From a87acfde949140946456859eafa5f15175d0f960 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 11 Sep 2021 16:04:50 -0600 Subject: io_uring: dump sqe contents if issue fails 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 --- include/trace/events/io_uring.h | 61 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 61 insertions(+) (limited to 'include') 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 +#include 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 */ -- cgit v1.2.3 From 6224590d242fc8c6b26941328e02a40b4384949b Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 2 Oct 2021 19:36:14 +0100 Subject: io_uring: add flag to not fail link after timeout For some reason non-off IORING_OP_TIMEOUT always fails links, it's pretty inconvenient and unnecessary limits chaining after it to hard linking, which is far from ideal, e.g. doesn't pair well with timeout cancellation. Add a flag forcing it to not fail links on -ETIME. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/17c7ec0fb7a6113cc6be8cdaedcada0ba836ac0e.1633199723.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 8 ++++++-- include/uapi/linux/io_uring.h | 1 + 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/fs/io_uring.c b/fs/io_uring.c index 5b3b52815b88..5b3b4f8f9659 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -5857,7 +5857,10 @@ err: static void io_req_task_timeout(struct io_kiocb *req, bool *locked) { - req_set_fail(req); + struct io_timeout_data *data = req->async_data; + + if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS)) + req_set_fail(req); io_req_complete_post(req, -ETIME, 0); } @@ -6063,7 +6066,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (off && is_timeout_link) return -EINVAL; flags = READ_ONCE(sqe->timeout_flags); - if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK)) + if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK | + IORING_TIMEOUT_ETIME_SUCCESS)) return -EINVAL; /* more than one clock specified is invalid, obviously */ if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index b270a07b285e..c45b5e9a9387 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -158,6 +158,7 @@ enum { #define IORING_TIMEOUT_BOOTTIME (1U << 2) #define IORING_TIMEOUT_REALTIME (1U << 3) #define IORING_LINK_TIMEOUT_UPDATE (1U << 4) +#define IORING_TIMEOUT_ETIME_SUCCESS (1U << 5) #define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME) #define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE) /* -- cgit v1.2.3