Merging upstream version 5.10.216.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

13 files changed, 122 insertions, 49 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index b58021666..77ca5e6f4 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2466,16 +2466,11 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 		unsigned int alloc_flags, const struct alloc_context *ac,
 		enum compact_priority prio, struct page **capture)
 {
-	int may_perform_io = gfp_mask & __GFP_IO;
 	struct zoneref *z;
 	struct zone *zone;
 	enum compact_result rc = COMPACT_SKIPPED;
 
-	/*
-	 * Check if the GFP flags allow compaction - GFP_NOIO is really
-	 * tricky context because the migration might require IO
-	 */
-	if (!may_perform_io)
+	if (!gfp_compaction_allowed(gfp_mask))
 		return COMPACT_SKIPPED;
 
 	trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 81949f6d2..02b7c8f9b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5108,12 +5108,13 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	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, add = -1;
+	long chg, add = -1;
 	struct hstate *h = hstate_inode(inode);
 	struct hugepage_subpool *spool = subpool_inode(inode);
 	struct resv_map *resv_map;
@@ -5123,7 +5124,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 	/* This should never happen */
 	if (from > to) {
 		VM_WARN(1, "%s called with a negative range\n", __func__);
-		return -EINVAL;
+		return false;
 	}
 
 	/*
@@ -5132,7 +5133,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 	 * without using reserves
 	 */
 	if (vm_flags & VM_NORESERVE)
-		return 0;
+		return true;
 
 	/*
 	 * Shared mappings base their reservation on the number of pages that
@@ -5154,7 +5155,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 		/* Private mapping. */
 		resv_map = resv_map_alloc();
 		if (!resv_map)
-			return -ENOMEM;
+			return false;
 
 		chg = to - from;
 
@@ -5162,18 +5163,12 @@ 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;
-	}
-
-	ret = hugetlb_cgroup_charge_cgroup_rsvd(
-		hstate_index(h), chg * pages_per_huge_page(h), &h_cg);
 
-	if (ret < 0) {
-		ret = -ENOMEM;
+	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
@@ -5188,19 +5183,15 @@ 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;
+	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) {
+	if (hugetlb_acct_memory(h, gbl_reserve) < 0)
 		goto out_put_pages;
-	}
 
 	/*
 	 * Account for the reservations made. Shared mappings record regions
@@ -5218,7 +5209,6 @@ int hugetlb_reserve_pages(struct inode *inode,
 
 		if (unlikely(add < 0)) {
 			hugetlb_acct_memory(h, -gbl_reserve);
-			ret = add;
 			goto out_put_pages;
 		} else if (unlikely(chg > add)) {
 			/*
@@ -5251,7 +5241,8 @@ int hugetlb_reserve_pages(struct inode *inode,
 			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);
@@ -5267,7 +5258,7 @@ out_err:
 			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,
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index f320ff02c..dba293629 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1075,7 +1075,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 				unmap_success = false;
 			}
 		} else {
-			unmap_success = try_to_unmap(p, ttu);
+			unmap_success = try_to_unmap(hpage, ttu);
 		}
 	}
 	if (!unmap_success)
diff --git a/mm/memory.c b/mm/memory.c
index 1d101aeae..218300368 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4934,6 +4934,10 @@ int follow_phys(struct vm_area_struct *vma,
 		goto out;
 	pte = *ptep;
 
+	/* Never return PFNs of anon folios in COW mappings. */
+	if (vm_normal_page(vma, address, pte))
+		goto unlock;
+
 	if ((flags & FOLL_WRITE) && !pte_write(pte))
 		goto unlock;
 
diff --git a/mm/memtest.c b/mm/memtest.c
index f53ace709..d407373f2 100644
--- a/mm/memtest.c
+++ b/mm/memtest.c
@@ -46,10 +46,10 @@ static void __init memtest(u64 pattern, phys_addr_t start_phys, phys_addr_t size
 	last_bad = 0;
 
 	for (p = start; p < end; p++)
-		*p = pattern;
+		WRITE_ONCE(*p, pattern);
 
