1 files changed, 106 insertions, 43 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6f4ce9547658..2f769a661568 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -68,6 +68,21 @@ DEFINE_SPINLOCK(hugetlb_lock);
 static int num_fault_mutexes;
 struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
 
+static inline bool PageHugeFreed(struct page *head)
+{
+	return page_private(head + 4) == -1UL;
+}
+
+static inline void SetPageHugeFreed(struct page *head)
+{
+	set_page_private(head + 4, -1UL);
+}
+
+static inline void ClearPageHugeFreed(struct page *head)
+{
+	set_page_private(head + 4, 0);
+}
+
 /* Forward declaration */
 static int hugetlb_acct_memory(struct hstate *h, long delta);
 
@@ -573,13 +588,20 @@ 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");
 }
 
 /*
@@ -858,6 +880,7 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
 	list_move(&page->lru, &h->hugepage_freelists[nid]);
 	h->free_huge_pages++;
 	h->free_huge_pages_node[nid]++;
+	SetPageHugeFreed(page);
 }
 
 static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
@@ -875,6 +898,7 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 		return NULL;
 	list_move(&page->lru, &h->hugepage_activelist);
 	set_page_refcounted(page);
+	ClearPageHugeFreed(page);
 	h->free_huge_pages--;
 	h->free_huge_pages_node[nid]--;
 	return page;
@@ -1154,14 +1178,16 @@ static inline void destroy_compound_gigantic_page(struct page *page,
 static void update_and_free_page(struct hstate *h, struct page *page)
 {
 	int i;
+	struct page *subpage = page;
 
 	if (hstate_is_gigantic(h) && !gigantic_page_supported())
 		return;
 
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[page_to_nid(page)]--;
-	for (i = 0; i < pages_per_huge_page(h); i++) {
-		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
+	for (i = 0; i < pages_per_huge_page(h);
+	     i++, subpage = mem_map_next(subpage, 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);
@@ -1196,12 +1222,11 @@ struct hstate *size_to_hstate(unsigned long size)
  */
 bool page_huge_active(struct page *page)
 {
-	VM_BUG_ON_PAGE(!PageHuge(page), page);
-	return PageHead(page) && PagePrivate(&page[1]);
+	return PageHeadHuge(page) && PagePrivate(&page[1]);
 }
 
 /* never called for tail page */
-static void set_page_huge_active(struct page *page)
+void set_page_huge_active(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
 	SetPagePrivate(&page[1]);
@@ -1305,6 +1330,7 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 	set_hugetlb_cgroup(page, NULL);
 	h->nr_huge_pages++;
 	h->nr_huge_pages_node[nid]++;
+	ClearPageHugeFreed(page);
 	spin_unlock(&hugetlb_lock);
 }
 
@@ -1500,6 +1526,7 @@ 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;
@@ -1516,6 +1543,26 @@ int dissolve_free_huge_page(struct page *page)
 		int nid = page_to_nid(head);
 		if (h->free_huge_pages - h->resv_huge_pages == 0)
 			goto out;
+
+		/*
+		 * We should make sure that the page is already on the free list
+		 * when it is dissolved.
+		 */
+		if (unlikely(!PageHugeFreed(head))) {
+			spin_unlock(&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;
+		}
+
 		/*
 		 * Move PageHWPoison flag from head page to the raw error page,
 		 * which makes any subpages rather than the error page reusable.
@@ -2610,8 +2657,10 @@ 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;
 }
@@ -2918,6 +2967,22 @@ static unsigned int cpuset_mems_nr(unsigned int *array)
 }
 
 #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)
@@ -2929,9 +2994,8 @@ 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;
 
@@ -2975,9 +3039,8 @@ 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;
 
@@ -3799,7 +3862,7 @@ retry:
 			 * handling userfault.  Reacquire after handling
 			 * fault to make calling code simpler.
 			 */
-			hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr);
+			hash = hugetlb_fault_mutex_hash(h, mapping, idx);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			ret = handle_userfault(&vmf, VM_UFFD_MISSING);
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
@@ -3838,7 +3901,7 @@ 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;
 		}
@@ -3908,7 +3971,7 @@ backout_unlocked:
 
 #ifdef CONFIG_SMP
 u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
-			    pgoff_t idx, unsigned long address)
+			    pgoff_t idx)
 {
 	unsigned long key[2];
 	u32 hash;
@@ -3916,7 +3979,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
 	key[0] = (unsigned long) mapping;
 	key[1] = idx;
 
-	hash = jhash2((u32 *)&key, sizeof(key)/sizeof(u32), 0);
+	hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0);
 
 	return hash & (num_fault_mutexes - 1);
 }
@@ -3926,7 +3989,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
  * return 0 and avoid the hashing overhead.
  */
 u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
-			    pgoff_t idx, unsigned long address)
+			    pgoff_t idx)
 {
 	return 0;
 }
@@ -3970,7 +4033,7 @@ 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, mapping, idx, haddr);
+	hash = hugetlb_fault_mutex_hash(h, mapping, idx);
 	mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 	entry = huge_ptep_get(ptep);
@@ -4650,25 +4713,23 @@ 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 need span at least one aligned PUD size and the start,end range
+	 * must at least partialy within it.
+	 */
+	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 sharing is possible, adjust start/end if necessary.
-		 */
-		if (range_in_vma(vma, a_start, a_end)) {
-			if (a_start < *start)
-				*start = a_start;
-			if (a_end > *end)
-				*end = a_end;
-		}
-	}
+	if (*end < v_end)
+		*end = ALIGN(*end, PUD_SIZE);
 }
 
 /*
@@ -4820,8 +4881,8 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
+	pud_t *pud, pud_entry;
+	pmd_t *pmd, pmd_entry;
 
 	pgd = pgd_offset(mm, addr);
 	if (!pgd_present(*pgd))
@@ -4831,17 +4892,19 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		return NULL;
 
 	pud = pud_offset(p4d, addr);
-	if (sz != PUD_SIZE && pud_none(*pud))
+	pud_entry = READ_ONCE(*pud);
+	if (sz != PUD_SIZE && pud_none(pud_entry))
 		return NULL;
 	/* hugepage or swap? */
-	if (pud_huge(*pud) || !pud_present(*pud))
+	if (pud_huge(pud_entry) || !pud_present(pud_entry))
 		return (pte_t *)pud;
 
 	pmd = pmd_offset(pud, addr);
-	if (sz != PMD_SIZE && pmd_none(*pmd))
+	pmd_entry = READ_ONCE(*pmd);
+	if (sz != PMD_SIZE && pmd_none(pmd_entry))
 		return NULL;
 	/* hugepage or swap? */
-	if (pmd_huge(*pmd) || !pmd_present(*pmd))
+	if (pmd_huge(pmd_entry) || !pmd_present(pmd_entry))
 		return (pte_t *)pmd;
 
 	return NULL;
@@ -4928,9 +4991,9 @@ bool isolate_huge_page(struct page *page, struct list_head *list)
 {
 	bool ret = true;
 
-	VM_BUG_ON_PAGE(!PageHead(page), page);
 	spin_lock(&hugetlb_lock);
-	if (!page_huge_active(page) || !get_page_unless_zero(page)) {
+	if (!PageHeadHuge(page) || !page_huge_active(page) ||
+	    !get_page_unless_zero(page)) {
 		ret = false;
 		goto unlock;
 	}