io_uring: enable task/files specific overflow flushing

commit e6c8aa9ac33bd7c968af7816240fc081401fddcd upstream.

This allows us to selectively flush out pending overflows, depending on
the task and/or files_struct being passed in.

No intended functional changes in this patch.

Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 25 insertions, 16 deletions

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 5ddb8b2fe3e5..046d06266a11 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1344,12 +1344,24 @@ static void io_cqring_mark_overflow(struct io_ring_ctx *ctx)
 	}
 }
 
+static inline bool io_match_files(struct io_kiocb *req,
+				       struct files_struct *files)
+{
+	if (!files)
+		return true;
+	if (req->flags & REQ_F_WORK_INITIALIZED)
+		return req->work.files == files;
+	return false;
+}
+
 /* Returns true if there are no backlogged entries after the flush */
-static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
+static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
+				     struct task_struct *tsk,
+				     struct files_struct *files)
 {
 	struct io_rings *rings = ctx->rings;
+	struct io_kiocb *req, *tmp;
 	struct io_uring_cqe *cqe;
-	struct io_kiocb *req;
 	unsigned long flags;
 	LIST_HEAD(list);
 
@@ -1368,13 +1380,16 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 		ctx->cq_overflow_flushed = 1;
 
 	cqe = NULL;
-	while (!list_empty(&ctx->cq_overflow_list)) {
+	list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, compl.list) {
+		if (tsk && req->task != tsk)
+			continue;
+		if (!io_match_files(req, files))
+			continue;
+
 		cqe = io_get_cqring(ctx);
 		if (!cqe && !force)
 			break;
 
-		req = list_first_entry(&ctx->cq_overflow_list, struct io_kiocb,
-						compl.list);
 		list_move(&req->compl.list, &list);
 		if (cqe) {
 			WRITE_ONCE(cqe->user_data, req->user_data);
@@ -1988,7 +2003,7 @@ static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush)
 		if (noflush && !list_empty(&ctx->cq_overflow_list))
 			return -1U;
 
-		io_cqring_overflow_flush(ctx, false);
+		io_cqring_overflow_flush(ctx, false, NULL, NULL);
 	}
 
 	/* See comment at the top of this file */
@@ -6489,7 +6504,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
 	/* if we have a backlog and couldn't flush it all, return BUSY */
 	if (test_bit(0, &ctx->sq_check_overflow)) {
 		if (!list_empty(&ctx->cq_overflow_list) &&
-		    !io_cqring_overflow_flush(ctx, false))
+		    !io_cqring_overflow_flush(ctx, false, NULL, NULL))
 			return -EBUSY;
 	}
 
@@ -7993,7 +8008,7 @@ static void io_ring_exit_work(struct work_struct *work)
 	 */
 	do {
 		if (ctx->rings)
-			io_cqring_overflow_flush(ctx, true);
+			io_cqring_overflow_flush(ctx, true, NULL, NULL);
 		io_iopoll_try_reap_events(ctx);
 	} while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20));
 	io_ring_ctx_free(ctx);
@@ -8013,7 +8028,7 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 
 	/* if we failed setting up the ctx, we might not have any rings */
 	if (ctx->rings)
-		io_cqring_overflow_flush(ctx, true);
+		io_cqring_overflow_flush(ctx, true, NULL, NULL);
 	io_iopoll_try_reap_events(ctx);
 	idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx);
 
@@ -8069,12 +8084,6 @@ static bool io_match_link(struct io_kiocb *preq, struct io_kiocb *req)
 	return false;
 }
 
-static inline bool io_match_files(struct io_kiocb *req,
-				       struct files_struct *files)
-{
-	return (req->flags & REQ_F_WORK_INITIALIZED) && req->work.files == files;
-}
-
 static bool io_match_link_files(struct io_kiocb *req,
 				struct files_struct *files)
 {
@@ -8365,7 +8374,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 	ret = 0;
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		if (!list_empty_careful(&ctx->cq_overflow_list))
-			io_cqring_overflow_flush(ctx, false);
+			io_cqring_overflow_flush(ctx, false, NULL, NULL);
 		if (flags & IORING_ENTER_SQ_WAKEUP)
 			wake_up(&ctx->sqo_wait);
 		submitted = to_submit;