Skip to contentSkip to conversation

Add io_uring support for waitid

PATCH Superseded Jens Axboe 1 participant 6 messages Aug 11, 2023 io_uring

v3 of 4 Superseded Latest is v4 →

lore
Share & tools
lore

Jens Axboe

author maintainer
#0 lore raw

v3 cover Add io_uring support for waitid

Hi,

This adds support for IORING_OP_WAITID, which is an async variant of the waitid(2) syscall. Rather than have a parent need to block waiting on a child task state change, it can now simply get an async notication when the requested state change has occured.

Patches 1..4 are purely prep patches, and should not have functional changes. They split out parts of do_wait() into __do_wait(), so that the prepare-to-wait and sleep parts are contained within do_wait().

Patch 5 adds io_uring support.

I wrote a few basic tests for this, which can be found in the 'waitid' branch of liburing:

https://git.kernel.dk/cgit/liburing/log/?h=waitid

Also spun a custom kernel for someone to test it, and no issues reported so far.

 include/linux/io_uring_types.h |   2 +
 include/uapi/linux/io_uring.h  |   2 +
 io_uring/Makefile              |   2 +-
 io_uring/cancel.c              |   5 +
 io_uring/io_uring.c            |   3 +
 io_uring/opdef.c               |   9 +
 io_uring/waitid.c              | 312 +++++++++++++++++++++++++++++++++
 io_uring/waitid.h              |  15 ++
 kernel/exit.c                  | 129 ++++++++------
 kernel/exit.h                  |  30 ++++
 10 files changed, 450 insertions(+), 59 deletions(-)

The code can also be found here:

https://git.kernel.dk/cgit/linux/log/?h=io_uring-waitid

Changes since v2:
- Get rid of 'f_flags' in kernel_waitid_prepare() (Christian)

Signature · 1 line
Jens Axboe
author maintainer
#1 lore raw

PATCH v3 1/5 exit: abstract out should_wake helper for child_wait_callback()

Abstract out the helper that decides if we should wake up following a wake_up() callback on our internal waitqueue.

No functional changes intended in this patch.

---
 kernel/exit.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)
kernel/exit.c +14 -6
index edb50b4c9972..2809dad69492 100644
@@ -1520,6 +1520,17 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
 	return 0;
 }
 
+static bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p)
+{
+	if (!eligible_pid(wo, p))
+		return false;
+
+	if ((wo->wo_flags & __WNOTHREAD) && wo->child_wait.private != p->parent)
+		return false;
+
+	return true;
+}
+
 static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode,
 				int sync, void *key)
 {
@@ -1527,13 +1538,10 @@ static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode,
 						child_wait);
 	struct task_struct *p = key;
 
-	if (!eligible_pid(wo, p))
-		return 0;
+	if (pid_child_should_wake(wo, p))
+		return default_wake_function(wait, mode, sync, key);
 
-	if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent)
-		return 0;
-
-	return default_wake_function(wait, mode, sync, key);
+	return 0;
 }
 
 void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
Signature · 1 line
2.40.1
author maintainer
#2 lore raw

PATCH v3 2/5 exit: move core of do_wait() into helper

In reply to Jens Axboe

Rather than have a maze of gotos, put the actual logic in __do_wait() and have do_wait() loop deal with waitqueue setup/teardown and whether to call __do_wait() again.

No functional changes intended in this patch.

---
 kernel/exit.c | 49 ++++++++++++++++++++++++++++++-------------------
 1 file changed, 30 insertions(+), 19 deletions(-)
kernel/exit.c +30 -19
index 2809dad69492..d8fb124cc038 100644
@@ -1590,16 +1590,10 @@ static int do_wait_pid(struct wait_opts *wo)
 	return 0;
 }
 
-static long do_wait(struct wait_opts *wo)
+static long __do_wait(struct wait_opts *wo)
 {
-	int retval;
-
-	trace_sched_process_wait(wo->wo_pid);
+	long retval;
 
