Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Several conflicts, seemingly all over the place.

I used Stephen Rothwell's sample resolutions for many of these, if not
just to double check my own work, so definitely the credit largely
goes to him.

The NFP conflict consisted of a bug fix (moving operations
past the rhashtable operation) while chaning the initial
argument in the function call in the moved code.

The net/dsa/master.c conflict had to do with a bug fix intermixing of
making dsa_master_set_mtu() static with the fixing of the tagging
attribute location.

cls_flower had a conflict because the dup reject fix from Or
overlapped with the addition of port range classifiction.

__set_phy_supported()'s conflict was relatively easy to resolve
because Andrew fixed it in both trees, so it was just a matter
of taking the net-next copy.  Or at least I think it was :-)

Joe Stringer's fix to the handling of netns id 0 in bpf_sk_lookup()
intermixed with changes on how the sdif and caller_net are calculated
in these code paths in net-next.

The remaining BPF conflicts were largely about the addition of the
__bpf_md_ptr stuff in 'net' overlapping with adjustments and additions
to the relevant data structure where the MD pointer macros are used.

Signed-off-by: David S. Miller <davem@davemloft.net>

11 files changed, 258 insertions, 153 deletions

diff --git a/mm/gup.c b/mm/gup.c
index aa43620a3270..8cb68a50dbdf 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -702,12 +702,11 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		if (!vma || start >= vma->vm_end) {
 			vma = find_extend_vma(mm, start);
 			if (!vma && in_gate_area(mm, start)) {
-				int ret;
 				ret = get_gate_page(mm, start & PAGE_MASK,
 						gup_flags, &vma,
 						pages ? &pages[i] : NULL);
 				if (ret)
-					return i ? : ret;
+					goto out;
 				ctx.page_mask = 0;
 				goto next_page;
 			}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 55478ab3c83b..5da55b38b1b7 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -629,40 +629,30 @@ release:
  *	    available
  * never: never stall for any thp allocation
  */
-static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr)
+static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
 {
 	const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
-	gfp_t this_node = 0;
-
-#ifdef CONFIG_NUMA
-	struct mempolicy *pol;
-	/*
-	 * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not
-	 * specified, to express a general desire to stay on the current
-	 * node for optimistic allocation attempts. If the defrag mode
-	 * and/or madvise hint requires the direct reclaim then we prefer
-	 * to fallback to other node rather than node reclaim because that
-	 * can lead to excessive reclaim even though there is free memory
-	 * on other nodes. We expect that NUMA preferences are specified
-	 * by memory policies.
-	 */
-	pol = get_vma_policy(vma, addr);
-	if (pol->mode != MPOL_BIND)
-		this_node = __GFP_THISNODE;
-	mpol_cond_put(pol);
-#endif
 
+	/* Always do synchronous compaction */
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
 		return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
+
+	/* Kick kcompactd and fail quickly */
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
-		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node;
+		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
+
+	/* Synchronous compaction if madvised, otherwise kick kcompactd */
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
-		return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
-							     __GFP_KSWAPD_RECLAIM | this_node);
+		return GFP_TRANSHUGE_LIGHT |
+			(vma_madvised ? __GFP_DIRECT_RECLAIM :
+					__GFP_KSWAPD_RECLAIM);
+
+	/* Only do synchronous compaction if madvised */
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
-		return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
-							     this_node);
-	return GFP_TRANSHUGE_LIGHT | this_node;
+		return GFP_TRANSHUGE_LIGHT |
+		       (vma_madvised ? __GFP_DIRECT_RECLAIM : 0);
+
+	return GFP_TRANSHUGE_LIGHT;
 }
 
 /* Caller must hold page table lock. */
@@ -734,8 +724,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 			pte_free(vma->vm_mm, pgtable);
 		return ret;
 	}
-	gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
-	page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id());
+	gfp = alloc_hugepage_direct_gfpmask(vma);
+	page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);
 	if (unlikely(!page)) {
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -1305,9 +1295,8 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
 alloc:
 	if (transparent_hugepage_enabled(vma) &&
 	    !transparent_hugepage_debug_cow()) {
-		huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
-		new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma,
-				haddr, numa_node_id());
+		huge_gfp = alloc_hugepage_direct_gfpmask(vma);
+		new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);
 	} else
 		new_page = NULL;
 
