Add io_uring futex/futexv support
Jens Axboe
maintainerPATCH 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
@@ -219,6 +219,7 @@ 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 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. The return value of futex_unqueue() is used to gate who wins the potential race between cancelation and futex wakeups. Whomever gets a 'ret == 1' return from that claims ownership of the io_uring futex request.
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 | 5 + include/uapi/linux/io_uring.h | 3 + io_uring/Makefile | 1 + io_uring/cancel.c | 5 + io_uring/cancel.h | 4 + io_uring/futex.c | 230 +++++++++++++++++++++++++++++++++ io_uring/futex.h | 34 +++++ io_uring/io_uring.c | 7 + io_uring/opdef.c | 23 ++++ 9 files changed, 312 insertions(+) create mode 100644 io_uring/futex.c create mode 100644 io_uring/futex.h
include/linux/io_uring_types.h +5 -0
@@ -315,6 +315,11 @@ struct io_ring_ctx {struct hlist_head waitid_list; +#ifdef CONFIG_FUTEX +struct hlist_head futex_list; +struct io_alloc_cache futex_cache; +#endif +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
@@ -66,6 +66,7 @@ struct io_uring_sqe {__u32 msg_ring_flags;__u32 uring_cmd_flags;__u32 waitid_flags; +__u32 futex_flags; };__u64 user_data;/* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */
@@ -243,6 +244,8 @@ enum io_uring_op {IORING_OP_SENDMSG_ZC ,IORING_OP_READ_MULTISHOT ,IORING_OP_WAITID , +IORING_OP_FUTEX_WAIT , +IORING_OP_FUTEX_WAKE ,/* this goes last, obviously */ IORING_OP_LAST,
io_uring/Makefile +1 -0
@@ -10,3 +10,4 @@ obj-$(CONFIG_IO_URING) += io_uring.o xattr.o nop.o fs.o splice.o \ cancel.o kbuf.o rsrc.o rw.o opdef.o \ notif.o waitid.o obj-$(CONFIG_IO_WQ) += io-wq.o +obj-$(CONFIG_FUTEX) += futex.o
io_uring/cancel.c +5 -0
@@ -16,6 +16,7 @@#include "poll.h" #include "timeout.h" #include "waitid.h" +#include "futex.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_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 +230 -0
230 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 +7 -0
@@ -93,6 +93,7 @@#include "net.h" #include "notif.h" #include "waitid.h" +#include "futex.h" #include "timeout.h" #include "poll.h"
@@ -330,6 +331,7 @@ 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);
@@ -350,6 +352,9 @@ 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->waitid_list); +#ifdef CONFIG_FUTEX +INIT_HLIST_HEAD (&ctx->futex_list); +#endif INIT_DELAYED_WORK (&ctx->fallback_work, io_fallback_req_func);INIT_WQ_LIST (&ctx->submit_state.compl_reqs);return ctx;
@@ -2894,6 +2899,7 @@ 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)
@@ -3306,6 +3312,7 @@ 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_waitid_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 -0
@@ -34,6 +34,7 @@#include "cancel.h" #include "rw.h" #include "waitid.h" +#include "futex.h" static int io_no_issue (struct io_kiocb *req,unsigned int issue_flags) {
@@ -444,6 +445,22 @@ const struct io_issue_def io_issue_defs[] = { .prep = io_waitid_prep, .issue = io_waitid, }, + [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[] = {
@@ -670,6 +687,12 @@ const struct io_cold_def io_cold_defs[] = { .name = "WAITID", .async_size = sizeof(struct io_waitid_async), }, + [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 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 | 16 +++++++++++----- 2 files changed, 16 insertions(+), 5 deletions(-)
kernel/futex/futex.h +5 -0
@@ -361,6 +361,11 @@ 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 +11 -5
@@ -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;
@@ -214,6 +217,8 @@ 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 ;
@@ -306,7 +311,8 @@ 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 );
@@ -421,7 +427,7 @@ SYSCALL_DEFINE4(futex_requeue,if (!waiters)return -EINVAL ; - ret =futex_parse_waitv (futexes, waiters,2 ); + ret =futex_parse_waitv (futexes, waiters,2 , futex_wake_mark,NULL );if (ret)return ret;
Signature · 1 line
2.40.1
Jens Axboe
maintainerPATCH 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
@@ -366,6 +366,11 @@ 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
@@ -372,7 +372,7 @@ 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 *
@@ -382,7 +382,7 @@ 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;
@@ -410,7 +410,7 @@ 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;
@@ -472,7 +472,7 @@ 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 ;
@@ -557,7 +557,7 @@ 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 2/8 futex: factor out the futex wake handling
In reply to Jens AxboeIn 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 | 5 +++++ kernel/futex/requeue.c | 3 ++- kernel/futex/waitwake.c | 6 +++--- 3 files changed, 10 insertions(+), 4 deletions(-)
kernel/futex/futex.h +5 -0
@@ -139,11 +139,15 @@ 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 * @task: the task waiting on the futex * @lock_ptr: the hash bucket lock +* @wake: the wake handler for this queue * @key: the key the futex is hashed on * @pi_state: optional priority inheritance state * @rt_waiter: rt_waiter storage for use with requeue_pi
@@ -168,6 +172,7 @@ 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 ),
@@ -593,7 +594,7 @@ int futex_requeue(u32 __user *uaddr1, unsigned int flags1,/* 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
@@ -177,7 +177,7 @@ 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 ; }
@@ -292,7 +292,7 @@ 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 ; }
@@ -306,7 +306,7 @@ 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 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.