-	init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
-	wo->child_wait.private = current;
-	add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
-repeat:
 	/*
 	 * If there is nothing that can match our criteria, just get out.
 	 * We will clear ->notask_error to zero if we see any child that
@@ -1617,18 +1611,18 @@ static long do_wait(struct wait_opts *wo)
 	if (wo->wo_type == PIDTYPE_PID) {
 		retval = do_wait_pid(wo);
 		if (retval)
-			goto end;
+			return retval;
 	} else {
 		struct task_struct *tsk = current;
 
 		do {
 			retval = do_wait_thread(wo, tsk);
 			if (retval)
-				goto end;
+				return retval;
 
 			retval = ptrace_do_wait(wo, tsk);
 			if (retval)
-				goto end;
+				return retval;
 
 			if (wo->wo_flags & __WNOTHREAD)
 				break;
@@ -1638,14 +1632,31 @@ static long do_wait(struct wait_opts *wo)
 
 notask:
 	retval = wo->notask_error;
-	if (!retval && !(wo->wo_flags & WNOHANG)) {
-		retval = -ERESTARTSYS;
-		if (!signal_pending(current)) {
-			schedule();
-			goto repeat;
-		}
-	}
-end:
+	if (!retval && !(wo->wo_flags & WNOHANG))
+		return -ERESTARTSYS;
+
+	return retval;
+}
+
+static long do_wait(struct wait_opts *wo)
+{
+	int retval;
+
+	trace_sched_process_wait(wo->wo_pid);
+
+	init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
+	wo->child_wait.private = current;
+	add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
+
+	do {
+		retval = __do_wait(wo);
+		if (retval != -ERESTARTSYS)
+			break;
+		if (signal_pending(current))
+			break;
+		schedule();
+	} while (1);
+
 	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
 	return retval;
Signature · 1 line
2.40.1
author maintainer
#3 lore raw

PATCH v3 3/5 exit: add kernel_waitid_prepare() helper

In reply to Jens Axboe

Move the setup logic out of kernel_waitid(), and into a separate helper.

No functional changes intended in this patch.

---
 kernel/exit.c | 38 +++++++++++++++++++++++++-------------
 1 file changed, 25 insertions(+), 13 deletions(-)
kernel/exit.c +25 -13
index d8fb124cc038..5c4cd1769641 100644
@@ -1662,14 +1662,13 @@ static long do_wait(struct wait_opts *wo)
 	return retval;
 }
 
-static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
-			  int options, struct rusage *ru)
+static int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid,
+				 struct waitid_info *infop, int options,
+				 struct rusage *ru)
 {
-	struct wait_opts wo;
+	unsigned int f_flags = 0;
 	struct pid *pid = NULL;
 	enum pid_type type;
-	long ret;
-	unsigned int f_flags = 0;
 
 	if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED|
 			__WNOTHREAD|__WCLONE|__WALL))
@@ -1712,19 +1711,32 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
 		return -EINVAL;
 	}
 
-	wo.wo_type	= type;
-	wo.wo_pid	= pid;
-	wo.wo_flags	= options;
-	wo.wo_info	= infop;
-	wo.wo_rusage	= ru;
+	wo->wo_type	= type;
+	wo->wo_pid	= pid;
+	wo->wo_flags	= options;
+	wo->wo_info	= infop;
+	wo->wo_rusage	= ru;
 	if (f_flags & O_NONBLOCK)
-		wo.wo_flags |= WNOHANG;
+		wo->wo_flags |= WNOHANG;
+
+	return 0;
+}
+
+static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
+			  int options, struct rusage *ru)
+{
+	struct wait_opts wo;
+	long ret;
+
+	ret = kernel_waitid_prepare(&wo, which, upid, infop, options, ru);
+	if (ret)
+		return ret;
 
 	ret = do_wait(&wo);
-	if (!ret && !(options & WNOHANG) && (f_flags & O_NONBLOCK))
+	if (!ret && !(options & WNOHANG) && (wo.wo_flags & WNOHANG))
 		ret = -EAGAIN;
 
-	put_pid(pid);
+	put_pid(wo.wo_pid);
 	return ret;
 }
 
Signature · 1 line
2.40.1
author maintainer
#4 lore raw

PATCH v3 4/5 exit: add internal include file with helpers

In reply to Jens Axboe

Move struct wait_opts and waitid_info into kernel/exit.h, and include function declarations for the recently added helpers. Make them non-static as well.

This is in preparation for adding a waitid operation through io_uring. With the abtracted helpers, this is now possible.