 	for (p = start; p < end; p++, start_phys_aligned += incr) {
-		if (*p == pattern)
+		if (READ_ONCE(*p) == pattern)
 			continue;
 		if (start_phys_aligned == last_bad + incr) {
 			last_bad += incr;
diff --git a/mm/migrate.c b/mm/migrate.c
index fcb7eb6a6..c0a8f3c9e 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -447,8 +447,12 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	if (PageSwapBacked(page)) {
 		__SetPageSwapBacked(newpage);
 		if (PageSwapCache(page)) {
+			int i;
+
 			SetPageSwapCache(newpage);
-			set_page_private(newpage, page_private(page));
+			for (i = 0; i < (1 << compound_order(page)); i++)
+				set_page_private(newpage + i,
+						 page_private(page + i));
 		}
 	} else {
 		VM_BUG_ON_PAGE(PageSwapCache(page), page);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index eb34d204d..e8d7d3c2b 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1524,7 +1524,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc)
 	 */
 	dtc->wb_thresh = __wb_calc_thresh(dtc);
 	dtc->wb_bg_thresh = dtc->thresh ?
-		div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
+		div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
 
 	/*
 	 * In order to avoid the stacked BDI deadlock we need
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 124ab9324..ed6660104 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4644,6 +4644,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 						struct alloc_context *ac)
 {
 	bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
+	bool can_compact = gfp_compaction_allowed(gfp_mask);
 	const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER;
 	struct page *page = NULL;
 	unsigned int alloc_flags;
@@ -4709,7 +4710,7 @@ restart:
 	 * Don't try this for allocations that are allowed to ignore
 	 * watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen.
 	 */
-	if (can_direct_reclaim &&
+	if (can_direct_reclaim && can_compact &&
 			(costly_order ||
 			   (order > 0 && ac->migratetype != MIGRATE_MOVABLE))
 			&& !gfp_pfmemalloc_allowed(gfp_mask)) {
@@ -4806,9 +4807,10 @@ retry:
 
 	/*
 	 * Do not retry costly high order allocations unless they are
-	 * __GFP_RETRY_MAYFAIL
+	 * __GFP_RETRY_MAYFAIL and we can compact
 	 */
-	if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL))
+	if (costly_order && (!can_compact ||
+			     !(gfp_mask & __GFP_RETRY_MAYFAIL)))
 		goto nopage;
 
 	if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
@@ -4821,7 +4823,7 @@ retry:
 	 * implementation of the compaction depends on the sufficient amount
 	 * of free memory (see __compaction_suitable)
 	 */
-	if (did_some_progress > 0 &&
+	if (did_some_progress > 0 && can_compact &&
 			should_compact_retry(ac, order, alloc_flags,
 				compact_result, &compact_priority,
 				&compaction_retries))
diff --git a/mm/sparse.c b/mm/sparse.c
index 33406ea2e..db0a7c537 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -810,6 +810,13 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 		unsigned long section_nr = pfn_to_section_nr(pfn);
 
 		/*
+		 * Mark the section invalid so that valid_section()
+		 * return false. This prevents code from dereferencing
+		 * ms->usage array.
+		 */
+		ms->section_mem_map &= ~SECTION_HAS_MEM_MAP;
+
+		/*
 		 * When removing an early section, the usage map is kept (as the
 		 * usage maps of other sections fall into the same page). It
 		 * will be re-used when re-adding the section - which is then no
@@ -817,16 +824,10 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 		 * was allocated during boot.
 		 */
 		if (!PageReserved(virt_to_page(ms->usage))) {
-			kfree(ms->usage);
-			ms->usage = NULL;
+			kfree_rcu(ms->usage, rcu);
+			WRITE_ONCE(ms->usage, NULL);
 		}
 		memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
-		/*
-		 * Mark the section invalid so that valid_section()
-		 * return false. This prevents code from dereferencing
-		 * ms->usage array.
-		 */
-		ms->section_mem_map &= ~SECTION_HAS_MEM_MAP;
 	}
 
 	/*
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 86ade667a..4ca1d04d8 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1271,6 +1271,11 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p,
 }
 
 /*
+ * Note that when only holding the PTL, swapoff might succeed immediately
+ * after freeing a swap entry. Therefore, immediately after
+ * __swap_entry_free(), the swap info might become stale and should not
+ * be touched without a prior get_swap_device().
+ *
  * Check whether swap entry is valid in the swap device.  If so,
  * return pointer to swap_info_struct, and keep the swap entry valid
  * via preventing the swap device from being swapoff, until
@@ -1797,13 +1802,19 @@ int free_swap_and_cache(swp_entry_t entry)
 	if (non_swap_entry(entry))
 		return 1;
 
