From a87acfde949140946456859eafa5f15175d0f960 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sat, 11 Sep 2021 16:04:50 -0600
Subject: [PATCH] io_uring: dump sqe contents if issue fails
Git-commit: a87acfde949140946456859eafa5f15175d0f960
Patch-mainline: v5.16-rc1
References: bsc#1205205

I recently had to look at a production problem where a request ended
up getting the dreaded -EINVAL error on submit. The most used and
hence useless of error codes, as it just tells you that something
was wrong with your request, but not more than that.

Let's dump the full sqe contents if we run into an issue failure,
that'll allow easier diagnosing of a wide variety of issues.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
---
 fs/io_uring.c                   |  2 ++
 include/trace/events/io_uring.h | 61 +++++++++++++++++++++++++++++++++
 2 files changed, 63 insertions(+)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index d4631a55a692..5daee36c1f33 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7117,6 +7117,8 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	ret = io_init_req(ctx, req, sqe);
 	if (unlikely(ret)) {
 fail_req:
+		trace_io_uring_req_failed(sqe, ret);
+
 		/* fail even hard links since we don't submit */
 		if (link->head) {
 			/*
diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h
index 0dd30de00e5b..7346f0164cf4 100644
--- a/include/trace/events/io_uring.h
+++ b/include/trace/events/io_uring.h
@@ -6,6 +6,7 @@
 #define _TRACE_IO_URING_H
 
 #include <linux/tracepoint.h>
+#include <uapi/linux/io_uring.h>
 
 struct io_wq_work;
 
@@ -497,6 +498,66 @@ TRACE_EVENT(io_uring_task_run,
 		  (unsigned long long) __entry->user_data)
 );
 
+/*
+ * io_uring_req_failed - called when an sqe is errored dring submission
+ *
+ * @sqe:		pointer to the io_uring_sqe that failed
+ * @error:		error it failed with
+ *
+ * Allows easier diagnosing of malformed requests in production systems.
+ */
+TRACE_EVENT(io_uring_req_failed,
+
+	TP_PROTO(const struct io_uring_sqe *sqe, int error),
+
+	TP_ARGS(sqe, error),
+
+	TP_STRUCT__entry (
+		__field(  u8,	opcode )
+		__field(  u8,	flags )
+		__field(  u8,	ioprio )
+		__field( u64,	off )
+		__field( u64,	addr )
+		__field( u32,	len )
+		__field( u32,	op_flags )
+		__field( u64,	user_data )
+		__field( u16,	buf_index )
+		__field( u16,	personality )
+		__field( u32,	file_index )
+		__field( u64,	pad1 )
+		__field( u64,	pad2 )
+		__field( int,	error )
+	),
+
+	TP_fast_assign(
+		__entry->opcode		= sqe->opcode;
+		__entry->flags		= sqe->flags;
+		__entry->ioprio		= sqe->ioprio;
+		__entry->off		= sqe->off;
+		__entry->addr		= sqe->addr;
+		__entry->len		= sqe->len;
+		__entry->op_flags	= sqe->rw_flags;
+		__entry->user_data	= sqe->user_data;
+		__entry->buf_index	= sqe->buf_index;
+		__entry->personality	= sqe->personality;
+		__entry->file_index	= sqe->file_index;
+		__entry->pad1		= sqe->__pad2[0];
+		__entry->pad2		= sqe->__pad2[1];
+		__entry->error		= error;
+	),
+
+	TP_printk("op %d, flags=0x%x, prio=%d, off=%llu, addr=%llu, "
+		  "len=%u, rw_flags=0x%x, user_data=0x%llx, buf_index=%d, "
+		  "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d",
+		  __entry->opcode, __entry->flags, __entry->ioprio,
+		  (unsigned long long)__entry->off,
+		  (unsigned long long) __entry->addr, __entry->len,
+		  __entry->op_flags, (unsigned long long) __entry->user_data,
+		  __entry->buf_index, __entry->personality, __entry->file_index,
+		  (unsigned long long) __entry->pad1,
+		  (unsigned long long) __entry->pad2, __entry->error)
+);
+
 #endif /* _TRACE_IO_URING_H */
 
 /* This part must be outside protection */
-- 
2.35.3