---
 kernel/exit.c | 32 +++++++-------------------------
 kernel/exit.h | 30 ++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+), 25 deletions(-)
 create mode 100644 kernel/exit.h
kernel/exit.c +7 -25
index 5c4cd1769641..2e39468823e7 100644
@@ -74,6 +74,8 @@
 #include <asm/unistd.h>
 #include <asm/mmu_context.h>
 
+#include "exit.h"
+
 /*
  * The default value should be high enough to not crash a system that randomly
  * crashes its kernel from time to time, but low enough to at least not permit
@@ -1037,26 +1039,6 @@ SYSCALL_DEFINE1(exit_group, int, error_code)
 	return 0;
 }
 
-struct waitid_info {
-	pid_t pid;
-	uid_t uid;
-	int status;
-	int cause;
-};
-
-struct wait_opts {
-	enum pid_type		wo_type;
-	int			wo_flags;
-	struct pid		*wo_pid;
-
-	struct waitid_info	*wo_info;
-	int			wo_stat;
-	struct rusage		*wo_rusage;
-
-	wait_queue_entry_t		child_wait;
-	int			notask_error;
-};
-
 static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
 {
 	return	wo->wo_type == PIDTYPE_MAX ||
@@ -1520,7 +1502,7 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
 	return 0;
 }
 
-static bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p)
+bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p)
 {
 	if (!eligible_pid(wo, p))
 		return false;
@@ -1590,7 +1572,7 @@ static int do_wait_pid(struct wait_opts *wo)
 	return 0;
 }
 
-static long __do_wait(struct wait_opts *wo)
+long __do_wait(struct wait_opts *wo)
 {
 	long retval;
 
@@ -1662,9 +1644,9 @@ static long do_wait(struct wait_opts *wo)
 	return retval;
 }
 
-static int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid,
-				 struct waitid_info *infop, int options,
-				 struct rusage *ru)
+int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid,
+			  struct waitid_info *infop, int options,
+			  struct rusage *ru)
 {
 	unsigned int f_flags = 0;
 	struct pid *pid = NULL;
kernel/exit.h new file +30 -0
new file mode 100644
index 000000000000..278faa26a653
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#ifndef LINUX_WAITID_H
+#define LINUX_WAITID_H
+
+struct waitid_info {
+	pid_t pid;
+	uid_t uid;
+	int status;
+	int cause;
+};
+
+struct wait_opts {
+	enum pid_type		wo_type;
+	int			wo_flags;
+	struct pid		*wo_pid;
+
+	struct waitid_info	*wo_info;
+	int			wo_stat;
+	struct rusage		*wo_rusage;
+
+	wait_queue_entry_t		child_wait;
+	int			notask_error;
+};
+
+bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p);
+long __do_wait(struct wait_opts *wo);
+int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid,
+			  struct waitid_info *infop, int options,
+			  struct rusage *ru);
+#endif
Signature · 1 line
2.40.1
author maintainer
#5 lore raw

PATCH v3 5/5 io_uring: add IORING_OP_WAITID support

In reply to Jens Axboe

This adds support for an async version of waitid(2), in a fully async version. If an event isn't immediately available, wait for a callback to trigger a retry.

The format of the sqe is as follows:

sqe->len The 'which', the idtype being queried/waited for.
sqe->fd The 'pid' (or id) being waited for.
sqe->file_index The 'options' being set.
sqe->addr2 A pointer to siginfo_t, if any, being filled in.

buf_index, add3, and waitid_flags are reserved/unused for now. waitid_flags will be used for options for this request type. One interesting use case may be to add multi-shot support, so that the request stays armed and posts a notification every time a monitored process state change occurs.

Note that this does not support rusage, on Arnd's recommendation.

See the waitid(2) man page for details on the arguments.

---
 include/linux/io_uring_types.h |   2 +
 include/uapi/linux/io_uring.h  |   2 +
 io_uring/Makefile              |   2 +-
 io_uring/cancel.c              |   5 +
 io_uring/io_uring.c            |   3 +
 io_uring/opdef.c               |   9 +
 io_uring/waitid.c              | 312 +++++++++++++++++++++++++++++++++
 io_uring/waitid.h              |  15 ++
 8 files changed, 349 insertions(+), 1 deletion(-)
 create mode 100644 io_uring/waitid.c
 create mode 100644 io_uring/waitid.h
include/linux/io_uring_types.h +2 -0
index a7f03d8d879f..598553877fc2 100644
@@ -276,6 +276,8 @@ struct io_ring_ctx {
 	struct hlist_head	futex_list;
 	struct io_alloc_cache	futex_cache;
 
