Add io_uring futex/futexv support
Jens Axboe
maintainerv2 cover Add io_uring futex/futexv support
Hi,
This patchset adds support for first futex wake and wait, and then futexv. Patches 1..3 are just prep patches, patch 4 adds the wait and wake support for io_uring, and then patches 5..7 are again prep patches to end up with futexv support in patch 8.
For both wait/wake/waitv, we support the bitset variant, as the "normal" variants can be easily implemented on top of that.
PI and requeue are not supported through io_uring, just the above mentioned parts. This may change in the future, but in the spirit of keeping this small (and based on what people have been asking for), this is what we currently have.
When I did these patches, I forgot that Pavel had previously posted a futex variant for io_uring. The major thing that had been holding me back from people asking about futexes and io_uring, is that I wanted to do this what I consider the right way - no usage of io-wq or thread offload, an actually async implementation that is efficient to use and don't rely on a blocking thread for futex wait/waitv. This is what this patchset attempts to do, while being minimally invasive on the futex side. I believe the diffstat reflects that.
As far as I can recall, the first request for futex support with io_uring came from Andres Freund, working on postgres. His aio rework of postgres was one of the early adopters of io_uring, and futex support was a natural extension for that. This is relevant from both a usability point of view, as well as for effiency and performance. In Andres's words, for the former:
"Futex wait support in io_uring makes it a lot easier to avoid deadlocks in concurrent programs that have their own buffer pool: Obviously pages in the application buffer pool have to be locked during IO. If the initiator of IO A needs to wait for a held lock B, the holder of lock B might wait for the IO A to complete. The ability to wait for a lock and IO completions at the same time provides an efficient way to avoid such deadlocks."
and in terms of effiency, even without unlocking the full potential yet, Andres says:
"Futex wake support in io_uring is useful because it allows for more efficient directed wakeups. For some "locks" postgres has queues implemented in userspace, with wakeup logic that cannot easily be implemented with FUTEX_WAKE_BITSET on a single "futex word" (imagine waiting for journal flushes to have completed up to a certain point). Thus a "lock release" sometimes need to wake up many processes in a row. A quick-and-dirty conversion to doing these wakeups via io_uring lead to a 3% throughput increase, with 12% fewer context switches, albeit in a fairly extreme workload."
Some basic io_uring futex support and test cases are available in the liburing 'futex' branch:
https://git.kernel.dk/cgit/liburing/log/?h=futex
testing all of the variants. I originally wrote this code about a month ago and Andres has been using it with postgres, and I'm not aware of any bugs in it. That's not to say it's perfect, obviously, and I welcome some feedback so we can move this forward and hash out any potential issues.
include/linux/io_uring_types.h | 3 + include/uapi/linux/io_uring.h | 4 + io_uring/Makefile | 4 +- io_uring/cancel.c | 5 + io_uring/cancel.h | 4 + io_uring/futex.c | 376 +++++++++++++++++++++++++++++++++ io_uring/futex.h | 36 ++++ io_uring/io_uring.c | 5 + io_uring/opdef.c | 35 ++- kernel/futex/futex.h | 33 +++ kernel/futex/requeue.c | 3 +- kernel/futex/syscalls.c | 27 ++- kernel/futex/waitwake.c | 49 +++-- 13 files changed, 548 insertions(+), 36 deletions(-)
You can also find the code here:
https://git.kernel.dk/cgit/linux/log/?h=io_uring-futex
V2:
- Abstract out __futex_wake_mark() helper. Use it both in the futex and io_uring code. This also fixes a missing WARN_ON on the io_uring side.
- Have futex_op_to_flags() unconditionally clear flags to zero rather than do that in both callers.
- Remove comment on needing to open-code futex_queue(), and associated hunk doing that. This was a leftover from an earlier version.
- Expand the commit message logs in various patches.
Signature · 1 line
Jens Axboe
Jens Axboe
maintainerPATCH v2 2/8 futex: factor out the futex wake handling
In preparation for having another waker that isn't futex_wake_mark(), add a wake handler in futex_q. No extra data is associated with the handler outside of struct futex_q itself. futex_wake_mark() is defined as the standard wakeup helper, now set through futex_q_init like other defaults.
Normal sync futex waiting relies on wake_q holding tasks that should be woken up. This is what futex_wake_mark() does, it'll unqueue the futex and add the associated task to the wake queue. For async usage of futex waiting, rather than having tasks sleeping on the futex, we'll need to deal with a futex wake differently. For the planned io_uring case, that means posting a completion event for the task in question. Having a definable wake handler can help support that use case.