@@ -2350,7 +2339,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 	}
 }
 
-static void freeze_page(struct page *page)
+static void unmap_page(struct page *page)
 {
 	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
 		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
@@ -2365,7 +2354,7 @@ static void freeze_page(struct page *page)
 	VM_BUG_ON_PAGE(!unmap_success, page);
 }
 
-static void unfreeze_page(struct page *page)
+static void remap_page(struct page *page)
 {
 	int i;
 	if (PageTransHuge(page)) {
@@ -2402,6 +2391,12 @@ static void __split_huge_page_tail(struct page *head, int tail,
 			 (1L << PG_unevictable) |
 			 (1L << PG_dirty)));
 
+	/* ->mapping in first tail page is compound_mapcount */
+	VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
+			page_tail);
+	page_tail->mapping = head->mapping;
+	page_tail->index = head->index + tail;
+
 	/* Page flags must be visible before we make the page non-compound. */
 	smp_wmb();
 
@@ -2422,12 +2417,6 @@ static void __split_huge_page_tail(struct page *head, int tail,
 	if (page_is_idle(head))
 		set_page_idle(page_tail);
 
-	/* ->mapping in first tail page is compound_mapcount */
-	VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
-			page_tail);
-	page_tail->mapping = head->mapping;
-
-	page_tail->index = head->index + tail;
 	page_cpupid_xchg_last(page_tail, page_cpupid_last(head));
 
 	/*
@@ -2439,12 +2428,11 @@ static void __split_huge_page_tail(struct page *head, int tail,
 }
 
 static void __split_huge_page(struct page *page, struct list_head *list,
-		unsigned long flags)
+		pgoff_t end, unsigned long flags)
 {
 	struct page *head = compound_head(page);
 	struct zone *zone = page_zone(head);
 	struct lruvec *lruvec;
-	pgoff_t end = -1;
 	int i;
 
 	lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat);
@@ -2452,9 +2440,6 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	/* complete memcg works before add pages to LRU */
 	mem_cgroup_split_huge_fixup(head);
 
-	if (!PageAnon(page))
-		end = DIV_ROUND_UP(i_size_read(head->mapping->host), PAGE_SIZE);
-
 	for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
 		__split_huge_page_tail(head, i, lruvec, list);
 		/* Some pages can be beyond i_size: drop them from page cache */
@@ -2483,7 +2468,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 
 	spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
 
-	unfreeze_page(head);
+	remap_page(head);
 
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
 		struct page *subpage = head + i;
@@ -2626,6 +2611,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	int count, mapcount, extra_pins, ret;
 	bool mlocked;
 	unsigned long flags;
+	pgoff_t end;
 
 	VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
@@ -2648,6 +2634,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 			ret = -EBUSY;
 			goto out;
 		}
+		end = -1;
 		mapping = NULL;
 		anon_vma_lock_write(anon_vma);
 	} else {
@@ -2661,10 +2648,19 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 
 		anon_vma = NULL;
 		i_mmap_lock_read(mapping);
+
+		/*
+		 *__split_huge_page() may need to trim off pages beyond EOF:
+		 * but on 32-bit, i_size_read() takes an irq-unsafe seqlock,
+		 * which cannot be nested inside the page tree lock. So note
+		 * end now: i_size itself may be changed at any moment, but
+		 * head page lock is good enough to serialize the trimming.
+		 */
+		end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
 	}
 
 	/*
-	 * Racy check if we can split the page, before freeze_page() will
+	 * Racy check if we can split the page, before unmap_page() will
 	 * split PMDs
 	 */
 	if (!can_split_huge_page(head, &extra_pins)) {
@@ -2673,7 +2669,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	}
 
 	mlocked = PageMlocked(page);
-	freeze_page(head);
+	unmap_page(head);
 	VM_BUG_ON_PAGE(compound_mapcount(head), head);
 
 	/* Make sure the page is not on per-CPU pagevec as it takes pin */
@@ -2707,7 +2703,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		if (mapping)
 			__dec_node_page_state(page, NR_SHMEM_THPS);
 		spin_unlock(&pgdata->split_queue_lock);
-		__split_huge_page(page, list, flags);
+		__split_huge_page(page, list, end, flags);
 		if (PageSwapCache(head)) {
 			swp_entry_t entry = { .val = page_private(head) };
 
