Adding upstream version 4.19.269.upstream/4.19.269

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

6 files changed, 79 insertions, 41 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index f2e777003..e61ec2c88 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3140,7 +3140,7 @@ ssize_t generic_perform_write(struct file *file,
 		unsigned long offset;	/* Offset into pagecache page */
 		unsigned long bytes;	/* Bytes to write to page */
 		size_t copied;		/* Bytes copied from user */
-		void *fsdata;
+		void *fsdata = NULL;
 
 		offset = (pos & (PAGE_SIZE - 1));
 		bytes = min_t(unsigned long, PAGE_SIZE - offset,
diff --git a/mm/frame_vector.c b/mm/frame_vector.c
index c64dca6e2..7124410a0 100644
--- a/mm/frame_vector.c
+++ b/mm/frame_vector.c
@@ -37,7 +37,6 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	int ret = 0;
-	int err;
 	int locked;
 
 	if (nr_frames == 0)
@@ -72,32 +71,14 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
 		vec->is_pfns = false;
 		ret = get_user_pages_locked(start, nr_frames,
 			gup_flags, (struct page **)(vec->ptrs), &locked);
-		goto out;
+		if (likely(ret > 0))
+			goto out;
 	}
 
-	vec->got_ref = false;
-	vec->is_pfns = true;
-	do {
-		unsigned long *nums = frame_vector_pfns(vec);
-
-		while (ret < nr_frames && start + PAGE_SIZE <= vma->vm_end) {
-			err = follow_pfn(vma, start, &nums[ret]);
-			if (err) {
-				if (ret == 0)
-					ret = err;
-				goto out;
-			}
-			start += PAGE_SIZE;
-			ret++;
-		}
-		/*
-		 * We stop if we have enough pages or if VMA doesn't completely
-		 * cover the tail page.
-		 */
-		if (ret >= nr_frames || start < vma->vm_end)
-			break;
-		vma = find_vma_intersection(mm, start, start + 1);
-	} while (vma && vma->vm_flags & (VM_IO | VM_PFNMAP));
+	/* This used to (racily) return non-refcounted pfns. Let people know */
+	WARN_ONCE(1, "get_vaddr_frames() cannot follow VM_IO mapping");
+	vec->nr_frames = 0;
+
 out:
 	if (locked)
 		up_read(&mm->mmap_sem);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 45e874faf..47e98a572 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2116,11 +2116,11 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 		page = alloc_buddy_huge_page_with_mpol(h, vma, addr);
 		if (!page)
 			goto out_uncharge_cgroup;
+		spin_lock(&hugetlb_lock);
 		if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) {
 			SetPagePrivate(page);
 			h->resv_huge_pages--;
 		}
-		spin_lock(&hugetlb_lock);
 		list_move(&page->lru, &h->hugepage_activelist);
 		/* Fall through */
 	}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f3aa6e621..bc4c61dcf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4120,6 +4120,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 	unsigned int efd, cfd;
 	struct fd efile;
 	struct fd cfile;
+	struct dentry *cdentry;
 	const char *name;
 	char *endp;
 	int ret;
@@ -4171,6 +4172,16 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 		goto out_put_cfile;
 
 	/*
+	 * The control file must be a regular cgroup1 file. As a regular cgroup
+	 * file can't be renamed, it's safe to access its name afterwards.
+	 */
+	cdentry = cfile.file->f_path.dentry;
+	if (cdentry->d_sb->s_type != &cgroup_fs_type || !d_is_reg(cdentry)) {
+		ret = -EINVAL;
+		goto out_put_cfile;
+	}
+
+	/*
 	 * Determine the event callbacks and set them in @event.  This used
 	 * to be done via struct cftype but cgroup core no longer knows
 	 * about these events.  The following is crude but the whole thing
@@ -4178,7 +4189,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 	 *
 	 * DO NOT ADD NEW FILES.
 	 */
-	name = cfile.file->f_path.dentry->d_name.name;
+	name = cdentry->d_name.name;
 
 	if (!strcmp(name, "memory.usage_in_bytes")) {
 		event->register_event = mem_cgroup_usage_register_event;
@@ -4202,7 +4213,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 	 * automatically removed on cgroup destruction but the removal is
 	 * asynchronous, so take an extra ref on @css.
 	 */
-	cfile_css = css_tryget_online_from_dir(cfile.file->f_path.dentry->d_parent,
+	cfile_css = css_tryget_online_from_dir(cdentry->d_parent,
 					       &memory_cgrp_subsys);
 	ret = -EINVAL;
 	if (IS_ERR(cfile_css))
diff --git a/mm/migrate.c b/mm/migrate.c
index 76f8dedc0..171573613 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2359,13 +2359,14 @@ next:
 		migrate->dst[migrate->npages] = 0;
 		migrate->src[migrate->npages++] = mpfn;
 	}
-	arch_leave_lazy_mmu_mode();
-	pte_unmap_unlock(ptep - 1, ptl);
 