For cancelations, FUTEX_WAITV does not rely on the futex_unqueue() return value as we're dealing with multiple futexes. Instead, a separate per io_uring request atomic is used to claim ownership of the request.
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, 169 insertions(+), 9 deletions(-)
include/uapi/linux/io_uring.h +1 -0
@@ -246,6 +246,7 @@ enum io_uring_op {IORING_OP_WAITID ,IORING_OP_FUTEX_WAIT ,IORING_OP_FUTEX_WAKE , +IORING_OP_FUTEX_WAITV ,/* this goes last, obviously */ IORING_OP_LAST,
io_uring/futex.c +155 -9
205 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_futexv_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 )
io_uring/opdef.c +11 -0
@@ -459,6 +459,14 @@ 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_futexv_wait, +#else + .prep = io_eopnotsupp_prep,#endif }, };
@@ -693,6 +701,9 @@ 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 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 | 2 ++ 1 file changed, 2 insertions(+)
kernel/futex/futex.h +2 -0
@@ -148,6 +148,7 @@ typedef void (futex_wake_fn)(struct wake_q_head *wake_q, struct futex_q *q);* @task: the task waiting on the futex * @lock_ptr: the hash bucket lock * @wake: the wake handler for this queue +* @wake_data: data associated with the wake handler * @key: the key the futex is hashed on * @pi_state: optional priority inheritance state * @rt_waiter: rt_waiter storage for use with requeue_pi
@@ -173,6 +174,7 @@ 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 1/8 futex: move FUTEX2_VALID_MASK to futex.h
In reply to Jens AxboeWe need this for validating the futex2 flags outside of the normal futex syscalls.
--- kernel/futex/futex.h | 2 ++ kernel/futex/syscalls.c | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-)
kernel/futex/futex.h +2 -0
@@ -52,6 +52,8 @@ static inline unsigned int futex_to_flags(unsigned int op)return flags; } +#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_PRIVATE) +/* FUTEX2_ to FLAGS_ */ static inline unsigned int futex2_to_flags (unsigned int flags2) {
kernel/futex/syscalls.c +0 -2
@@ -179,8 +179,6 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,return do_futex (uaddr, op, val, tp, uaddr2, (unsigned long )utime, val3); } -#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_PRIVATE) -/** * futex_parse_waitv - Parse a waitv array from userspace * @futexv: Kernel side list of waiters to be filled
Signature · 1 line
2.40.1
Jens Axboe
maintainerPATCH v5 1/1 Add io_uring futex/futexv support
Hi,
This patchset adds support for first futex wake and wait, and then futexv.
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.
In terms of testing, there's a functionality and beat-up test case in liburing, and I've run all the ltp futex test cases as well to ensure we didn't inadvertently break anything. It's also been in linux-next for a long time and haven't heard any complaints.
include/linux/io_uring_types.h | 5 + include/uapi/linux/io_uring.h | 4 + io_uring/Makefile | 1 + 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 | 7 + io_uring/opdef.c | 34 +++ kernel/futex/futex.h | 20 ++ kernel/futex/requeue.c | 3 +- kernel/futex/syscalls.c | 18 +- kernel/futex/waitwake.c | 49 +++-- 13 files changed, 535 insertions(+), 27 deletions(-)
You can also find the code here:
https://git.kernel.dk/cgit/linux/log/?h=io_uring-futex
V5:
- Rebase on PeterZ's futex2 changes. Pulled in the tip locking/core branch.