@@ -2727,7 +2723,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 fail:		if (mapping)
 			xa_unlock(&mapping->i_pages);
 		spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
-		unfreeze_page(head);
+		remap_page(head);
 		ret = -EBUSY;
 	}
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7f2a28ab46d5..705a3e9cc910 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4080,7 +4080,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 
 		/* fallback to copy_from_user outside mmap_sem */
 		if (unlikely(ret)) {
-			ret = -EFAULT;
+			ret = -ENOENT;
 			*pagep = page;
 			/* don't free the page */
 			goto out;
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index c13625c1ad5e..8e2ff195ecb3 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1287,7 +1287,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
  * collapse_shmem - collapse small tmpfs/shmem pages into huge one.
  *
  * Basic scheme is simple, details are more complex:
- *  - allocate and freeze a new huge page;
+ *  - allocate and lock a new huge page;
  *  - scan page cache replacing old pages with the new one
  *    + swap in pages if necessary;
  *    + fill in gaps;
@@ -1295,11 +1295,11 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
  *  - if replacing succeeds:
  *    + copy data over;
  *    + free old pages;
- *    + unfreeze huge page;
+ *    + unlock huge page;
  *  - if replacing failed;
  *    + put all pages back and unfreeze them;
  *    + restore gaps in the page cache;
- *    + free huge page;
+ *    + unlock and free huge page;
  */
 static void collapse_shmem(struct mm_struct *mm,
 		struct address_space *mapping, pgoff_t start,
@@ -1329,19 +1329,6 @@ static void collapse_shmem(struct mm_struct *mm,
 		goto out;
 	}
 
-	new_page->index = start;
-	new_page->mapping = mapping;
-	__SetPageSwapBacked(new_page);
-	__SetPageLocked(new_page);
-	BUG_ON(!page_ref_freeze(new_page, 1));
-
-	/*
-	 * At this point the new_page is 'frozen' (page_count() is zero),
-	 * locked and not up-to-date. It's safe to insert it into the page
-	 * cache, because nobody would be able to map it or use it in other
-	 * way until we unfreeze it.
-	 */
-
 	/* This will be less messy when we use multi-index entries */
 	do {
 		xas_lock_irq(&xas);
@@ -1349,19 +1336,44 @@ static void collapse_shmem(struct mm_struct *mm,
 		if (!xas_error(&xas))
 			break;
 		xas_unlock_irq(&xas);
-		if (!xas_nomem(&xas, GFP_KERNEL))
+		if (!xas_nomem(&xas, GFP_KERNEL)) {
+			mem_cgroup_cancel_charge(new_page, memcg, true);
+			result = SCAN_FAIL;
 			goto out;
+		}
 	} while (1);
 
+	__SetPageLocked(new_page);
+	__SetPageSwapBacked(new_page);
+	new_page->index = start;
+	new_page->mapping = mapping;
+
+	/*
+	 * At this point the new_page is locked and not up-to-date.
+	 * It's safe to insert it into the page cache, because nobody would
+	 * be able to map it or use it in another way until we unlock it.
+	 */
+
 	xas_set(&xas, start);
 	for (index = start; index < end; index++) {
 		struct page *page = xas_next(&xas);
 
 		VM_BUG_ON(index != xas.xa_index);
 		if (!page) {
+			/*
+			 * Stop if extent has been truncated or hole-punched,
+			 * and is now completely empty.
+			 */
+			if (index == start) {
+				if (!xas_next_entry(&xas, end - 1)) {
+					result = SCAN_TRUNCATED;
+					goto xa_locked;
+				}
+				xas_set(&xas, index);
+			}
 			if (!shmem_charge(mapping->host, 1)) {
 				result = SCAN_FAIL;
-				break;
+				goto xa_locked;
 			}
 			xas_store(&xas, new_page + (index % HPAGE_PMD_NR));
 			nr_none++;
@@ -1376,13 +1388,12 @@ static void collapse_shmem(struct mm_struct *mm,
 				result = SCAN_FAIL;
 				goto xa_unlocked;
 			}
-			xas_lock_irq(&xas);
-			xas_set(&xas, index);
 		} else if (trylock_page(page)) {
 			get_page(page);
+			xas_unlock_irq(&xas);
 		} else {
 			result = SCAN_PAGE_LOCK;
-			break;
+			goto xa_locked;
 		}
 
