and must be removed. It is to + * be called after calling vma_needs_reservation to determine if a reservation + * exists. */ enum vma_resv_mode { VMA_NEEDS_RESV, VMA_COMMIT_RESV, VMA_END_RESV, VMA_ADD_RESV, + VMA_DEL_RESV, }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, @@ -1870,6 +2538,7 @@ static long __vma_reservation_common(struct hstate *h, struct resv_map *resv; pgoff_t idx; long ret; + long dummy_out_regions_needed; resv = vma_resv_map(vma); if (!resv) @@ -1878,50 +2547,68 @@ static long __vma_reservation_common(struct hstate *h, idx = vma_hugecache_offset(h, vma, addr); switch (mode) { case VMA_NEEDS_RESV: - ret = region_chg(resv, idx, idx + 1); + ret = region_chg(resv, idx, idx + 1, &dummy_out_regions_needed); + /* We assume that vma_reservation_* routines always operate on + * 1 page, and that adding to resv map a 1 page entry can only + * ever require 1 region. + */ + VM_BUG_ON(dummy_out_regions_needed != 1); break; case VMA_COMMIT_RESV: - ret = region_add(resv, idx, idx + 1); + ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); + /* region_add calls of range 1 should never fail. */ + VM_BUG_ON(ret < 0); break; case VMA_END_RESV: - region_abort(resv, idx, idx + 1); + region_abort(resv, idx, idx + 1, 1); ret = 0; break; case VMA_ADD_RESV: - if (vma->vm_flags & VM_MAYSHARE) - ret = region_add(resv, idx, idx + 1); - else { - region_abort(resv, idx, idx + 1); + if (vma->vm_flags & VM_MAYSHARE) { + ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); + /* region_add calls of range 1 should never fail. */ + VM_BUG_ON(ret < 0); + } else { + region_abort(resv, idx, idx + 1, 1); + ret = region_del(resv, idx, idx + 1); + } + break; + case VMA_DEL_RESV: + if (vma->vm_flags & VM_MAYSHARE) { + region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); + } else { + ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); + /* region_add calls of range 1 should never fail. */ + VM_BUG_ON(ret < 0); } break; default: BUG(); } - if (vma->vm_flags & VM_MAYSHARE) + if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV) return ret; - else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && ret >= 0) { - /* - * In most cases, reserves always exist for private mappings. - * However, a file associated with mapping could have been - * hole punched or truncated after reserves were consumed. - * As subsequent fault on such a range will not use reserves. - * Subtle - The reserve map for private mappings has the - * opposite meaning than that of shared mappings. If NO - * entry is in the reserve map, it means a reservation exists. - * If an entry exists in the reserve map, it means the - * reservation has already been consumed. As a result, the - * return value of this routine is the opposite of the - * value returned from reserve map manipulation routines above. - */ - if (ret) - return 0; - else - return 1; - } - else - return ret < 0 ? ret : 0; + /* + * We know private mapping must have HPAGE_RESV_OWNER set. + * + * In most cases, reserves always exist for private mappings. + * However, a file associated with mapping could have been + * hole punched or truncated after reserves were consumed. + * As subsequent fault on such a range will not use reserves. + * Subtle - The reserve map for private mappings has the + * opposite meaning than that of shared mappings. If NO + * entry is in the reserve map, it means a reservation exists. + * If an entry exists in the reserve map, it means the + * reservation has already been consumed. As a result, the + * return value of this routine is the opposite of the + * value returned from reserve map manipulation routines above. + */ + if (ret > 0) + return 0; + if (ret == 0) + return 1; + return ret; } static long vma_needs_reservation(struct hstate *h, @@ -1948,28 +2635,42 @@ static long vma_add_reservation(struct hstate *h, return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); } +static long vma_del_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV); +} + /* - * This routine is called to restore a reservation on error paths. In the - * specific error paths, a huge page was allocated (via alloc_huge_page) - * and is about to be freed. If a reservation for the page existed, - * alloc_huge_page would have consumed the reservation and set PagePrivate - * in the newly allocated page. When the page is freed via free_huge_page, - * the global reservation count will be incremented if PagePrivate is set. - * However, free_huge_page can not adjust the reserve map. Adjust the - * reserve map here to be consistent with global reserve count adjustments - * to be made by free_huge_page. + * This routine is called to restore reservation information on error paths. + * It should ONLY be called for pages allocated via alloc_huge_page(), and + * the hugetlb mutex should remain held when calling this routine. + * + * It handles two specific cases: + * 1) A reservation was in place and the page consumed the reservation. + * HPageRestoreReserve is set in the page. + * 2) No reservation was in place for the page, so HPageRestoreReserve is + * not set. However, alloc_huge_page always updates the reserve map. + * + * In case 1, free_huge_page later in the error path will increment the + * global reserve count. But, free_huge_page does not have enough context + * to adjust the reservation map. This case deals primarily with private + * mappings. Adjust the reserve map here to be consistent with global + * reserve count adjustments to be made by free_huge_page. Make sure the + * reserve map indicates there is a reservation present. + * + * In case 2, simply undo reserve map modifications done by alloc_huge_page. */ -static void restore_reserve_on_error(struct hstate *h, - struct vm_area_struct *vma, unsigned long address, - struct page *page) +void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, + unsigned long address, struct page *page) { - if (unlikely(PagePrivate(page))) { - long rc = vma_needs_reservation(h, vma, address); + long rc = vma_needs_reservation(h, vma, address); - if (unlikely(rc < 0)) { + if (HPageRestoreReserve(page)) { + if (unlikely(rc < 0)) /* * Rare out of memory condition in reserve map - * manipulation. Clear PagePrivate so that + * manipulation. Clear HPageRestoreReserve so that * global reserve count will not be incremented * by free_huge_page. This will make it appear * as though the reservation for this page was @@ -1978,20 +2679,185 @@ static void restore_reserve_on_error(struct hstate *h, * is better than inconsistent global huge page * accounting of reserve counts. */ - ClearPagePrivate(page); - } else if (rc) { - rc = vma_add_reservation(h, vma, address); - if (unlikely(rc < 0)) + ClearHPageRestoreReserve(page); + else if (rc) + (void)vma_add_reservation(h, vma, address); + else + vma_end_reservation(h, vma, address); + } else { + if (!rc) { + /* + * This indicates there is an entry in the reserve map + * not added by alloc_huge_page. We know it was added + * before the alloc_huge_page call, otherwise + * HPageRestoreReserve would be set on the page. + * Remove the entry so that a subsequent allocation + * does not consume a reservation. + */ + rc = vma_del_reservation(h, vma, address); + if (rc < 0) + /* + * VERY rare out of memory condition. Since + * we can not delete the entry, set + * HPageRestoreReserve so that the reserve + * count will be incremented when the page + * is freed. This reserve will be consumed + * on a subsequent allocation. + */ + SetHPageRestoreReserve(page); + } else if (rc < 0) { + /* + * Rare out of memory condition from + * vma_needs_reservation call. Memory allocation is + * only attempted if a new entry is needed. Therefore, + * this implies there is not an entry in the + * reserve map. + * + * For shared mappings, no entry in the map indicates + * no reservation. We are done. + */ + if (!(vma->vm_flags & VM_MAYSHARE)) /* - * See above comment about rare out of - * memory condition. + * For private mappings, no entry indicates + * a reservation is present. Since we can + * not add an entry, set SetHPageRestoreReserve + * on the page so reserve count will be + * incremented when freed. This reserve will + * be consumed on a subsequent allocation. */ - ClearPagePrivate(page); + SetHPageRestoreReserve(page); } else - vma_end_reservation(h, vma, address); + /* + * No reservation present, do nothing + */ + vma_end_reservation(h, vma, address); } } +/* + * alloc_and_dissolve_huge_page - Allocate a new page and dissolve the old one + * @h: struct hstate old page belongs to + * @old_page: Old page to dissolve + * @list: List to isolate the page in case we need to + * Returns 0 on success, otherwise negated error. + */ +static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page, + struct list_head *list) +{ + gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; + int nid = page_to_nid(old_page); + struct page *new_page; + int ret = 0; + + /* + * Before dissolving the page, we need to allocate a new one for the + * pool to remain stable. Here, we allocate the page and 'prep' it + * by doing everything but actually updating counters and adding to + * the pool. This simplifies and let us do most of the processing + * under the lock. + */ + new_page = alloc_buddy_huge_page(h, gfp_mask, nid, NULL, NULL); + if (!new_page) + return -ENOMEM; + __prep_new_huge_page(h, new_page); + +retry: + spin_lock_irq(&hugetlb_lock); + if (!PageHuge(old_page)) { + /* + * Freed from under us. Drop new_page too. + */ + goto free_new; + } else if (page_count(old_page)) { + /* + * Someone has grabbed the page, try to isolate it here. + * Fail with -EBUSY if not possible. + */ + spin_unlock_irq(&hugetlb_lock); + ret = isolate_hugetlb(old_page, list); + spin_lock_irq(&hugetlb_lock); + goto free_new; + } else if (!HPageFreed(old_page)) { + /* + * Page's refcount is 0 but it has not been enqueued in the + * freelist yet. Race window is small, so we can succeed here if + * we retry. + */ + spin_unlock_irq(&hugetlb_lock); + cond_resched(); + goto retry; + } else { + /* + * Ok, old_page is still a genuine free hugepage. Remove it from + * the freelist and decrease the counters. These will be + * incremented again when calling __prep_account_new_huge_page() + * and enqueue_huge_page() for new_page. The counters will remain + * stable since this happens under the lock. + */ + remove_hugetlb_page(h, old_page, false); + + /* + * Ref count on new page is already zero as it was dropped + * earlier. It can be directly added to the pool free list. + */ + __prep_account_new_huge_page(h, nid); + enqueue_huge_page(h, new_page); + + /* + * Pages have been replaced, we can safely free the old one. + */ + spin_unlock_irq(&hugetlb_lock); + update_and_free_page(h, old_page, false); + } + + return ret; + +free_new: + spin_unlock_irq(&hugetlb_lock); + /* Page has a zero ref count, but needs a ref to be freed */ + set_page_refcounted(new_page); + update_and_free_page(h, new_page, false); + + return ret; +} + +int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) +{ + struct hstate *h; + struct page *head; + int ret = -EBUSY; + + /* + * The page might have been dissolved from under our feet, so make sure + * to carefully check the state under the lock. + * Return success when racing as if we dissolved the page ourselves. + */ + spin_lock_irq(&hugetlb_lock); + if (PageHuge(page)) { + head = compound_head(page); + h = page_hstate(head); + } else { + spin_unlock_irq(&hugetlb_lock); + return 0; + } + spin_unlock_irq(&hugetlb_lock); + + /* + * Fence off gigantic pages as there is a cyclic dependency between + * alloc_contig_range and them. Return -ENOMEM as this has the effect + * of bailing out right away without further retrying. + */ + if (hstate_is_gigantic(h)) + return -ENOMEM; + + if (page_count(head) && !isolate_hugetlb(head, list)) + ret = 0; + else if (!page_count(head)) + ret = alloc_and_dissolve_huge_page(h, head, list); + + return ret; +} + struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { @@ -2002,6 +2868,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, long gbl_chg; int ret, idx; struct hugetlb_cgroup *h_cg; + bool deferred_reserve; idx = hstate_index(h); /* @@ -2039,11 +2906,21 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, gbl_chg = 1; } + /* If this allocation is not consuming a reservation, charge it now. + */ + deferred_reserve = map_chg || avoid_reserve; + if (deferred_reserve) { + ret = hugetlb_cgroup_charge_cgroup_rsvd( + idx, pages_per_huge_page(h), &h_cg); + if (ret) + goto out_subpool_put; + } + ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); if (ret) - goto out_subpool_put; + goto out_uncharge_cgroup_reservation; - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); /* * glb_chg is passed to indicate whether or not a page must be taken * from the global free pool (global change). gbl_chg == 0 indicates @@ -2051,22 +2928,31 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, */ page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg); if (!page) { - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); page = alloc_buddy_huge_page_with_mpol(h, vma, addr); if (!page) goto out_uncharge_cgroup; + spin_lock_irq(&hugetlb_lock); if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { - SetPagePrivate(page); + SetHPageRestoreReserve(page); h->resv_huge_pages--; } - spin_lock(&hugetlb_lock); - list_move(&page->lru, &h->hugepage_activelist); + list_add(&page->lru, &h->hugepage_activelist); + set_page_refcounted(page); /* Fall through */ } hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page); - spin_unlock(&hugetlb_lock); + /* If allocation is not consuming a reservation, also store the + * hugetlb_cgroup pointer on the page. + */ + if (deferred_reserve) { + hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h), + h_cg, page); + } - set_page_private(page, (unsigned long)spool); + spin_unlock_irq(&hugetlb_lock); + + hugetlb_set_page_subpool(page, spool); map_commit = vma_commit_reservation(h, vma, addr); if (unlikely(map_chg > map_commit)) { @@ -2083,11 +2969,18 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); + if (deferred_reserve) + hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), + pages_per_huge_page(h), page); } return page; out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); +out_uncharge_cgroup_reservation: + if (deferred_reserve) + hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), + h_cg); out_subpool_put: if (map_chg || avoid_reserve) hugepage_subpool_put_pages(spool, 1); @@ -2095,33 +2988,37 @@ out_subpool_put: return ERR_PTR(-ENOSPC); } -int alloc_bootmem_huge_page(struct hstate *h) +int alloc_bootmem_huge_page(struct hstate *h, int nid) __attribute__ ((weak, alias("__alloc_bootmem_huge_page"))); -int __alloc_bootmem_huge_page(struct hstate *h) +int __alloc_bootmem_huge_page(struct hstate *h, int nid) { - struct huge_bootmem_page *m; + struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node; + /* do node specific alloc */ + if (nid != NUMA_NO_NODE) { + m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), + 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); + if (!m) + return 0; + goto found; + } + /* allocate from next node when distributing huge pages */ for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) { - void *addr; - - addr = memblock_alloc_try_nid_raw( + m = memblock_alloc_try_nid_raw( huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, node); - if (addr) { - /* - * Use the beginning of the huge page to store the - * huge_bootmem_page struct (until gather_bootmem - * puts them into the mem_map). - */ - m = addr; - goto found; - } + /* + * Use the beginning of the huge page to store the + * huge_bootmem_page struct (until gather_bootmem + * puts them into the mem_map). + */ + if (!m) + return 0; + goto found; } - return 0; found: - BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h))); /* Put them into a private list first because mem_map is not up yet */ INIT_LIST_HEAD(&m->list); list_add(&m->list, &huge_boot_pages); @@ -2129,16 +3026,10 @@ found: return 1; } -static void __init prep_compound_huge_page(struct page *page, - unsigned int order) -{ - if (unlikely(order > (MAX_ORDER - 1))) - prep_compound_gigantic_page(page, order); - else - prep_compound_page(page, order); -} - -/* Put bootmem huge pages into the standard lists after mem_map is up */ +/* + * Put bootmem huge pages into the standard lists after mem_map is up. + * Note: This only applies to gigantic (order > MAX_ORDER) pages. + */ static void __init gather_bootmem_prealloc(void) { struct huge_bootmem_page *m; @@ -2147,29 +3038,81 @@ static void __init gather_bootmem_prealloc(void) struct page *page = virt_to_page(m); struct hstate *h = m->hstate; + VM_BUG_ON(!hstate_is_gigantic(h)); WARN_ON(page_count(page) != 1); - prep_compound_huge_page(page, h->order); - WARN_ON(PageReserved(page)); - prep_new_huge_page(h, page, page_to_nid(page)); - put_page(page); /* free it into the hugepage allocator */ + if (prep_compound_gigantic_page(page, huge_page_order(h))) { + WARN_ON(PageReserved(page)); + prep_new_huge_page(h, page, page_to_nid(page)); + free_huge_page(page); /* add to the hugepage allocator */ + } else { + /* VERY unlikely inflated ref count on a tail page */ + free_gigantic_page(page, huge_page_order(h)); + } /* - * If we had gigantic hugepages allocated at boot time, we need - * to restore the 'stolen' pages to totalram_pages in order to - * fix confusing memory reports from free(1) and another - * side-effects, like CommitLimit going negative. + * We need to restore the 'stolen' pages to totalram_pages + * in order to fix confusing memory reports from free(1) and + * other side-effects, like CommitLimit going negative. */ - if (hstate_is_gigantic(h)) - adjust_managed_page_count(page, 1 << h->order); + adjust_managed_page_count(page, pages_per_huge_page(h)); cond_resched(); } } +static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) +{ + unsigned long i; + char buf[32]; + + for (i = 0; i < h->max_huge_pages_node[nid]; ++i) { + if (hstate_is_gigantic(h)) { + if (!alloc_bootmem_huge_page(h, nid)) + break; + } else { + struct page *page; + gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; + + page = alloc_fresh_huge_page(h, gfp_mask, nid, + &node_states[N_MEMORY], NULL); + if (!page) + break; + free_huge_page(page); /* free it into the hugepage allocator */ + } + cond_resched(); + } + if (i == h->max_huge_pages_node[nid]) + return; + + string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); + pr_warn("HugeTLB: allocating %u of page size %s failed node%d. Only allocated %lu hugepages.