--- kernel/futex/futex.h | 4 ++++ kernel/futex/requeue.c | 3 ++- kernel/futex/waitwake.c | 6 +++--- 3 files changed, 9 insertions(+), 4 deletions(-)
kernel/futex/futex.h +4 -0
@@ -69,6 +69,9 @@ struct futex_pi_state {union futex_key key; } __randomize_layout; +struct futex_q ; +typedef void (futex_wake_fn )(struct wake_q_head *wake_q,struct futex_q *q); +/** * struct futex_q - The hashed futex queue entry, one per waiting task * @list: priority-sorted list of tasks waiting on this futex
@@ -98,6 +101,7 @@ struct futex_q {struct task_struct *task;spinlock_t *lock_ptr; +futex_wake_fn *wake;union futex_key key;struct futex_pi_state *pi_state;struct rt_mutex_waiter *rt_waiter;
kernel/futex/requeue.c +2 -1
@@ -58,6 +58,7 @@ enum {const struct futex_q futex_q_init = {/* list gets initialized in futex_queue()*/ + .wake = futex_wake_mark, .key =FUTEX_KEY_INIT , .bitset =FUTEX_BITSET_MATCH_ANY , .requeue_state =ATOMIC_INIT (Q_REQUEUE_PI_NONE ),
@@ -591,7 +592,7 @@ int futex_requeue(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,/* Plain futexes just wake or requeue and are done */ if (!requeue_pi) {if (++task_count <= nr_wake) -futex_wake_mark (&wake_q, this); + this->wake (&wake_q, this);else requeue_futex (this, hb1, hb2, &key2);continue ;
kernel/futex/waitwake.c +3 -3
@@ -174,7 +174,7 @@ int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)if (!(this->bitset & bitset))continue ; -futex_wake_mark (&wake_q, this); + this->wake (&wake_q, this);if (++ret >= nr_wake)break ; }
@@ -289,7 +289,7 @@ int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, ret = -EINVAL ; goto out_unlock; } -futex_wake_mark (&wake_q, this); + this->wake (&wake_q, this);if (++ret >= nr_wake)break ; }
@@ -303,7 +303,7 @@ int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, ret = -EINVAL ; goto out_unlock; } -futex_wake_mark (&wake_q, this); + this->wake (&wake_q, this);if (++op_ret >= nr_wake2)break ; }
Signature · 1 line
2.40.1
Jens Axboe
maintainerPATCH v2 3/8 futex: abstract out a __futex_wake_mark() helper
In reply to Jens AxboeMove the unqueue and lock_ptr clear into a helper that futex_wake_mark() calls. Add it to the public functions as well, in preparation for using it outside the core futex code.
--- kernel/futex/futex.h | 1 + kernel/futex/waitwake.c | 33 ++++++++++++++++++++++----------- 2 files changed, 23 insertions(+), 11 deletions(-)
kernel/futex/futex.h +1 -0
@@ -148,6 +148,7 @@ extern int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, struct futex_q *q, struct futex_hash_bucket **hb);extern void futex_wait_queue (struct futex_hash_bucket *hb,struct futex_q *q,struct hrtimer_sleeper *timeout); +extern bool __futex_wake_mark (struct futex_q *q);extern void futex_wake_mark (struct wake_q_head *wake_q,struct futex_q *q);extern int fault_in_user_writeable (u32 __user *uaddr);
kernel/futex/waitwake.c +22 -11
@@ -106,20 +106,11 @@* double_lock_hb() and double_unlock_hb(), respectively. */ -/* -* The hash bucket lock must be held when this is called. -* Afterwards, the futex_q must not be accessed. Callers -* must ensure to later call wake_up_q() for the actual -* wakeups to occur. -*/ -void futex_wake_mark (struct wake_q_head *wake_q,struct futex_q *q) +bool __futex_wake_mark (struct futex_q *q) { -struct task_struct *p = q->task; -if (WARN (q->pi_state || q->rt_waiter,"refusing to wake PI futex\n" )) -return ; +return false; -get_task_struct (p);__futex_unqueue (q);/* * The waiting task can free the futex_q as soon as q->lock_ptr = NULL
@@ -130,6 +121,26 @@ void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q)*/ smp_store_release (&q->lock_ptr,NULL ); +return true; +} + +/* +* The hash bucket lock must be held when this is called. +* Afterwards, the futex_q must not be accessed. Callers +* must ensure to later call wake_up_q() for the actual +* wakeups to occur. +*/ +void futex_wake_mark (struct wake_q_head *wake_q,struct futex_q *q) +{ +struct task_struct *p = q->task; + +get_task_struct (p); + +if (!__futex_wake_mark (q)) { +put_task_struct (p); +return ; + } +/* * Queue the task for later wakeup for after we've released * the hb->lock.
Signature · 1 line
2.40.1
Jens Axboe
maintainerPATCH v2 4/8 io_uring: add support for futex wake and wait
In reply to Jens AxboeAdd support for FUTEX_WAKE/WAIT primitives.
IORING_OP_FUTEX_WAKE is mix of FUTEX_WAKE and FUTEX_WAKE_BITSET, as it does support passing in a bitset.
Similary, IORING_OP_FUTEX_WAIT is a mix of FUTEX_WAIT and FUTEX_WAIT_BITSET.
FUTEX_WAKE is straight forward, as those can always be done directly from the io_uring submission without needing async handling. For FUTEX_WAIT, things are a bit more complicated. If the futex isn't ready, then we rely on a callback via futex_queue->wake() when someone wakes up the futex. From that calback, we queue up task_work with the original task, which will post a CQE and wake it, if necessary.
Cancelations are supported, both from the application point-of-view, but also to be able to cancel pending waits if the ring exits before all events have occurred.
This is just the barebones wait/wake support. PI or REQUEUE support is not added at this point, unclear if we might look into that later.
Likewise, explicit timeouts are not supported either. It is expected that users that need timeouts would do so via the usual io_uring mechanism to do that using linked timeouts.
