Merge tag 'v4.18.20' into dev-4.18dev-4.18

This is the 4.18.20 stable release

Signed-off-by: Joel Stanley <joel@jms.id.au>

4 files changed, 53 insertions, 9 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5b38fbef9441..bf15bd78846b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3240,7 +3240,7 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte)
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			    struct vm_area_struct *vma)
 {
-	pte_t *src_pte, *dst_pte, entry;
+	pte_t *src_pte, *dst_pte, entry, dst_entry;
 	struct page *ptepage;
 	unsigned long addr;
 	int cow;
@@ -3268,15 +3268,30 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			break;
 		}
 
-		/* If the pagetables are shared don't copy or take references */
-		if (dst_pte == src_pte)
+		/*
+		 * If the pagetables are shared don't copy or take references.
+		 * 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.
+		 */
+		dst_entry = huge_ptep_get(dst_pte);
+		if ((dst_pte == src_pte) || !huge_pte_none(dst_entry))
 			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);
-		if (huge_pte_none(entry)) { /* skip none entry */
+		dst_entry = huge_ptep_get(dst_pte);
+		if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) {
+			/*
+			 * Skip if src entry none.  Also, skip in the
+			 * unlikely case dst entry !none as this implies
+			 * sharing with another vma.
+			 */
 			;
 		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
 				    is_hugetlb_entry_hwpoisoned(entry))) {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 785252397e35..03fd2d08c361 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -587,6 +587,7 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 	for (i = 0; i < sections_to_remove; i++) {
 		unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
 
+		cond_resched();
 		ret = __remove_section(zone, __pfn_to_section(pfn), map_offset,
 				altmap);
 		map_offset = 0;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 01f1a14facc4..73fd00d2df8c 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2046,8 +2046,36 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		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);
+			/*
+			 * We cannot invoke reclaim if __GFP_THISNODE
+			 * is set. Invoking reclaim with
+			 * __GFP_THISNODE set, would cause THP
+			 * allocations to trigger heavy swapping
+			 * despite there may be tons of free memory
+			 * (including potentially plenty of THP
+			 * already available in the buddy) on all the
+			 * other NUMA nodes.
+			 *
+			 * At most we could invoke compaction when
+			 * __GFP_THISNODE is set (but we would need to
+			 * refrain from invoking reclaim even if
+			 * compaction returned COMPACT_SKIPPED because
+			 * there wasn't not enough memory to succeed
+			 * compaction). For now just avoid
+			 * __GFP_THISNODE instead of limiting the
+			 * allocation path to a strict and single
+			 * compaction invocation.
+			 *
+			 * Supposedly if direct reclaim was enabled by
+			 * the caller, the app prefers THP regardless
+			 * of the node it comes from so this would be
+			 * more desiderable behavior than only
+			 * providing THP originated from the local
+			 * node in such case.
+			 */
+			if (!(gfp & __GFP_DIRECT_RECLAIM))
+				gfp |= __GFP_THISNODE;
+			page = __alloc_pages_node(hpage_node, gfp, order);
 			goto out;
 		}
 	}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 18185ae4f223..f8b846b5108c 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2837,7 +2837,7 @@ static struct swap_info_struct *alloc_swap_info(void)
 	unsigned int type;
 	int i;
 
-	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	p = kvzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p)
 		return ERR_PTR(-ENOMEM);
 
@@ -2848,7 +2848,7 @@ static struct swap_info_struct *alloc_swap_info(void)
 	}
 	if (type >= MAX_SWAPFILES) {
 		spin_unlock(&swap_lock);
-		kfree(p);
+		kvfree(p);
 		return ERR_PTR(-EPERM);
 	}
 	if (type >= nr_swapfiles) {
@@ -2862,7 +2862,7 @@ static struct swap_info_struct *alloc_swap_info(void)
 		smp_wmb();
 		nr_swapfiles++;
 	} else {
-		kfree(p);
+		kvfree(p);
 		p = swap_info[type];
 		/*
 		 * Do not memset this entry: a racing procfs swap_next()