From: Thomas Gleixner <tglx@linutronix.de> To: Jens Axboe <axboe@kernel.dk> Cc: linux-aio@kvack.org, linux-block@vger.kernel.org, linux-api@vger.kernel.org, hch@lst.de, jmoyer@redhat.com, avi@scylladb.com, jannh@google.com, viro@ZenIV.linux.org.uk Subject: Re: [PATCH 05/19] Add io_uring IO interface Date: Sun, 10 Feb 2019 13:03:14 +0100 (CET) [thread overview] Message-ID: <alpine.DEB.2.21.1902101048100.8784@nanos.tec.linutronix.de> (raw) In-Reply-To: <20190209211346.26060-6-axboe@kernel.dk> On Sat, 9 Feb 2019, Jens Axboe wrote: > +static void io_commit_cqring(struct io_ring_ctx *ctx) > +{ > + struct io_cq_ring *ring = ctx->cq_ring; > + > + if (ctx->cached_cq_tail != READ_ONCE(ring->r.tail)) { > + /* order cqe stores with ring update */ This lacks a reference to the matching rmb() > + smp_wmb(); > + WRITE_ONCE(ring->r.tail, ctx->cached_cq_tail); > + /* write side barrier of tail update, app has read side */ That's a bit meager. Can you please document the barriers which are paired with user space barriers very elaborate? > + smp_wmb(); > + > + if (wq_has_sleeper(&ctx->cq_wait)) { > + wake_up_interruptible(&ctx->cq_wait); > + kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); > + } > + } > +} > + > +static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) > +{ > + struct io_cq_ring *ring = ctx->cq_ring; > + unsigned tail; > + > + tail = ctx->cached_cq_tail; > + smp_rmb(); Undocumented barrier > + if (tail + 1 == READ_ONCE(ring->r.head)) > + return NULL; > +static void io_commit_sqring(struct io_ring_ctx *ctx) > +{ > + struct io_sq_ring *ring = ctx->sq_ring; > + > + if (ctx->cached_sq_head != READ_ONCE(ring->r.head)) { > + WRITE_ONCE(ring->r.head, ctx->cached_sq_head); > + /* write side barrier of head update, app has read side */ See above. > + smp_wmb(); > + } > +} > +static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) > +{ > + struct io_sq_ring *ring = ctx->sq_ring; > + unsigned head; > + > + /* > + * The cached sq head (or cq tail) serves two purposes: > + * > + * 1) allows us to batch the cost of updating the user visible > + * head updates. > + * 2) allows the kernel side to track the head on its own, even > + * though the application is the one updating it. > + */ > + head = ctx->cached_sq_head; > + smp_rmb(); Undocumented barrier > + if (head == READ_ONCE(ring->r.tail)) > + return false; > + > + head = READ_ONCE(ring->array[head & ctx->sq_mask]); > + if (head < ctx->sq_entries) { > + s->index = head; > + s->sqe = &ctx->sq_sqes[head]; > + ctx->cached_sq_head++; > + return true; > + } > + > + /* drop invalid entries */ > + ctx->cached_sq_head++; > + ring->dropped++; > + smp_wmb(); Undocumented barrier > + return false; > +} > + > +static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, > + const sigset_t __user *sig, size_t sigsz) > +{ > + struct io_cq_ring *ring = ctx->cq_ring; > + sigset_t ksigmask, sigsaved; > + DEFINE_WAIT(wait); > + int ret = 0; > + > + smp_rmb(); > + if (READ_ONCE(ring->r.head) != READ_ONCE(ring->r.tail)) > + return 0; > + if (!min_events) > + return 0; > + > + if (sig) { > + ret = set_user_sigmask(sig, &ksigmask, &sigsaved, sigsz); > + if (ret) > + return ret; > + } > + > + do { > + prepare_to_wait(&ctx->wait, &wait, TASK_INTERRUPTIBLE); > + > + ret = 0; > + smp_rmb(); Undocumented barrier > + if (READ_ONCE(ring->r.head) != READ_ONCE(ring->r.tail)) > + break; > + There are undocumented smp_wmb()'s in 'io_uring: Add submission polling' as well. It's really hard to tell where the corresponding barriers are and what they are supposed to order. Especially the barriers which are paired with user space barriers need some careful documentation. What are the side effects if user space is missing a barrier? Just user space seing unconsistent data or is there something which goes the other way round and might cause havoc in the kernel? Thanks, tglx
WARNING: multiple messages have this Message-ID (diff)