\n", + h->max_huge_pages_node[nid], buf, nid, i); + h->max_huge_pages -= (h->max_huge_pages_node[nid] - i); + h->max_huge_pages_node[nid] = i; +} static void __init hugetlb_hstate_alloc_pages(struct hstate *h) { unsigned long i; nodemask_t *node_alloc_noretry; + bool node_specific_alloc = false; + + /* skip gigantic hugepages allocation if hugetlb_cma enabled */ + if (hstate_is_gigantic(h) && hugetlb_cma_size) { + pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); + return; + } + /* do node specific alloc */ + for_each_online_node(i) { + if (h->max_huge_pages_node[i] > 0) { + hugetlb_hstate_alloc_pages_onenode(h, i); + node_specific_alloc = true; + } + } + + if (node_specific_alloc) + return; + + /* below will do all node balanced alloc */ if (!hstate_is_gigantic(h)) { /* * Bit mask controlling how hard we retry per-node allocations. @@ -2190,7 +3133,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) for (i = 0; i < h->max_huge_pages; ++i) { if (hstate_is_gigantic(h)) { - if (!alloc_bootmem_huge_page(h)) + if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE)) break; } else if (!alloc_pool_huge_page(h, &node_states[N_MEMORY], @@ -2206,23 +3149,38 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) h->max_huge_pages, buf, i); h->max_huge_pages = i; } - kfree(node_alloc_noretry); } static void __init hugetlb_init_hstates(void) { - struct hstate *h; + struct hstate *h, *h2; for_each_hstate(h) { - if (minimum_order > huge_page_order(h)) - minimum_order = huge_page_order(h); - /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); + + /* + * Set demote order for each hstate. Note that + * h->demote_order is initially 0. + * - We can not demote gigantic pages if runtime freeing + * is not supported, so skip this. + * - If CMA allocation is possible, we can not demote + * HUGETLB_PAGE_ORDER or smaller size pages. + */ + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) + continue; + if (hugetlb_cma_size && h->order <= HUGETLB_PAGE_ORDER) + continue; + for_each_hstate(h2) { + if (h2 == h) + continue; + if (h2->order < h->order && + h2->order > h->demote_order) + h->demote_order = h2->order; + } } - VM_BUG_ON(minimum_order == UINT_MAX); } static void __init report_hugepages(void) @@ -2233,8 +3191,10 @@ static void __init report_hugepages(void) char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); - pr_info("HugeTLB registered %s page size, pre-allocated %ld pages\n", + pr_info("HugeTLB: registered %s page size, pre-allocated %ld pages\n", buf, h->free_huge_pages); + pr_info("HugeTLB: %d KiB vmemmap can be freed for a %s page\n", + hugetlb_vmemmap_optimizable_size(h) / SZ_1K, buf); } } @@ -2243,24 +3203,32 @@ static void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { int i; + LIST_HEAD(page_list); + lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h)) return; + /* + * Collect pages to be freed on a list, and free after dropping lock + */ for_each_node_mask(i, *nodes_allowed) { struct page *page, *next; struct list_head *freel = &h->hugepage_freelists[i]; list_for_each_entry_safe(page, next, freel, lru) { if (count >= h->nr_huge_pages) - return; + goto out; if (PageHighMem(page)) continue; - list_del(&page->lru); - update_and_free_page(h, page); - h->free_huge_pages--; - h->free_huge_pages_node[page_to_nid(page)]--; + remove_hugetlb_page(h, page, false); + list_add(&page->lru, &page_list); } } + +out: + spin_unlock_irq(&hugetlb_lock); + update_and_free_pages_bulk(h, &page_list); + spin_lock_irq(&hugetlb_lock); } #else static inline void try_to_free_low(struct hstate *h, unsigned long count, @@ -2279,6 +3247,7 @@ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, { int nr_nodes, node; + lockdep_assert_held(&hugetlb_lock); VM_BUG_ON(delta != -1 && delta != 1); if (delta < 0) { @@ -2306,6 +3275,8 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, nodemask_t *nodes_allowed) { unsigned long min_count, ret; + struct page *page; + LIST_HEAD(page_list); NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL); /* @@ -2318,7 +3289,13 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, else return -ENOMEM; - spin_lock(&hugetlb_lock); + /* + * resize_lock mutex prevents concurrent adjustments to number of + * pages in hstate via the proc/sysfs interfaces. + */ + mutex_lock(&h->resize_lock); + flush_free_hpage_work(h); + spin_lock_irq(&hugetlb_lock); /* * Check for a node specific request. @@ -2349,7 +3326,8 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, */ if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) { if (count > persistent_huge_pages(h)) { - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); + mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return -EINVAL; } @@ -2378,14 +3356,14 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, * page, free_huge_page will handle it by freeing the page * and reducing the surplus. */ - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); /* yield cpu to avoid soft lockup */ cond_resched(); ret = alloc_pool_huge_page(h, nodes_allowed, node_alloc_noretry); - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); if (!ret) goto out; @@ -2412,30 +3390,138 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages; min_count = max(count, min_count); try_to_free_low(h, min_count, nodes_allowed); + + /* + * Collect pages to be removed on list without dropping lock + */ while (min_count < persistent_huge_pages(h)) { - if (!free_pool_huge_page(h, nodes_allowed, 0)) + page = remove_pool_huge_page(h, nodes_allowed, 0); + if (!page) break; - cond_resched_lock(&hugetlb_lock); + + list_add(&page->lru, &page_list); } + /* free the pages after dropping lock */ + spin_unlock_irq(&hugetlb_lock); + update_and_free_pages_bulk(h, &page_list); + flush_free_hpage_work(h); + spin_lock_irq(&hugetlb_lock); + while (count < persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, 1)) break; } out: h->max_huge_pages = persistent_huge_pages(h); - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); + mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return 0; } +static int demote_free_huge_page(struct hstate *h, struct page *page) +{ + int i, nid = page_to_nid(page); + struct hstate *target_hstate; + struct page *subpage; + int rc = 0; + + target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order); + + remove_hugetlb_page_for_demote(h, page, false); + spin_unlock_irq(&hugetlb_lock); + + rc = hugetlb_vmemmap_restore(h, page); + if (rc) { + /* Allocation of vmemmmap failed, we can not demote page */ + spin_lock_irq(&hugetlb_lock); + set_page_refcounted(page); + add_hugetlb_page(h, page, false); + return rc; + } + + /* + * Use destroy_compound_hugetlb_page_for_demote for all huge page + * sizes as it will not ref count pages. + */ + destroy_compound_hugetlb_page_for_demote(page, huge_page_order(h)); + + /* + * Taking target hstate mutex synchronizes with set_max_huge_pages. + * Without the mutex, pages added to target hstate could be marked + * as surplus. + * + * Note that we already hold h->resize_lock. To prevent deadlock, + * use the convention of always taking larger size hstate mutex first. + */ + mutex_lock(&target_hstate->resize_lock); + for (i = 0; i < pages_per_huge_page(h); + i += pages_per_huge_page(target_hstate)) { + subpage = nth_page(page, i); + if (hstate_is_gigantic(target_hstate)) + prep_compound_gigantic_page_for_demote(subpage, + target_hstate->order); + else + prep_compound_page(subpage, target_hstate->order); + set_page_private(subpage, 0); + prep_new_huge_page(target_hstate, subpage, nid); + free_huge_page(subpage); + } + mutex_unlock(&target_hstate->resize_lock); + + spin_lock_irq(&hugetlb_lock); + + /* + * Not absolutely necessary, but for consistency update max_huge_pages + * based on pool changes for the demoted page. + */ + h->max_huge_pages--; + target_hstate->max_huge_pages += + pages_per_huge_page(h) / pages_per_huge_page(target_hstate); + + return rc; +} + +static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) + __must_hold(&hugetlb_lock) +{ + int nr_nodes, node; + struct page *page; + + lockdep_assert_held(&hugetlb_lock); + + /* We should never get here if no demote order */ + if (!h->demote_order) { + pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n"); + return -EINVAL; /* internal error */ + } + + for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { + list_for_each_entry(page, &h->hugepage_freelists[node], lru) { + if (PageHWPoison(page)) + continue; + + return demote_free_huge_page(h, page); + } + } + + /* + * Only way to get here is if all pages on free lists are poisoned. + * Return -EBUSY so that caller will not retry. + */ + return -EBUSY; +} + #define HSTATE_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) +#define HSTATE_ATTR_WO(_name) \ + static struct kobj_attribute _name##_attr = __ATTR_WO(_name) + #define HSTATE_ATTR(_name) \ - static struct kobj_attribute _name##_attr = \ - __ATTR(_name, 0644, _name##_show, _name##_store) + static struct kobj_attribute _name##_attr = __ATTR_RW(_name) static struct kobject *hugepages_kobj; static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; @@ -2469,7 +3555,7 @@ static ssize_t nr_hugepages_show_common(struct kobject *kobj, else nr_huge_pages = h->nr_huge_pages_node[nid]; - return sprintf(buf, "%lu\n", nr_huge_pages); + return sysfs_emit(buf, "%lu\n", nr_huge_pages); } static ssize_t __nr_hugepages_store_common(bool obey_mempolicy, @@ -2542,7 +3628,8 @@ HSTATE_ATTR(nr_hugepages); * huge page alloc/free. */ static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) + struct kobj_attribute *attr, + char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } @@ -2560,7 +3647,7 @@ static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); - return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages); + return sysfs_emit(buf, "%lu\n", h->nr_overcommit_huge_pages); } static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, @@ -2577,9 +3664,9 @@ static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, if (err) return err; - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); h->nr_overcommit_huge_pages = input; - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); return count; } @@ -2598,7 +3685,7 @@ static ssize_t free_hugepages_show(struct kobject *kobj, else free_huge_pages = h->free_huge_pages_node[nid]; - return sprintf(buf, "%lu\n", free_huge_pages); + return sysfs_emit(buf, "%lu\n", free_huge_pages); } HSTATE_ATTR_RO(free_hugepages); @@ -2606,7 +3693,7 @@ static ssize_t resv_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); - return sprintf(buf, "%lu\n", h->resv_huge_pages); + return sysfs_emit(buf, "%lu\n", h->resv_huge_pages); } HSTATE_ATTR_RO(resv_hugepages); @@ -2623,10 +3710,105 @@ static ssize_t surplus_hugepages_show(struct kobject *kobj, else surplus_huge_pages = h->surplus_huge_pages_node[nid]; - return sprintf(buf, "%lu\n", surplus_huge_pages); + return sysfs_emit(buf, "%lu\n", surplus_huge_pages); } HSTATE_ATTR_RO(surplus_hugepages); +static ssize_t demote_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t len) +{ + unsigned long nr_demote; + unsigned long nr_available; + nodemask_t nodes_allowed, *n_mask; + struct hstate *h; + int err; + int nid; + + err = kstrtoul(buf, 10, &nr_demote); + if (err) + return err; + h = kobj_to_hstate(kobj, &nid); + + if (nid != NUMA_NO_NODE) { + init_nodemask_of_node(&nodes_allowed, nid); + n_mask = &nodes_allowed; + } else { + n_mask = &node_states[N_MEMORY]; + } + + /* Synchronize with other sysfs operations modifying huge pages */ + mutex_lock(&h->resize_lock); + spin_lock_irq(&hugetlb_lock); + + while (nr_demote) { + /* + * Check for available pages to demote each time thorough the + * loop as demote_pool_huge_page will drop hugetlb_lock. + */ + if (nid != NUMA_NO_NODE) + nr_available = h->free_huge_pages_node[nid]; + else + nr_available = h->free_huge_pages; + nr_available -= h->resv_huge_pages; + if (!nr_available) + break; + + err = demote_pool_huge_page(h, n_mask); + if (err) + break; + + nr_demote--; + } + + spin_unlock_irq(&hugetlb_lock); + mutex_unlock(&h->resize_lock); + + if (err) + return err; + return len; +} +HSTATE_ATTR_WO(demote); + +static ssize_t demote_size_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj, NULL); + unsigned long demote_size = (PAGE_SIZE << h->demote_order) / SZ_1K; + + return sysfs_emit(buf, "%lukB\n", demote_size); +} + +static ssize_t demote_size_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct hstate *h, *demote_hstate; + unsigned long demote_size; + unsigned int demote_order; + + demote_size = (unsigned long)memparse(buf, NULL); + + demote_hstate = size_to_hstate(demote_size); + if (!demote_hstate) + return -EINVAL; + demote_order = demote_hstate->order; + if (demote_order < HUGETLB_PAGE_ORDER) + return -EINVAL; + + /* demote order must be smaller than hstate order */ + h = kobj_to_hstate(kobj, NULL); + if (demote_order >= h->order) + return -EINVAL; + + /* resize_lock synchronizes access to demote size and writes */ + mutex_lock(&h->resize_lock); + h->demote_order = demote_order; + mutex_unlock(&h->resize_lock); + + return count; +} +HSTATE_ATTR(demote_size); + static struct attribute *hstate_attrs[] = { &nr_hugepages_attr.attr, &nr_overcommit_hugepages_attr.attr, @@ -2643,6 +3825,16 @@ static const struct attribute_group hstate_attr_group = { .attrs = hstate_attrs, }; +static struct attribute *hstate_demote_attrs[] = { + &demote_size_attr.attr, + &demote_attr.attr, + NULL, +}; + +static const struct attribute_group hstate_demote_attr_group = { + .attrs = hstate_demote_attrs, +}; + static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, struct kobject **hstate_kobjs, const struct attribute_group *hstate_attr_group) @@ -2655,30 +3847,29 @@ static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, return -ENOMEM; retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group); - if (retval) + if (retval) { kobject_put(hstate_kobjs[hi]); + hstate_kobjs[hi] = NULL; + return retval; + } - return retval; -} - -static void __init hugetlb_sysfs_init(void) -{ - struct hstate *h; - int err; - - hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj); - if (!hugepages_kobj) - return; - - for_each_hstate(h) { - err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, - hstate_kobjs, &hstate_attr_group); - if (err) - pr_err("Hugetlb: Unable to add hstate %s", h->name); + if (h->demote_order) { + retval = sysfs_create_group(hstate_kobjs[hi], + &hstate_demote_attr_group); + if (retval) { + pr_warn("HugeTLB unable to create demote interfaces for %s\n", h->name); + sysfs_remove_group(hstate_kobjs[hi], hstate_attr_group); + kobject_put(hstate_kobjs[hi]); + hstate_kobjs[hi] = NULL; + return retval; + } } + + return 0; } #ifdef CONFIG_NUMA +static bool hugetlb_sysfs_initialized __ro_after_init; /* * node_hstate/s - associate per node hstate attributes, via their kobjects, @@ -2734,7 +3925,7 @@ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) * Unregister hstate attributes from a single node device. * No-op if no hstate attributes attached. */ -static void hugetlb_unregister_node(struct node *node) +void hugetlb_unregister_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; @@ -2744,10 +3935,15 @@ static void hugetlb_unregister_node(struct node *node) for_each_hstate(h) { int idx = hstate_index(h); - if (nhs->hstate_kobjs[idx]) { - kobject_put(nhs->hstate_kobjs[idx]); - nhs->hstate_kobjs[idx] = NULL; - } + struct kobject *hstate_kobj = nhs->hstate_kobjs[idx]; + + if (!hstate_kobj) + continue; + if (h->demote_order) + sysfs_remove_group(hstate_kobj, &hstate_demote_attr_group); + sysfs_remove_group(hstate_kobj, &per_node_hstate_attr_group); + kobject_put(hstate_kobj); + nhs->hstate_kobjs[idx] = NULL; } kobject_put(nhs->hugepages_kobj); @@ -2759,12 +3955,15 @@ static void hugetlb_unregister_node(struct node *node) * Register hstate attributes for a single node device. * No-op if attributes already registered. */ -static void hugetlb_register_node(struct node *node) +void hugetlb_register_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; int err; + if (!hugetlb_sysfs_initialized) + return; + if (nhs->hugepages_kobj) return; /* already allocated */ @@ -2778,7 +3977,7 @@ static void hugetlb_register_node(struct node *node) nhs->hstate_kobjs, &per_node_hstate_attr_group); if (err) { - pr_err("Hugetlb: Unable to add hstate %s for node %d\n", + pr_err("HugeTLB: Unable to add hstate %s for node %d\n", h->name, node->dev.id); hugetlb_unregister_node(node); break; @@ -2795,18 +3994,8 @@ static void __init hugetlb_register_all_nodes(void) { int nid; - for_each_node_state(nid, N_MEMORY) { - struct node *node = node_devices[nid]; - if (node->dev.id == nid) - hugetlb_register_node(node); - } - - /* - * Let the node device driver know we're here so it can - * [un]register hstate attributes on node hotplug. - */ - register_hugetlbfs_with_node(hugetlb_register_node, - hugetlb_unregister_node); + for_each_online_node(nid) + hugetlb_register_node(node_devices[nid]); } #else /* !CONFIG_NUMA */ @@ -2822,35 +4011,90 @@ static void hugetlb_register_all_nodes(void) { } #endif +#ifdef CONFIG_CMA +static void __init hugetlb_cma_check(void); +#else +static inline __init void hugetlb_cma_check(void) +{ +} +#endif + +static void __init hugetlb_sysfs_init(void) +{ + struct hstate *h; + int err; + + hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj); + if (!hugepages_kobj) + return; + + for_each_hstate(h) { + err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, + hstate_kobjs, &hstate_attr_group); + if (err) + pr_err("HugeTLB: Unable to add hstate %s", h->name); + } + +#ifdef CONFIG_NUMA + hugetlb_sysfs_initialized = true; +#endif + hugetlb_register_all_nodes(); +} + static int __init hugetlb_init(void) { int i; - if (!hugepages_supported()) + BUILD_BUG_ON(sizeof_field(struct page, private) * BITS_PER_BYTE < + __NR_HPAGEFLAGS); + + if (!hugepages_supported()) { + if (hugetlb_max_hstate || default_hstate_max_huge_pages) + pr_warn("HugeTLB: huge pages not supported, ignoring associated command-line parameters\n"); return 0; + } - if (!size_to_hstate(default_hstate_size)) { - if (default_hstate_size != 0) { - pr_err("HugeTLB: unsupported default_hugepagesz %lu. Reverting to %lu\n", - default_hstate_size, HPAGE_SIZE); - } + /* + * Make sure HPAGE_SIZE (HUGETLB_PAGE_ORDER) hstate exists. Some + * architectures depend on setup being done here. + */ + hugetlb_add_hstate(HUGETLB_PAGE_ORDER); + if (!parsed_default_hugepagesz) { + /* + * If we did not parse a default huge page size, set + * default_hstate_idx to HPAGE_SIZE hstate. And, if the + * number of huge pages for this default size was implicitly + * specified, set that here as well. + * Note that the implicit setting will overwrite an explicit + * setting. A warning will be printed in this case. + */ + default_hstate_idx = hstate_index(size_to_hstate(HPAGE_SIZE)); + if (default_hstate_max_huge_pages) { + if (default_hstate.max_huge_pages) { + char buf[32]; + + string_get_size(huge_page_size(&default_hstate), + 1, STRING_UNITS_2, buf, 32); + pr_warn("HugeTLB: Ignoring hugepages=%lu associated with %s page size\n", + default_hstate.max_huge_pages, buf); + pr_warn("HugeTLB: Using hugepages=%lu for number of default huge pages\n", + default_hstate_max_huge_pages); + } + default_hstate.max_huge_pages = + default_hstate_max_huge_pages; - default_hstate_size = HPAGE_SIZE; - if (!size_to_hstate(default_hstate_size)) - hugetlb_add_hstate(HUGETLB_PAGE_ORDER); - } - default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size)); - if (default_hstate_max_huge_pages) { - if (!default_hstate.max_huge_pages) - default_hstate.max_huge_pages = default_hstate_max_huge_pages; + for_each_online_node(i) + default_hstate.max_huge_pages_node[i] = + default_hugepages_in_node[i]; + } } + hugetlb_cma_check(); hugetlb_init_hstates(); gather_bootmem_prealloc(); report_hugepages(); hugetlb_sysfs_init(); - hugetlb_register_all_nodes(); hugetlb_cgroup_file_init(); #ifdef CONFIG_SMP @@ -2869,10 +4113,10 @@ static int __init hugetlb_init(void) } subsys_initcall(hugetlb_init); -/* Should be called on processing a hugepagesz=... option */ -void __init hugetlb_bad_size(void) +/* Overwritten by architectures with more huge page sizes */ +bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size) { - parsed_valid_hugepagesz = false; + return size == HPAGE_SIZE; } void __init hugetlb_add_hstate(unsigned int order) @@ -2881,41 +4125,70 @@ void __init hugetlb_add_hstate(unsigned int order) unsigned long i; if (size_to_hstate(PAGE_SIZE << order)) { - pr_warn("hugepagesz= specified twice, ignoring\n"); return; } BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); BUG_ON(order == 0); h = &hstates[hugetlb_max_hstate++]; + mutex_init(&h->resize_lock); h->order = order; - h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1); - h->nr_huge_pages = 0; - h->free_huge_pages = 0; + h->mask = ~(huge_page_size(h) - 1); for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); INIT_LIST_HEAD(&h->hugepage_activelist); h->next_nid_to_alloc = first_memory_node; h->next_nid_to_free = first_memory_node; snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", - huge_page_size(h)/1024); + huge_page_size(h)/SZ_1K); parsed_hstate = h; } -static int __init hugetlb_nrpages_setup(char *s) +bool __init __weak hugetlb_node_alloc_supported(void) +{ + return true; +} + +static void __init hugepages_clear_pages_in_node(void) +{ + if (!hugetlb_max_hstate) { + default_hstate_max_huge_pages = 0; + memset(default_hugepages_in_node, 0, + sizeof(default_hugepages_in_node)); + } else { + parsed_hstate->max_huge_pages = 0; + memset(parsed_hstate->max_huge_pages_node, 0, + sizeof(parsed_hstate->max_huge_pages_node)); + } +} + +/* + * hugepages command line processing + * hugepages normally follows a valid hugepagsz or default_hugepagsz + * specification. If not, ignore the hugepages value. hugepages can also + * be the first huge page command line option in which case it implicitly + * specifies the number of huge pages for the default size. + */ +static int __init hugepages_setup(char *s) { unsigned long *mhp; static unsigned long *last_mhp; + int node = NUMA_NO_NODE; + int count; + unsigned long tmp; + char *p = s; if (!parsed_valid_hugepagesz) { - pr_warn("hugepages = %s preceded by " - "an unsupported hugepagesz, ignoring\n", s); + pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); parsed_valid_hugepagesz = true; return 1; } + /* - * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter yet, - * so this hugepages= parameter goes to the "default hstate". + * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter + * yet, so this hugepages= parameter goes to the "default hstate". + * Otherwise, it goes with the previously parsed hugepagesz or + * default_hugepagesz. */ else if (!hugetlb_max_hstate) mhp = &default_hstate_max_huge_pages; @@ -2923,49 +4196,217 @@ static int __init hugetlb_nrpages_setup(char *s) mhp = &parsed_hstate->max_huge_pages; if (mhp == last_mhp) { - pr_warn("hugepages= specified twice without interleaving hugepagesz=, ignoring\n"); + pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s); return 1; } - if (sscanf(s, "%lu", mhp) <= 0) - *mhp = 0; + while (*p) { + count = 0; + if (sscanf(p, "%lu%n", &tmp, &count) != 1) + goto invalid; + /* Parameter is node format */ + if (p[count] == ':') { + if (!hugetlb_node_alloc_supported()) { + pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); + return 1; + } + if (tmp >= MAX_NUMNODES || !node_online(tmp)) + goto invalid; + node = array_index_nospec(tmp, MAX_NUMNODES); + p += count + 1; + /* Parse hugepages */ + if (sscanf(p, "%lu%n", &tmp, &count) != 1) + goto invalid; + if (!hugetlb_max_hstate) + default_hugepages_in_node[node] = tmp; + else + parsed_hstate->max_huge_pages_node[node] = tmp; + *mhp += tmp; + /* Go to parse next node*/ + if (p[count] == ',') + p += count + 1; + else + break; + } else { + if (p != s) + goto invalid; + *mhp = tmp; + break; + } + } /* * Global state is always initialized later in hugetlb_init. - * But we need to allocate >= MAX_ORDER hstates here early to still + * But we need to allocate gigantic hstates here early to still * use the bootmem allocator. */ - if (hugetlb_max_hstate && parsed_hstate->order >= MAX_ORDER) + if (hugetlb_max_hstate && hstate_is_gigantic(parsed_hstate)) hugetlb_hstate_alloc_pages(parsed_hstate); last_mhp = mhp; return 1; + +invalid: + pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p); + hugepages_clear_pages_in_node(); + return 1; +} +__setup("hugepages=", hugepages_setup); + +/* + * hugepagesz command line processing + * A specific huge page size can only be specified once with hugepagesz. + * hugepagesz is followed by hugepages on the command line. The global + * variable 'parsed_valid_hugepagesz' is used to determine if prior + * hugepagesz argument was valid. + */ +static int __init hugepagesz_setup(char *s) +{ + unsigned long size; + struct hstate *h; + + parsed_valid_hugepagesz = false; + size = (unsigned long)memparse(s, NULL); + + if (!arch_hugetlb_valid_size(size)) { + pr_err("HugeTLB: unsupported hugepagesz=%s\n", s); + return 1; + } + + h = size_to_hstate(size); + if (h) { + /* + * hstate for this size already exists. This is normally + * an error, but is allowed if the existing hstate is the + * default hstate. More specifically, it is only allowed if + * the number of huge pages for the default hstate was not + * previously specified. + */ + if (!parsed_default_hugepagesz || h != &default_hstate || + default_hstate.max_huge_pages) { + pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s); + return 1; + } + + /* + * No need to call hugetlb_add_hstate() as hstate already + * exists. But, do set parsed_hstate so that a following + * hugepages= parameter will be applied to this hstate. + */ + parsed_hstate = h; + parsed_valid_hugepagesz = true; + return 1; + } + + hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); + parsed_valid_hugepagesz = true; + return 1; } -__setup("hugepages=", hugetlb_nrpages_setup); +__setup("hugepagesz=", hugepagesz_setup); -static int __init hugetlb_default_setup(char *s) +/* + * default_hugepagesz command line input + * Only one instance of default_hugepagesz allowed on command line. + */ +static int __init default_hugepagesz_setup(char *s) { - default_hstate_size = memparse(s, &s); + unsigned long size; + int i; + + parsed_valid_hugepagesz = false; + if (parsed_default_hugepagesz) { + pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); + return 1; + } + + size = (unsigned long)memparse(s, NULL); + + if (!arch_hugetlb_valid_size(size)) { + pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s); + return 1; + } + + hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); + parsed_valid_hugepagesz = true; + parsed_default_hugepagesz = true; + default_hstate_idx = hstate_index(size_to_hstate(size)); + + /* + * The number of default huge pages (for this size) could have been + * specified as the first hugetlb parameter: hugepages=X. If so, + * then default_hstate_max_huge_pages is set. If the default huge + * page size is gigantic (>= MAX_ORDER), then the pages must be + * allocated here from bootmem allocator. + */ + if (default_hstate_max_huge_pages) { + default_hstate.max_huge_pages = default_hstate_max_huge_pages; + for_each_online_node(i) + default_hstate.max_huge_pages_node[i] = + default_hugepages_in_node[i]; + if (hstate_is_gigantic(&default_hstate)) + hugetlb_hstate_alloc_pages(&default_hstate); + default_hstate_max_huge_pages = 0; + } + return 1; } -__setup("default_hugepagesz=", hugetlb_default_setup); +__setup("default_hugepagesz=", default_hugepagesz_setup); + +static nodemask_t *policy_mbind_nodemask(gfp_t gfp) +{ +#ifdef CONFIG_NUMA + struct mempolicy *mpol = get_task_policy(current); + + /* + * Only enforce MPOL_BIND policy which overlaps with cpuset policy + * (from policy_nodemask) specifically for hugetlb case + */ + if (mpol->mode == MPOL_BIND && + (apply_policy_zone(mpol, gfp_zone(gfp)) && + cpuset_nodemask_valid_mems_allowed(&mpol->nodes))) + return &mpol->nodes; +#endif + return NULL; +} -static unsigned int cpuset_mems_nr(unsigned int *array) +static unsigned int allowed_mems_nr(struct hstate *h) { int node; unsigned int nr = 0; + nodemask_t *mbind_nodemask; + unsigned int *array = h->free_huge_pages_node; + gfp_t gfp_mask = htlb_alloc_mask(h); - for_each_node_mask(node, cpuset_current_mems_allowed) - nr += array[node]; + mbind_nodemask = policy_mbind_nodemask(gfp_mask); + for_each_node_mask(node, cpuset_current_mems_allowed) { + if (!mbind_nodemask || node_isset(node, *mbind_nodemask)) + nr += array[node]; + } return nr; } #ifdef CONFIG_SYSCTL +static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write, + void *buffer, size_t *length, + loff_t *ppos, unsigned long *out) +{ + struct ctl_table dup_table; + + /* + * In order to avoid races with __do_proc_doulongvec_minmax(), we + * can duplicate the @table and alter the duplicate of it. + */ + dup_table = *table; + dup_table.data = out; + + return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos); +} + static int hugetlb_sysctl_handler_common(bool obey_mempolicy, struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) + void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp = h->max_huge_pages; @@ -2974,9 +4415,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, if (!hugepages_supported()) return -EOPNOTSUPP; - table->data = &tmp; - table->maxlen = sizeof(unsigned long); - ret = proc_doulongvec_minmax(table, write, buffer, length, ppos); + ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, + &tmp); if (ret) goto out; @@ -2988,7 +4428,7 @@ out: } int hugetlb_sysctl_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) + void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(false, table, write, @@ -2997,7 +4437,7 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write, #ifdef CONFIG_NUMA int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) + void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(true, table, write, buffer, length, ppos); @@ -3005,8 +4445,7 @@ int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, #endif /* CONFIG_NUMA */ int hugetlb_overcommit_handler(struct ctl_table *table, int write, - void __user *buffer, - size_t *length, loff_t *ppos) + void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp; @@ -3020,16 +4459,15 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, if (write && hstate_is_gigantic(h)) return -EINVAL; - table->data = &tmp; - table->maxlen = sizeof(unsigned long); - ret = proc_doulongvec_minmax(table, write, buffer, length, ppos); + ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, + &tmp); if (ret) goto out; if (write) { - spin_lock(&hugetlb_lock); + spin_lock_irq(&hugetlb_lock); h->nr_overcommit_huge_pages = tmp; - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); } out: return ret; @@ -3048,7 +4486,7 @@ void hugetlb_report_meminfo(struct seq_file *m) for_each_hstate(h) { unsigned long count = h->nr_huge_pages; - total += (PAGE_SIZE << huge_page_order(h)) * count; + total += huge_page_size(h) * count; if (h == &default_hstate) seq_printf(m, @@ -3061,42 +4499,42 @@ void hugetlb_report_meminfo(struct seq_file *m) h->free_huge_pages, h->resv_huge_pages, h->surplus_huge_pages, - (PAGE_SIZE << huge_page_order(h)) / 1024); + huge_page_size(h) / SZ_1K); } - seq_printf(m, "Hugetlb: %8lu kB\n", total / 1024); + seq_printf(m, "Hugetlb: %8lu kB\n", total / SZ_1K); } -int hugetlb_report_node_meminfo(int nid, char *buf) +int hugetlb_report_node_meminfo(char *buf, int len, int nid) { struct hstate *h = &default_hstate; + if (!hugepages_supported()) return 0; - return sprintf(buf, - "Node %d HugePages_Total: %5u\n" - "Node %d HugePages_Free: %5u\n" - "Node %d HugePages_Surp: %5u\n", - nid, h->nr_huge_pages_node[nid], - nid, h->free_huge_pages_node[nid], - nid, h->surplus_huge_pages_node[nid]); + + return sysfs_emit_at(buf, len, + "Node %d HugePages_Total: %5u\n" + "Node %d HugePages_Free: %5u\n" + "Node %d HugePages_Surp: %5u\n", + nid, h->nr_huge_pages_node[nid], + nid, h->free_huge_pages_node[nid], + nid, h->surplus_huge_pages_node[nid]); } -void hugetlb_show_meminfo(void) +void hugetlb_show_meminfo_node(int nid) { struct hstate *h; - int nid; if (!hugepages_supported()) return; - for_each_node_state(nid, N_MEMORY) - for_each_hstate(h) - pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", - nid, - h->nr_huge_pages_node[nid], - h->free_huge_pages_node[nid], - h->surplus_huge_pages_node[nid], - 1UL << (huge_page_order(h) + PAGE_SHIFT - 10)); + for_each_hstate(h) + printk("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", + nid, + h->nr_huge_pages_node[nid], + h->free_huge_pages_node[nid], + h->surplus_huge_pages_node[nid], + huge_page_size(h) / SZ_1K); } void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm) @@ -3120,7 +4558,10 @@ static int hugetlb_acct_memory(struct hstate *h, long delta) { int ret = -ENOMEM; - spin_lock(&hugetlb_lock); + if (!delta) + return 0; + + spin_lock_irq(&hugetlb_lock); /* * When cpuset is configured, it breaks the strict hugetlb page * reservation as the accounting is done on a global variable. Such @@ -3137,12 +4578,18 @@ static int hugetlb_acct_memory(struct hstate *h, long delta) * we fall back to check against current free page availability as * a best attempt and hopefully to minimize the impact of changing * semantics that cpuset has. + * + * Apart from cpuset, we also have memory policy mechanism that + * also determines from which node the kernel will allocate memory + * in a NUMA system. So similar to cpuset, we also should consider + * the memory policy of the current task. Similar to the description + * above. */ if (delta > 0) { if (gather_surplus_pages(h, delta) < 0) goto out; - if (delta > cpuset_mems_nr(h->free_huge_pages_node)) { + if (delta > allowed_mems_nr(h)) { return_unused_surplus_pages(h, delta); goto out; } @@ -3153,7 +4600,7 @@ static int hugetlb_acct_memory(struct hstate *h, long delta) return_unused_surplus_pages(h, (unsigned long) -delta); out: - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); return ret; } @@ -3162,6 +4609,7 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma) struct resv_map *resv = vma_resv_map(vma); /* + * HPAGE_RESV_OWNER indicates a private mapping. * This new VMA should share its siblings reservation map if present. * The VMA will only ever have a valid reservation map pointer where * it is being copied for another still existing VMA. As that VMA @@ -3169,18 +4617,42 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma) * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ - if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + resv_map_dup_hugetlb_cgroup_uncharge_info(resv); kref_get(&resv->refs); + } + + /* + * vma_lock structure for sharable mappings is vma specific. + * Clear old pointer (if copied via vm_area_dup) and allocate + * new structure. Before clearing, make sure vma_lock is not + * for this vma. + */ + if (vma->vm_flags & VM_MAYSHARE) { + struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; + + if (vma_lock) { + if (vma_lock->vma != vma) { + vma->vm_private_data = NULL; + hugetlb_vma_lock_alloc(vma); + } else + pr_warn("HugeTLB: vma_lock already exists in %s.\n", __func__); + } else + hugetlb_vma_lock_alloc(vma); + } } static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); - struct resv_map *resv = vma_resv_map(vma); + struct resv_map *resv; struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve, start, end; long gbl_reserve; + hugetlb_vma_lock_free(vma); + + resv = vma_resv_map(vma); if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return; @@ -3188,9 +4660,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) end = vma_hugecache_offset(h, vma, vma->vm_end); reserve = (end - start) - region_count(resv, start, end); - - kref_put(&resv->refs, resv_map_release); - + hugetlb_cgroup_uncharge_counter(resv, start, end); if (reserve) { /* * Decrement reserve counts. The global reserve count may be @@ -3199,6 +4669,8 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) gbl_reserve = hugepage_subpool_put_pages(spool, reserve); hugetlb_acct_memory(h, -gbl_reserve); } + + kref_put(&resv->refs, resv_map_release); } static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) @@ -3210,15 +4682,13 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) { - struct hstate *hstate = hstate_vma(vma); - - return 1UL << huge_page_shift(hstate); + return huge_page_size(hstate_vma(vma)); } /* * We cannot handle pagefaults against hugetlb pages at all. They cause * handle_mm_fault() to try to instantiate regular-sized pages in the - * hugegpage VMA. do_page_fault() is supposed to trap this, so BUG is we get + * hugepage VMA. do_page_fault() is supposed to trap this, so BUG is we get * this far. */ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf) @@ -3238,7 +4708,7 @@ const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, .close = hugetlb_vm_op_close, - .split = hugetlb_vm_op_split, + .may_split = hugetlb_vm_op_split, .pagesize = hugetlb_vm_op_pagesize, }; @@ -3246,6 +4716,7 @@ static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, int writable) { pte_t entry; + unsigned int shift = huge_page_shift(hstate_vma(vma)); if (writable) { entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page, @@ -3255,8 +4726,7 @@ static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, vma->vm_page_prot)); } entry = pte_mkyoung(entry); - entry = pte_mkhuge(entry); - entry = arch_make_huge_pte(entry, vma, page, writable); + entry = arch_make_huge_pte(entry, shift, vma->vm_flags); return entry; } @@ -3278,52 +4748,78 @@ bool is_hugetlb_entry_migration(pte_t pte) if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); - if (non_swap_entry(swp) && is_migration_entry(swp)) + if (is_migration_entry(swp)) return true; else return false; } -static int is_hugetlb_entry_hwpoisoned(pte_t pte) +static bool is_hugetlb_entry_hwpoisoned(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) - return 0; + return false; swp = pte_to_swp_entry(pte); - if (non_swap_entry(swp) && is_hwpoison_entry(swp)) - return 1; + if (is_hwpoison_entry(swp)) + return true; else - return 0; + return false; +} + +static void +hugetlb_install_page(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr, + struct page *new_page) +{ + __SetPageUptodate(new_page); + hugepage_add_new_anon_rmap(new_page, vma, addr); + set_huge_pte_at(vma->vm_mm, addr, ptep, make_huge_pte(vma, new_page, 1)); + hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm); + ClearHPageRestoreReserve(new_page); + SetHPageMigratable(new_page); } int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, - struct vm_area_struct *vma) + struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma) { - pte_t *src_pte, *dst_pte, entry, dst_entry; + pte_t *src_pte, *dst_pte, entry; struct page *ptepage; unsigned long addr; - int cow; - struct hstate *h = hstate_vma(vma); + bool cow = is_cow_mapping(src_vma->vm_flags); + struct hstate *h = hstate_vma(src_vma); unsigned long sz = huge_page_size(h); + unsigned long npages = pages_per_huge_page(h); struct mmu_notifier_range range; + unsigned long last_addr_mask; int ret = 0; - cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; - if (cow) { - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src, - vma->vm_start, - vma->vm_end); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src_vma, src, + src_vma->vm_start, + src_vma->vm_end); mmu_notifier_invalidate_range_start(&range); + mmap_assert_write_locked(src); + raw_write_seqcount_begin(&src->write_protect_seq); + } else { + /* + * For shared mappings the vma lock must be held before + * calling huge_pte_offset in the src vma. Otherwise, the + * returned ptep could go away if part of a shared pmd and + * another thread calls huge_pmd_unshare. + */ + hugetlb_vma_lock_read(src_vma); } - for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { + last_addr_mask = hugetlb_mask_last_page(h); + for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; src_pte = huge_pte_offset(src, addr, sz); - if (!src_pte) + if (!src_pte) { + addr |= last_addr_mask; continue; - dst_pte = huge_pte_alloc(dst, addr, sz); + } + dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz); if (!dst_pte) { ret = -ENOMEM; break; @@ -3331,75 +4827,234 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, /* * If the pagetables are shared don't copy or take references. - * dst_pte == src_pte is the common case of src/dest sharing. * + * dst_pte == src_pte is the common case of src/dest sharing. * However, src could have 'unshared' and dst shares with - * another vma. If dst_pte !none, this implies sharing. - * Check here before taking page table lock, and once again - * after taking the lock below. + * another vma. So page_count of ptep page is checked instead + * to reliably determine whether pte is shared. */ - dst_entry = huge_ptep_get(dst_pte); - if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) + if (page_count(virt_to_page(dst_pte)) > 1) { + addr |= last_addr_mask; continue; + } dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); - dst_entry = huge_ptep_get(dst_pte); - if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) { +again: + if (huge_pte_none(entry)) { /* - * Skip if src entry none. Also, skip in the - * unlikely case dst entry !none as this implies - * sharing with another vma. + * Skip if src entry none. */ ; - } else if (unlikely(is_hugetlb_entry_migration(entry) || - is_hugetlb_entry_hwpoisoned(entry))) { + } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) { + bool uffd_wp = huge_pte_uffd_wp(entry); + + if (!userfaultfd_wp(dst_vma) && uffd_wp) + entry = huge_pte_clear_uffd_wp(entry); + set_huge_pte_at(dst, addr, dst_pte, entry); + } else if (unlikely(is_hugetlb_entry_migration(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); + bool uffd_wp = huge_pte_uffd_wp(entry); - if (is_write_migration_entry(swp_entry) && cow) { + if (!is_readable_migration_entry(swp_entry) && cow) { /* * COW mappings require pages in both * parent and child to be set to read. */ - make_migration_entry_read(&swp_entry); + swp_entry = make_readable_migration_entry( + swp_offset(swp_entry)); entry = swp_entry_to_pte(swp_entry); - set_huge_swap_pte_at(src, addr, src_pte, - entry, sz); + if (userfaultfd_wp(src_vma) && uffd_wp) + entry = huge_pte_mkuffd_wp(entry); + set_huge_pte_at(src, addr, src_pte, entry); } - set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz); + if (!userfaultfd_wp(dst_vma) && uffd_wp) + entry = huge_pte_clear_uffd_wp(entry); + set_huge_pte_at(dst, addr, dst_pte, entry); + } else if (unlikely(is_pte_marker(entry))) { + /* + * We copy the pte marker only if the dst vma has + * uffd-wp enabled. + */ + if (userfaultfd_wp(dst_vma)) + set_huge_pte_at(dst, addr, dst_pte, entry); } else { + entry = huge_ptep_get(src_pte); + ptepage = pte_page(entry); + get_page(ptepage); + + /* + * Failing to duplicate the anon rmap is a rare case + * where we see pinned hugetlb pages while they're + * prone to COW. We need to do the COW earlier during + * fork. + * + * When pre-allocating the page or copying data, we + * need to be without the pgtable locks since we could + * sleep during the process. + */ + if (!PageAnon(ptepage)) { + page_dup_file_rmap(ptepage, true); + } else if (page_try_dup_anon_rmap(ptepage, true, + src_vma)) { + pte_t src_pte_old = entry; + struct page *new; + + spin_unlock(src_ptl); + spin_unlock(dst_ptl); + /* Do not use reserve as it's private owned */ + new = alloc_huge_page(dst_vma, addr, 1); + if (IS_ERR(new)) { + put_page(ptepage); + ret = PTR_ERR(new); + break; + } + copy_user_huge_page(new, ptepage, addr, dst_vma, + npages); + put_page(ptepage); + + /* Install the new huge page if src pte stable */ + dst_ptl = huge_pte_lock(h, dst, dst_pte); + src_ptl = huge_pte_lockptr(h, src, src_pte); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + entry = huge_ptep_get(src_pte); + if (!pte_same(src_pte_old, entry)) { + restore_reserve_on_error(h, dst_vma, addr, + new); + put_page(new); + /* huge_ptep of dst_pte won't change as in child */ + goto again; + } + hugetlb_install_page(dst_vma, dst_pte, addr, new); + spin_unlock(src_ptl); + spin_unlock(dst_ptl); + continue; + } + if (cow) { /* * No need to notify as we are downgrading page * table protection not changing it to point * to a new page. * - * See Documentation/vm/mmu_notifier.rst + * See Documentation/mm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); + entry = huge_pte_wrprotect(entry); } - entry = huge_ptep_get(src_pte); - ptepage = pte_page(entry); - get_page(ptepage); - page_dup_rmap(ptepage, true); + set_huge_pte_at(dst, addr, dst_pte, entry); - hugetlb_count_add(pages_per_huge_page(h), dst); + hugetlb_count_add(npages, dst); } spin_unlock(src_ptl); spin_unlock(dst_ptl); } - if (cow) + if (cow) { + raw_write_seqcount_end(&src->write_protect_seq); mmu_notifier_invalidate_range_end(&range); + } else { + hugetlb_vma_unlock_read(src_vma); + } return ret; } -void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct page *ref_page) +static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, + unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte) +{ + struct hstate *h = hstate_vma(vma); + struct mm_struct *mm = vma->vm_mm; + spinlock_t *src_ptl, *dst_ptl; + pte_t pte; + + dst_ptl = huge_pte_lock(h, mm, dst_pte); + src_ptl = huge_pte_lockptr(h, mm, src_pte); + + /* + * We don't have to worry about the ordering of src and dst ptlocks + * because exclusive mmap_sem (or the i_mmap_lock) prevents deadlock. + */ + if (src_ptl != dst_ptl) + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + + pte = huge_ptep_get_and_clear(mm, old_addr, src_pte); + set_huge_pte_at(mm, new_addr, dst_pte, pte); + + if (src_ptl != dst_ptl) + spin_unlock(src_ptl); + spin_unlock(dst_ptl); +} + +int move_hugetlb_page_tables(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, unsigned long new_addr, + unsigned long len) +{ + struct hstate *h = hstate_vma(vma); + struct address_space *mapping = vma->vm_file->f_mapping; + unsigned long sz = huge_page_size(h); + struct mm_struct *mm = vma->vm_mm; + unsigned long old_end = old_addr + len; + unsigned long last_addr_mask; + pte_t *src_pte, *dst_pte; + struct mmu_notifier_range range; + bool shared_pmd = false; + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, old_addr, + old_end); + adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); + /* + * In case of shared PMDs, we should cover the maximum possible + * range. + */ + flush_cache_range(vma, range.start, range.end); + + mmu_notifier_invalidate_range_start(&range); + last_addr_mask = hugetlb_mask_last_page(h); + /* Prevent race with file truncation */ + hugetlb_vma_lock_write(vma); + i_mmap_lock_write(mapping); + for (; old_addr < old_end; old_addr += sz, new_addr += sz) { + src_pte = huge_pte_offset(mm, old_addr, sz); + if (!src_pte) { + old_addr |= last_addr_mask; + new_addr |= last_addr_mask; + continue; + } + if (huge_pte_none(huge_ptep_get(src_pte))) + continue; + + if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) { + shared_pmd = true; + old_addr |= last_addr_mask; + new_addr |= last_addr_mask; + continue; + } + + dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz); + if (!dst_pte) + break; + + move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte); + } + + if (shared_pmd) + flush_tlb_range(vma, range.start, range.end); + else + flush_tlb_range(vma, old_end - len, old_end); + mmu_notifier_invalidate_range_end(&range); + i_mmap_unlock_write(mapping); + hugetlb_vma_unlock_write(vma); + + return len + old_addr - old_end; +} + +static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct page *ref_page, zap_flags_t zap_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long address; @@ -3410,6 +5065,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mmu_notifier_range range; + unsigned long last_addr_mask; + bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -3429,19 +5086,21 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); mmu_notifier_invalidate_range_start(&range); + last_addr_mask = hugetlb_mask_last_page(h); address = start; for (; address < end; address += sz) { ptep = huge_pte_offset(mm, address, sz); - if (!ptep) + if (!ptep) { + address |= last_addr_mask; continue; + } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, &address, ptep)) { + if (huge_pmd_unshare(mm, vma, address, ptep)) { spin_unlock(ptl); - /* - * We just unmapped a page of PMDs by clearing a PUD. - * The caller's TLB flush range should cover this area. - */ + tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); + force_flush = true; + address |= last_addr_mask; continue; } @@ -3456,7 +5115,20 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { - huge_pte_clear(mm, address, ptep, sz); +#ifdef CONFIG_PTE_MARKER_UFFD_WP + /* + * If the pte was wr-protected by uffd-wp in any of the + * swap forms, meanwhile the caller does not want to + * drop the uffd-wp bit in this zap, then replace the + * pte with a marker. + */ + if (pte_swp_uffd_wp_any(pte) && + !