- Shuffle order of some io_uring patchsets, which changed the value of the futex opcodes.
V4:
- Refactor the prep setup so it's fully independent between the vectoed and non-vectored futex handling.
- Ensure we -EINVAL any futex/futexv wait/waitv that specifies unused fields.
- Fix a comment typo
- Update the patches from Peter.
- Fix two kerneldoc warnings
- Add a prep patch moving FUTEX2_MASK to futex.h
Signature · 1 line
Jens Axboe
Jens Axboe
maintainerRe: [PATCH 8/8] io_uring: add support for vectored futex waits
In reply to Jens AxboeAfter discussing this one with Thomas yesterday at KR2023 I had this nagging feeling that something was still amiss. Took a closer look at it, and there is an issue with the odd case of futex_wait_multiple_setup() returning 1. It does so if a wakeup was triggered during setup. Which is fine, except then it also unqueues ALL the futexes at that point, which is unlike the normal wakeup path on the io_uring side.
It'd be nice to unify those and leave the cleanup to the caller, but since we also re-loop in that setup handler if nobody was woken AND we use the futex_unqueue_multiple() to see if we were woken to begin with, I think it's cleaner to just note this fact in io_uring and deal with it.
I'm folding in the below incremental for now. Has a few cleanups in there too that I spotted while doing that, the important bit is the ->futexv_unqueued part.
io_uring/futex.c +29 -25
@@ -23,6 +23,7 @@ struct io_futex {unsigned long futexv_owned;u32 futex_flags;unsigned int futex_nr; +bool futexv_unqueued; };struct io_futex_data {
@@ -71,25 +72,21 @@ static void io_futexv_complete(struct io_kiocb *req, struct io_tw_state *ts) { struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);struct futex_vector *futexv = req->async_data; -struct io_ring_ctx *ctx = req->ctx; -int res =0 ; -io_tw_lock (ctx, ts); +io_tw_lock (req->ctx, ts); + +if (!iof->futexv_unqueued) { +int res =futex_unqueue_multiple (futexv, iof->futex_nr); - res =futex_unqueue_multiple (futexv, iof->futex_nr); -if (res !=-1 ) -io_req_set_res (req, res,0 ); +if (res !=-1 ) +io_req_set_res (req, res,0 ); + }kfree (req->async_data); req->flags &= ~REQ_F_ASYNC_DATA ;__io_futex_complete (req, ts); } -static bool io_futexv_claimed (struct io_futex *iof) -{ -return test_bit (0 , &iof->futexv_owned); -} -static bool io_futexv_claim (struct io_futex *iof) { if (test_bit(0, &iof->futexv_owned) ||
@@ -238,6 +235,7 @@ int io_futexv_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) } iof->futexv_owned =0 ; + iof->futexv_unqueued =0 ; req->flags |=REQ_F_ASYNC_DATA ; req->async_data = futexv;return 0 ;
@@ -278,6 +276,18 @@ int io_futexv_wait(struct io_kiocb *req, unsigned int issue_flags) ret =futex_wait_multiple_setup (futexv, iof->futex_nr, &woken); +/* +* We got woken while setting up, let that side do the completion. +* Note that futex_wait_multiple_setup() will have unqueued all +* the futexes in this case. Mark us as having done that already, +* since this is different from normal wakeup. +*/ +if (ret ==1 ) { + iof->futexv_unqueued =1 ; +io_req_set_res (req, woken,0 ); + goto skip; + } +/* * The above call leaves us potentially non-running. This is fine * for the sync syscall as it'll be blocking unless we already got