 		/*
@@ -1391,17 +1402,24 @@ static void collapse_shmem(struct mm_struct *mm,
 		 */
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
 		VM_BUG_ON_PAGE(!PageUptodate(page), page);
-		VM_BUG_ON_PAGE(PageTransCompound(page), page);
+
+		/*
+		 * If file was truncated then extended, or hole-punched, before
+		 * we locked the first page, then a THP might be there already.
+		 */
+		if (PageTransCompound(page)) {
+			result = SCAN_PAGE_COMPOUND;
+			goto out_unlock;
+		}
 
 		if (page_mapping(page) != mapping) {
 			result = SCAN_TRUNCATED;
 			goto out_unlock;
 		}
-		xas_unlock_irq(&xas);
 
 		if (isolate_lru_page(page)) {
 			result = SCAN_DEL_PAGE_LRU;
-			goto out_isolate_failed;
+			goto out_unlock;
 		}
 
 		if (page_mapped(page))
@@ -1421,7 +1439,9 @@ static void collapse_shmem(struct mm_struct *mm,
 		 */
 		if (!page_ref_freeze(page, 3)) {
 			result = SCAN_PAGE_COUNT;
-			goto out_lru;
+			xas_unlock_irq(&xas);
+			putback_lru_page(page);
+			goto out_unlock;
 		}
 
 		/*
@@ -1433,71 +1453,74 @@ static void collapse_shmem(struct mm_struct *mm,
 		/* Finally, replace with the new page. */
 		xas_store(&xas, new_page + (index % HPAGE_PMD_NR));
 		continue;
-out_lru:
-		xas_unlock_irq(&xas);
-		putback_lru_page(page);
-out_isolate_failed:
-		unlock_page(page);
-		put_page(page);
-		goto xa_unlocked;
 out_unlock:
 		unlock_page(page);
 		put_page(page);
-		break;
+		goto xa_unlocked;
 	}
-	xas_unlock_irq(&xas);
 
+	__inc_node_page_state(new_page, NR_SHMEM_THPS);
+	if (nr_none) {
+		struct zone *zone = page_zone(new_page);
+
+		__mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
+		__mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
+	}
+
+xa_locked:
+	xas_unlock_irq(&xas);
 xa_unlocked:
+
 	if (result == SCAN_SUCCEED) {
 		struct page *page, *tmp;
-		struct zone *zone = page_zone(new_page);
 
 		/*
 		 * Replacing old pages with new one has succeeded, now we
 		 * need to copy the content and free the old pages.
 		 */
+		index = start;
 		list_for_each_entry_safe(page, tmp, &pagelist, lru) {
+			while (index < page->index) {
+				clear_highpage(new_page + (index % HPAGE_PMD_NR));
+				index++;
+			}
 			copy_highpage(new_page + (page->index % HPAGE_PMD_NR),
 					page);
 			list_del(&page->lru);
-			unlock_page(page);
-			page_ref_unfreeze(page, 1);
 			page->mapping = NULL;
+			page_ref_unfreeze(page, 1);
 			ClearPageActive(page);
 			ClearPageUnevictable(page);
+			unlock_page(page);
 			put_page(page);
+			index++;
 		}
-
-		local_irq_disable();
-		__inc_node_page_state(new_page, NR_SHMEM_THPS);
-		if (nr_none) {
-			__mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
-			__mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
+		while (index < end) {
+			clear_highpage(new_page + (index % HPAGE_PMD_NR));
+			index++;
 		}
-		local_irq_enable();
 
-		/*
-		 * Remove pte page tables, so we can re-fault
-		 * the page as huge.
-		 */
-		retract_page_tables(mapping, start);
-
-		/* Everything is ready, let's unfreeze the new_page */
-		set_page_dirty(new_page);
 		SetPageUptodate(new_page);
-		page_ref_unfreeze(new_page, HPAGE_PMD_NR);
+		page_ref_add(new_page, HPAGE_PMD_NR - 1);
+		set_page_dirty(new_page);
 		mem_cgroup_commit_charge(new_page, memcg, false, true);
 		lru_cache_add_anon(new_page);
-		unlock_page(new_page);
 