--- include/linux/io_uring_types.h | 3 + include/uapi/linux/io_uring.h | 3 + io_uring/Makefile | 4 +- io_uring/cancel.c | 5 + io_uring/cancel.h | 4 + io_uring/futex.c | 232 +++++++++++++++++++++++++++++++++ io_uring/futex.h | 34 +++++ io_uring/io_uring.c | 5 + io_uring/opdef.c | 24 +++- 9 files changed, 312 insertions(+), 2 deletions(-) create mode 100644 io_uring/futex.c create mode 100644 io_uring/futex.h
include/linux/io_uring_types.h +3 -0
@@ -273,6 +273,9 @@ struct io_ring_ctx {struct io_wq_work_list locked_free_list;unsigned int locked_free_nr; +struct hlist_head futex_list; +struct io_alloc_cache futex_cache; +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 +3 -0
@@ -65,6 +65,7 @@ struct io_uring_sqe {__u32 xattr_flags;__u32 msg_ring_flags;__u32 uring_cmd_flags; +__u32 futex_flags; };__u64 user_data;/* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */
@@ -235,6 +236,8 @@ enum io_uring_op {IORING_OP_URING_CMD ,IORING_OP_SEND_ZC ,IORING_OP_SENDMSG_ZC , +IORING_OP_FUTEX_WAIT , +IORING_OP_FUTEX_WAKE ,/* this goes last, obviously */ IORING_OP_LAST,
io_uring/Makefile +3 -1
@@ -7,5 +7,7 @@ obj-$(CONFIG_IO_URING) += io_uring.o xattr.o nop.o fs.o splice.o \ openclose.o uring_cmd.o epoll.o \ statx.o net.o msg_ring.o timeout.o \ sqpoll.o fdinfo.o tctx.o poll.o \ - cancel.o kbuf.o rsrc.o rw.o opdef.o notif.o + cancel.o kbuf.o rsrc.o rw.o opdef.o \ + notif.o obj-$(CONFIG_IO_WQ) += io-wq.o +obj-$(CONFIG_FUTEX) += futex.o
io_uring/cancel.c +5 -0
@@ -15,6 +15,7 @@#include "tctx.h" #include "poll.h" #include "timeout.h" +#include "futex.h" #include "cancel.h" struct io_cancel {
@@ -119,6 +120,10 @@ int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd,if (ret != -ENOENT )return ret; + ret =io_futex_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/cancel.h +4 -0
@@ -1,4 +1,6 @@// SPDX-License-Identifier: GPL-2.0 +#ifndef IORING_CANCEL_H +#define IORING_CANCEL_H #include <linux/io_uring_types.h>
@@ -22,3 +24,5 @@ void init_hash_table(struct io_hash_table *table, unsigned size);int io_sync_cancel (struct io_ring_ctx *ctx,void __user *arg);bool io_cancel_req_match (struct io_kiocb *req,struct io_cancel_data *cd); + +#endif
io_uring/futex.c new file +232 -0
232 lines not on this page · raw message
io_uring/futex.h new file +34 -0
@@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "cancel.h" + +int io_futex_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe); +int io_futex_wait (struct io_kiocb *req,unsigned int issue_flags); +int io_futex_wake (struct io_kiocb *req,unsigned int issue_flags); + +#if defined(CONFIG_FUTEX ) +int io_futex_cancel (struct io_ring_ctx *ctx,struct io_cancel_data *cd, +unsigned int issue_flags); +bool io_futex_remove_all (struct io_ring_ctx *ctx,struct task_struct *task, +bool cancel_all); +void io_futex_cache_init (struct io_ring_ctx *ctx); +void io_futex_cache_free (struct io_ring_ctx *ctx); +#else +static inline int io_futex_cancel (struct io_ring_ctx *ctx, +struct io_cancel_data *cd, +unsigned int issue_flags) +{ +return 0 ; +} +static inline bool io_futex_remove_all (struct io_ring_ctx *ctx, +struct task_struct *task,bool cancel_all) +{ +return false; +} +static inline void io_futex_cache_init (struct io_ring_ctx *ctx) +{ +} +static inline void io_futex_cache_free (struct io_ring_ctx *ctx) +{ +} +#endif
io_uring/io_uring.c +5 -0
@@ -92,6 +92,7 @@#include "cancel.h" #include "net.h" #include "notif.h" +#include "futex.h" #include "timeout.h" #include "poll.h"
@@ -314,6 +315,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) sizeof(struct async_poll));io_alloc_cache_init (&ctx->netmsg_cache,IO_ALLOC_CACHE_MAX ,sizeof (struct io_async_msghdr )); +io_futex_cache_init (ctx);init_completion (&ctx->ref_comp);xa_init_flags (&ctx->personalities,XA_FLAGS_ALLOC1 );mutex_init (&ctx->uring_lock);
@@ -333,6 +335,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)INIT_LIST_HEAD (&ctx->tctx_list); ctx->submit_state.free_list.next =NULL ;INIT_WQ_LIST (&ctx->locked_free_list); +INIT_HLIST_HEAD (&ctx->futex_list);INIT_DELAYED_WORK (&ctx->fallback_work, io_fallback_req_func);INIT_WQ_LIST (&ctx->submit_state.compl_reqs);return ctx;
@@ -2842,6 +2845,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)io_eventfd_unregister (ctx);io_alloc_cache_free (&ctx->apoll_cache, io_apoll_cache_free);io_alloc_cache_free (&ctx->netmsg_cache, io_netmsg_cache_free); +io_futex_cache_free (ctx);io_destroy_buffers (ctx);mutex_unlock (&ctx->uring_lock);if (ctx->sq_creds)
