io_uring_enter
Partial in Antinomie 0.7.0 · Syscall list
Synopsis
Section titled “Synopsis”long io_uring_enter(unsigned int fd, u32 to_submit, u32 min_complete, u32 flags, const void *argp, size_t argsz);| Number (x86-64) | 426 |
| ABI | common |
| Kernel entry point | sys_io_uring_enter |
This is the raw kernel prototype from the pinned Linux 6.12.94 schema, not the libc wrapper.
Description
Section titled “Description”Submits queued io_uring entries and optionally waits for completions.
Arguments
Section titled “Arguments”| Name | Type | Meaning |
|---|---|---|
fd (arg0) |
unsigned int |
io_uring file descriptor. |
to_submit (arg1) |
u32 |
Number of queued submissions to hand to the kernel. |
min_complete (arg2) |
u32 |
Number of completions to wait for. |
flags (arg3) |
u32 |
IORING_ENTER_* flags. |
argp (arg4) |
const void * |
Pointer to the argument. |
argsz (arg5) |
size_t |
Size of the argument. |
Return value
Section titled “Return value”On success: the number of entries consumed.
In an Antinomie trace the Return column and the ret filter field show the raw kernel return value. On failure that is the negative errno, for example -2 for ENOENT, not the -1 plus errno that the libc wrapper gives. syscall.errno holds the positive errno and syscall.success is false.
Common errors
Section titled “Common errors”| Raw return | Name | Meaning |
|---|---|---|
-9 |
EBADF |
A file descriptor is not valid for this operation. |
-4 |
EINTR |
The call was interrupted by a signal. |
Man page
Section titled “Man page”Captured by Antinomie
Section titled “Captured by Antinomie”Coverage mark: Partial. Submissions are observed as asynchronous requests; requests whose operand has no decoder (for example a driver URING_CMD) and buffers the kernel reads later in another context are recorded with the “no decoder” or “not observed asynchronously” status.
Every call is recorded as an Entry record (the six argument words and the pointees copied at entry) and an Exit record (the return value and the pointees copied at exit).
Arguments
Section titled “Arguments”| Argument | When | How | Recorded field key | Condition |
|---|---|---|---|---|
fd (arg0) |
Entry | raw scalar word | args.0, args.fd |
|
to_submit (arg1) |
Entry | raw scalar word | args.1, args.to_submit |
|
min_complete (arg2) |
Entry | raw scalar word | args.2, args.min_complete |
|
flags (arg3) |
Entry | raw scalar word; Syscall Trace also decodes it into flag names (uring_enter group), listing unknown bits separately |
args.3, args.flags |
|
argp (arg4) |
Entry | the pointer itself, as a raw word | args.4, args.raw[4] |
|
| ↳ pointee | Entry | structure io_uring_getevents_arg |
arg4.ext_arg |
IORING_ENTER_EXT_ARG is set and the pointer is not NULL; “invalid extent” if argsz (arg5) is not its size |
| ↳ pointee | Entry | structure timespec from the extended argument |
arg4.timeout |
the extended argument has a timeout |
| ↳ pointee | Entry | signal set, size from argsz (arg5) or from the extended argument |
signal.mask |
a mask is given |
argsz (arg5) |
Entry | raw scalar word | args.5, args.argsz |
Family notes
Section titled “Family notes”- The submission queue entries are observed as asynchronous requests when the kernel consumes them; see Async observations.
Filter fields
Section titled “Filter fields”- Result:
ret,syscall.errno,syscall.success,syscall.duration_ns. - Argument words:
args.fd(arg0),args.to_submit(arg1),args.min_complete(arg2),args.flags(arg3),args.argp(arg4),args.argsz(arg5);args.0toargs.5by position.
See Syscall Trace filter for the full syntax.
Known gaps
Section titled “Known gaps”- See the coverage mark above for the code paths that record a gap.
For what the capture statuses mean, see Capture statuses. For what is never recorded, see Known gaps.