+		/*
+		 * Remove pte page tables, so we can re-fault the page as huge.
+		 */
+		retract_page_tables(mapping, start);
 		*hpage = NULL;
 
 		khugepaged_pages_collapsed++;
 	} else {
 		struct page *page;
+
 		/* Something went wrong: roll back page cache changes */
-		shmem_uncharge(mapping->host, nr_none);
 		xas_lock_irq(&xas);
+		mapping->nrpages -= nr_none;
+		shmem_uncharge(mapping->host, nr_none);
+
 		xas_set(&xas, start);
 		xas_for_each(&xas, page, end - 1) {
 			page = list_first_entry_or_null(&pagelist,
@@ -1519,19 +1542,18 @@ xa_unlocked:
 			xas_store(&xas, page);
 			xas_pause(&xas);
 			xas_unlock_irq(&xas);
-			putback_lru_page(page);
 			unlock_page(page);
+			putback_lru_page(page);
 			xas_lock_irq(&xas);
 		}
 		VM_BUG_ON(nr_none);
 		xas_unlock_irq(&xas);
 
-		/* Unfreeze new_page, caller would take care about freeing it */
-		page_ref_unfreeze(new_page, 1);
 		mem_cgroup_cancel_charge(new_page, memcg, true);
-		unlock_page(new_page);
 		new_page->mapping = NULL;
 	}
+
+	unlock_page(new_page);
 out:
 	VM_BUG_ON(!list_empty(&pagelist));
 	/* TODO: tracepoints */
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 0cd3de3550f0..7c72f2a95785 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1161,6 +1161,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 	LIST_HEAD(tokill);
 	int rc = -EBUSY;
 	loff_t start;
+	dax_entry_t cookie;
 
 	/*
 	 * Prevent the inode from being freed while we are interrogating
@@ -1169,7 +1170,8 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 	 * also prevents changes to the mapping of this pfn until
 	 * poison signaling is complete.
 	 */
-	if (!dax_lock_mapping_entry(page))
+	cookie = dax_lock_page(page);
+	if (!cookie)
 		goto out;
 
 	if (hwpoison_filter(page)) {
@@ -1220,7 +1222,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 	kill_procs(&tokill, flags & MF_MUST_KILL, !unmap_success, pfn, flags);
 	rc = 0;
 unlock:
-	dax_unlock_mapping_entry(page);
+	dax_unlock_page(page, cookie);
 out:
 	/* drop pgmap ref acquired in caller */
 	put_dev_pagemap(pgmap);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 5837a067124d..d4496d9d34f5 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1116,8 +1116,8 @@ static struct page *new_page(struct page *page, unsigned long start)
 	} else if (PageTransHuge(page)) {
 		struct page *thp;
 
-		thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma,
-				address, numa_node_id());
+		thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address,
+					 HPAGE_PMD_ORDER);
 		if (!thp)
 			return NULL;
 		prep_transhuge_page(thp);
@@ -1662,7 +1662,7 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
  * freeing by another task.  It is the caller's responsibility to free the
  * extra reference for shared policies.
  */
-struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+static struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
 						unsigned long addr)
 {
 	struct mempolicy *pol = __get_vma_policy(vma, addr);
@@ -2011,6 +2011,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  * 	@vma:  Pointer to VMA or NULL if not available.
  *	@addr: Virtual Address of the allocation. Must be inside the VMA.
  *	@node: Which node to prefer for allocation (modulo policy).
+ *	@hugepage: for hugepages try only the preferred node if possible
  *
  * 	This function allocates a page from the kernel page pool and applies
  *	a NUMA policy associated with the VMA or the current process.
@@ -2021,7 +2022,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  */
 struct page *
 alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
-		unsigned long addr, int node)
+		unsigned long addr, int node, bool hugepage)
 {
 	struct mempolicy *pol;
 	struct page *page;
@@ -2039,6 +2040,31 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		goto out;
 	}
 