From: Thomas Gleixner <tglx@linutronix.de> To: Jens Axboe <axboe@kernel.dk> Cc: linux-aio@kvack.org, linux-block@vger.kernel.org, linux-api@vger.kernel.org, hch@lst.de, jmoyer@redhat.com, avi@scylladb.com, jannh@google.com, viro@ZenIV.linux.org.uk Subject: Re: [PATCH 05/19] Add io_uring IO interface Date: Sun, 10 Feb 2019 13:03:14 +0100 (CET) [thread overview] Message-ID: <alpine.DEB.2.21.1902101048100.8784@nanos.tec.linutronix.de> (raw) In-Reply-To: <20190209211346.26060-6-axboe@kernel.dk> On Sat, 9 Feb 2019, Jens Axboe wrote: > +static void io_commit_cqring(struct io_ring_ctx *ctx) > +{ > + struct io_cq_ring *ring = ctx->cq_ring; > + > + if (ctx->cached_cq_tail != READ_ONCE(ring->r.tail)) { > + /* order cqe stores with ring update */ This lacks a reference to the matching rmb() > + smp_wmb(); > + WRITE_ONCE(ring->r.tail, ctx->cached_cq_tail); > + /* write side barrier of tail update, app has read side */ That's a bit meager. Can you please document the barriers which are paired with user space barriers very elaborate? > + smp_wmb(); > + > + if (wq_has_sleeper(&ctx->cq_wait)) { > + wake_up_interruptible(&ctx->cq_wait); > + kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); > + } > + } > +} > + > +static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) > +{ > + struct io_cq_ring *ring = ctx->cq_ring; > + unsigned tail; > + > + tail = ctx->cached_cq_tail; > + smp_rmb(); Undocumented barrier > + if (tail + 1 == READ_ONCE(ring->r.head)) > + return NULL; > +static void io_commit_sqring(struct io_ring_ctx *ctx) > +{ > + struct io_sq_ring *ring = ctx->sq_ring; > + > + if (ctx->cached_sq_head != READ_ONCE(ring->r.head)) { > + WRITE_ONCE(ring->r.head, ctx->cached_sq_head); > + /* write side barrier of head update, app has read side */ See above. > + smp_wmb(); > + } > +} > +static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) > +{ > + struct io_sq_ring *ring = ctx->sq_ring; > + unsigned head; > + > + /* > + * The cached sq head (or cq tail) serves two purposes: > + * > + * 1) allows us to batch the cost of updating the user visible > + * head updates. > + * 2) allows the kernel side to track the head on its own, even > + * though the application is the one updating it. > + */ > + head = ctx->cached_sq_head; > + smp_rmb(); Undocumented barrier > + if (head == READ_ONCE(ring->r.tail)) > + return false; > + > + head = READ_ONCE(ring->array[head & ctx->sq_mask]); > + if (head < ctx->sq_entries) { > + s->index = head; > + s->sqe = &ctx->sq_sqes[head]; > + ctx->cached_sq_head++; > + return true; > + } > + > + /* drop invalid entries */ > + ctx->cached_sq_head++; > + ring->dropped++; > + smp_wmb(); Undocumented barrier > + return false; > +} > + > +static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, > + const sigset_t __user *sig, size_t sigsz) > +{ > + struct io_cq_ring *ring = ctx->cq_ring; > + sigset_t ksigmask, sigsaved; > + DEFINE_WAIT(wait); > + int ret = 0; > + > + smp_rmb(); > + if (READ_ONCE(ring->r.head) != READ_ONCE(ring->r.tail)) > + return 0; > + if (!min_events) > + return 0; > + > + if (sig) { > + ret = set_user_sigmask(sig, &ksigmask, &sigsaved, sigsz); > + if (ret) > + return ret; > + } > + > + do { > + prepare_to_wait(&ctx->wait, &wait, TASK_INTERRUPTIBLE); > + > + ret = 0; > + smp_rmb(); Undocumented barrier > + if (READ_ONCE(ring->r.head) != READ_ONCE(ring->r.tail)) > + break; > + There are undocumented smp_wmb()'s in 'io_uring: Add submission polling' as well. It's really hard to tell where the corresponding barriers are and what they are supposed to order. Especially the barriers which are paired with user space barriers need some careful documentation. What are the side effects if user space is missing a barrier? Just user space seing unconsistent data or is there something which goes the other way round and might cause havoc in the kernel? Thanks, tglx -- To unsubscribe, send a message with 'unsubscribe linux-aio' in the body to majordomo@kvack.org. For more info on Linux AIO, see: http://www.kvack.org/aio/ Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