@@ -287,29 +297,23 @@ int io_futexv_wait(struct io_kiocb *req, unsigned int issue_flags)__set_current_state (TASK_RUNNING );/* -* We got woken while setting up, let that side do the completion +* 0 return means that we successfully setup the waiters, and that +* nobody triggered a wakeup while we were doing so. If the wakeup +* happened post setup, the task_work will be run post this issue +* and under the submission lock. */ -if (io_futexv_claimed (iof)) { +if (!ret) { +hlist_add_head (&req->hash_node, &ctx->futex_list); skip:io_ring_submit_unlock (ctx, issue_flags);return IOU_ISSUE_SKIP_COMPLETE ; }/* -* 0 return means that we successfully setup the waiters, and that -* nobody triggered a wakeup while we were doing so. < 0 or 1 return -* is either an error or we got a wakeup while setting up. +* Error case, ret is < 0. Mark the request as failed. */ -if (!ret) { -hlist_add_head (&req->hash_node, &ctx->futex_list); - goto skip; - } -io_ring_submit_unlock (ctx, issue_flags); -if (ret <0 ) -req_set_fail (req); -else if (woken !=-1 ) - ret = woken; +req_set_fail (req);io_req_set_res (req, ret,0 );kfree (futexv); req->flags &= ~REQ_F_ASYNC_DATA ;
Signature · 1 line
Jens Axboe
Jens Axboe
maintainerRe: [PATCH 8/8] io_uring: add support for vectored futex waits
Quoted 14 lines · Jens Axboe
After discussing this one with Thomas yesterday at KR2023 I had this nagging feeling that something was still amiss. Took a closer look at it, and there is an issue with the odd case of
futex_wait_multiple_setup()returning 1. It does so if a wakeup was triggered during setup. Which is fine, except then it also unqueues ALL the futexes at that point, which is unlike the normal wakeup path on theio_uringside.It'd be nice to unify those and leave the cleanup to the caller, but since we also re-loop in that setup handler if nobody was woken AND we use the
futex_unqueue_multiple()to see if we were woken to begin with, I think it's cleaner to just note this fact inio_uringand deal with it.
Quoted 3 lines
I'm folding in the below incremental for now. Has a few cleanups in there too that I spotted while doing that, the important bit is the ->futexv_unqueued part.
For completeness, here's the V2 of this patch. Did a few more cleanups since changes were being made. This is what is in the io_uring-futex branch as of earlier today. Didn't think it was worthwhile to spin a new full patchset version for this and post it.
commit 61f8c9c0b48632ea1f14519dfae9176ffbf65050
Author: Jens Axboe <[email protected]> Date: Mon Jun 12 19:04:32 2023 -0600
io_uring: add support for vectored futex waits
This 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.
For cancelations, FUTEX_WAITV does not rely on the futex_unqueue() return value as we're dealing with multiple futexes. Instead, a separate per io_uring request atomic is used to claim ownership of the request.
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 -0
@@ -246,6 +246,7 @@ enum io_uring_op {IORING_OP_WAITID ,IORING_OP_FUTEX_WAIT ,IORING_OP_FUTEX_WAKE , +IORING_OP_FUTEX_WAITV ,/* this goes last, obviously */ IORING_OP_LAST,
io_uring/futex.c +160 -9
210 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_futexv_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 )
io_uring/opdef.c +11 -0
@@ -459,6 +459,14 @@ 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_futexv_wait, +#else + .prep = io_eopnotsupp_prep,#endif }, };
@@ -693,6 +701,9 @@ 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
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); +u32 flags; + +if (unlikely (sqe->fd || sqe->len || sqe->buf_index || sqe->file_index)) +return -EINVAL ;
io_uring/futex.c line 138
Quoted 10 lines
io_uring/futex.c new file +10
-0+ + iof->uaddr =u64_to_user_ptr (READ_ONCE (sqe->addr)); + iof->futex_val =READ_ONCE (sqe->addr2); + iof->futex_mask =READ_ONCE (sqe->addr3); + flags =READ_ONCE (sqe->futex_flags); + +if (flags & ~FUTEX2_VALID_MASK ) +return -EINVAL ; + + iof->futex_flags =futex2_to_flags (flags);
So prep does the flags conversion..