@@ -3254,6 +3258,7 @@ static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, ret |=io_cancel_defer_files (ctx, task, cancel_all);mutex_lock (&ctx->uring_lock); ret |=io_poll_remove_all (ctx, task, cancel_all); + ret |=io_futex_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 +23 -1
@@ -33,6 +33,7 @@#include "poll.h" #include "cancel.h" #include "rw.h" +#include "futex.h" static int io_no_issue (struct io_kiocb *req,unsigned int issue_flags) {
@@ -426,11 +427,26 @@ const struct io_issue_def io_issue_defs[] = { .issue = io_sendmsg_zc, #else .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_FUTEX_WAIT ] = { +#if defined(CONFIG_FUTEX) + .prep = io_futex_prep, + .issue = io_futex_wait, +#else + .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_FUTEX_WAKE ] = { +#if defined(CONFIG_FUTEX) + .prep = io_futex_prep, + .issue = io_futex_wake, +#else + .prep = io_eopnotsupp_prep, #endif }, }; -const struct io_cold_def io_cold_defs[] = { [IORING_OP_NOP ] = { .name ="NOP" ,
@@ -648,6 +664,12 @@ const struct io_cold_def io_cold_defs[] = { .fail = io_sendrecv_fail, #endif }, + [IORING_OP_FUTEX_WAIT ] = { + .name ="FUTEX_WAIT" , + }, + [IORING_OP_FUTEX_WAKE ] = { + .name ="FUTEX_WAKE" , + }, };const char *io_uring_get_opcode (u8 opcode)
Signature · 1 line
2.40.1
Jens Axboe
maintainerPATCH v2 5/8 futex: add wake_data to struct futex_q
In reply to Jens AxboeWith handling multiple futex_q for waitv, we cannot easily go from the futex_q to data related to that request or queue. Add a wake_data argument that belongs to the wake handler assigned.
--- kernel/futex/futex.h | 1 + 1 file changed, 1 insertion(+)
kernel/futex/futex.h +1 -0
@@ -102,6 +102,7 @@ struct futex_q {struct task_struct *task;spinlock_t *lock_ptr;futex_wake_fn *wake; +void *wake_data;union futex_key key;struct futex_pi_state *pi_state;struct rt_mutex_waiter *rt_waiter;
Signature · 1 line
2.40.1
Jens Axboe
maintainerPATCH v2 6/8 futex: make futex_parse_waitv() available as a helper
In reply to Jens AxboeTo make it more generically useful, augment it with allowing the caller to pass in the wake handler and wake data. Convert the futex_waitv() syscall, passing in the default handlers.
--- kernel/futex/futex.h | 5 +++++ kernel/futex/syscalls.c | 14 ++++++++++---- 2 files changed, 15 insertions(+), 4 deletions(-)
kernel/futex/futex.h +5 -0
@@ -285,6 +285,11 @@ struct futex_vector {struct futex_q q; }; +extern int futex_parse_waitv (struct futex_vector *futexv, +struct futex_waitv __user *uwaitv, +unsigned int nr_futexes,futex_wake_fn *wake, +void *wake_data); +extern int futex_wait_multiple (struct futex_vector *vs,unsigned int count,struct hrtimer_sleeper *to);
kernel/futex/syscalls.c +10 -4
@@ -184,12 +184,15 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,* @futexv: Kernel side list of waiters to be filled * @uwaitv: Userspace list to be parsed * @nr_futexes: Length of futexv +* @wake: Wake to call when futex is woken +* @wake_data: Data for the wake handler * * Return: Error code on failure, 0 on success */ -static int futex_parse_waitv (struct futex_vector *futexv, -struct futex_waitv __user *uwaitv, -unsigned int nr_futexes) +int futex_parse_waitv (struct futex_vector *futexv, +struct futex_waitv __user *uwaitv, +unsigned int nr_futexes,futex_wake_fn *wake, +void *wake_data) {struct futex_waitv aux;unsigned int i;
@@ -208,6 +211,8 @@ static int futex_parse_waitv(struct futex_vector *futexv, futexv[i].w.val = aux.val; futexv[i].w.uaddr = aux.uaddr; futexv[i].q = futex_q_init; + futexv[i].q.wake = wake; + futexv[i].q.wake_data = wake_data; }return 0 ;
@@ -284,7 +289,8 @@ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, goto destroy_timer; } - ret =futex_parse_waitv (futexv, waiters, nr_futexes); + ret =futex_parse_waitv (futexv, waiters, nr_futexes, futex_wake_mark, +NULL );if (!ret) ret =futex_wait_multiple (futexv, nr_futexes, timeout ? &to :NULL );
Signature · 1 line
2.40.1
Jens Axboe
maintainerPATCH v2 7/8 futex: make the vectored futex operations available
In reply to Jens AxboeRename unqueue_multiple() as futex_unqueue_multiple(), and make both that and futex_wait_multiple_setup() available for external users. This is in preparation for wiring up vectored waits in io_uring.
