[PATCH liburing v3 08/11] add docs for overflow lost errors

[Dylan Yudaken <dylany@fb.com>]

Add man docs for return values indicating a CQE was lost.

Signed-off-by: Dylan Yudaken <dylany@fb.com>
---
 man/io_uring_enter.2 | 11 +++++++++++
 man/io_uring_setup.2 | 11 +++++++++--
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/man/io_uring_enter.2 b/man/io_uring_enter.2
index 4d8d488b5c1f..3c4aa04016cf 100644
--- a/man/io_uring_enter.2
+++ b/man/io_uring_enter.2
@@ -1329,6 +1329,17 @@ is a valid file descriptor, but the io_uring ring is not in the right state
 .BR io_uring_register (2)
 for details on how to enable the ring.
 .TP
+.B EBADR
+At least one CQE was dropped even with the
+.B IORING_FEAT_NODROP
+feature, and there are no otherwise available CQEs. This clears the error state
+and so with no other changes the next call to
+.BR io_uring_setup (2)
+will not have this error. This error should be extremely rare and indicates the
+machine is running critically low on memory and. It may be reasonable for the
+application to terminate running unless it is able to safely handle any CQE
+being lost.
+.TP
 .B EBUSY
 If the
 .B IORING_FEAT_NODROP
diff --git a/man/io_uring_setup.2 b/man/io_uring_setup.2
index 01eb70d95292..41c9e5f269c5 100644
--- a/man/io_uring_setup.2
+++ b/man/io_uring_setup.2
@@ -298,7 +298,7 @@ call. The SQEs must still be allocated separately. This brings the necessary
 calls down from three to two. Available since kernel 5.4.
 .TP
 .B IORING_FEAT_NODROP
-If this flag is set, io_uring supports never dropping completion events.
+If this flag is set, io_uring supports almost never dropping completion events.
 If a completion event occurs and the CQ ring is full, the kernel stores
 the event internally until such a time that the CQ ring has room for more
 entries. If this overflow condition is entered, attempting to submit more
@@ -306,7 +306,14 @@ IO will fail with the
 .B -EBUSY
 error value, if it can't flush the overflown events to the CQ ring. If this
 happens, the application must reap events from the CQ ring and attempt the
-submit again. Available since kernel 5.5.
+submit again. If the kernel has no free memory to store the event internally
+it will be visible by an increase in the overflow value on the cqring.
+Available since kernel 5.5. Additionally
+.BR io_uring_enter (2)
+will return
+.B -EBADR
+the next time it would otherwise sleep waiting for completions (since kernel 5.19).
+
 .TP
 .B IORING_FEAT_SUBMIT_STABLE
 If this flag is set, applications can be certain that any data for
-- 
2.30.2