Quoted 28 lines
io_uring/futex.c new file +27
-0+if (!futex_flags_valid (iof->futex_flags)) +return -EINVAL ; + +if (!futex_validate_input (iof->futex_flags, iof->futex_val) || + !futex_validate_input (iof->futex_flags, iof->futex_mask)) +return -EINVAL ; + +return 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; +struct io_futex_data *ifd =NULL ; +struct futex_hash_bucket *hb; +int ret; + +if (!iof->futex_mask) { + ret = -EINVAL ; + goto done; + } + +io_ring_submit_lock (ctx, issue_flags); + ifd =io_alloc_ifd (ctx); +if (!ifd) { + ret = -ENOMEM ; + goto done_unlock;
io_uring/futex.c line 200
Quoted 10 lines
io_uring/futex.c new file +10
-0+ } + + 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, +futex2_to_flags (iof->futex_flags), &ifd->q, &hb);
But then wait and..
Quoted 14 lines
io_uring/futex.c new file +14
-0+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 ) +req_set_fail (req); +io_req_set_res (req, ret,0 );
io_uring/futex.c line 224
Quoted 10 lines
io_uring/futex.c new file +10
-0+kfree (ifd); +return IOU_OK ; +} + +int io_futex_wake (struct io_kiocb *req,unsigned int issue_flags) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); +int ret; + + ret = futex_wake(iof->uaddr, futex2_to_flags(iof->futex_flags),
... wake do it both again?
Also, I think we want wake to have wake do:
'FLAGS_STRICT | iof->futex_flags'
See 43adf8449510 ("futex: FLAGS_STRICT"), I'm thinking that waking 0 futexes should honour that request by waking 0, not 1 :-)
Quoted 6 lines
io_uring/futex.c new file +6
-0+ iof->futex_val, iof->futex_mask); +if (ret <0 ) +req_set_fail (req); +io_req_set_res (req, ret,0 ); +return IOU_OK ; +}
Jens Axboe
maintainerRe: [PATCH 4/8] io_uring: add support for futex wake and wait
Quoted 81 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); +u32 flags; + +if (unlikely (sqe->fd || sqe->len || sqe->buf_index || sqe->file_index)) +return -EINVAL ;io_uring/futex.c line 138
Quoted 10 lines
io_uring/futex.c new file +10
-0+ + iof->uaddr =u64_to_user_ptr (READ_ONCE (sqe->addr)); + iof->futex_val =READ_ONCE (sqe->addr2); + iof->futex_mask =READ_ONCE (sqe->addr3); + flags =READ_ONCE (sqe->futex_flags); + +if (flags & ~FUTEX2_VALID_MASK ) +return -EINVAL ; + + iof->futex_flags =futex2_to_flags (flags);So prep does the flags conversion..
Quoted 28 lines
io_uring/futex.c new file +27
-0+if (!futex_flags_valid (iof->futex_flags)) +return -EINVAL ; + +if (!futex_validate_input (iof->futex_flags, iof->futex_val) || + !futex_validate_input (iof->futex_flags, iof->futex_mask)) +return -EINVAL ; + +return 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; +struct io_futex_data *ifd =NULL ; +struct futex_hash_bucket *hb; +int ret; + +if (!iof->futex_mask) { + ret = -EINVAL ; + goto done; + } + +io_ring_submit_lock (ctx, issue_flags); + ifd =io_alloc_ifd (ctx); +if (!ifd) { + ret = -ENOMEM ; + goto done_unlock;io_uring/futex.c line 200
Quoted 10 lines
io_uring/futex.c new file +10
-0+ } + + 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, +futex2_to_flags (iof->futex_flags), &ifd->q, &hb);But then wait and..
Quoted 18 lines
io_uring/futex.c new file +18
-0+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 ) +req_set_fail (req); +io_req_set_res (req, ret,0 ); +kfree (ifd); +return IOU_OK ; +} +
Quoted 8 lines
io_uring/futex.c line 224
Quoted 6 lines
io_uring/futex.c new file +6
-0+int io_futex_wake (struct io_kiocb *req,unsigned int issue_flags) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); +int ret; + + ret = futex_wake(iof->uaddr, futex2_to_flags(iof->futex_flags),... wake do it both again?
Oops good catch, yes just the prep side should do it of course. I'll fix that up.
Quoted 6 lines
Also, I think we want wake to have wake do:
'
FLAGS_STRICT|iof->futex_flags'See
43adf8449510("futex:FLAGS_STRICT"), I'm thinking that waking 0 futexes should honour that request by waking 0, not 1 :-)
Thanks for the pointer, yeah agree that sounds sane. Most syscalls that take an number/size that is zero will indeed return zero. I'll add a test case for that too.
Signature · 1 line
Jens Axboe