+	if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) {
+		int hpage_node = node;
+
+		/*
+		 * For hugepage allocation and non-interleave policy which
+		 * allows the current node (or other explicitly preferred
+		 * node) we only try to allocate from the current/preferred
+		 * node and don't fall back to other nodes, as the cost of
+		 * remote accesses would likely offset THP benefits.
+		 *
+		 * If the policy is interleave, or does not allow the current
+		 * node in its nodemask, we allocate the standard way.
+		 */
+		if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL))
+			hpage_node = pol->v.preferred_node;
+
+		nmask = policy_nodemask(gfp, pol);
+		if (!nmask || node_isset(hpage_node, *nmask)) {
+			mpol_cond_put(pol);
+			page = __alloc_pages_node(hpage_node,
+						gfp | __GFP_THISNODE, order);
+			goto out;
+		}
+	}
+
 	nmask = policy_nodemask(gfp, pol);
 	preferred_nid = policy_node(gfp, pol, node);
 	page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6847177dc4a1..2ec9cc407216 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5813,8 +5813,10 @@ void __meminit init_currently_empty_zone(struct zone *zone,
 					unsigned long size)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
+	int zone_idx = zone_idx(zone) + 1;
 
-	pgdat->nr_zones = zone_idx(zone) + 1;
+	if (zone_idx > pgdat->nr_zones)
+		pgdat->nr_zones = zone_idx;
 
 	zone->zone_start_pfn = zone_start_pfn;
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 1e79fac3186b..85b7f9423352 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1627,16 +1627,9 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 						      address + PAGE_SIZE);
 		} else {
 			/*
-			 * We should not need to notify here as we reach this
-			 * case only from freeze_page() itself only call from
-			 * split_huge_page_to_list() so everything below must
-			 * be true:
-			 *   - page is not anonymous
-			 *   - page is locked
-			 *
-			 * So as it is a locked file back page thus it can not
-			 * be remove from the page cache and replace by a new
-			 * page before mmu_notifier_invalidate_range_end so no
+			 * This is a locked file-backed page, thus it cannot
+			 * be removed from the page cache and replaced by a new
+			 * page before mmu_notifier_invalidate_range_end, so no
 			 * concurrent thread might update its page table to
 			 * point at new page while a device still is using this
 			 * page.
diff --git a/mm/shmem.c b/mm/shmem.c
index d44991ea5ed4..921f80488bb3 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -297,12 +297,14 @@ bool shmem_charge(struct inode *inode, long pages)
 	if (!shmem_inode_acct_block(inode, pages))
 		return false;
 
+	/* nrpages adjustment first, then shmem_recalc_inode() when balanced */
+	inode->i_mapping->nrpages += pages;
+
 	spin_lock_irqsave(&info->lock, flags);
 	info->alloced += pages;
 	inode->i_blocks += pages * BLOCKS_PER_PAGE;
 	shmem_recalc_inode(inode);
 	spin_unlock_irqrestore(&info->lock, flags);
-	inode->i_mapping->nrpages += pages;
 
 	return true;
 }
@@ -312,6 +314,8 @@ void shmem_uncharge(struct inode *inode, long pages)
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	unsigned long flags;
 
+	/* nrpages adjustment done by __delete_from_page_cache() or caller */
+
 	spin_lock_irqsave(&info->lock, flags);
 	info->alloced -= pages;
 	inode->i_blocks -= pages * BLOCKS_PER_PAGE;
@@ -1435,7 +1439,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp,
 
 	shmem_pseudo_vma_init(&pvma, info, hindex);
 	page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN,
-			HPAGE_PMD_ORDER, &pvma, 0, numa_node_id());
+			HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true);
 	shmem_pseudo_vma_destroy(&pvma);
 	if (page)
 		prep_transhuge_page(page);
@@ -1509,11 +1513,13 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 {
 	struct page *oldpage, *newpage;
 	struct address_space *swap_mapping;
+	swp_entry_t entry;
 	pgoff_t swap_index;
 	int error;
 
 	oldpage = *pagep;
-	swap_index = page_private(oldpage);
+	entry.val = page_private(oldpage);
+	swap_index = swp_offset(entry);
 	swap_mapping = page_mapping(oldpage);
 
