Merging upstream version 5.10.216.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 11 insertions, 225 deletions

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 936abc6ee..93f9ecedc 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -62,7 +62,6 @@
 #include <linux/net.h>
 #include <net/sock.h>
 #include <net/af_unix.h>
-#include <net/scm.h>
 #include <linux/anon_inodes.h>
 #include <linux/sched/mm.h>
 #include <linux/uaccess.h>
@@ -440,9 +439,6 @@ struct io_ring_ctx {
 
 	/* Keep this last, we don't need it for the fast path */
 	struct {
-		#if defined(CONFIG_UNIX)
-			struct socket		*ring_sock;
-		#endif
 		/* hashed buffered write serialization */
 		struct io_wq_hash		*hash_map;
 
@@ -1113,19 +1109,6 @@ static struct kmem_cache *req_cachep;
 
 static const struct file_operations io_uring_fops;
 
-struct sock *io_uring_get_socket(struct file *file)
-{
-#if defined(CONFIG_UNIX)
-	if (file->f_op == &io_uring_fops) {
-		struct io_ring_ctx *ctx = file->private_data;
-
-		return ctx->ring_sock->sk;
-	}
-#endif
-	return NULL;
-}
-EXPORT_SYMBOL(io_uring_get_socket);
-
 static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked)
 {
 	if (!*locked) {
@@ -7657,7 +7640,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 					  struct io_wait_queue *iowq,
 					  ktime_t *timeout)
 {
-	int io_wait, ret;
+	int ret;
 
 	/* make sure we run task_work before checking for signals */
 	ret = io_run_task_work_sig();
@@ -7672,13 +7655,12 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 	 * can take into account that the task is waiting for IO - turns out
 	 * to be important for low QD IO.
 	 */
-	io_wait = current->in_iowait;
 	if (current_pending_io())
 		current->in_iowait = 1;
 	ret = 1;
 	if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS))
 		ret = -ETIME;
-	current->in_iowait = io_wait;
+	current->in_iowait = 0;
 	return ret;
 }
 
@@ -7989,15 +7971,6 @@ static void io_free_file_tables(struct io_file_table *table)
 
 static void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
 {
-#if defined(CONFIG_UNIX)
-	if (ctx->ring_sock) {
-		struct sock *sock = ctx->ring_sock->sk;
-		struct sk_buff *skb;
-
-		while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL)
-			kfree_skb(skb);
-	}
-#else
 	int i;
 
 	for (i = 0; i < ctx->nr_user_files; i++) {
@@ -8007,7 +7980,6 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
 		if (file)
 			fput(file);
 	}
-#endif
 	io_free_file_tables(&ctx->file_table);
 	io_rsrc_data_free(ctx->file_data);
 	ctx->file_data = NULL;
@@ -8159,170 +8131,11 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p,
 	return sqd;
 }
 
-#if defined(CONFIG_UNIX)
-/*
- * Ensure the UNIX gc is aware of our file set, so we are certain that
- * the io_uring can be safely unregistered on process exit, even if we have
- * loops in the file referencing.
- */
-static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset)
-{
-	struct sock *sk = ctx->ring_sock->sk;
-	struct scm_fp_list *fpl;
-	struct sk_buff *skb;
-	int i, nr_files;
-
-	fpl = kzalloc(sizeof(*fpl), GFP_KERNEL);
-	if (!fpl)
-		return -ENOMEM;
-
-	skb = alloc_skb(0, GFP_KERNEL);
-	if (!skb) {
-		kfree(fpl);
-		return -ENOMEM;
-	}
-
-	skb->sk = sk;
-	skb->scm_io_uring = 1;
-
-	nr_files = 0;
-	fpl->user = get_uid(current_user());
-	for (i = 0; i < nr; i++) {
-		struct file *file = io_file_from_index(ctx, i + offset);
-
-		if (!file)
-			continue;
-		fpl->fp[nr_files] = get_file(file);
-		unix_inflight(fpl->user, fpl->fp[nr_files]);
-		nr_files++;
-	}
-
-	if (nr_files) {
-		fpl->max = SCM_MAX_FD;
-		fpl->count = nr_files;
-		UNIXCB(skb).fp = fpl;
-		skb->destructor = unix_destruct_scm;
-		refcount_add(skb->truesize, &sk->sk_wmem_alloc);
-		skb_queue_head(&sk->sk_receive_queue, skb);
-
-		for (i = 0; i < nr; i++) {
-			struct file *file = io_file_from_index(ctx, i + offset);
-
-			if (file)
-				fput(file);
-		}
-	} else {
-		kfree_skb(skb);
-		free_uid(fpl->user);
-		kfree(fpl);
-	}
-
-	return 0;
-}
-
-/*
- * If UNIX sockets are enabled, fd passing can cause a reference cycle which
- * causes regular reference counting to break down. We rely on the UNIX
- * garbage collection to take care of this problem for us.
- */
-static int io_sqe_files_scm(struct io_ring_ctx *ctx)
-{
-	unsigned left, total;
-	int ret = 0;
-
-	total = 0;
-	left = ctx->nr_user_files;
-	while (left) {
-		unsigned this_files = min_t(unsigned, left, SCM_MAX_FD);
-
-		ret = __io_sqe_files_scm(ctx, this_files, total);
-		if (ret)
-			break;
-		left -= this_files;
-		total += this_files;
-	}
-
-	if (!ret)
-		return 0;
-
-	while (total < ctx->nr_user_files) {
-		struct file *file = io_file_from_index(ctx, total);
-
-		if (file)
-			fput(file);
-		total++;
-	}
-
-	return ret;
-}
-#else
-static int io_sqe_files_scm(struct io_ring_ctx *ctx)
-{
-	return 0;
-}
-#endif
-
 static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
 {
 	struct file *file = prsrc->file;
-#if defined(CONFIG_UNIX)
-	struct sock *sock = ctx->ring_sock->sk;
-	struct sk_buff_head list, *head = &sock->sk_receive_queue;
-	struct sk_buff *skb;
-	int i;
-
-	__skb_queue_head_init(&list);
-
-	/*
-	 * Find the skb that holds this file in its SCM_RIGHTS. When found,
-	 * remove this entry and rearrange the file array.
-	 */
-	skb = skb_dequeue(head);
-	while (skb) {
-		struct scm_fp_list *fp;
-
-		fp = UNIXCB(skb).fp;
-		for (i = 0; i < fp->count; i++) {
-			int left;
-
-			if (fp->fp[i] != file)
-				continue;
-
-			unix_notinflight(fp->user, fp->fp[i]);
-			left = fp->count - 1 - i;
-			if (left) {
-				memmove(&fp->fp[i], &fp->fp[i + 1],
-						left * sizeof(struct file *));
-			}
-			fp->count--;
-			if (!fp->count) {
-				kfree_skb(skb);
-				skb = NULL;
-			} else {
-				__skb_queue_tail(&list, skb);
-			}
-			fput(file);
-			file = NULL;
-			break;
-		}
-
-		if (!file)
-			break;
-
-		__skb_queue_tail(&list, skb);
-
-		skb = skb_dequeue(head);
-	}
 
