io_uring-5.11-2021-01-01

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl/vOCwQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpqA7D/9AyFvg16KEgfYCN2OYXU5jyphu7sCCb8Cx
 PJ4H+Lf7fWki+/yFdXLxQnuBMGEOYWqtEIPN9CnO/I1ixzOoNugxiFAyerhd/Noh
 COg2EUsUrWq/zobYP60wN9pBPnW6EHTnFVA02kMVKunm4d5O5DZWPXy5BwA9yU3u
 dE9LoYDjFiaahogi3x+EmYStexxT0FB0d5WTONA7qSFrskeNbyVaYy8mY09jPynG
 IbG41fv2n0Zwlcx4XDCebsZ1+08rAGZFhwiq8VBhPNiz7sOud9jW7rRFHXR2FVoo
 DsW2npiYHVvOYqkl1HjXw5Mo6p8UKrDEDAIS7OOAHXM9Lz2/YGS9h9ogROccBta2
 5er12VaahIEiH05KtxpGv/q+vyJK7Gdqg0jSuSzKHSdSpTS10Ejh82Xo2V6lRedb
 gP03ZiDZjLtvh8F5hrWTJqPTtnFDRkY/I7R3WP1Ga7mqajFhpFDMvjvyEMMBCz+K
 KGjMfahNo2nzc9nu5M1VjX42tz5VxKjA3N2netxBfDMVB/GpGcQ7xygS85wx7VPn
 UUChgqw0aJrrq5slOZEAVqSsBN/wN97+m6uLLdk025CzQngwiw5fkTooakPxnGee
 bW9WKMpWBj/ipPXvU5C1tvHk4gxMg+cmxcr6EZ3uaWfE+MC7Xk9c00lNF62CT0Xm
 e+0RWRV1ig==
 =XYT5
 -----END PGP SIGNATURE-----

Merge tag 'io_uring-5.11-2021-01-01' of git://git.kernel.dk/linux-block

Pull io_uring fixes from Jens Axboe:
 "A few fixes that should go into 5.11, all marked for stable as well:

   - Fix issue around identity COW'ing and users that share a ring
     across processes

   - Fix a hang associated with unregistering fixed files (Pavel)

   - Move the 'process is exiting' cancelation a bit earlier, so
     task_works aren't affected by it (Pavel)"

* tag 'io_uring-5.11-2021-01-01' of git://git.kernel.dk/linux-block:
  kernel/io_uring: cancel io_uring before task works
  io_uring: fix io_sqe_files_unregister() hangs
  io_uring: add a helper for setting a ref node
  io_uring: don't assume mm is constant across submits

fs/file.c

@@ -21,7 +21,6 @@
 #include <linux/rcupdate.h>
 #include <linux/close_range.h>
 #include <net/sock.h>
-#include <linux/io_uring.h>
 
 unsigned int sysctl_nr_open __read_mostly = 1024*1024;
 unsigned int sysctl_nr_open_min = BITS_PER_LONG;
@@ -428,7 +427,6 @@ void exit_files(struct task_struct *tsk)
 	struct files_struct * files = tsk->files;
 
 	if (files) {
-		io_uring_files_cancel(files);
 		task_lock(tsk);
 		tsk->files = NULL;
 		task_unlock(tsk);

fs/io_uring.c

@@ -992,6 +992,10 @@ enum io_mem_account {
 	ACCT_PINNED,
 };
 
+static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node);
+static struct fixed_file_ref_node *alloc_fixed_file_ref_node(
+			struct io_ring_ctx *ctx);
+
 static void __io_complete_rw(struct io_kiocb *req, long res, long res2,
 			     struct io_comp_state *cs);
 static void io_cqring_fill_event(struct io_kiocb *req, long res);
@@ -1501,6 +1505,13 @@ static bool io_grab_identity(struct io_kiocb *req)
 		spin_unlock_irq(&ctx->inflight_lock);
 		req->work.flags |= IO_WQ_WORK_FILES;
 	}
+	if (!(req->work.flags & IO_WQ_WORK_MM) &&
+	    (def->work_flags & IO_WQ_WORK_MM)) {
+		if (id->mm != current->mm)
+			return false;
+		mmgrab(id->mm);
+		req->work.flags |= IO_WQ_WORK_MM;
+	}
 
 	return true;
 }
@@ -1525,13 +1536,6 @@ static void io_prep_async_work(struct io_kiocb *req)
 			req->work.flags |= IO_WQ_WORK_UNBOUND;
 	}
 