--- kernel/futex/futex.h | 5 +++++ kernel/futex/waitwake.c | 10 +++++----- 2 files changed, 10 insertions(+), 5 deletions(-)
kernel/futex/futex.h +5 -0
@@ -290,6 +290,11 @@ extern int futex_parse_waitv(struct futex_vector *futexv, unsigned int nr_futexes, futex_wake_fn *wake, void *wake_data); +extern int futex_wait_multiple_setup (struct futex_vector *vs,int count, +int *woken); + +extern int futex_unqueue_multiple (struct futex_vector *v,int count); +extern int futex_wait_multiple (struct futex_vector *vs,unsigned int count,struct hrtimer_sleeper *to);
kernel/futex/waitwake.c +5 -5
@@ -369,7 +369,7 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, }/** -* unqueue_multiple - Remove various futexes from their hash bucket +* futex_unqueue_multiple - Remove various futexes from their hash bucket * @v: The list of futexes to unqueue * @count: Number of futexes in the list *
@@ -379,7 +379,7 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q,* - >=0 - Index of the last futex that was awoken; * - -1 - No futex was awoken */ -static int unqueue_multiple (struct futex_vector *v,int count) +int futex_unqueue_multiple (struct futex_vector *v,int count) {int ret =-1 , i;
@@ -407,7 +407,7 @@ static int unqueue_multiple(struct futex_vector *v, int count)* - 0 - Success * - <0 - -EFAULT, -EWOULDBLOCK or -EINVAL */ -static int futex_wait_multiple_setup (struct futex_vector *vs,int count,int *woken) +int futex_wait_multiple_setup (struct futex_vector *vs,int count,int *woken) {struct futex_hash_bucket *hb;bool retry = false;
@@ -469,7 +469,7 @@ static int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *wo* was woken, we don't return error and return this index to * userspace */ - *woken =unqueue_multiple (vs, i); + *woken =futex_unqueue_multiple (vs, i);if (*woken >=0 )return 1 ;
@@ -554,7 +554,7 @@ int futex_wait_multiple(struct futex_vector *vs, unsigned int count,__set_current_state (TASK_RUNNING ); - ret =unqueue_multiple (vs, count); + ret =futex_unqueue_multiple (vs, count);if (ret >=0 )return ret;
Signature · 1 line
2.40.1
Jens Axboe
maintainerPATCH v2 8/8 io_uring: add support for vectored futex waits
In reply to Jens AxboeThis adds support for IORING_OP_FUTEX_WAITV, which allows registering a notification for a number of futexes at once. If one of the futexes are woken, then the request will complete with the index of the futex that got woken as the result. This is identical to what the normal vectored futex waitv operation does.
Use like IORING_OP_FUTEX_WAIT, except sqe->addr must now contain the a pointer to a struct futex_waitv array, and sqe->off must now contain the number of elements in that array.
Waiting on N futexes could be done with IORING_OP_FUTEX_WAIT as well, but that punts a lot of the work to the application:
1) Application would need to submit N IORING_OP_FUTEX_WAIT requests, rather than just a single IORING_OP_FUTEX_WAITV.
2) When one futex is woken, application would need to cancel the remaining N-1 requests that didn't trigger.
While this is of course doable, having a single vectored futex wait makes for much simpler application code.
--- include/uapi/linux/io_uring.h | 1 + io_uring/futex.c | 164 +++++++++++++++++++++++++++++++--- io_uring/futex.h | 2 + io_uring/opdef.c | 11 +++ 4 files changed, 168 insertions(+), 10 deletions(-)
include/uapi/linux/io_uring.h +1 -0
@@ -238,6 +238,7 @@ enum io_uring_op {IORING_OP_SENDMSG_ZC ,IORING_OP_FUTEX_WAIT ,IORING_OP_FUTEX_WAKE , +IORING_OP_FUTEX_WAITV ,/* this goes last, obviously */ IORING_OP_LAST,
io_uring/futex.c +154 -10
212 lines not on this page · raw message
io_uring/futex.h +2 -0
@@ -3,7 +3,9 @@#include "cancel.h" int io_futex_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe); +int io_futexv_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe);int io_futex_wait (struct io_kiocb *req,unsigned int issue_flags); +int io_futex_waitv (struct io_kiocb *req,unsigned int issue_flags);int io_futex_wake (struct io_kiocb *req,unsigned int issue_flags);#if defined(CONFIG_FUTEX )
io_uring/opdef.c +11 -0
@@ -443,6 +443,14 @@ const struct io_issue_def io_issue_defs[] = { .issue = io_futex_wake, #else .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_FUTEX_WAITV] = { +#if defined(CONFIG_FUTEX ) + .prep = io_futexv_prep, + .issue = io_futex_waitv, +#else + .prep = io_eopnotsupp_prep,#endif }, };
@@ -670,6 +678,9 @@ const struct io_cold_def io_cold_defs[] = { [IORING_OP_FUTEX_WAKE ] = { .name ="FUTEX_WAKE" , }, + [IORING_OP_FUTEX_WAITV ] = { + .name ="FUTEX_WAITV" , + }, };const char *io_uring_get_opcode (u8 opcode)
Signature · 1 line
2.40.1
Jens Axboe
maintainerPATCH v2 1/8 futex: abstract out futex_op_to_flags() helper
In reply to Jens AxboeRather than needing to duplicate this for the io_uring hook of futexes, abstract out a helper.