 	/*
@@ -1532,7 +1538,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 	__SetPageLocked(newpage);
 	__SetPageSwapBacked(newpage);
 	SetPageUptodate(newpage);
-	set_page_private(newpage, swap_index);
+	set_page_private(newpage, entry.val);
 	SetPageSwapCache(newpage);
 
 	/*
@@ -2214,6 +2220,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 	struct page *page;
 	pte_t _dst_pte, *dst_pte;
 	int ret;
+	pgoff_t offset, max_off;
 
 	ret = -ENOMEM;
 	if (!shmem_inode_acct_block(inode, 1))
@@ -2236,7 +2243,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 				*pagep = page;
 				shmem_inode_unacct_blocks(inode, 1);
 				/* don't free the page */
-				return -EFAULT;
+				return -ENOENT;
 			}
 		} else {		/* mfill_zeropage_atomic */
 			clear_highpage(page);
@@ -2251,6 +2258,12 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 	__SetPageSwapBacked(page);
 	__SetPageUptodate(page);
 
+	ret = -EFAULT;
+	offset = linear_page_index(dst_vma, dst_addr);
+	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+	if (unlikely(offset >= max_off))
+		goto out_release;
+
 	ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg, false);
 	if (ret)
 		goto out_release;
@@ -2265,9 +2278,25 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 	_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
 	if (dst_vma->vm_flags & VM_WRITE)
 		_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
+	else {
+		/*
+		 * We don't set the pte dirty if the vma has no
+		 * VM_WRITE permission, so mark the page dirty or it
+		 * could be freed from under us. We could do it
+		 * unconditionally before unlock_page(), but doing it
+		 * only if VM_WRITE is not set is faster.
+		 */
+		set_page_dirty(page);
+	}
 
-	ret = -EEXIST;
 	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
+
+	ret = -EFAULT;
+	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+	if (unlikely(offset >= max_off))
+		goto out_release_uncharge_unlock;
+
+	ret = -EEXIST;
 	if (!pte_none(*dst_pte))
 		goto out_release_uncharge_unlock;
 
@@ -2285,13 +2314,15 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 
 	/* No need to invalidate - it was non-present before */
 	update_mmu_cache(dst_vma, dst_addr, dst_pte);
-	unlock_page(page);
 	pte_unmap_unlock(dst_pte, ptl);
+	unlock_page(page);
 	ret = 0;
 out:
 	return ret;
 out_release_uncharge_unlock:
 	pte_unmap_unlock(dst_pte, ptl);
+	ClearPageDirty(page);
+	delete_from_page_cache(page);
 out_release_uncharge:
 	mem_cgroup_cancel_charge(page, memcg, false);
 out_release:
diff --git a/mm/truncate.c b/mm/truncate.c
index 45d68e90b703..798e7ccfb030 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -517,9 +517,13 @@ void truncate_inode_pages_final(struct address_space *mapping)
 		 */
 		xa_lock_irq(&mapping->i_pages);
 		xa_unlock_irq(&mapping->i_pages);
-
-		truncate_inode_pages(mapping, 0);
 	}
+
+	/*
+	 * Cleancache needs notification even if there are no pages or shadow
+	 * entries.
+	 */
+	truncate_inode_pages(mapping, 0);
 }
 EXPORT_SYMBOL(truncate_inode_pages_final);
 
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 5029f241908f..458acda96f20 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -33,6 +33,8 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 	void *page_kaddr;
 	int ret;
 	struct page *page;
+	pgoff_t offset, max_off;
+	struct inode *inode;
 
 	if (!*pagep) {
 		ret = -ENOMEM;
@@ -48,7 +50,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 
 		/* fallback to copy_from_user outside mmap_sem */
 		if (unlikely(ret)) {
-			ret = -EFAULT;
+			ret = -ENOENT;
 			*pagep = page;
 			/* don't free the page */
 			goto out;
@@ -73,8 +75,17 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 	if (dst_vma->vm_flags & VM_WRITE)
 		_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
 
-	ret = -EEXIST;
 	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
+	if (dst_vma->vm_file) {
+		/* the shmem MAP_PRIVATE case requires checking the i_size */
+		inode = dst_vma->vm_file->f_inode;
+		offset = linear_page_index(dst_vma, dst_addr);
+		max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+		ret = -EFAULT;
+		if (unlikely(offset >= max_off))
+			goto out_release_uncharge_unlock;
+	}
+	ret = -EEXIST;
 	if (!pte_none(*dst_pte))
 		goto out_release_uncharge_unlock;
 