-	if (skb_peek(&list)) {
-		spin_lock_irq(&head->lock);
-		while ((skb = __skb_dequeue(&list)) != NULL)
-			__skb_queue_tail(head, skb);
-		spin_unlock_irq(&head->lock);
-	}
-#else
 	fput(file);
-#endif
 }
 
 static void __io_rsrc_put_work(struct io_rsrc_node *ref_node)
@@ -8433,14 +8246,8 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 		io_fixed_file_set(io_fixed_file_slot(&ctx->file_table, i), file);
 	}
 
-	ret = io_sqe_files_scm(ctx);
-	if (ret) {
-		__io_sqe_files_unregister(ctx);
-		return ret;
-	}
-
 	io_rsrc_node_switch(ctx, NULL);
-	return ret;
+	return 0;
 out_fput:
 	for (i = 0; i < ctx->nr_user_files; i++) {
 		file = io_file_from_index(ctx, i);
@@ -9395,12 +9202,6 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list));
 	WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist));
 
-#if defined(CONFIG_UNIX)
-	if (ctx->ring_sock) {
-		ctx->ring_sock->file = NULL; /* so that iput() is called */
-		sock_release(ctx->ring_sock);
-	}
-#endif
 	WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list));
 
 	if (ctx->mm_account) {
@@ -10275,6 +10076,11 @@ static const struct file_operations io_uring_fops = {
 #endif
 };
 
+bool io_is_uring_fops(struct file *file)
+{
+	return file->f_op == &io_uring_fops;
+}
+
 static int io_allocate_scq_urings(struct io_ring_ctx *ctx,
 				  struct io_uring_params *p)
 {
@@ -10337,32 +10143,12 @@ static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file)
 /*
  * Allocate an anonymous fd, this is what constitutes the application
  * visible backing of an io_uring instance. The application mmaps this
- * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled,
- * we have to tie this fd to a socket for file garbage collection purposes.
+ * fd to gain access to the SQ/CQ ring details.
  */
 static struct file *io_uring_get_file(struct io_ring_ctx *ctx)
 {
-	struct file *file;
-#if defined(CONFIG_UNIX)
-	int ret;
-
-	ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP,
-				&ctx->ring_sock);
-	if (ret)
-		return ERR_PTR(ret);
-#endif
-
-	file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx,
-					O_RDWR | O_CLOEXEC);
-#if defined(CONFIG_UNIX)
-	if (IS_ERR(file)) {
-		sock_release(ctx->ring_sock);
-		ctx->ring_sock = NULL;
-	} else {
-		ctx->ring_sock->file = file;
-	}
-#endif
-	return file;
+	return anon_inode_getfile("[io_uring]", &io_uring_fops, ctx,
+				  O_RDWR | O_CLOEXEC);
 }
 
 static int io_uring_create(unsigned entries, struct io_uring_params *p,