No functional changes intended in this patch.
--- kernel/futex/futex.h | 17 +++++++++++++++++ kernel/futex/syscalls.c | 13 +++---------- 2 files changed, 20 insertions(+), 10 deletions(-)
kernel/futex/futex.h +17 -0
@@ -291,4 +291,21 @@ extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags);extern int futex_lock_pi (u32 __user *uaddr,unsigned int flags,ktime_t *time,int trylock); +static inline bool futex_op_to_flags (int op,int cmd,unsigned int *flags) +{ + *flags =0 ; + +if (!(op &FUTEX_PRIVATE_FLAG )) + *flags |=FLAGS_SHARED ; + +if (op &FUTEX_CLOCK_REALTIME ) { + *flags |=FLAGS_CLOCKRT ; +if (cmd !=FUTEX_WAIT_BITSET && cmd !=FUTEX_WAIT_REQUEUE_PI && + cmd !=FUTEX_LOCK_PI2 ) +return false; + } + +return true; +} +#endif /* _FUTEX_H */
kernel/futex/syscalls.c +3 -10
@@ -86,17 +86,10 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) { int cmd = op & FUTEX_CMD_MASK; -unsigned int flags =0 ; +unsigned int flags; -if (!(op &FUTEX_PRIVATE_FLAG )) - flags |=FLAGS_SHARED ; - -if (op &FUTEX_CLOCK_REALTIME ) { - flags |=FLAGS_CLOCKRT ; -if (cmd !=FUTEX_WAIT_BITSET && cmd !=FUTEX_WAIT_REQUEUE_PI && - cmd !=FUTEX_LOCK_PI2 ) -return -ENOSYS ; - } +if (!futex_op_to_flags (op, cmd, &flags)) +return -ENOSYS ;switch (cmd) {case FUTEX_WAIT :
Signature · 1 line
2.40.1
Jens Axboe
maintainerNeglected to mention, that I have run this through the ltp futex tests, and there are no changes. All tests pass.
Signature · 1 line
Jens Axboe
Peter Zijlstra
reviewerRe: [PATCH 4/8] io_uring: add support for futex wake and wait
In reply to Jens AxboeQuoted 7 lines · Jens Axboe
io_uring/futex.c new file +7
-0+int io_futex_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + +if (unlikely (sqe->addr2 || sqe->buf_index || sqe->addr3)) +return -EINVAL ; +
io_uring/futex.c line 139
Quoted 10 lines
io_uring/futex.c new file +10
-0+ iof->futex_op =READ_ONCE (sqe->fd); + iof->uaddr =u64_to_user_ptr (READ_ONCE (sqe->addr)); + iof->futex_val =READ_ONCE (sqe->len); + iof->futex_mask =READ_ONCE (sqe->file_index); + iof->futex_flags =READ_ONCE (sqe->futex_flags); +if (iof->futex_flags &FUTEX_CMD_MASK ) +return -EINVAL ; + +return 0 ; +}
I'm a little confused on the purpose of iof->futex_op, it doesn't appear to be used. Instead iof->futex_flags is used as the ~FUTEX_CMD_MASK part of ops.
The latter actually makes sense since you encode the actual op in the IOURING_OP_ space.
Quoted 4 lines
io_uring/futex.c new file +4
-0+int io_futex_wait (struct io_kiocb *req,unsigned int issue_flags) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); +struct io_ring_ctx *ctx = req->ctx;
io_uring/futex.c line 178
Quoted 10 lines
io_uring/futex.c new file +10
-0+struct io_futex_data *ifd =NULL ; +struct futex_hash_bucket *hb; +unsigned int flags; +int ret; + +if (!iof->futex_mask) { + ret = -EINVAL ; + goto done; + } +if (!futex_op_to_flags (FUTEX_WAIT , iof->futex_flags, &flags)) {
A little confusing since you then implement FUTEX_WAIT_BITSET, but using FUTEX_WAIT ensures this goes -ENOSYS when setting FUTEX_CLOCK_REALTIME, since you handle timeouts through the iouring thing.
Perhaps a comment?
Quoted 25 lines
io_uring/futex.c new file +25
-0+ ret = -ENOSYS ; + goto done; + } + +io_ring_submit_lock (ctx, issue_flags); + ifd =io_alloc_ifd (ctx); +if (!ifd) { + ret = -ENOMEM ; + goto done_unlock; + } + + req->async_data = ifd; + ifd->q = futex_q_init; + ifd->q.bitset = iof->futex_mask; + ifd->q.wake = io_futex_wake_fn; + ifd->req = req; + + ret =futex_wait_setup (iof->uaddr, iof->futex_val, flags, &ifd->q, &hb); +if (!ret) { +hlist_add_head (&req->hash_node, &ctx->futex_list); +io_ring_submit_unlock (ctx, issue_flags); + +futex_queue (&ifd->q, hb); +return IOU_ISSUE_SKIP_COMPLETE ; + }
io_uring/futex.c line 213
Quoted 10 lines
io_uring/futex.c new file +10
-0+ +done_unlock: +io_ring_submit_unlock (ctx, issue_flags); +done: +if (ret <0 ) +req_set_fail (req); +io_req_set_res (req, ret,0 ); +kfree (ifd); +return IOU_OK ; +}
Other than that, I think these things are indeed transparant wrt the existing futex interface. If we add a flag this shouldn't care.
