mm: slub: call WARN() when detecting a slab corruption

commit 3f6f32b
Author: Hyesoo Yu <[email protected]>
Date:   Wed Feb 26 17:12:01 2025 +0900

    mm: slub: call WARN() when detecting a slab corruption

    If a slab object is corrupted or an error occurs in its internal
    validation, continuing after restoration may cause other side effects.
    At this point, it is difficult to debug because the problem occurred in
    the past. It is useful to use WARN() to catch errors at the point of
    issue because WARN() could trigger panic for system debugging when
    panic_on_warn is enabled. WARN() is added where to detect the error on
    slab_err and object_err.

    It makes sense to only do the WARN() after printing the logs. slab_err
    is splited to __slab_err that calls the WARN() and it is called after
    printing logs.

    Signed-off-by: Hyesoo Yu <[email protected]>
    Reviewed-by: Harry Yoo <[email protected]>
    Signed-off-by: Vlastimil Babka <[email protected]>

JIRA: https://issues.redhat.com/browse/RHEL-77742
Signed-off-by: Nico Pache <[email protected]>

Author: PacheNico

mm/slub.c

@@ -1026,7 +1026,7 @@ static void slab_bug(struct kmem_cache *s, char *fmt, ...)
 	vaf.fmt = fmt;
 	vaf.va = &args;
 	pr_err("=============================================================================\n");
-	pr_err("BUG %s (%s): %pV\n", s->name, print_tainted(), &vaf);
+	pr_err("BUG %s (%s): %pV\n", s ? s->name : "<unknown>", print_tainted(), &vaf);
 	pr_err("-----------------------------------------------------------------------------\n\n");
 	va_end(args);
 }
@@ -1085,8 +1085,6 @@ static void print_trailer(struct kmem_cache *s, struct slab *slab, u8 *p)
 		/* Beginning of the filler is the free pointer */
 		print_section(KERN_ERR, "Padding  ", p + off,
 			      size_from_object(s) - off);
-
-	dump_stack();
 }
 
 static void object_err(struct kmem_cache *s, struct slab *slab,
@@ -1098,6 +1096,8 @@ static void object_err(struct kmem_cache *s, struct slab *slab,
 	slab_bug(s, "%s", reason);
 	print_trailer(s, slab, object);
 	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
+
+	WARN_ON(1);
 }
 
 static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab,
@@ -1114,6 +1114,17 @@ static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab,
 	return false;
 }
 
+static void __slab_err(struct slab *slab)
+{
+	if (slab_in_kunit_test())
+		return;
+
+	print_slab_info(slab);
+	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
+
+	WARN_ON(1);
+}
+
 static __printf(3, 4) void slab_err(struct kmem_cache *s, struct slab *slab,
 			const char *fmt, ...)
 {
@@ -1127,9 +1138,7 @@ static __printf(3, 4) void slab_err(struct kmem_cache *s, struct slab *slab,
 	vsnprintf(buf, sizeof(buf), fmt, args);
 	va_end(args);
 	slab_bug(s, "%s", buf);
-	print_slab_info(slab);
-	dump_stack();
-	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
+	__slab_err(slab);
 }
 
 static void init_object(struct kmem_cache *s, void *object, u8 val)
@@ -1302,9 +1311,10 @@ slab_pad_check(struct kmem_cache *s, struct slab *slab)
 	while (end > fault && end[-1] == POISON_INUSE)
 		end--;
 
-	slab_err(s, slab, "Padding overwritten. 0x%p-0x%p @offset=%tu",
-			fault, end - 1, fault - start);
+	slab_bug(s, "Padding overwritten. 0x%p-0x%p @offset=%tu",
+		 fault, end - 1, fault - start);
 	print_section(KERN_ERR, "Padding ", pad, remainder);
+	__slab_err(slab);
 
 	restore_bytes(s, "slab padding", POISON_INUSE, fault, end);
 }
@@ -1620,12 +1630,12 @@ static inline int free_consistency_checks(struct kmem_cache *s,
 			slab_err(s, slab, "Attempt to free object(0x%p) outside of slab",
 				 object);
 		} else if (!slab->slab_cache) {
-			pr_err("SLUB <none>: no slab for object 0x%p.\n",
-			       object);
-			dump_stack();
-		} else
+			slab_err(NULL, slab, "No slab cache for object 0x%p",
+				 object);
+		} else {
 			object_err(s, slab, object,
-					"page slab pointer corrupt.");
+				   "page slab pointer corrupt.");
+		}
 		return 0;
 	}
 	return 1;
@@ -5570,14 +5580,14 @@ static int calculate_sizes(struct kmem_cache_args *args, struct kmem_cache *s)
 	return !!oo_objects(s->oo);
 }
 
-static void list_slab_objects(struct kmem_cache *s, struct slab *slab,
-			      const char *text)
+static void list_slab_objects(struct kmem_cache *s, struct slab *slab)
 {
 #ifdef CONFIG_SLUB_DEBUG
 	void *addr = slab_address(slab);
 	void *p;
 
-	slab_err(s, slab, text, s->name);
+	if (!slab_add_kunit_errors())
+		slab_bug(s, "Objects remaining on __kmem_cache_shutdown()");
 
 	spin_lock(&object_map_lock);
 	__fill_map(object_map, s, slab);
@@ -5592,6 +5602,8 @@ static void list_slab_objects(struct kmem_cache *s, struct slab *slab,
 		}
 	}
 	spin_unlock(&object_map_lock);
+
+	__slab_err(slab);
 #endif
 }
 
@@ -5612,8 +5624,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 			remove_partial(n, slab);
 			list_add(&slab->slab_list, &discard);
 		} else {
-			list_slab_objects(s, slab,
-			  "Objects remaining in %s on __kmem_cache_shutdown()");
+			list_slab_objects(s, slab);
 		}
 	}
 	spin_unlock_irq(&n->list_lock);