-	p = _swap_info_get(entry);
+	p = get_swap_device(entry);
 	if (p) {
+		if (WARN_ON(data_race(!p->swap_map[swp_offset(entry)]))) {
+			put_swap_device(p);
+			return 0;
+		}
+
 		count = __swap_entry_free(p, entry);
 		if (count == SWAP_HAS_CACHE &&
 		    !swap_page_trans_huge_swapped(p, entry))
 			__try_to_reclaim_swap(p, swp_offset(entry),
 					      TTRS_UNMAPPED | TTRS_FULL);
+		put_swap_device(p);
 	}
 	return p != NULL;
 }
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 078d95cd3..c28ff36f5 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -209,6 +209,7 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
 					      unsigned long dst_start,
 					      unsigned long src_start,
 					      unsigned long len,
+					      bool *mmap_changing,
 					      bool zeropage)
 {
 	int vm_alloc_shared = dst_vma->vm_flags & VM_SHARED;
@@ -329,6 +330,15 @@ retry:
 				goto out;
 			}
 			mmap_read_lock(dst_mm);
+			/*
+			 * If memory mappings are changing because of non-cooperative
+			 * operation (e.g. mremap) running in parallel, bail out and
+			 * request the user to retry later
+			 */
+			if (mmap_changing && READ_ONCE(*mmap_changing)) {
+				err = -EAGAIN;
+				break;
+			}
 
 			dst_vma = NULL;
 			goto retry;
@@ -410,6 +420,7 @@ extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
 				      unsigned long dst_start,
 				      unsigned long src_start,
 				      unsigned long len,
+				      bool *mmap_changing,
 				      bool zeropage);
 #endif /* CONFIG_HUGETLB_PAGE */
 
@@ -529,7 +540,8 @@ retry:
 	 */
 	if (is_vm_hugetlb_page(dst_vma))
 		return  __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start,
-						src_start, len, zeropage);
+					       src_start, len, mmap_changing,
+					       zeropage);
 
 	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
 		goto out_unlock;
diff --git a/mm/util.c b/mm/util.c
index 25bfda774..7fd3c2bb3 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -686,6 +686,56 @@ static inline void *__page_rmapping(struct page *page)
 	return (void *)mapping;
 }
 
+/**
+ * __vmalloc_array - allocate memory for a virtually contiguous array.
+ * @n: number of elements.
+ * @size: element size.
+ * @flags: the type of memory to allocate (see kmalloc).
+ */
+void *__vmalloc_array(size_t n, size_t size, gfp_t flags)
+{
+	size_t bytes;
+
+	if (unlikely(check_mul_overflow(n, size, &bytes)))
+		return NULL;
+	return __vmalloc(bytes, flags);
+}
+EXPORT_SYMBOL(__vmalloc_array);
+
+/**
+ * vmalloc_array - allocate memory for a virtually contiguous array.
+ * @n: number of elements.
+ * @size: element size.
+ */
+void *vmalloc_array(size_t n, size_t size)
+{
+	return __vmalloc_array(n, size, GFP_KERNEL);
+}
+EXPORT_SYMBOL(vmalloc_array);
+
+/**
+ * __vcalloc - allocate and zero memory for a virtually contiguous array.
+ * @n: number of elements.
+ * @size: element size.
+ * @flags: the type of memory to allocate (see kmalloc).
+ */
+void *__vcalloc(size_t n, size_t size, gfp_t flags)
+{
+	return __vmalloc_array(n, size, flags | __GFP_ZERO);
+}
+EXPORT_SYMBOL(__vcalloc);
+
+/**
+ * vcalloc - allocate and zero memory for a virtually contiguous array.
+ * @n: number of elements.
+ * @size: element size.
+ */
+void *vcalloc(size_t n, size_t size)
+{
+	return __vmalloc_array(n, size, GFP_KERNEL | __GFP_ZERO);
+}
+EXPORT_SYMBOL(vcalloc);
+
 /* Neutral page->mapping pointer to address_space or anon_vma or other */
 void *page_rmapping(struct page *page)
 {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 51ccd80e7..e2b8cee1d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2546,7 +2546,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 /* Use reclaim/compaction for costly allocs or under memory pressure */
 static bool in_reclaim_compaction(struct scan_control *sc)
 {
-	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
+	if (gfp_compaction_allowed(sc->gfp_mask) && sc->order &&
 			(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
 			 sc->priority < DEF_PRIORITY - 2))
 		return true;
@@ -2873,6 +2873,9 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
 	unsigned long watermark;
 	enum compact_result suitable;
 
+	if (!gfp_compaction_allowed(sc->gfp_mask))
+		return false;
+
 	suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx);
 	if (suitable == COMPACT_SUCCESS)
 		/* Allocation should succeed already. Don't reclaim. */