(zap_flags & ZAP_FLAG_DROP_MARKER)) + set_huge_pte_at(mm, address, ptep, + make_pte_marker(PTE_MARKER_UFFD_WP)); + else +#endif + huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; } @@ -3484,9 +5156,15 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page); - +#ifdef CONFIG_PTE_MARKER_UFFD_WP + /* Leave a uffd-wp pte marker if needed */ + if (huge_pte_uffd_wp(pte) && + !(zap_flags & ZAP_FLAG_DROP_MARKER)) + set_huge_pte_at(mm, address, ptep, + make_pte_marker(PTE_MARKER_UFFD_WP)); +#endif hugetlb_count_sub(pages_per_huge_page(h), mm); - page_remove_rmap(page, true); + page_remove_rmap(page, vma, true); spin_unlock(ptl); tlb_remove_page_size(tlb, page, huge_page_size(h)); @@ -3498,54 +5176,61 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } mmu_notifier_invalidate_range_end(&range); tlb_end_vma(tlb, vma); + + /* + * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We + * could defer the flush until now, since by holding i_mmap_rwsem we + * guaranteed that the last refernece would not be dropped. But we must + * do the flushing before we return, as otherwise i_mmap_rwsem will be + * dropped and the last reference to the shared PMDs page might be + * dropped as well. + * + * In theory we could defer the freeing of the PMD pages as well, but + * huge_pmd_unshare() relies on the exact page_count for the PMD page to + * detect sharing, so we cannot defer the release of the page either. + * Instead, do flush now. + */ + if (force_flush) + tlb_flush_mmu_tlbonly(tlb); } void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) + unsigned long end, struct page *ref_page, + zap_flags_t zap_flags) { - __unmap_hugepage_range(tlb, vma, start, end, ref_page); + hugetlb_vma_lock_write(vma); + i_mmap_lock_write(vma->vm_file->f_mapping); + + __unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags); /* - * Clear this flag so that x86's huge_pmd_share page_table_shareable - * test will fail on a vma being torn down, and not grab a page table - * on its way out. We're lucky that the flag has such an appropriate - * name, and can in fact be safely cleared here. We could clear it - * before the __unmap_hugepage_range above, but all that's necessary - * is to clear it before releasing the i_mmap_rwsem. This works - * because in the context this is called, the VMA is about to be - * destroyed and the i_mmap_rwsem is held. + * Unlock and free the vma lock before releasing i_mmap_rwsem. When + * the vma_lock is freed, this makes the vma ineligible for pmd + * sharing. And, i_mmap_rwsem is required to set up pmd sharing. + * This is important as page tables for this unmapped range will + * be asynchrously deleted. If the page tables are shared, there + * will be issues when accessed by someone else. */ - vma->vm_flags &= ~VM_MAYSHARE; + __hugetlb_vma_unlock_write_free(vma); + + i_mmap_unlock_write(vma->vm_file->f_mapping); } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) + unsigned long end, struct page *ref_page, + zap_flags_t zap_flags) { - struct mm_struct *mm; struct mmu_gather tlb; - unsigned long tlb_start = start; - unsigned long tlb_end = end; - /* - * If shared PMDs were possibly used within this vma range, adjust - * start/end for worst case tlb flushing. - * Note that we can not be sure if PMDs are shared until we try to - * unmap pages. However, we want to make sure TLB flushing covers - * the largest possible range. - */ - adjust_range_if_pmd_sharing_possible(vma, &tlb_start, &tlb_end); - - mm = vma->vm_mm; - - tlb_gather_mmu(&tlb, mm, tlb_start, tlb_end); - __unmap_hugepage_range(&tlb, vma, start, end, ref_page); - tlb_finish_mmu(&tlb, tlb_start, tlb_end); + tlb_gather_mmu(&tlb, vma->vm_mm); + __unmap_hugepage_range(&tlb, vma, start, end, ref_page, zap_flags); + tlb_finish_mmu(&tlb); } /* * This is called when the original mapper is failing to COW a MAP_PRIVATE - * mappping it owns the reserve page for. The intention is to unmap the page + * mapping it owns the reserve page for. The intention is to unmap the page * from other VMAs and let the children be SIGKILLed if they are faulting the * same region. */ @@ -3594,21 +5279,22 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) unmap_hugepage_range(iter_vma, address, - address + huge_page_size(h), page); + address + huge_page_size(h), page, 0); } i_mmap_unlock_write(mapping); } /* - * Hugetlb_cow() should be called with page lock of the original hugepage held. - * Called with hugetlb_instantiation_mutex held and pte_page locked so we + * hugetlb_wp() should be called with page lock of the original hugepage held. + * Called with hugetlb_fault_mutex_table held and pte_page locked so we * cannot race with other handlers or page migration. * Keep the pte_same checks anyway to make transition from the mutex easier. */ -static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *ptep, +static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, unsigned int flags, struct page *pagecache_page, spinlock_t *ptl) { + const bool unshare = flags & FAULT_FLAG_UNSHARE; pte_t pte; struct hstate *h = hstate_vma(vma); struct page *old_page, *new_page; @@ -3617,17 +5303,45 @@ static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr = address & huge_page_mask(h); struct mmu_notifier_range range; + VM_BUG_ON(unshare && (flags & FOLL_WRITE)); + VM_BUG_ON(!unshare && !(flags & FOLL_WRITE)); + + /* + * hugetlb does not support FOLL_FORCE-style write faults that keep the + * PTE mapped R/O such as maybe_mkwrite() would do. + */ + if (WARN_ON_ONCE(!unshare && !(vma->vm_flags & VM_WRITE))) + return VM_FAULT_SIGSEGV; + + /* Let's take out MAP_SHARED mappings first. */ + if (vma->vm_flags & VM_MAYSHARE) { + if (unlikely(unshare)) + return 0; + set_huge_ptep_writable(vma, haddr, ptep); + return 0; + } + pte = huge_ptep_get(ptep); old_page = pte_page(pte); + delayacct_wpcopy_start(); + retry_avoidcopy: - /* If no-one else is actually using this page, avoid the copy - * and just make the page writable */ + /* + * If no-one else is actually using this page, we're the exclusive + * owner and can reuse this page. + */ if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { - page_move_anon_rmap(old_page, vma); - set_huge_ptep_writable(vma, haddr, ptep); + if (!PageAnonExclusive(old_page)) + page_move_anon_rmap(old_page, vma); + if (likely(!unshare)) + set_huge_ptep_writable(vma, haddr, ptep); + + delayacct_wpcopy_end(); return 0; } + VM_BUG_ON_PAGE(PageAnon(old_page) && PageAnonExclusive(old_page), + old_page); /* * If the process that created a MAP_PRIVATE mapping is about to @@ -3660,10 +5374,29 @@ retry_avoidcopy: * may get SIGKILLed if it later faults. */ if (outside_reserve) { + struct address_space *mapping = vma->vm_file->f_mapping; + pgoff_t idx; + u32 hash; + put_page(old_page); - BUG_ON(huge_pte_none(pte)); + /* + * Drop hugetlb_fault_mutex and vma_lock before + * unmapping. unmapping needs to hold vma_lock + * in write mode. Dropping vma_lock in read mode + * here is OK as COW mappings do not interact with + * PMD sharing. + * + * Reacquire both after unmap operation. + */ + idx = vma_hugecache_offset(h, vma, haddr); + hash = hugetlb_fault_mutex_hash(mapping, idx); + hugetlb_vma_unlock_read(vma); + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + unmap_ref_private(mm, vma, old_page, haddr); - BUG_ON(huge_pte_none(pte)); + + mutex_lock(&hugetlb_fault_mutex_table[hash]); + hugetlb_vma_lock_read(vma); spin_lock(ptl); ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (likely(ptep && @@ -3673,6 +5406,7 @@ retry_avoidcopy: * race occurs while re-acquiring page table * lock, and our job is done. */ + delayacct_wpcopy_end(); return 0; } @@ -3704,42 +5438,36 @@ retry_avoidcopy: spin_lock(ptl); ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) { - ClearPagePrivate(new_page); + ClearHPageRestoreReserve(new_page); - /* Break COW */ + /* Break COW or unshare */ huge_ptep_clear_flush(vma, haddr, ptep); mmu_notifier_invalidate_range(mm, range.start, range.end); - set_huge_pte_at(mm, haddr, ptep, - make_huge_pte(vma, new_page, 1)); - page_remove_rmap(old_page, true); + page_remove_rmap(old_page, vma, true); hugepage_add_new_anon_rmap(new_page, vma, haddr); - set_page_huge_active(new_page); + set_huge_pte_at(mm, haddr, ptep, + make_huge_pte(vma, new_page, !unshare)); + SetHPageMigratable(new_page); /* Make the old page be freed below */ new_page = old_page; } spin_unlock(ptl); mmu_notifier_invalidate_range_end(&range); out_release_all: - restore_reserve_on_error(h, vma, haddr, new_page); + /* + * No restore in case of successful pagetable update (Break COW or + * unshare) + */ + if (new_page != old_page) + restore_reserve_on_error(h, vma, haddr, new_page); put_page(new_page); out_release_old: put_page(old_page); spin_lock(ptl); /* Caller expects lock to be held */ - return ret; -} -/* Return the pagecache page at a given address within a VMA */ -static struct page *hugetlbfs_pagecache_page(struct hstate *h, - struct vm_area_struct *vma, unsigned long address) -{ - struct address_space *mapping; - pgoff_t idx; - - mapping = vma->vm_file->f_mapping; - idx = vma_hugecache_offset(h, vma, address); - - return find_lock_page(mapping, idx); + delayacct_wpcopy_end(); + return ret; } /* @@ -3762,22 +5490,28 @@ static bool hugetlbfs_pagecache_present(struct hstate *h, return page != NULL; } -int huge_add_to_page_cache(struct page *page, struct address_space *mapping, +int hugetlb_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx) { + struct folio *folio = page_folio(page); struct inode *inode = mapping->host; struct hstate *h = hstate_inode(inode); - int err = add_to_page_cache(page, mapping, idx, GFP_KERNEL); + int err; - if (err) + __folio_set_locked(folio); + err = __filemap_add_folio(mapping, folio, idx, GFP_KERNEL, NULL); + + if (unlikely(err)) { + __folio_clear_locked(folio); return err; - ClearPagePrivate(page); + } + ClearHPageRestoreReserve(page); /* - * set page dirty so that it will not be removed from cache/file + * mark folio dirty so that it will not be removed from cache/file * by non-hugetlbfs specific code paths. */ - set_page_dirty(page); + folio_mark_dirty(folio); spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); @@ -3785,10 +5519,63 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping, return 0; } +static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma, + struct address_space *mapping, + pgoff_t idx, + unsigned int flags, + unsigned long haddr, + unsigned long addr, + unsigned long reason) +{ + u32 hash; + struct vm_fault vmf = { + .vma = vma, + .address = haddr, + .real_address = addr, + .flags = flags, + + /* + * Hard to debug if it ends up being + * used by a callee that assumes + * something about the other + * uninitialized fields... same as in + * memory.c + */ + }; + + /* + * vma_lock and hugetlb_fault_mutex must be dropped before handling + * userfault. Also mmap_lock could be dropped due to handling + * userfault, any vma operation should be careful from here. + */ + hugetlb_vma_unlock_read(vma); + hash = hugetlb_fault_mutex_hash(mapping, idx); + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + return handle_userfault(&vmf, reason); +} + +/* + * Recheck pte with pgtable lock. Returns true if pte didn't change, or + * false if pte changed or is changing. + */ +static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm, + pte_t *ptep, pte_t old_pte) +{ + spinlock_t *ptl; + bool same; + + ptl = huge_pte_lock(h, mm, ptep); + same = pte_same(huge_ptep_get(ptep), old_pte); + spin_unlock(ptl); + + return same; +} + static vm_fault_t hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, struct address_space *mapping, pgoff_t idx, - unsigned long address, pte_t *ptep, unsigned int flags) + unsigned long address, pte_t *ptep, + pte_t old_pte, unsigned int flags) { struct hstate *h = hstate_vma(vma); vm_fault_t ret = VM_FAULT_SIGBUS; @@ -3798,58 +5585,58 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, pte_t new_pte; spinlock_t *ptl; unsigned long haddr = address & huge_page_mask(h); - bool new_page = false; + bool new_page, new_pagecache_page = false; + u32 hash = hugetlb_fault_mutex_hash(mapping, idx); /* * Currently, we are forced to kill the process in the event the * original mapper has unmapped pages from the child due to a failed - * COW. Warn that such a situation has occurred as it may not be obvious + * COW/unsharing. Warn that such a situation has occurred as it may not + * be obvious. */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", current->pid); - return ret; + goto out; } /* * Use page lock to guard against racing truncation * before we get page_table_lock. */ -retry: + new_page = false; page = find_lock_page(mapping, idx); if (!page) { size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) goto out; - - /* - * Check for page in userfault range - */ + /* Check for page in userfault range */ if (userfaultfd_missing(vma)) { - u32 hash; - struct vm_fault vmf = { - .vma = vma, - .address = haddr, - .flags = flags, - /* - * Hard to debug if it ends up being - * used by a callee that assumes - * something about the other - * uninitialized fields... same as in - * memory.c - */ - }; - /* - * hugetlb_fault_mutex must be dropped before - * handling userfault. Reacquire after handling - * fault to make calling code simpler. + * Since hugetlb_no_page() was examining pte + * without pgtable lock, we need to re-test under + * lock because the pte may not be stable and could + * have changed from under us. Try to detect + * either changed or during-changing ptes and retry + * properly when needed. + * + * Note that userfaultfd is actually fine with + * false positives (e.g. caused by pte changed), + * but not wrong logical events (e.g. caused by + * reading a pte during changing). The latter can + * confuse the userspace, so the strictness is very + * much preferred. E.g., MISSING event should + * never happen on the page after UFFDIO_COPY has + * correctly installed the page and returned. */ - hash = hugetlb_fault_mutex_hash(mapping, idx); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); - ret = handle_userfault(&vmf, VM_UFFD_MISSING); - mutex_lock(&hugetlb_fault_mutex_table[hash]); - goto out; + if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) { + ret = 0; + goto out; + } + + return hugetlb_handle_userfault(vma, mapping, idx, flags, + haddr, address, + VM_UFFD_MISSING); } page = alloc_huge_page(vma, haddr, 0); @@ -3866,14 +5653,10 @@ retry: * here. Before returning error, get ptl and make * sure there really is no pte entry. */ - ptl = huge_pte_lock(h, mm, ptep); - if (!huge_pte_none(huge_ptep_get(ptep))) { + if (hugetlb_pte_stable(h, mm, ptep, old_pte)) + ret = vmf_error(PTR_ERR(page)); + else ret = 0; - spin_unlock(ptl); - goto out; - } - spin_unlock(ptl); - ret = vmf_error(PTR_ERR(page)); goto out; } clear_huge_page(page, address, pages_per_huge_page(h)); @@ -3881,13 +5664,20 @@ retry: new_page = true; if (vma->vm_flags & VM_MAYSHARE) { - int err = huge_add_to_page_cache(page, mapping, idx); + int err = hugetlb_add_to_page_cache(page, mapping, idx); if (err) { + /* + * err can't be -EEXIST which implies someone + * else consumed the reservation since hugetlb + * fault mutex is held when add a hugetlb