 	/* Only flush the TLB if we actually modified any entries */
 	if (unmapped)
 		flush_tlb_range(walk->vma, start, end);
 
+	arch_leave_lazy_mmu_mode();
+	pte_unmap_unlock(ptep - 1, ptl);
+
 	return 0;
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9c35403d9..1cffd4e1f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3779,6 +3779,30 @@ void fs_reclaim_release(gfp_t gfp_mask)
 EXPORT_SYMBOL_GPL(fs_reclaim_release);
 #endif
 
+/*
+ * Zonelists may change due to hotplug during allocation. Detect when zonelists
+ * have been rebuilt so allocation retries. Reader side does not lock and
+ * retries the allocation if zonelist changes. Writer side is protected by the
+ * embedded spin_lock.
+ */
+static DEFINE_SEQLOCK(zonelist_update_seq);
+
+static unsigned int zonelist_iter_begin(void)
+{
+	if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE))
+		return read_seqbegin(&zonelist_update_seq);
+
+	return 0;
+}
+
+static unsigned int check_retry_zonelist(unsigned int seq)
+{
+	if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE))
+		return read_seqretry(&zonelist_update_seq, seq);
+
+	return seq;
+}
+
 /* Perform direct synchronous page reclaim */
 static int
 __perform_reclaim(gfp_t gfp_mask, unsigned int order,
@@ -4084,6 +4108,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	int compaction_retries;
 	int no_progress_loops;
 	unsigned int cpuset_mems_cookie;
+	unsigned int zonelist_iter_cookie;
 	int reserve_flags;
 
 	/*
@@ -4094,11 +4119,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 				(__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
 		gfp_mask &= ~__GFP_ATOMIC;
 
-retry_cpuset:
+restart:
 	compaction_retries = 0;
 	no_progress_loops = 0;
 	compact_priority = DEF_COMPACT_PRIORITY;
 	cpuset_mems_cookie = read_mems_allowed_begin();
+	zonelist_iter_cookie = zonelist_iter_begin();
 
 	/*
 	 * The fast path uses conservative alloc_flags to succeed only until
@@ -4247,9 +4273,13 @@ retry:
 		goto retry;
 
 
-	/* Deal with possible cpuset update races before we start OOM killing */
-	if (check_retry_cpuset(cpuset_mems_cookie, ac))
-		goto retry_cpuset;
+	/*
+	 * Deal with possible cpuset update races or zonelist updates to avoid
+	 * a unnecessary OOM kill.
+	 */
+	if (check_retry_cpuset(cpuset_mems_cookie, ac) ||
+	    check_retry_zonelist(zonelist_iter_cookie))
+		goto restart;
 
 	/* Reclaim has failed us, start killing things */
 	page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
@@ -4269,9 +4299,13 @@ retry:
 	}
 
 nopage:
-	/* Deal with possible cpuset update races before we fail */
-	if (check_retry_cpuset(cpuset_mems_cookie, ac))
-		goto retry_cpuset;
+	/*
+	 * Deal with possible cpuset update races or zonelist updates to avoid
+	 * a unnecessary OOM kill.
+	 */
+	if (check_retry_cpuset(cpuset_mems_cookie, ac) ||
+	    check_retry_zonelist(zonelist_iter_cookie))
+		goto restart;
 
 	/*
 	 * Make sure that __GFP_NOFAIL request doesn't leak out and make sure
@@ -4569,6 +4603,18 @@ refill:
 		/* reset page count bias and offset to start of new frag */
 		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
 		offset = size - fragsz;
+		if (unlikely(offset < 0)) {
+			/*
+			 * The caller is trying to allocate a fragment
+			 * with fragsz > PAGE_SIZE but the cache isn't big
+			 * enough to satisfy the request, this may
+			 * happen in low memory conditions.
+			 * We don't release the cache page because
+			 * it could make memory pressure worse
+			 * so we simply return NULL here.
+			 */
+			return NULL;
+		}
 	}
 
 	nc->pagecnt_bias--;
@@ -5379,9 +5425,8 @@ static void __build_all_zonelists(void *data)
 	int nid;
 	int __maybe_unused cpu;
 	pg_data_t *self = data;
-	static DEFINE_SPINLOCK(lock);
 
-	spin_lock(&lock);
+	write_seqlock(&zonelist_update_seq);
 
 #ifdef CONFIG_NUMA
 	memset(node_load, 0, sizeof(node_load));
@@ -5414,7 +5459,7 @@ static void __build_all_zonelists(void *data)
 #endif
 	}
 
-	spin_unlock(&lock);
+	write_sequnlock(&zonelist_update_seq);
 }
 
 static noinline void __init