-	/* ->mm can never change on us */
-	if (!(req->work.flags & IO_WQ_WORK_MM) &&
-	    (def->work_flags & IO_WQ_WORK_MM)) {
-		mmgrab(id->mm);
-		req->work.flags |= IO_WQ_WORK_MM;
-	}
-
 	/* if we fail grabbing identity, we must COW, regrab, and retry */
 	if (io_grab_identity(req))
 		return;
@@ -7231,14 +7235,28 @@ static void io_file_ref_kill(struct percpu_ref *ref)
 	complete(&data->done);
 }
 
+static void io_sqe_files_set_node(struct fixed_file_data *file_data,
+				  struct fixed_file_ref_node *ref_node)
+{
+	spin_lock_bh(&file_data->lock);
+	file_data->node = ref_node;
+	list_add_tail(&ref_node->node, &file_data->ref_list);
+	spin_unlock_bh(&file_data->lock);
+	percpu_ref_get(&file_data->refs);
+}
+
 static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 {
 	struct fixed_file_data *data = ctx->file_data;
-	struct fixed_file_ref_node *ref_node = NULL;
+	struct fixed_file_ref_node *backup_node, *ref_node = NULL;
 	unsigned nr_tables, i;
+	int ret;
 
 	if (!data)
 		return -ENXIO;
+	backup_node = alloc_fixed_file_ref_node(ctx);
+	if (!backup_node)
+		return -ENOMEM;
 
 	spin_lock_bh(&data->lock);
 	ref_node = data->node;
@@ -7250,7 +7268,18 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 
 	/* wait for all refs nodes to complete */
 	flush_delayed_work(&ctx->file_put_work);
-	wait_for_completion(&data->done);
+	do {
+		ret = wait_for_completion_interruptible(&data->done);
+		if (!ret)
+			break;
+		ret = io_run_task_work_sig();
+		if (ret < 0) {
+			percpu_ref_resurrect(&data->refs);
+			reinit_completion(&data->done);
+			io_sqe_files_set_node(data, backup_node);
+			return ret;
+		}
+	} while (1);
 
 	__io_sqe_files_unregister(ctx);
 	nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE);
@@ -7261,6 +7290,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 	kfree(data);
 	ctx->file_data = NULL;
 	ctx->nr_user_files = 0;
+	destroy_fixed_file_ref_node(backup_node);
 	return 0;
 }
 
@@ -7758,11 +7788,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 		return PTR_ERR(ref_node);
 	}
 
-	file_data->node = ref_node;
+	io_sqe_files_set_node(file_data, ref_node);
-	spin_lock_bh(&file_data->lock);
-	list_add_tail(&ref_node->node, &file_data->ref_list);
-	spin_unlock_bh(&file_data->lock);
-	percpu_ref_get(&file_data->refs);
 	return ret;
 out_fput:
 	for (i = 0; i < ctx->nr_user_files; i++) {
@@ -7918,11 +7944,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 
 	if (needs_switch) {
 		percpu_ref_kill(&data->node->refs);
-		spin_lock_bh(&data->lock);
+		io_sqe_files_set_node(data, ref_node);
-		list_add_tail(&ref_node->node, &data->ref_list);
-		data->node = ref_node;
-		spin_unlock_bh(&data->lock);
-		percpu_ref_get(&ctx->file_data->refs);
 	} else
 		destroy_fixed_file_ref_node(ref_node);
 

kernel/exit.c

@@ -63,6 +63,7 @@
 #include <linux/random.h>
 #include <linux/rcuwait.h>
 #include <linux/compat.h>
+#include <linux/io_uring.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -776,6 +777,7 @@ void __noreturn do_exit(long code)
 		schedule();
 	}
 
+	io_uring_files_cancel(tsk->files);
 	exit_signals(tsk);  /* sets PF_EXITING */
 
 	/* sync mm's RSS info before statistics gathering */