page + * to the page cache. So it's safe to call + * restore_reserve_on_error() here. + */ + restore_reserve_on_error(h, vma, haddr, page); put_page(page); - if (err == -EEXIST) - goto retry; goto out; } + new_pagecache_page = true; } else { lock_page(page); if (unlikely(anon_vma_prepare(vma))) { @@ -3903,10 +5693,24 @@ retry: * So we need to block hugepage fault by PG_hwpoison bit check. */ if (unlikely(PageHWPoison(page))) { - ret = VM_FAULT_HWPOISON | + ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; } + + /* Check for page in userfault range. */ + if (userfaultfd_minor(vma)) { + unlock_page(page); + put_page(page); + /* See comment in userfaultfd_missing() block above */ + if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) { + ret = 0; + goto out; + } + return hugetlb_handle_userfault(vma, mapping, idx, flags, + haddr, address, + VM_UFFD_MINOR); + } } /* @@ -3925,48 +5729,55 @@ retry: } ptl = huge_pte_lock(h, mm, ptep); - size = i_size_read(mapping->host) >> huge_page_shift(h); - if (idx >= size) - goto backout; - ret = 0; - if (!huge_pte_none(huge_ptep_get(ptep))) + /* If pte changed from under us, retry */ + if (!pte_same(huge_ptep_get(ptep), old_pte)) goto backout; if (anon_rmap) { - ClearPagePrivate(page); + ClearHPageRestoreReserve(page); hugepage_add_new_anon_rmap(page, vma, haddr); } else - page_dup_rmap(page, true); + page_dup_file_rmap(page, true); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); + /* + * If this pte was previously wr-protected, keep it wr-protected even + * if populated. + */ + if (unlikely(pte_marker_uffd_wp(old_pte))) + new_pte = huge_pte_wrprotect(huge_pte_mkuffd_wp(new_pte)); set_huge_pte_at(mm, haddr, ptep, new_pte); hugetlb_count_add(pages_per_huge_page(h), mm); if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ - ret = hugetlb_cow(mm, vma, address, ptep, page, ptl); + ret = hugetlb_wp(mm, vma, address, ptep, flags, page, ptl); } spin_unlock(ptl); /* - * Only make newly allocated pages active. Existing pages found - * in the pagecache could be !page_huge_active() if they have been - * isolated for migration. + * Only set HPageMigratable in newly allocated pages. Existing pages + * found in the pagecache may not have HPageMigratableset if they have + * been isolated for migration. */ if (new_page) - set_page_huge_active(page); + SetHPageMigratable(page); unlock_page(page); out: + hugetlb_vma_unlock_read(vma); + mutex_unlock(&hugetlb_fault_mutex_table[hash]); return ret; backout: spin_unlock(ptl); backout_unlocked: + if (new_page && !new_pagecache_page) + restore_reserve_on_error(h, vma, haddr, page); + unlock_page(page); - restore_reserve_on_error(h, vma, haddr, page); put_page(page); goto out; } @@ -3986,7 +5797,7 @@ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) } #else /* - * For uniprocesor systems we always use a single mutex, so just + * For uniprocessor systems we always use a single mutex, so just * return 0 and avoid the hashing overhead. */ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) @@ -4012,57 +5823,78 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (ptep) { + /* + * Since we hold no locks, ptep could be stale. That is + * OK as we are only making decisions based on content and + * not actually modifying content here. + */ entry = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_migration(entry))) { - migration_entry_wait_huge(vma, mm, ptep); + migration_entry_wait_huge(vma, ptep); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); - } else { - ptep = huge_pte_alloc(mm, haddr, huge_page_size(h)); - if (!ptep) - return VM_FAULT_OOM; } - mapping = vma->vm_file->f_mapping; - idx = vma_hugecache_offset(h, vma, haddr); - /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ + mapping = vma->vm_file->f_mapping; + idx = vma_hugecache_offset(h, vma, haddr); hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); - entry = huge_ptep_get(ptep); - if (huge_pte_none(entry)) { - ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags); - goto out_mutex; + /* + * Acquire vma lock before calling huge_pte_alloc and hold + * until finished with ptep. This prevents huge_pmd_unshare from + * being called elsewhere and making the ptep no longer valid. + * + * ptep could have already be assigned via huge_pte_offset. That + * is OK, as huge_pte_alloc will return the same value unless + * something has changed. + */ + hugetlb_vma_lock_read(vma); + ptep = huge_pte_alloc(mm, vma, haddr, huge_page_size(h)); + if (!ptep) { + hugetlb_vma_unlock_read(vma); + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + return VM_FAULT_OOM; } + entry = huge_ptep_get(ptep); + /* PTE markers should be handled the same way as none pte */ + if (huge_pte_none_mostly(entry)) + /* + * hugetlb_no_page will drop vma lock and hugetlb fault + * mutex internally, which make us return immediately. + */ + return hugetlb_no_page(mm, vma, mapping, idx, address, ptep, + entry, flags); + ret = 0; /* * entry could be a migration/hwpoison entry at this point, so this * check prevents the kernel from going below assuming that we have - * a active hugepage in pagecache. This goto expects the 2nd page fault, - * and is_hugetlb_entry_(migration|hwpoisoned) check will properly - * handle it. + * an active hugepage in pagecache. This goto expects the 2nd page + * fault, and is_hugetlb_entry_(migration|hwpoisoned) check will + * properly handle it. */ if (!pte_present(entry)) goto out_mutex; /* - * If we are going to COW the mapping later, we examine the pending - * reservations for this page now. This will ensure that any + * If we are going to COW/unshare the mapping later, we examine the + * pending reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the - * spinlock. For private mappings, we also lookup the pagecache - * page now as it is used to determine if a reservation has been - * consumed. + * spinlock. Also lookup the pagecache page now as it is used to + * determine if a reservation has been consumed. */ - if ((flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { + if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && + !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(entry)) { if (vma_needs_reservation(h, vma, haddr) < 0) { ret = VM_FAULT_OOM; goto out_mutex; @@ -4070,19 +5902,37 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, haddr); - if (!(vma->vm_flags & VM_MAYSHARE)) - pagecache_page = hugetlbfs_pagecache_page(h, - vma, haddr); + pagecache_page = find_lock_page(mapping, idx); } ptl = huge_pte_lock(h, mm, ptep); - /* Check for a racing update before calling hugetlb_cow */ + /* Check for a racing update before calling hugetlb_wp() */ if (unlikely(!pte_same(entry, huge_ptep_get(ptep)))) goto out_ptl; + /* Handle userfault-wp first, before trying to lock more pages */ + if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(ptep)) && + (flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { + struct vm_fault vmf = { + .vma = vma, + .address = haddr, + .real_address = address, + .flags = flags, + }; + + spin_unlock(ptl); + if (pagecache_page) { + unlock_page(pagecache_page); + put_page(pagecache_page); + } + hugetlb_vma_unlock_read(vma); + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + return handle_userfault(&vmf, VM_UFFD_WP); + } + /* - * hugetlb_cow() requires page locks of pte_page(entry) and + * hugetlb_wp() requires page locks of pte_page(entry) and * pagecache_page, so here we need take the former one * when page != pagecache_page or !pagecache_page. */ @@ -4095,13 +5945,14 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, get_page(page); - if (flags & FAULT_FLAG_WRITE) { + if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!huge_pte_write(entry)) { - ret = hugetlb_cow(mm, vma, address, ptep, - pagecache_page, ptl); + ret = hugetlb_wp(mm, vma, address, ptep, flags, + pagecache_page, ptl); goto out_put_page; + } else if (likely(flags & FAULT_FLAG_WRITE)) { + entry = huge_pte_mkdirty(entry); } - entry = huge_pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (huge_ptep_set_access_flags(vma, haddr, ptep, entry, @@ -4119,6 +5970,7 @@ out_ptl: put_page(pagecache_page); } out_mutex: + hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); /* * Generally it's safe to hold refcount during waiting page lock. But @@ -4132,6 +5984,7 @@ out_mutex: return ret; } +#ifdef CONFIG_USERFAULTFD /* * Used by userfaultfd UFFDIO_COPY. Based on mcopy_atomic_pte with * modifications for huge pages. @@ -4141,37 +5994,92 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - struct page **pagep) + enum mcopy_atomic_mode mode, + struct page **pagep, + bool wp_copy) { - struct address_space *mapping; - pgoff_t idx; + bool is_continue = (mode == MCOPY_ATOMIC_CONTINUE); + struct hstate *h = hstate_vma(dst_vma); + struct address_space *mapping = dst_vma->vm_file->f_mapping; + pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr); unsigned long size; int vm_shared = dst_vma->vm_flags & VM_SHARED; - struct hstate *h = hstate_vma(dst_vma); pte_t _dst_pte; spinlock_t *ptl; - int ret; + int ret = -ENOMEM; struct page *page; + int writable; + bool page_in_pagecache = false; + + if (is_continue) { + ret = -EFAULT; + page = find_lock_page(mapping, idx); + if (!page) + goto out; + page_in_pagecache = true; + } else if (!*pagep) { + /* If a page already exists, then it's UFFDIO_COPY for + * a non-missing case. Return -EEXIST. + */ + if (vm_shared && + hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { + ret = -EEXIST; + goto out; + } - if (!*pagep) { - ret = -ENOMEM; page = alloc_huge_page(dst_vma, dst_addr, 0); - if (IS_ERR(page)) + if (IS_ERR(page)) { + ret = -ENOMEM; goto out; + } ret = copy_huge_page_from_user(page, (const void __user *) src_addr, pages_per_huge_page(h), false); - /* fallback to copy_from_user outside mmap_sem */ + /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; + /* Free the allocated page which may have + * consumed a reservation. + */ + restore_reserve_on_error(h, dst_vma, dst_addr, page); + put_page(page); + + /* Allocate a temporary page to hold the copied + * contents. + */ + page = alloc_huge_page_vma(h, dst_vma, dst_addr); + if (!page) { + ret = -ENOMEM; + goto out; + } *pagep = page; - /* don't free the page */ + /* Set the outparam pagep and return to the caller to + * copy the contents outside the lock. Don't free the + * page. + */ goto out; } } else { - page = *pagep; + if (vm_shared && + hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { + put_page(*pagep); + ret = -EEXIST; + *pagep = NULL; + goto out; + } + + page = alloc_huge_page(dst_vma, dst_addr, 0); + if (IS_ERR(page)) { + put_page(*pagep); + ret = -ENOMEM; + *pagep = NULL; + goto out; + } + copy_user_huge_page(page, *pagep, dst_addr, dst_vma, + pages_per_huge_page(h)); + put_page(*pagep); *pagep = NULL; } @@ -4182,13 +6090,8 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, */ __SetPageUptodate(page); - mapping = dst_vma->vm_file->f_mapping; - idx = vma_hugecache_offset(h, dst_vma, dst_addr); - - /* - * If shared, add to page cache - */ - if (vm_shared) { + /* Add shared, newly allocated pages to the page cache. */ + if (vm_shared && !is_continue) { size = i_size_read(mapping->host) >> huge_page_shift(h); ret = -EFAULT; if (idx >= size) @@ -4196,87 +6099,135 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, /* * Serialization between remove_inode_hugepages() and - * huge_add_to_page_cache() below happens through the + * hugetlb_add_to_page_cache() below happens through the * hugetlb_fault_mutex_table that here must be hold by * the caller. */ - ret = huge_add_to_page_cache(page, mapping, idx); + ret = hugetlb_add_to_page_cache(page, mapping, idx); if (ret) goto out_release_nounlock; + page_in_pagecache = true; } - ptl = huge_pte_lockptr(h, dst_mm, dst_pte); - spin_lock(ptl); + ptl = huge_pte_lock(h, dst_mm, dst_pte); - /* - * Recheck the i_size after holding PT lock to make sure not - * to leave any page mapped (as page_mapped()) beyond the end - * of the i_size (remove_inode_hugepages() is strict about - * enforcing that). If we bail out here, we'll also leave a - * page in the radix tree in the vm_shared case beyond the end - * of the i_size, but remove_inode_hugepages() will take care - * of it as soon as we drop the hugetlb_fault_mutex_table. - */ - size = i_size_read(mapping->host) >> huge_page_shift(h); - ret = -EFAULT; - if (idx >= size) + ret = -EIO; + if (PageHWPoison(page)) goto out_release_unlock; + /* + * We allow to overwrite a pte marker: consider when both MISSING|WP + * registered, we firstly wr-protect a none pte which has no page cache + * page backing it, then access the page. + */ ret = -EEXIST; - if (!huge_pte_none(huge_ptep_get(dst_pte))) + if (!huge_pte_none_mostly(huge_ptep_get(dst_pte))) goto out_release_unlock; - if (vm_shared) { - page_dup_rmap(page, true); + if (page_in_pagecache) { + page_dup_file_rmap(page, true); } else { - ClearPagePrivate(page); + ClearHPageRestoreReserve(page); hugepage_add_new_anon_rmap(page, dst_vma, dst_addr); } - _dst_pte = make_huge_pte(dst_vma, page, dst_vma->vm_flags & VM_WRITE); - if (dst_vma->vm_flags & VM_WRITE) - _dst_pte = huge_pte_mkdirty(_dst_pte); + /* + * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY + * with wp flag set, don't set pte write bit. + */ + if (wp_copy || (is_continue && !vm_shared)) + writable = 0; + else + writable = dst_vma->vm_flags & VM_WRITE; + + _dst_pte = make_huge_pte(dst_vma, page, writable); + /* + * Always mark UFFDIO_COPY page dirty; note that this may not be + * extremely important for hugetlbfs for now since swapping is not + * supported, but we should still be clear in that this page cannot be + * thrown away at will, even if write bit not set. + */ + _dst_pte = huge_pte_mkdirty(_dst_pte); _dst_pte = pte_mkyoung(_dst_pte); + if (wp_copy) + _dst_pte = huge_pte_mkuffd_wp(_dst_pte); + set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); - (void)huge_ptep_set_access_flags(dst_vma, dst_addr, dst_pte, _dst_pte, - dst_vma->vm_flags & VM_WRITE); hugetlb_count_add(pages_per_huge_page(h), dst_mm); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); - set_page_huge_active(page); - if (vm_shared) + if (!is_continue) + SetHPageMigratable(page); + if (vm_shared || is_continue) unlock_page(page); ret = 0; out: return ret; out_release_unlock: spin_unlock(ptl); - if (vm_shared) + if (vm_shared || is_continue) unlock_page(page); out_release_nounlock: + if (!page_in_pagecache) + restore_reserve_on_error(h, dst_vma, dst_addr, page); put_page(page); goto out; } +#endif /* CONFIG_USERFAULTFD */ + +static void record_subpages_vmas(struct page *page, struct vm_area_struct *vma, + int refs, struct page **pages, + struct vm_area_struct **vmas) +{ + int nr; + + for (nr = 0; nr < refs; nr++) { + if (likely(pages)) + pages[nr] = nth_page(page, nr); + if (vmas) + vmas[nr] = vma; + } +} + +static inline bool __follow_hugetlb_must_fault(unsigned int flags, pte_t *pte, + bool *unshare) +{ + pte_t pteval = huge_ptep_get(pte); + + *unshare = false; + if (is_swap_pte(pteval)) + return true; + if (huge_pte_write(pteval)) + return false; + if (flags & FOLL_WRITE) + return true; + if (gup_must_unshare(flags, pte_page(pteval))) { + *unshare = true; + return true; + } + return false; +} long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page **pages, struct vm_area_struct **vmas, unsigned long *position, unsigned long *nr_pages, - long i, unsigned int flags, int *nonblocking) + long i, unsigned int flags, int *locked) { unsigned long pfn_offset; unsigned long vaddr = *position; unsigned long remainder = *nr_pages; struct hstate *h = hstate_vma(vma); - int err = -EFAULT; + int err = -EFAULT, refs; while (vaddr < vma->vm_end && remainder) { pte_t *pte; spinlock_t *ptl = NULL; + bool unshare = false; int absent; struct page *page; @@ -4327,9 +6278,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, * both cases, and because we can't follow correct pages * directly from any kind of swap entries. */ - if (absent || is_swap_pte(huge_ptep_get(pte)) || - ((flags & FOLL_WRITE) && - !huge_pte_write(huge_ptep_get(pte)))) { + if (absent || + __follow_hugetlb_must_fault(flags, pte, &unshare)) { vm_fault_t ret; unsigned int fault_flags = 0; @@ -4337,14 +6287,19 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, spin_unlock(ptl); if (flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; - if (nonblocking) - fault_flags |= FAULT_FLAG_ALLOW_RETRY; + else if (unshare) + fault_flags |= FAULT_FLAG_UNSHARE; + if (locked) + fault_flags |= FAULT_FLAG_ALLOW_RETRY | + FAULT_FLAG_KILLABLE; if (flags & FOLL_NOWAIT) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; if (flags & FOLL_TRIED) { - VM_WARN_ON_ONCE(fault_flags & - FAULT_FLAG_ALLOW_RETRY); + /* + * Note: FAULT_FLAG_ALLOW_RETRY and + * FAULT_FLAG_TRIED can co-exist + */ fault_flags |= FAULT_FLAG_TRIED; } ret = hugetlb_fault(mm, vma, vaddr, fault_flags); @@ -4354,9 +6309,9 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, break; } if (ret & VM_FAULT_RETRY) { - if (nonblocking && + if (locked && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) - *nonblocking = 0; + *locked = 0; *nr_pages = 0; /* * VM_FAULT_RETRY must not return an @@ -4375,18 +6330,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; page = pte_page(huge_ptep_get(pte)); - /* - * Instead of doing 'try_get_page()' below in the same_page - * loop, just check the count once here. - */ - if (unlikely(page_count(page) <= 0)) { - if (pages) { - spin_unlock(ptl); - remainder = 0; - err = -ENOMEM; - break; - } - } + VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && + !PageAnonExclusive(page), page); /* * If subpage information not requested, update counters @@ -4402,27 +6347,40 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, continue; } -same_page: - if (pages) { - pages[i] = mem_map_offset(page, pfn_offset); - get_page(pages[i]); - } + /* vaddr may not be aligned to PAGE_SIZE */ + refs = min3(pages_per_huge_page(h) - pfn_offset, remainder, + (vma->vm_end - ALIGN_DOWN(vaddr, PAGE_SIZE)) >> PAGE_SHIFT); - if (vmas) - vmas[i] = vma; - - vaddr += PAGE_SIZE; - ++pfn_offset; - --remainder; - ++i; - if (vaddr < vma->vm_end && remainder && - pfn_offset < pages_per_huge_page(h)) { + if (pages || vmas) + record_subpages_vmas(nth_page(page, pfn_offset), + vma, refs, + likely(pages) ? pages + i : NULL, + vmas ? vmas + i : NULL); + + if (pages) { /* - * We use pfn_offset to avoid touching the pageframes - * of this compound page. + * try_grab_folio() should always succeed here, + * because: a) we hold the ptl lock, and b) we've just + * checked that the huge page is present in the page + * tables. If the huge page is present, then the tail + * pages must also be present. The ptl prevents the + * head page and tail pages from being rearranged in + * any way. So this page must be available at this + * point, unless the page refcount overflowed: */ - goto same_page; + if (WARN_ON_ONCE(!try_grab_folio(pages[i], refs, + flags))) { + spin_unlock(ptl); + remainder = 0; + err = -ENOMEM; + break; + } } + + vaddr += (refs << PAGE_SHIFT); + remainder -= refs; + i += refs; + spin_unlock(ptl); } *nr_pages = remainder; @@ -4436,25 +6394,21 @@ same_page: return i ? i : err; } -#ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE -/* - * ARCHes with special requirements for evicting HUGETLB backing TLB entries can - * implement this. - */ -#define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) -#endif - unsigned long hugetlb_change_protection(struct vm_area_struct *vma, - unsigned long address, unsigned long end, pgprot_t newprot) + unsigned long address, unsigned long end, + pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long start = address; pte_t *ptep; pte_t pte; struct hstate *h = hstate_vma(vma); - unsigned long pages = 0; + unsigned long pages = 0, psize = huge_page_size(h); bool shared_pmd = false; struct mmu_notifier_range range; + unsigned long last_addr_mask; + bool uffd_wp = cp_flags & MM_CP_UFFD_WP; + bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; /* * In the case of shared PMDs, the area to flush could be beyond @@ -4469,17 +6423,28 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, flush_cache_range(vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); + hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); - for (; address < end; address += huge_page_size(h)) { + last_addr_mask = hugetlb_mask_last_page(h); + for (; address < end; address += psize) { spinlock_t *ptl; - ptep = huge_pte_offset(mm, address, huge_page_size(h)); - if (!ptep) + ptep = huge_pte_offset(mm, address, psize); + if (!ptep) { + address |= last_addr_mask; continue; + } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, &address, ptep)) { + if (huge_pmd_unshare(mm, vma, address, ptep)) { + /* + * When uffd-wp is enabled on the vma, unshare + * shouldn't happen at all. Warn about it if it + * happened due to some reason. + */ + WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); shared_pmd = true; + address |= last_addr_mask; continue; } pte = huge_ptep_get(ptep); @@ -4489,27 +6454,55 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, } if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); + struct page *page = pfn_swap_entry_to_page(entry); - if (is_write_migration_entry(entry)) { + if (!is_readable_migration_entry(entry)) { pte_t newpte; - make_migration_entry_read(&entry); + if (PageAnon(page)) + entry = make_readable_exclusive_migration_entry( + swp_offset(entry)); + else + entry = make_readable_migration_entry( + swp_offset(entry)); newpte = swp_entry_to_pte(entry); - set_huge_swap_pte_at(mm, address, ptep, - newpte, huge_page_size(h)); + if (uffd_wp) + newpte = pte_swp_mkuffd_wp(newpte); + else if (uffd_wp_resolve) + newpte = pte_swp_clear_uffd_wp(newpte); + set_huge_pte_at(mm, address, ptep, newpte); pages++; } spin_unlock(ptl); continue; } + if (unlikely(pte_marker_uffd_wp(pte))) { + /* + * This is changing a non-present pte into a none pte, + * no need for huge_ptep_modify_prot_start/commit(). + */ + if (uffd_wp_resolve) + huge_pte_clear(mm, address, ptep, psize); + } if (!huge_pte_none(pte)) { pte_t old_pte; + unsigned int shift = huge_page_shift(hstate_vma(vma)); old_pte = huge_ptep_modify_prot_start(vma, address, ptep); - pte = pte_mkhuge(huge_pte_modify(old_pte, newprot)); - pte = arch_make_huge_pte(pte, vma, NULL, 0); + pte = huge_pte_modify(old_pte, newprot); + pte = arch_make_huge_pte(pte, shift, vma->vm_flags); + if (uffd_wp) + pte = huge_pte_mkuffd_wp(huge_pte_wrprotect(pte)); + else if (uffd_wp_resolve) + pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; + } else { + /* None pte */ + if (unlikely(uffd_wp)) + /* Safe to modify directly (none->non-present). */ + set_huge_pte_at(mm, address, ptep, + make_pte_marker(PTE_MARKER_UFFD_WP)); } spin_unlock(ptl); } @@ -4528,38 +6521,46 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * No need to call mmu_notifier_invalidate_range() we are downgrading * page table protection not changing it to point to a new page. * - * See Documentation/vm/mmu_notifier.rst + * See Documentation/mm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); + hugetlb_vma_unlock_write(vma); mmu_notifier_invalidate_range_end(&range); return pages << h->order; } -int hugetlb_reserve_pages(struct inode *inode, +/* Return true if reservation was successful, false otherwise. */ +bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags) { - long ret, chg; + long chg, add = -1; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; - long gbl_reserve; + struct hugetlb_cgroup *h_cg = NULL; + long gbl_reserve, regions_needed = 0; /* This should never happen */ if (from > to) { VM_WARN(1, "%s called with a negative range\n", __func__); - return -EINVAL; + return false; } /* + * vma specific semaphore used for pmd sharing synchronization + */ + hugetlb_vma_lock_alloc(vma); + + /* * Only apply hugepage reservation if asked. At fault time, an * attempt will be made for VM_NORESERVE to allocate a page * without using reserves */ if (vm_flags & VM_NORESERVE) - return 0; + return true; /* * Shared mappings base their reservation on the number of pages that @@ -4575,12 +6576,12 @@ int hugetlb_reserve_pages(struct inode *inode, */ resv_map = inode_resv_map(inode); - chg = region_chg(resv_map, from, to); - + chg = region_chg(resv_map, from, to, ®ions_needed); } else { + /* Private mapping. */ resv_map = resv_map_alloc(); if (!resv_map) - return -ENOMEM; + goto out_err; chg = to - from; @@ -4588,9 +6589,18 @@ int hugetlb_reserve_pages(struct inode *inode, set_vma_resv_flags(vma, HPAGE_RESV_OWNER); } - if (chg < 0) { - ret = chg; + if (chg < 0) + goto out_err; + + if (hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h), + chg * pages_per_huge_page(h), &h_cg) < 0) goto out_err; + + if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) { + /* For private mappings, the hugetlb_cgroup uncharge info hangs + * of the resv_map. + */ + resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h); } /* @@ -4599,21 +6609,15 @@ int hugetlb_reserve_pages(struct inode *inode, * reservations already in place (gbl_reserve). */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); - if (gbl_reserve < 0) { - ret = -ENOSPC; - goto out_err; - } + if (gbl_reserve < 0) + goto out_uncharge_cgroup; /* * Check enough hugepages are available for the reservation. * Hand the pages back to the subpool if there are not */ - ret = hugetlb_acct_memory(h, gbl_reserve); - if (ret < 0) { - /* put back original number of pages, chg */ - (void)hugepage_subpool_put_pages(spool, chg); - goto out_err; - } + if (hugetlb_acct_memory(h, gbl_reserve) < 0) + goto out_put_pages; /* * Account for the reservations made. Shared mappings record regions @@ -4627,9 +6631,12 @@ int hugetlb_reserve_pages(struct inode *inode, * else has to be done for private mappings here */ if (!vma || vma->vm_flags & VM_MAYSHARE) { - long add = region_add(resv_map, from, to); + add = region_add(resv_map, from, to, regions_needed, h, h_cg); - if (unlikely(chg > add)) { + if (unlikely(add < 0)) { + hugetlb_acct_memory(h, -gbl_reserve); + goto out_put_pages; + } else if (unlikely(chg > add)) { /* * pages in this range were added to the reserve * map between region_chg and region_add. This @@ -4639,20 +6646,46 @@ int hugetlb_reserve_pages(struct inode *inode, */ long rsv_adjust; + /* + * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the + * reference to h_cg->css. See comment below for detail. + */ + hugetlb_cgroup_uncharge_cgroup_rsvd( + hstate_index(h), + (chg - add) * pages_per_huge_page(h), h_cg); + rsv_adjust = hugepage_subpool_put_pages(spool, chg - add); hugetlb_acct_memory(h, -rsv_adjust); + } else if (h_cg) { + /* + * The file_regions will hold their own reference to + * h_cg->css. So we should release the reference held + * via hugetlb_cgroup_charge_cgroup_rsvd() when we are + * done. + */ + hugetlb_cgroup_put_rsvd_cgroup(h_cg); } } - return 0; + return true; + +out_put_pages: + /* put back original number of pages, chg */ + (void)hugepage_subpool_put_pages(spool, chg); +out_uncharge_cgroup: + hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), + chg * pages_per_huge_page(h), h_cg); out_err: + hugetlb_vma_lock_free(vma); if (!vma || vma->vm_flags & VM_MAYSHARE) - /* Don't call region_abort if region_chg failed */ - if (chg >= 0) - region_abort(resv_map, from, to); + /* Only call region_abort if the region_chg succeeded but the + * region_add failed or didn't run. + */ + if (chg >= 0 && add < 0) + region_abort(resv_map, from, to, regions_needed); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) kref_put(&resv_map->refs, resv_map_release); - return ret; + return false; } long hugetlb_unreserve_pages(struct inode *inode, long start, long end, @@ -4686,6 +6719,9 @@ long hugetlb_unreserve_pages(struct inode *inode, long start, long end, /* * If the subpool has a minimum size, the number of global * reservations to be released may be adjusted. + * + * Note that !resv_map implies freed == 0. So (chg - freed) + * won't go negative. */ gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed)); hugetlb_acct_memory(h, -gbl_reserve); @@ -4710,26 +6746,37 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma, /* * match the virtual addresses, permission and the alignment of the * page table page. + * + * Also, vma_lock (vm_private_data) is required for sharing. */ if (pmd_index(addr) != pmd_index(saddr) || vm_flags != svm_flags || - sbase < svma->vm_start || svma->vm_end < s_end) + !range_in_vma(svma, sbase, s_end) || + !svma->vm_private_data) return 0; return saddr; } -static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr) +bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) { - unsigned long base = addr & PUD_MASK; - unsigned long end = base + PUD_SIZE; + unsigned long start = addr & PUD_MASK; + unsigned long end = start + PUD_SIZE; +#ifdef CONFIG_USERFAULTFD + if (uffd_disable_huge_pmd_share(vma)) + return false; +#endif /* * check on proper vm_flags and page table alignment */ - if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end)) - return true; - return false; + if (!(vma->vm_flags & VM_MAYSHARE)) + return false; + if (!vma->vm_private_data) /* vma lock required for sharing */ + return false; + if (!range_in_vma(vma, start, end)) + return false; + return true; } /* @@ -4740,25 +6787,166 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr) void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { - unsigned long check_addr = *start; + unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE), + v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); - if (!(vma->vm_flags & VM_MAYSHARE)) + /* + * vma needs to span at least one aligned PUD size, and the range + * must be at least partially within in. + */ + if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) || + (*end <= v_start) || (*start >= v_end)) return; - for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) { - unsigned long a_start = check_addr & PUD_MASK; - unsigned long a_end = a_start + PUD_SIZE; + /* Extend the range to be PUD aligned for a worst case scenario */ + if (*start > v_start) + *start = ALIGN_DOWN(*start, PUD_SIZE); + + if (*end < v_end) + *end = ALIGN(*end, PUD_SIZE); +} + +static bool __vma_shareable_flags_pmd(struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_MAYSHARE | VM_SHARED) && + vma->vm_private_data; +} + +void hugetlb_vma_lock_read(struct vm_area_struct *vma) +{ + if (__vma_shareable_flags_pmd(vma)) { + struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; + + down_read(&vma_lock->rw_sema); + } +} +void hugetlb_vma_unlock_read(struct vm_area_struct *vma) +{ + if (__vma_shareable_flags_pmd(vma)) { + struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; + + up_read(&vma_lock->rw_sema); + } +} + +void hugetlb_vma_lock_write(struct vm_area_struct *vma) +{ + if (__vma_shareable_flags_pmd(vma)) { + struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; + + down_write(&vma_lock->rw_sema); + } +} + +void hugetlb_vma_unlock_write(struct vm_area_struct *vma) +{ + if (__vma_shareable_flags_pmd(vma)) { + struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; + + up_write(&vma_lock->rw_sema); + } +} + +int hugetlb_vma_trylock_write(struct vm_area_struct *vma) +{ + struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; + + if (!__vma_shareable_flags_pmd(vma)) + return 1; + + return down_write_trylock(&vma_lock->rw_sema); +} + +void hugetlb_vma_assert_locked(struct vm_area_struct *vma) +{ + if (__vma_shareable_flags_pmd(vma)) { + struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; + + lockdep_assert_held(&vma_lock->rw_sema); + } +} + +void hugetlb_vma_lock_release(struct kref *kref) +{ + struct hugetlb_vma_lock *vma_lock = container_of(kref, + struct hugetlb_vma_lock, refs); + + kfree(vma_lock); +} + +static void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock) +{ + struct vm_area_struct *vma = vma_lock->vma; + + /* + * vma_lock structure may or not be released as a result of put, + * it certainly will no longer be attached to vma so clear pointer. + * Semaphore synchronizes access to vma_lock->vma field. + */ + vma_lock->vma = NULL; + vma->vm_private_data = NULL; + up_write(&vma_lock->rw_sema); + kref_put(&vma_lock->refs, hugetlb_vma_lock_release); +} + +static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma) +{ + if (__vma_shareable_flags_pmd(vma)) { + struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; + + __hugetlb_vma_unlock_write_put(vma_lock); + } +} + +static void hugetlb_vma_lock_free(struct vm_area_struct *vma) +{ + /* + * Only present in sharable vmas. + */ + if (!vma || !__vma_shareable_flags_pmd(vma)) + return; + + if (vma->vm_private_data) { + struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; + + down_write(&vma_lock->rw_sema); + __hugetlb_vma_unlock_write_put(vma_lock); + } +} + +static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma) +{ + struct hugetlb_vma_lock *vma_lock; + + /* Only establish in (flags) sharable vmas */ + if (!vma || !