Peter Zijlstra
reviewerRe: [PATCH 8/8] io_uring: add support for vectored futex waits
In reply to Jens Axboeio_uring/futex.h line 9
Quoted 5 lines · Jens Axboe
int
io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);io_uring/futex.h +2
-0+int io_futexv_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe);int io_futex_wait (struct io_kiocb *req,unsigned int issue_flags); +int io_futex_waitv (struct io_kiocb *req,unsigned int issue_flags);int io_futex_wake (struct io_kiocb *req,unsigned int issue_flags);
That's an inconsistent naming convention.. I'll stare at the rest later.
Jens Axboe
maintainerRe: [PATCH 4/8] io_uring: add support for futex wake and wait
In reply to Peter ZijlstraQuoted 24 lines · Peter Zijlstra
Quoted 7 lines · Jens Axboe
(quoted diff) +7
-0+int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + + if (unlikely(sqe->addr2 || sqe->buf_index || sqe->addr3)) + return -EINVAL; +Review
Quoted 10 lines
(quoted diff) +10
-0+ iof->futex_op = READ_ONCE(sqe->fd); + iof->uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + iof->futex_val = READ_ONCE(sqe->len); + iof->futex_mask = READ_ONCE(sqe->file_index); + iof->futex_flags = READ_ONCE(sqe->futex_flags); + if (iof->futex_flags & FUTEX_CMD_MASK) + return -EINVAL; + + return 0; +}I'm a little confused on the purpose of
iof->futex_op, it doesn't appear to be used. Insteadiof->futex_flagsis used as the ~FUTEX_CMD_MASK part of ops.
Quoted 2 lines
The latter actually makes sense since you encode the actual op in the
IOURING_OP_space.
Yep, I think this is also a leftover from when I had it multiplexed a bit more. The liburing side got fixed for that, but neglected this bit. Good catch. I'll fold the below in.
Quoted 20 lines
Quoted 5 lines
(quoted diff) +4
-0+int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + struct io_ring_ctx *ctx = req->ctx;Review
Quoted 10 lines
(quoted diff) +10
-0+ struct io_futex_data *ifd = NULL; + struct futex_hash_bucket *hb; + unsigned int flags; + int ret; + + if (!iof->futex_mask) { + ret = -EINVAL; + goto done; + } + if (!futex_op_to_flags(FUTEX_WAIT, iof->futex_flags, &flags)) {A little confusing since you then implement
FUTEX_WAIT_BITSET, but usingFUTEX_WAITensures this goes-ENOSYSwhen settingFUTEX_CLOCK_REALTIME, since you handle timeouts through the iouring thing.
Quoted 1 line
Perhaps a comment?
OK, will add a comment on that.
Quoted 30 lines
Quoted 30 lines
(quoted diff) +30
-0+ ret = -ENOSYS; + goto done; + } + + io_ring_submit_lock(ctx, issue_flags); + ifd = io_alloc_ifd(ctx); + if (!ifd) { + ret = -ENOMEM; + goto done_unlock; + } + + req->async_data = ifd; + ifd->q = futex_q_init; + ifd->q.bitset = iof->futex_mask; + ifd->q.wake = io_futex_wake_fn; + ifd->req = req; + + ret = futex_wait_setup(iof->uaddr, iof->futex_val, flags, &ifd->q, &hb); + if (!ret) { + hlist_add_head(&req->hash_node, &ctx->futex_list); + io_ring_submit_unlock(ctx, issue_flags); + + futex_queue(&ifd->q, hb); + return IOU_ISSUE_SKIP_COMPLETE; + } + +done_unlock: + io_ring_submit_unlock(ctx, issue_flags); +done: + if (ret < 0)
Quoted 8 lines
Review
Quoted 5 lines
(quoted diff) +5
-0+ req_set_fail(req); + io_req_set_res(req, ret, 0); + kfree(ifd); + return IOU_OK; +}Other than that, I think these things are indeed transparant wrt the existing futex interface. If we add a flag this shouldn't care.
Not sure I follow, what kind of flag do you want/need?
io_uring/futex.c +1 -3
@@ -18,7 +18,6 @@ struct io_futex {u32 __user *uaddr;struct futex_waitv __user *uwaitv; }; -int futex_op;unsigned int futex_val;unsigned int futex_flags;unsigned int futex_mask;
@@ -173,10 +172,9 @@ int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); -if (unlikely (sqe->buf_index || sqe->addr3)) +if (unlikely (sqe->fd || sqe->buf_index || sqe->addr3))return -EINVAL ; - iof->futex_op =READ_ONCE (sqe->fd); iof->uaddr =u64_to_user_ptr (READ_ONCE (sqe->addr)); iof->futex_val =READ_ONCE (sqe->len); iof->futex_mask =READ_ONCE (sqe->file_index);
Signature · 1 line
Jens Axboe
Jens Axboe
maintainerRe: [PATCH 8/8] io_uring: add support for vectored futex waits
In reply to Peter ZijlstraQuoted 8 lines · Peter Zijlstra
io_uring/futex.h line 9
Quoted 5 lines · Jens Axboe
int
io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);io_uring/futex.h +2
-0+int io_futexv_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe);int io_futex_wait (struct io_kiocb *req,unsigned int issue_flags); +int io_futex_waitv (struct io_kiocb *req,unsigned int issue_flags);int io_futex_wake (struct io_kiocb *req,unsigned int issue_flags);That's an inconsistent naming convention.. I'll stare at the rest later.
