diff options
Diffstat (limited to 'mm/hugetlb.c')
| -rw-r--r-- | mm/hugetlb.c | 180 |
1 files changed, 119 insertions, 61 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 641cedfc8c0f..81718c56b8f5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -740,7 +740,15 @@ void resv_map_release(struct kref *ref) static inline struct resv_map *inode_resv_map(struct inode *inode) { - return inode->i_mapping->private_data; + /* + * At inode evict time, i_mapping may not point to the original + * address space within the inode. This original address space + * contains the pointer to the resv_map. So, always use the + * address space embedded within the inode. + * The VERY common case is inode->mapping == &inode->i_data but, + * this may not be true for device special inodes. + */ + return (struct resv_map *)(&inode->i_data)->private_data; } static struct resv_map *vma_resv_map(struct vm_area_struct *vma) @@ -1059,6 +1067,7 @@ static void free_gigantic_page(struct page *page, unsigned int order) free_contig_range(page_to_pfn(page), 1 << order); } +#ifdef CONFIG_CONTIG_ALLOC static int __alloc_gigantic_page(unsigned long start_pfn, unsigned long nr_pages, gfp_t gfp_mask) { @@ -1143,11 +1152,20 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, 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) +{ + return NULL; +} +#endif /* CONFIG_CONTIG_ALLOC */ #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */ -static inline bool gigantic_page_supported(void) { return false; } static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, - int nid, nodemask_t *nodemask) { return NULL; } + int nid, nodemask_t *nodemask) +{ + return NULL; +} static inline void free_gigantic_page(struct page *page, unsigned int order) { } static inline void destroy_compound_gigantic_page(struct page *page, unsigned int order) { } @@ -1157,7 +1175,7 @@ static void update_and_free_page(struct hstate *h, struct page *page) { int i; - if (hstate_is_gigantic(h) && !gigantic_page_supported()) + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; h->nr_huge_pages--; @@ -1258,12 +1276,23 @@ void free_huge_page(struct page *page) ClearPagePrivate(page); /* - * A return code of zero implies that the subpool will be under its - * minimum size if the reservation is not restored after page is free. - * Therefore, force restore_reserve operation. + * If PagePrivate() 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 + * remove the reserved page from the subpool. */ - if (hugepage_subpool_put_pages(spool, 1) == 0) - restore_reserve = true; + if (!restore_reserve) { + /* + * A return code of zero implies that the subpool will be + * under its minimum size if the reservation is not restored + * after page is free. Therefore, force restore_reserve + * operation. + */ + if (hugepage_subpool_put_pages(spool, 1) == 0) + restore_reserve = true; + } spin_lock(&hugetlb_lock); clear_page_huge_active(page); @@ -1574,8 +1603,9 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, */ if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { SetPageHugeTemporary(page); + spin_unlock(&hugetlb_lock); put_page(page); - page = NULL; + return NULL; } else { h->surplus_huge_pages++; h->surplus_huge_pages_node[page_to_nid(page)]++; @@ -2277,13 +2307,47 @@ found: } #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) -static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, - nodemask_t *nodes_allowed) +static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, + nodemask_t *nodes_allowed) { unsigned long min_count, ret; - if (hstate_is_gigantic(h) && !gigantic_page_supported()) - return h->max_huge_pages; + spin_lock(&hugetlb_lock); + + /* + * Check for a node specific request. + * Changing node specific huge page count may require a corresponding + * change to the global count. In any case, the passed node mask + * (nodes_allowed) will restrict alloc/free to the specified node. + */ + if (nid != NUMA_NO_NODE) { + unsigned long old_count = count; + + count += h->nr_huge_pages - h->nr_huge_pages_node[nid]; + /* + * User may have specified a large count value which caused the + * above calculation to overflow. In this case, they wanted + * to allocate as many huge pages as possible. Set count to + * largest possible value to align with their intention. + */ + if (count < old_count) + count = ULONG_MAX; + } + + /* + * Gigantic pages runtime allocation depend on the capability for large + * page range allocation. + * If the system does not provide this feature, return an error when + * the user tries to allocate gigantic pages but let the user free the + * boottime allocated gigantic pages. + */ + if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) { + if (count > persistent_huge_pages(h)) { + spin_unlock(&hugetlb_lock); + return -EINVAL; + } + /* Fall through to decrease pool */ + } /* * Increase the pool size @@ -2296,7 +2360,6 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, * pool might be one hugepage larger than it needs to be, but * within all the constraints specified by the sysctls. */ - spin_lock(&hugetlb_lock); while (h->surplus_huge_pages && count > persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, -1)) break; @@ -2351,9 +2414,10 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, break; } out: - ret = persistent_huge_pages(h); + h->max_huge_pages = persistent_huge_pages(h); spin_unlock(&hugetlb_lock); - return ret; + + return 0; } #define HSTATE_ATTR_RO(_name) \ @@ -2403,41 +2467,32 @@ static ssize_t __nr_hugepages_store_common(bool obey_mempolicy, unsigned long count, size_t len) { int err; - NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY); + nodemask_t nodes_allowed, *n_mask; - if (hstate_is_gigantic(h) && !gigantic_page_supported()) { - err = -EINVAL; - goto out; - } + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) + return -EINVAL; if (nid == NUMA_NO_NODE) { /* * global hstate attribute */ if (!