(vma->vm_flags & VM_MAYSHARE)) + return; + + /* Should never get here with non-NULL vm_private_data */ + if (vma->vm_private_data) + return; + + vma_lock = kmalloc(sizeof(*vma_lock), GFP_KERNEL); + if (!vma_lock) { /* - * If sharing is possible, adjust start/end if necessary. + * If we can not allocate structure, then vma can not + * participate in pmd sharing. This is only a possible + * performance enhancement and memory saving issue. + * However, the lock is also used to synchronize page + * faults with truncation. If the lock is not present, + * unlikely races could leave pages in a file past i_size + * until the file is removed. Warn in the unlikely case of + * allocation failure. */ - if (range_in_vma(vma, a_start, a_end)) { - if (a_start < *start) - *start = a_start; - if (a_end > *end) - *end = a_end; - } + pr_warn_once("HugeTLB: unable to allocate vma specific lock\n"); + return; } + + kref_init(&vma_lock->refs); + init_rwsem(&vma_lock->rw_sema); + vma_lock->vma = vma; + vma->vm_private_data = vma_lock; } /* @@ -4770,9 +6958,9 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, * racing tasks could either miss the sharing (see huge_pte_offset) or select a * bad pmd for sharing. */ -pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pud_t *pud) { - struct vm_area_struct *vma = find_vma(mm, addr); struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; @@ -4782,9 +6970,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) pte_t *pte; spinlock_t *ptl; - if (!vma_shareable(vma, addr)) - return (pte_t *)pmd_alloc(mm, pud, addr); - i_mmap_lock_read(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) @@ -4826,17 +7011,20 @@ out: * indicated by page_count > 1, unmap is achieved by clearing pud and * decrementing the ref count. If count == 1, the pte page is not shared. * - * called with page table lock held. + * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page * 0 the underlying pte page is not shared, or it is the last user */ -int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { - pgd_t *pgd = pgd_offset(mm, *addr); - p4d_t *p4d = p4d_offset(pgd, *addr); - pud_t *pud = pud_offset(p4d, *addr); + pgd_t *pgd = pgd_offset(mm, addr); + p4d_t *p4d = p4d_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + hugetlb_vma_assert_locked(vma); BUG_ON(page_count(virt_to_page(ptep)) == 0); if (page_count(virt_to_page(ptep)) == 1) return 0; @@ -4844,17 +7032,60 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) pud_clear(pud); put_page(virt_to_page(ptep)); mm_dec_nr_pmds(mm); - *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; return 1; } -#define want_pmd_share() (1) + #else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ -pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) + +void hugetlb_vma_lock_read(struct vm_area_struct *vma) +{ +} + +void hugetlb_vma_unlock_read(struct vm_area_struct *vma) +{ +} + +void hugetlb_vma_lock_write(struct vm_area_struct *vma) +{ +} + +void hugetlb_vma_unlock_write(struct vm_area_struct *vma) +{ +} + +int hugetlb_vma_trylock_write(struct vm_area_struct *vma) +{ + return 1; +} + +void hugetlb_vma_assert_locked(struct vm_area_struct *vma) +{ +} + +void hugetlb_vma_lock_release(struct kref *kref) +{ +} + +static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma) +{ +} + +static void hugetlb_vma_lock_free(struct vm_area_struct *vma) +{ +} + +static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma) +{ +} + +pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pud_t *pud) { return NULL; } -int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { return 0; } @@ -4863,11 +7094,15 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } -#define want_pmd_share() (0) + +bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) +{ + return false; +} #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB -pte_t *huge_pte_alloc(struct mm_struct *mm, +pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { pgd_t *pgd; @@ -4885,8 +7120,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte = (pte_t *)pud; } else { BUG_ON(sz != PMD_SIZE); - if (want_pmd_share() && pud_none(*pud)) - pte = huge_pmd_share(mm, addr, pud); + if (want_pmd_share(vma, addr) && pud_none(*pud)) + pte = huge_pmd_share(mm, vma, addr, pud); else pte = (pte_t *)pmd_alloc(mm, pud, addr); } @@ -4900,8 +7135,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, * huge_pte_offset() - Walk the page table to resolve the hugepage * entry at address @addr * - * Return: Pointer to page table or swap entry (PUD or PMD) for - * address @addr, or NULL if a p*d_none() entry is encountered and the + * Return: Pointer to page table entry (PUD or PMD) for + * address @addr, or NULL if a !p*d_present() entry is encountered and the * size @sz doesn't match the hugepage size at this level of the page * table. */ @@ -4921,20 +7156,47 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return NULL; pud = pud_offset(p4d, addr); - if (sz != PUD_SIZE && pud_none(*pud)) - return NULL; - /* hugepage or swap? */ - if (pud_huge(*pud) || !pud_present(*pud)) + if (sz == PUD_SIZE) + /* must be pud huge, non-present or none */ return (pte_t *)pud; + if (!pud_present(*pud)) + return NULL; + /* must have a valid entry and size to go further */ pmd = pmd_offset(pud, addr); - if (sz != PMD_SIZE && pmd_none(*pmd)) - return NULL; - /* hugepage or swap? */ - if (pmd_huge(*pmd) || !pmd_present(*pmd)) - return (pte_t *)pmd; + /* must be pmd huge, non-present or none */ + return (pte_t *)pmd; +} - return NULL; +/* + * Return a mask that can be used to update an address to the last huge + * page in a page table page mapping size. Used to skip non-present + * page table entries when linearly scanning address ranges. Architectures + * with unique huge page to page table relationships can define their own + * version of this routine. + */ +unsigned long hugetlb_mask_last_page(struct hstate *h) +{ + unsigned long hp_size = huge_page_size(h); + + if (hp_size == PUD_SIZE) + return P4D_SIZE - PUD_SIZE; + else if (hp_size == PMD_SIZE) + return PUD_SIZE - PMD_SIZE; + else + return 0UL; +} + +#else + +/* See description above. Architectures can provide their own version. */ +__weak unsigned long hugetlb_mask_last_page(struct hstate *h) +{ +#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE + if (huge_page_size(h) == PMD_SIZE) + return PUD_SIZE - PMD_SIZE; +#endif + return 0UL; } #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ @@ -4959,30 +7221,47 @@ follow_huge_pd(struct vm_area_struct *vma, } struct page * __weak -follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int flags) +follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, int flags) { + struct hstate *h = hstate_vma(vma); + struct mm_struct *mm = vma->vm_mm; struct page *page = NULL; spinlock_t *ptl; - pte_t pte; -retry: - ptl = pmd_lockptr(mm, pmd); - spin_lock(ptl); + pte_t *ptep, pte; + /* - * make sure that the address range covered by this pmd is not - * unmapped from other threads. + * FOLL_PIN is not supported for follow_page(). Ordinary GUP goes via + * follow_hugetlb_page(). */ - if (!pmd_huge(*pmd)) - goto out; - pte = huge_ptep_get((pte_t *)pmd); + if (WARN_ON_ONCE(flags & FOLL_PIN)) + return NULL; + +retry: + ptep = huge_pte_offset(mm, address, huge_page_size(h)); + if (!ptep) + return NULL; + + ptl = huge_pte_lock(h, mm, ptep); + pte = huge_ptep_get(ptep); if (pte_present(pte)) { - page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT); - if (flags & FOLL_GET) - get_page(page); + page = pte_page(pte) + + ((address & ~huge_page_mask(h)) >> PAGE_SHIFT); + /* + * try_grab_page() should always succeed here, because: a) we + * hold the pmd (ptl) lock, and b) we've just checked that the + * huge pmd (head) page is present in the page tables. The ptl + * prevents the head page and tail pages from being rearranged + * in any way. So this page must be available at this point, + * unless the page refcount overflowed: + */ + if (WARN_ON_ONCE(!try_grab_page(page, flags))) { + page = NULL; + goto out; + } } else { if (is_hugetlb_entry_migration(pte)) { spin_unlock(ptl); - __migration_entry_wait(mm, (pte_t *)pmd, ptl); + __migration_entry_wait_huge(ptep, ptl); goto retry; } /* @@ -4999,45 +7278,102 @@ struct page * __weak follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags) { - if (flags & FOLL_GET) + struct page *page = NULL; + spinlock_t *ptl; + pte_t pte; + + if (WARN_ON_ONCE(flags & FOLL_PIN)) return NULL; - return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); +retry: + ptl = huge_pte_lock(hstate_sizelog(PUD_SHIFT), mm, (pte_t *)pud); + if (!pud_huge(*pud)) + goto out; + pte = huge_ptep_get((pte_t *)pud); + if (pte_present(pte)) { + page = pud_page(*pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); + if (WARN_ON_ONCE(!try_grab_page(page, flags))) { + page = NULL; + goto out; + } + } else { + if (is_hugetlb_entry_migration(pte)) { + spin_unlock(ptl); + __migration_entry_wait(mm, (pte_t *)pud, ptl); + goto retry; + } + /* + * hwpoisoned entry is treated as no_page_table in + * follow_page_mask(). + */ + } +out: + spin_unlock(ptl); + return page; } struct page * __weak follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int flags) { - if (flags & FOLL_GET) + if (flags & (FOLL_GET | FOLL_PIN)) return NULL; return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT); } -bool isolate_huge_page(struct page *page, struct list_head *list) +int isolate_hugetlb(struct page *page, struct list_head *list) { - bool ret = true; + int ret = 0; - VM_BUG_ON_PAGE(!PageHead(page), page); - spin_lock(&hugetlb_lock); - if (!page_huge_active(page) || !get_page_unless_zero(page)) { - ret = false; + spin_lock_irq(&hugetlb_lock); + if (!PageHeadHuge(page) || + !HPageMigratable(page) || + !get_page_unless_zero(page)) { + ret = -EBUSY; goto unlock; } - clear_page_huge_active(page); + ClearHPageMigratable(page); list_move_tail(&page->lru, list); unlock: - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); + return ret; +} + +int get_hwpoison_huge_page(struct page *page, bool *hugetlb) +{ + int ret = 0; + + *hugetlb = false; + spin_lock_irq(&hugetlb_lock); + if (PageHeadHuge(page)) { + *hugetlb = true; + if (HPageFreed(page)) + ret = 0; + else if (HPageMigratable(page)) + ret = get_page_unless_zero(page); + else + ret = -EBUSY; + } + spin_unlock_irq(&hugetlb_lock); + return ret; +} + +int get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + int ret; + + spin_lock_irq(&hugetlb_lock); + ret = __get_huge_page_for_hwpoison(pfn, flags); + spin_unlock_irq(&hugetlb_lock); return ret; } void putback_active_hugepage(struct page *page) { - VM_BUG_ON_PAGE(!PageHead(page), page); - spin_lock(&hugetlb_lock); - set_page_huge_active(page); + spin_lock_irq(&hugetlb_lock); + SetHPageMigratable(page); list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist); - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); put_page(page); } @@ -5058,18 +7394,228 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason) * here as well otherwise the global surplus count will not match * the per-node's. */ - if (PageHugeTemporary(newpage)) { + if (HPageTemporary(newpage)) { int old_nid = page_to_nid(oldpage); int new_nid = page_to_nid(newpage); - SetPageHugeTemporary(oldpage); - ClearPageHugeTemporary(newpage); + SetHPageTemporary(oldpage); + ClearHPageTemporary(newpage); - spin_lock(&hugetlb_lock); + /* + * There is no need to transfer the per-node surplus state + * when we do not cross the node. + */ + if (new_nid == old_nid) + return; + spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages_node[old_nid]) { h->surplus_huge_pages_node[old_nid]--; h->surplus_huge_pages_node[new_nid]++; } - spin_unlock(&hugetlb_lock); + spin_unlock_irq(&hugetlb_lock); } } + +/* + * This function will unconditionally remove all the shared pmd pgtable entries + * within the specific vma for a hugetlbfs memory range. + */ +void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) +{ + struct hstate *h = hstate_vma(vma); + unsigned long sz = huge_page_size(h); + struct mm_struct *mm = vma->vm_mm; + struct mmu_notifier_range range; + unsigned long address, start, end; + spinlock_t *ptl; + pte_t *ptep; + + if (!(vma->vm_flags & VM_MAYSHARE)) + return; + + start = ALIGN(vma->vm_start, PUD_SIZE); + end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); + + if (start >= end) + return; + + flush_cache_range(vma, start, end); + /* + * No need to call adjust_range_if_pmd_sharing_possible(), because + * we have already done the PUD_SIZE alignment. + */ + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, + start, end); + mmu_notifier_invalidate_range_start(&range); + hugetlb_vma_lock_write(vma); + i_mmap_lock_write(vma->vm_file->f_mapping); + for (address = start; address < end; address += PUD_SIZE) { + ptep = huge_pte_offset(mm, address, sz); + if (!ptep) + continue; + ptl = huge_pte_lock(h, mm, ptep); + huge_pmd_unshare(mm, vma, address, ptep); + spin_unlock(ptl); + } + flush_hugetlb_tlb_range(vma, start, end); + i_mmap_unlock_write(vma->vm_file->f_mapping); + hugetlb_vma_unlock_write(vma); + /* + * No need to call mmu_notifier_invalidate_range(), see + * Documentation/mm/mmu_notifier.rst. + */ + mmu_notifier_invalidate_range_end(&range); +} + +#ifdef CONFIG_CMA +static bool cma_reserve_called __initdata; + +static int __init cmdline_parse_hugetlb_cma(char *p) +{ + int nid, count = 0; + unsigned long tmp; + char *s = p; + + while (*s) { + if (sscanf(s, "%lu%n", &tmp, &count) != 1) + break; + + if (s[count] == ':') { + if (tmp >= MAX_NUMNODES) + break; + nid = array_index_nospec(tmp, MAX_NUMNODES); + + s += count + 1; + tmp = memparse(s, &s); + hugetlb_cma_size_in_node[nid] = tmp; + hugetlb_cma_size += tmp; + + /* + * Skip the separator if have one, otherwise + * break the parsing. + */ + if (*s == ',') + s++; + else + break; + } else { + hugetlb_cma_size = memparse(p, &p); + break; + } + } + + return 0; +} + +early_param("hugetlb_cma", cmdline_parse_hugetlb_cma); + +void __init hugetlb_cma_reserve(int order) +{ + unsigned long size, reserved, per_node; + bool node_specific_cma_alloc = false; + int nid; + + cma_reserve_called = true; + + if (!hugetlb_cma_size) + return; + + for (nid = 0; nid < MAX_NUMNODES; nid++) { + if (hugetlb_cma_size_in_node[nid] == 0) + continue; + + if (!node_online(nid)) { + pr_warn("hugetlb_cma: invalid node %d specified\n", nid); + hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; + hugetlb_cma_size_in_node[nid] = 0; + continue; + } + + if (hugetlb_cma_size_in_node[nid] < (PAGE_SIZE << order)) { + pr_warn("hugetlb_cma: cma area of node %d should be at least %lu MiB\n", + nid, (PAGE_SIZE << order) / SZ_1M); + hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; + hugetlb_cma_size_in_node[nid] = 0; + } else { + node_specific_cma_alloc = true; + } + } + + /* Validate the CMA size again in case some invalid nodes specified. */ + if (!hugetlb_cma_size) + return; + + if (hugetlb_cma_size < (PAGE_SIZE << order)) { + pr_warn("hugetlb_cma: cma area should be at least %lu MiB\n", + (PAGE_SIZE << order) / SZ_1M); + hugetlb_cma_size = 0; + return; + } + + if (!node_specific_cma_alloc) { + /* + * If 3 GB area is requested on a machine with 4 numa nodes, + * let's allocate 1 GB on first three nodes and ignore the last one. + */ + per_node = DIV_ROUND_UP(hugetlb_cma_size, nr_online_nodes); + pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n", + hugetlb_cma_size / SZ_1M, per_node / SZ_1M); + } + + reserved = 0; + for_each_online_node(nid) { + int res; + char name[CMA_MAX_NAME]; + + if (node_specific_cma_alloc) { + if (hugetlb_cma_size_in_node[nid] == 0) + continue; + + size = hugetlb_cma_size_in_node[nid]; + } else { + size = min(per_node, hugetlb_cma_size - reserved); + } + + size = round_up(size, PAGE_SIZE << order); + + snprintf(name, sizeof(name), "hugetlb%d", nid); + /* + * Note that 'order per bit' is based on smallest size that + * may be returned to CMA allocator in the case of + * huge page demotion. + */ + res = cma_declare_contiguous_nid(0, size, 0, + PAGE_SIZE << HUGETLB_PAGE_ORDER, + 0, false, name, + &hugetlb_cma[nid], nid); + if (res) { + pr_warn("hugetlb_cma: reservation failed: err %d, node %d", + res, nid); + continue; + } + + reserved += size; + pr_info("hugetlb_cma: reserved %lu MiB on node %d\n", + size / SZ_1M, nid); + + if (reserved >= hugetlb_cma_size) + break; + } + + if (!reserved) + /* + * hugetlb_cma_size is used to determine if allocations from + * cma are possible. Set to zero if no cma regions are set up. + */ + hugetlb_cma_size = 0; +} + +static void __init hugetlb_cma_check(void) +{ + if (!hugetlb_cma_size || cma_reserve_called) + return; + + pr_warn("hugetlb_cma: the option isn't supported by current arch\n"); +} + +#endif /* CONFIG_CMA */ |