io_uring: don't rely on weak ->files references

Grab actual references to the files_struct. To avoid circular references
issues due to this, we add a per-task note that keeps track of what
io_uring contexts a task has used. When the tasks execs or exits its
assigned files, we cancel requests based on this tracking.

With that, we can grab proper references to the files table, and no
longer need to rely on stashing away ring_fd and ring_file to check
if the ring_fd may have been closed.

Cc: [email protected] # v5.5+
Reviewed-by: Pavel Begunkov <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>

fs/exec.c

@@ -62,6 +62,7 @@
 #include <linux/oom.h>
 #include <linux/compat.h>
 #include <linux/vmalloc.h>
+#include <linux/io_uring.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -1895,6 +1896,11 @@ static int bprm_execve(struct linux_binprm *bprm,
 	struct files_struct *displaced;
 	int retval;
 
+	/*
+	 * Cancel any io_uring activity across execve
+	 */
+	io_uring_task_cancel();
+
 	retval = unshare_files(&displaced);
 	if (retval)
 		return retval;

fs/file.c

@@ -21,6 +21,7 @@
 #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;
@@ -452,6 +453,7 @@ 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);