(obey_mempolicy && - init_nodemask_of_mempolicy(nodes_allowed))) { - NODEMASK_FREE(nodes_allowed); - nodes_allowed = &node_states[N_MEMORY]; - } - } else if (nodes_allowed) { + init_nodemask_of_mempolicy(&nodes_allowed))) + n_mask = &node_states[N_MEMORY]; + else + n_mask = &nodes_allowed; + } else { /* - * per node hstate attribute: adjust count to global, - * but restrict alloc/free to the specified node. + * Node specific request. count adjustment happens in + * set_max_huge_pages() after acquiring hugetlb_lock. */ - count += h->nr_huge_pages - h->nr_huge_pages_node[nid]; - init_nodemask_of_node(nodes_allowed, nid); - } else - nodes_allowed = &node_states[N_MEMORY]; - - h->max_huge_pages = set_max_huge_pages(h, count, nodes_allowed); + init_nodemask_of_node(&nodes_allowed, nid); + n_mask = &nodes_allowed; + } - if (nodes_allowed != &node_states[N_MEMORY]) - NODEMASK_FREE(nodes_allowed); + err = set_max_huge_pages(h, count, nid, n_mask); - return len; -out: - NODEMASK_FREE(nodes_allowed); - return err; + return err ? err : len; } static ssize_t nr_hugepages_store_common(bool obey_mempolicy, @@ -3247,7 +3302,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; if (cow) { - mmu_notifier_range_init(&range, src, vma->vm_start, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src, + vma->vm_start, vma->vm_end); mmu_notifier_invalidate_range_start(&range); } @@ -3359,7 +3415,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, /* * If sharing possible, alert mmu notifiers of worst case. */ - mmu_notifier_range_init(&range, mm, start, end); + mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, mm, start, + end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); mmu_notifier_invalidate_range_start(&range); address = start; @@ -3626,7 +3683,8 @@ retry_avoidcopy: pages_per_huge_page(h)); __SetPageUptodate(new_page); - mmu_notifier_range_init(&range, mm, haddr, haddr + huge_page_size(h)); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, haddr, + haddr + huge_page_size(h)); mmu_notifier_invalidate_range_start(&range); /* @@ -3777,8 +3835,7 @@ retry: * handling userfault. Reacquire after handling * fault to make calling code simpler. */ - hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping, - idx, haddr); + hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr); mutex_unlock(&hugetlb_fault_mutex_table[hash]); ret = handle_userfault(&vmf, VM_UFFD_MISSING); mutex_lock(&hugetlb_fault_mutex_table[hash]); @@ -3886,21 +3943,14 @@ backout_unlocked: } #ifdef CONFIG_SMP -u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm, - struct vm_area_struct *vma, - struct address_space *mapping, +u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, pgoff_t idx, unsigned long address) { unsigned long key[2]; u32 hash; - if (vma->vm_flags & VM_SHARED) { - key[0] = (unsigned long) mapping; - key[1] = idx; - } else { - key[0] = (unsigned long) mm; - key[1] = address >> huge_page_shift(h); - } + key[0] = (unsigned long) mapping; + key[1] = idx; hash = jhash2((u32 *)&key, sizeof(key)/sizeof(u32), 0); @@ -3911,9 +3961,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm, * For uniprocesor systems we always use a single mutex, so just * return 0 and avoid the hashing overhead. */ -u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm, - struct vm_area_struct *vma, - struct address_space *mapping, +u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, pgoff_t idx, unsigned long address) { return 0; @@ -3958,7 +4006,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ - hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping, idx, haddr); + hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr); mutex_lock(&hugetlb_fault_mutex_table[hash]); entry = huge_ptep_get(ptep); @@ -4371,7 +4419,8 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * start/end. Set range.start/range.end to cover the maximum possible * range if PMD sharing is possible. */ - mmu_notifier_range_init(&range, mm, start, end); + mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, + 0, vma, mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); BUG_ON(address >= end); @@ -4477,6 +4526,11 @@ int hugetlb_reserve_pages(struct inode *inode, * called to make the mapping read-write. Assume !vma is a shm mapping */ if (!vma || vma->vm_flags & VM_MAYSHARE) { + /* + * resv_map can not be NULL as hugetlb_reserve_pages is only + * called for inodes for which resv_maps were created (see + * hugetlbfs_get_inode). + */ resv_map = inode_resv_map(inode); chg = region_chg(resv_map, from, to); @@ -4568,6 +4622,10 @@ long hugetlb_unreserve_pages(struct inode *inode, long start, long end, struct hugepage_subpool *spool = subpool_inode(inode); long gbl_reserve; + /* + * Since this routine can be called in the evict inode path for all + * hugetlbfs inodes, resv_map could be NULL. + */ if (resv_map) { chg = region_del(resv_map, start, end); /* |