+	struct hlist_head	waitid_list;
+
 	const struct cred	*sq_creds;	/* cred used for __io_sq_thread() */
 	struct io_sq_data	*sq_data;	/* if using sq thread polling */
 
include/uapi/linux/io_uring.h +2 -0
index 3dd3d7557531..ef42a8203bdd 100644
@@ -66,6 +66,7 @@ struct io_uring_sqe {
 		__u32		msg_ring_flags;
 		__u32		uring_cmd_flags;
 		__u32		futex_flags;
+		__u32		waitid_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	/* pack this to avoid bogus arm OABI complaints */
@@ -239,6 +240,7 @@ enum io_uring_op {
 	IORING_OP_FUTEX_WAIT,
 	IORING_OP_FUTEX_WAKE,
 	IORING_OP_FUTEX_WAITV,
+	IORING_OP_WAITID,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
io_uring/Makefile +1 -1
index 2e4779bc550c..e5be47e4fc3b 100644
@@ -8,6 +8,6 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o xattr.o nop.o fs.o splice.o \
 					statx.o net.o msg_ring.o timeout.o \
 					sqpoll.o fdinfo.o tctx.o poll.o \
 					cancel.o kbuf.o rsrc.o rw.o opdef.o \
-					notif.o
+					notif.o waitid.o
 obj-$(CONFIG_IO_WQ)		+= io-wq.o
 obj-$(CONFIG_FUTEX)		+= futex.o
io_uring/cancel.c +5 -0
index 3dba8ccb1cd8..a01f3f41012b 100644
@@ -16,6 +16,7 @@
 #include "poll.h"
 #include "timeout.h"
 #include "futex.h"
+#include "waitid.h"
 #include "cancel.h"
 
 struct io_cancel {
@@ -124,6 +125,10 @@ int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd,
 	if (ret != -ENOENT)
 		return ret;
 
+	ret = io_waitid_cancel(ctx, cd, issue_flags);
+	if (ret != -ENOENT)
+		return ret;
+
 	spin_lock(&ctx->completion_lock);
 	if (!(cd->flags & IORING_ASYNC_CANCEL_FD))
 		ret = io_timeout_cancel(ctx, cd);
io_uring/io_uring.c +3 -0
index f1dbbe51f867..d33d9d91f94c 100644
@@ -93,6 +93,7 @@
 #include "net.h"
 #include "notif.h"
 #include "futex.h"
+#include "waitid.h"
 
 #include "timeout.h"
 #include "poll.h"
@@ -335,6 +336,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	ctx->submit_state.free_list.next = NULL;
 	INIT_WQ_LIST(&ctx->locked_free_list);
 	INIT_HLIST_HEAD(&ctx->futex_list);
+	INIT_HLIST_HEAD(&ctx->waitid_list);
 	INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
 	INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
 	return ctx;
@@ -3277,6 +3279,7 @@ static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 	mutex_lock(&ctx->uring_lock);
 	ret |= io_poll_remove_all(ctx, task, cancel_all);
 	ret |= io_futex_remove_all(ctx, task, cancel_all);
+	ret |= io_waitid_remove_all(ctx, task, cancel_all);
 	mutex_unlock(&ctx->uring_lock);
 	ret |= io_kill_timeouts(ctx, task, cancel_all);
 	if (task)
io_uring/opdef.c +9 -0
index b9e1e12cac9c..1c5cfa9d7b31 100644
@@ -34,6 +34,7 @@
 #include "cancel.h"
 #include "rw.h"
 #include "futex.h"
+#include "waitid.h"
 
 static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags)
 {
@@ -453,6 +454,10 @@ const struct io_issue_def io_issue_defs[] = {
 		.prep			= io_eopnotsupp_prep,
 #endif
 	},
+	[IORING_OP_WAITID] = {
+		.prep			= io_waitid_prep,
+		.issue			= io_waitid,
+	},
 };
 
 const struct io_cold_def io_cold_defs[] = {
@@ -681,6 +686,10 @@ const struct io_cold_def io_cold_defs[] = {
 	[IORING_OP_FUTEX_WAITV] = {
 		.name			= "FUTEX_WAITV",
 	},
+	[IORING_OP_WAITID] = {
+		.name			= "WAITID",
+		.async_size		= sizeof(struct io_waitid_async),
+	},
 };
 
 const char *io_uring_get_opcode(u8 opcode)
io_uring/waitid.c new file +312 -0

312 lines not on this page · raw message

io_uring/waitid.h new file +15 -0
new file mode 100644
index 000000000000..956a8adafe8c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "../kernel/exit.h"
+
+struct io_waitid_async {
+	struct io_kiocb *req;
+	struct wait_opts wo;
+};
+
+int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_waitid(struct io_kiocb *req, unsigned int issue_flags);
+int io_waitid_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
+		     unsigned int issue_flags);
+bool io_waitid_remove_all(struct io_ring_ctx *ctx, struct task_struct *task,
+			  bool cancel_all);
Signature · 1 line
2.40.1