I had to stare at that a bit.. Yes it is, I'll unify that.
Signature · 1 line
Jens Axboe
Peter Zijlstra
reviewerRe: [PATCH 4/8] io_uring: add support for futex wake and wait
In reply to Peter ZijlstraQuoted 24 lines · Peter Zijlstra
Quoted 7 lines · Jens Axboe
io_uring/futex.c new file +7
-0+int io_futex_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + +if (unlikely (sqe->addr2 || sqe->buf_index || sqe->addr3)) +return -EINVAL ; +io_uring/futex.c line 139
Quoted 10 lines
io_uring/futex.c new file +10
-0+ iof->futex_op =READ_ONCE (sqe->fd); + iof->uaddr =u64_to_user_ptr (READ_ONCE (sqe->addr)); + iof->futex_val =READ_ONCE (sqe->len); + iof->futex_mask =READ_ONCE (sqe->file_index); + iof->futex_flags =READ_ONCE (sqe->futex_flags); +if (iof->futex_flags &FUTEX_CMD_MASK ) +return -EINVAL ; + +return 0 ; +}I'm a little confused on the purpose of
iof->futex_op, it doesn't appear to be used. Insteadiof->futex_flagsis used as the ~FUTEX_CMD_MASK part of ops.
Quoted 2 lines
The latter actually makes sense since you encode the actual op in the
IOURING_OP_space.
Futex is slowly getting back to me; I'm thinking these io_uring interfaces should perhaps use the futex2 flags instead of the futex_op encoded muck.
I'll try and send out a few patches tomorrow to clarify things a little -- the futex2 work seems to have stalled somewhere halfway :/
Jens Axboe
maintainerRe: [PATCH 4/8] io_uring: add support for futex wake and wait
Quoted 28 lines · Peter Zijlstra
Quoted 24 lines · Peter Zijlstra
Quoted 7 lines · Jens Axboe
io_uring/futex.c new file +7
-0+int io_futex_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + +if (unlikely (sqe->addr2 || sqe->buf_index || sqe->addr3)) +return -EINVAL ; +io_uring/futex.c line 139
Quoted 10 lines
io_uring/futex.c new file +10
-0+ iof->futex_op =READ_ONCE (sqe->fd); + iof->uaddr =u64_to_user_ptr (READ_ONCE (sqe->addr)); + iof->futex_val =READ_ONCE (sqe->len); + iof->futex_mask =READ_ONCE (sqe->file_index); + iof->futex_flags =READ_ONCE (sqe->futex_flags); +if (iof->futex_flags &FUTEX_CMD_MASK ) +return -EINVAL ; + +return 0 ; +}I'm a little confused on the purpose of
iof->futex_op, it doesn't appear to be used. Insteadiof->futex_flagsis used as the ~FUTEX_CMD_MASK part of ops.Quoted 2 lines
The latter actually makes sense since you encode the actual op in the
IOURING_OP_space.
Quoted 6 lines
Futex is slowly getting back to me; I'm thinking these
io_uringinterfaces should perhaps use the futex2 flags instead of thefutex_opencoded muck.I'll try and send out a few patches tomorrow to clarify things a little -- the futex2 work seems to have stalled somewhere halfway :/
Saw your series - I'll take a look. In terms of staging when we get there, would it be possible to split your flags series into the bare minimum and trivial, and then have that as a dependency for this series and the rest of your series?
Signature · 1 line
Jens Axboe
Peter Zijlstra
reviewerRe: [PATCH 4/8] io_uring: add support for futex wake and wait
Quoted 4 lines · Jens Axboe
Saw your series - I'll take a look. In terms of staging when we get there, would it be possible to split your flags series into the bare minimum and trivial, and then have that as a dependency for this series and the rest of your series?
I think you only really need the first three patches, and I hope those are the least controversial of the lot.
After those, I can implement the extra flags independently of the io_uring thing and all interfaces should just have it work.
So yes :-)
Jens Axboe
maintainerRe: [PATCH 4/8] io_uring: add support for futex wake and wait
Quoted 8 lines · Peter Zijlstra
Quoted 4 lines · Jens Axboe
Saw your series - I'll take a look. In terms of staging when we get there, would it be possible to split your flags series into the bare minimum and trivial, and then have that as a dependency for this series and the rest of your series?
I think you only really need the first three patches, and I hope those are the least controversial of the lot.
That's what it looks like to me, and yes those look trivial and risk free :-)
I'll just put those at the base of my series for now, and once they are stamped, would be great if you could then stuff them in a stable branch that I could pull in.
Quoted 4 lines
After those, I can implement the extra flags independently of the
io_uringthing and all interfaces should just have it work.So yes :-)
That's the plan then!
Signature · 1 line
Jens Axboe