Merge tag 'v5.15.72' into 5.15-2.1.x-imx

This is the 5.15.72 stable release

Signed-off-by: Daiane Angolini <daiane.angolini@foundries.io>

6 files changed, 81 insertions, 20 deletions

diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c
index 70a5cb977ed0..e670fb6b1126 100644
--- a/mm/damon/dbgfs.c
+++ b/mm/damon/dbgfs.c
@@ -443,6 +443,7 @@ static int dbgfs_rm_context(char *name)
 	struct dentry *root, *dir, **new_dirs;
 	struct damon_ctx **new_ctxs;
 	int i, j;
+	int ret = 0;
 
 	if (damon_nr_running_ctxs())
 		return -EBUSY;
@@ -457,14 +458,16 @@ static int dbgfs_rm_context(char *name)
 
 	new_dirs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_dirs),
 			GFP_KERNEL);
-	if (!new_dirs)
-		return -ENOMEM;
+	if (!new_dirs) {
+		ret = -ENOMEM;
+		goto out_dput;
+	}
 
 	new_ctxs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_ctxs),
 			GFP_KERNEL);
 	if (!new_ctxs) {
-		kfree(new_dirs);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out_new_dirs;
 	}
 
 	for (i = 0, j = 0; i < dbgfs_nr_ctxs; i++) {
@@ -484,7 +487,13 @@ static int dbgfs_rm_context(char *name)
 	dbgfs_ctxs = new_ctxs;
 	dbgfs_nr_ctxs--;
 
-	return 0;
+	goto out_dput;
+
+out_new_dirs:
+	kfree(new_dirs);
+out_dput:
+	dput(dir);
+	return ret;
 }
 
 static ssize_t dbgfs_rm_context_write(struct file *file,
diff --git a/mm/madvise.c b/mm/madvise.c
index 882767d58c27..6c099f8bb8e6 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -436,8 +436,11 @@ regular_page:
 			continue;
 		}
 
-		/* Do not interfere with other mappings of this page */
-		if (page_mapcount(page) != 1)
+		/*
+		 * Do not interfere with other mappings of this page and
+		 * non-LRU page.
+		 */
+		if (!PageLRU(page) || page_mapcount(page) != 1)
 			continue;
 
 		VM_BUG_ON_PAGE(PageTransCompound(page), page);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index c71135edd0a1..31db222b6deb 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -700,6 +700,9 @@ static int kill_accessing_process(struct task_struct *p, unsigned long pfn,
 	};
 	priv.tk.tsk = p;
 
+	if (!p->mm)
+		return -EFAULT;
+
 	mmap_read_lock(p->mm);
 	ret = walk_page_range(p->mm, 0, TASK_SIZE, &hwp_walk_ops,
 			      (void *)&priv);
diff --git a/mm/migrate.c b/mm/migrate.c
index afb944b600fe..7da052c6cf1e 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2422,13 +2422,14 @@ 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 61d7967897ce..a71722b4e464 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4581,6 +4581,30 @@ 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 unsigned long
 __perform_reclaim(gfp_t gfp_mask, unsigned int order,
@@ -4888,6 +4912,7 @@ __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;
 
 	/*
@@ -4898,11 +4923,12 @@ __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
@@ -5061,9 +5087,13 @@ 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);
@@ -5083,9 +5113,13 @@ 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
@@ -5566,6 +5600,18 @@ 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--;
@@ -6367,9 +6413,8 @@ 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));
@@ -6402,7 +6447,7 @@ static void __build_all_zonelists(void *data)
 #endif
 	}
 
-	spin_unlock(&lock);
+	write_sequnlock(&zonelist_update_seq);
 }
 
 static noinline void __init
diff --git a/mm/secretmem.c b/mm/secretmem.c
index 14f49c0aa66e..d1986ce2e7c7 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -283,7 +283,7 @@ static int secretmem_init(void)
 
 	secretmem_mnt = kern_mount(&secretmem_fs);
 	if (IS_ERR(secretmem_mnt))
-		ret = PTR_ERR(secretmem_mnt);
+		return PTR_ERR(secretmem_mnt);
 
 	/* prevent secretmem mappings from ever getting PROT_EXEC */
 	secretmem_mnt->mnt_flags |= MNT_NOEXEC;