@@ -108,11 +119,22 @@ static int mfill_zeropage_pte(struct mm_struct *dst_mm,
 	pte_t _dst_pte, *dst_pte;
 	spinlock_t *ptl;
 	int ret;
+	pgoff_t offset, max_off;
+	struct inode *inode;
 
 	_dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr),
 					 dst_vma->vm_page_prot));
-	ret = -EEXIST;
 	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
+	if (dst_vma->vm_file) {
+		/* the shmem MAP_PRIVATE case requires checking the i_size */
+		inode = dst_vma->vm_file->f_inode;
+		offset = linear_page_index(dst_vma, dst_addr);
+		max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+		ret = -EFAULT;
+		if (unlikely(offset >= max_off))
+			goto out_unlock;
+	}
+	ret = -EEXIST;
 	if (!pte_none(*dst_pte))
 		goto out_unlock;
 	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
@@ -205,8 +227,9 @@ retry:
 		if (!dst_vma || !is_vm_hugetlb_page(dst_vma))
 			goto out_unlock;
 		/*
-		 * Only allow __mcopy_atomic_hugetlb on userfaultfd
-		 * registered ranges.
+		 * Check the vma is registered in uffd, this is
+		 * required to enforce the VM_MAYWRITE check done at
+		 * uffd registration time.
 		 */
 		if (!dst_vma->vm_userfaultfd_ctx.ctx)
 			goto out_unlock;
@@ -274,7 +297,7 @@ retry:
 
 		cond_resched();
 
-		if (unlikely(err == -EFAULT)) {
+		if (unlikely(err == -ENOENT)) {
 			up_read(&dst_mm->mmap_sem);
 			BUG_ON(!page);
 
@@ -380,7 +403,17 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
 {
 	ssize_t err;
 
-	if (vma_is_anonymous(dst_vma)) {
+	/*
+	 * The normal page fault path for a shmem will invoke the
+	 * fault, fill the hole in the file and COW it right away. The
+	 * result generates plain anonymous memory. So when we are
+	 * asked to fill an hole in a MAP_PRIVATE shmem mapping, we'll
+	 * generate anonymous memory directly without actually filling
+	 * the hole. For the MAP_PRIVATE case the robustness check
+	 * only happens in the pagetable (to verify it's still none)
+	 * and not in the radix tree.
+	 */
+	if (!(dst_vma->vm_flags & VM_SHARED)) {
 		if (!zeropage)
 			err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma,
 					       dst_addr, src_addr, page);
@@ -449,13 +482,9 @@ retry:
 	if (!dst_vma)
 		goto out_unlock;
 	/*
-	 * Be strict and only allow __mcopy_atomic on userfaultfd
-	 * registered ranges to prevent userland errors going
-	 * unnoticed. As far as the VM consistency is concerned, it
-	 * would be perfectly safe to remove this check, but there's
-	 * no useful usage for __mcopy_atomic ouside of userfaultfd
-	 * registered ranges. This is after all why these are ioctls
-	 * belonging to the userfaultfd and not syscalls.
+	 * Check the vma is registered in uffd, this is required to
+	 * enforce the VM_MAYWRITE check done at uffd registration
+	 * time.
 	 */
 	if (!dst_vma->vm_userfaultfd_ctx.ctx)
 		goto out_unlock;
@@ -489,7 +518,8 @@ retry:
 	 * dst_vma.
 	 */
 	err = -ENOMEM;
-	if (vma_is_anonymous(dst_vma) && unlikely(anon_vma_prepare(dst_vma)))
+	if (!(dst_vma->vm_flags & VM_SHARED) &&
+	    unlikely(anon_vma_prepare(dst_vma)))
 		goto out_unlock;
 
 	while (src_addr < src_start + len) {
@@ -530,7 +560,7 @@ retry:
 				       src_addr, &page, zeropage);
 		cond_resched();
 
-		if (unlikely(err == -EFAULT)) {
+		if (unlikely(err == -ENOENT)) {
 			void *page_kaddr;
 
 			up_read(&dst_mm->mmap_sem);