io_uring: store SCM state in io_fixed_file->file_ptr

A previous commit removed SCM accounting for non-unix sockets, as those
are the only ones that can cause a fixed file reference. While that is
true, it also means we're now dereferencing the file as part of the
workqueue driven __io_sqe_files_unregister() after the process has
exited. This isn't safe for SCM files, as unix gc may have already
reaped them when the process exited. KASAN complains about this:

[   12.307040] Freed by task 0:
[   12.307592]  kasan_save_stack+0x28/0x4c
[   12.308318]  kasan_set_track+0x28/0x38
[   12.309049]  kasan_set_free_info+0x24/0x44
[   12.309890]  ____kasan_slab_free+0x108/0x11c
[   12.310739]  __kasan_slab_free+0x14/0x1c
[   12.311482]  slab_free_freelist_hook+0xd4/0x164
[   12.312382]  kmem_cache_free+0x100/0x1dc
[   12.313178]  file_free_rcu+0x58/0x74
[   12.313864]  rcu_core+0x59c/0x7c0
[   12.314675]  rcu_core_si+0xc/0x14
[   12.315496]  _stext+0x30c/0x414
[   12.316287]
[   12.316687] Last potentially related work creation:
[   12.317885]  kasan_save_stack+0x28/0x4c
[   12.318845]  __kasan_record_aux_stack+0x9c/0xb0
[   12.319976]  kasan_record_aux_stack_noalloc+0x10/0x18
[   12.321268]  call_rcu+0x50/0x35c
[   12.322082]  __fput+0x2fc/0x324
[   12.322873]  ____fput+0xc/0x14
[   12.323644]  task_work_run+0xac/0x10c
[   12.324561]  do_notify_resume+0x37c/0xe74
[   12.325420]  el0_svc+0x5c/0x68
[   12.326050]  el0t_64_sync_handler+0xb0/0x12c
[   12.326918]  el0t_64_sync+0x164/0x168
[   12.327657]
[   12.327976] Second to last potentially related work creation:
[   12.329134]  kasan_save_stack+0x28/0x4c
[   12.329864]  __kasan_record_aux_stack+0x9c/0xb0
[   12.330735]  kasan_record_aux_stack+0x10/0x18
[   12.331576]  task_work_add+0x34/0xf0
[   12.332284]  fput_many+0x11c/0x134
[   12.332960]  fput+0x10/0x94
[   12.333524]  __scm_destroy+0x80/0x84
[   12.334213]  unix_destruct_scm+0xc4/0x144
[   12.334948]  skb_release_head_state+0x5c/0x6c
[   12.335696]  skb_release_all+0x14/0x38
[   12.336339]  __kfree_skb+0x14/0x28
[   12.336928]  kfree_skb_reason+0xf4/0x108
[   12.337604]  unix_gc+0x1e8/0x42c
[   12.338154]  unix_release_sock+0x25c/0x2dc
[   12.338895]  unix_release+0x58/0x78
[   12.339531]  __sock_release+0x68/0xec
[   12.340170]  sock_close+0x14/0x20
[   12.340729]  __fput+0x18c/0x324
[   12.341254]  ____fput+0xc/0x14
[   12.341763]  task_work_run+0xac/0x10c
[   12.342367]  do_notify_resume+0x37c/0xe74
[   12.343086]  el0_svc+0x5c/0x68
[   12.343510]  el0t_64_sync_handler+0xb0/0x12c
[   12.344086]  el0t_64_sync+0x164/0x168

We have an extra bit we can use in file_ptr on 64-bit, use that to store
whether this file is SCM'ed or not, avoiding the need to look at the
file contents itself. This does mean that 32-bit will be stuck with SCM
for all registered files, just like 64-bit did before the referenced
commit.

Fixes: 1f59bc0f ("io_uring: don't scm-account for non af_unix sockets")
Signed-off-by: Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

@@ -223,6 +223,23 @@ struct io_overflow_cqe {
 	struct list_head list;
 };
 
+/*
+ * FFS_SCM is only available on 64-bit archs, for 32-bit we just define it as 0
+ * and define IO_URING_SCM_ALL. For this case, we use SCM for all files as we
+ * can't safely always dereference the file when the task has exited and ring
+ * cleanup is done. If a file is tracked and part of SCM, then unix gc on
+ * process exit may reap it before __io_sqe_files_unregister() is run.
+ */
+#define FFS_NOWAIT		0x1UL
+#define FFS_ISREG		0x2UL
+#if defined(CONFIG_64BIT)
+#define FFS_SCM			0x4UL
+#else
+#define IO_URING_SCM_ALL
+#define FFS_SCM			0x0UL
+#endif
+#define FFS_MASK		~(FFS_NOWAIT|FFS_ISREG|FFS_SCM)
+
 struct io_fixed_file {
 	/* file * with additional FFS_* flags */
 	unsigned long file_ptr;
@@ -1236,12 +1253,16 @@ EXPORT_SYMBOL(io_uring_get_socket);
 #if defined(CONFIG_UNIX)
 static inline bool io_file_need_scm(struct file *filp)
 {
+#if defined(IO_URING_SCM_ALL)
+	return true;
+#else
 	return !!unix_get_socket(filp);
+#endif
 }
 #else
 static inline bool io_file_need_scm(struct file *filp)
 {
-	return 0;
+	return false;
 }
 #endif
 
@@ -1651,10 +1672,6 @@ static bool req_need_defer(struct io_kiocb *req, u32 seq)
 	return false;
 }
 
-#define FFS_NOWAIT		0x1UL
-#define FFS_ISREG		0x2UL
-#define FFS_MASK		~(FFS_NOWAIT|FFS_ISREG)
-
 static inline bool io_req_ffs_set(struct io_kiocb *req)
 {
 	return req->flags & REQ_F_FIXED_FILE;
@@ -3197,6 +3214,8 @@ static unsigned int io_file_get_flags(struct file *file)
 		res |= FFS_ISREG;
 	if (__io_file_supports_nowait(file, mode))
 		res |= FFS_NOWAIT;
+	if (io_file_need_scm(file))
+		res |= FFS_SCM;
 	return res;
 }
 
@@ -8478,14 +8497,17 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
 {
 	int i;
 
+#if !defined(IO_URING_SCM_ALL)
 	for (i = 0; i < ctx->nr_user_files; i++) {
 		struct file *file = io_file_from_index(ctx, i);
 
-		if (!file || io_file_need_scm(file))
+		if (!file)
+			continue;
+		if (io_fixed_file_slot(&ctx->file_table, i)->file_ptr & FFS_SCM)
 			continue;
-		io_fixed_file_slot(&ctx->file_table, i)->file_ptr = 0;
 		fput(file);
 	}
+#endif
 
 #if defined(CONFIG_UNIX)
 	if (ctx->ring_sock) {