next prev parent reply other threads:[~2019-02-10 12:03 UTC|newest] Thread overview: 105+ messages / expand[flat|nested] mbox.gz Atom feed top 2019-02-09 21:13 [PATCHSET v14] io_uring IO interface Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 01/19] fs: add an iopoll method to struct file_operations Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 02/19] block: wire up block device iopoll method Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 03/19] block: add bio_set_polled() helper Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 04/19] iomap: wire up the iopoll method Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 05/19] Add io_uring IO interface Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-10 12:03 ` Thomas Gleixner [this message] 2019-02-10 12:03 ` Thomas Gleixner 2019-02-10 14:19 ` Jens Axboe 2019-02-10 14:19 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 06/19] io_uring: add fsync support Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 07/19] io_uring: support for IO polling Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 08/19] fs: add fget_many() and fput_many() Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 09/19] io_uring: use fget/fput_many() for file references Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 10/19] io_uring: batch io_kiocb allocation Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 11/19] block: implement bio helper to add iter bvec pages to bio Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 12/19] io_uring: add support for pre-mapped user IO buffers Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 13/19] net: split out functions related to registering inflight socket files Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 14/19] io_uring: add file set registration Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 23:52 ` Matt Mullins 2019-02-10 0:47 ` Jens Axboe 2019-02-10 0:47 ` Jens Axboe 2019-02-10 1:11 ` Matt Mullins 2019-02-10 2:34 ` Jens Axboe 2019-02-10 2:34 ` Jens Axboe 2019-02-10 2:57 ` Jens Axboe 2019-02-10 2:57 ` Jens Axboe 2019-02-10 19:55 ` Matt Mullins 2019-02-09 21:13 ` [PATCH 15/19] io_uring: add submission polling Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-09 21:13 ` [PATCH 16/19] io_uring: add io_kiocb ref count Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-10 9:19 ` Hannes Reinecke 2019-02-10 9:19 ` Hannes Reinecke 2019-02-09 21:13 ` [PATCH 17/19] io_uring: add support for IORING_OP_POLL Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-10 9:28 ` Hannes Reinecke 2019-02-10 9:28 ` Hannes Reinecke 2019-02-09 21:13 ` [PATCH 18/19] io_uring: allow workqueue item to handle multiple buffered requests Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-10 9:31 ` Hannes Reinecke 2019-02-10 9:31 ` Hannes Reinecke 2019-02-09 21:13 ` [PATCH 19/19] io_uring: add io_uring_event cache hit information Jens Axboe 2019-02-09 21:13 ` Jens Axboe 2019-02-10 9:36 ` Hannes Reinecke 2019-02-10 9:36 ` Hannes Reinecke 2019-02-10 13:39 ` Jens Axboe 2019-02-10 13:39 ` Jens Axboe -- strict thread matches above, loose matches on Subject: below -- 2019-02-11 19:00 [PATCHSET v15] io_uring IO interface Jens Axboe 2019-02-11 19:00 ` [PATCH 05/19] Add " Jens Axboe 2019-02-11 19:00 ` Jens Axboe 2019-02-08 17:34 [PATCHSET v13] " Jens Axboe 2019-02-08 17:34 ` [PATCH 05/19] Add " Jens Axboe 2019-02-08 17:34 ` Jens Axboe 2019-02-08 22:12 ` Jann Horn 2019-02-08 22:12 ` Jann Horn 2019-02-09 4:15 ` Jens Axboe 2019-02-09 4:15 ` Jens Axboe 2019-02-12 21:42 ` Jann Horn 2019-02-12 21:42 ` Jann Horn 2019-02-12 22:03 ` Jens Axboe 2019-02-12 22:03 ` Jens Axboe 2019-02-12 22:06 ` Jens Axboe 2019-02-12 22:06 ` Jens Axboe 2019-02-12 22:40 ` Jann Horn 2019-02-12 22:40 ` Jann Horn 2019-02-12 22:45 ` Jens Axboe 2019-02-12 22:45 ` Jens Axboe 2019-02-12 22:52 ` Jens Axboe 2019-02-12 22:52 ` Jens Axboe 2019-02-12 22:57 ` Jann Horn 2019-02-12 22:57 ` Jann Horn 2019-02-12 23:00 ` Jens Axboe 2019-02-12 23:00 ` Jens Axboe 2019-02-12 23:11 ` Jann Horn 2019-02-12 23:11 ` Jann Horn 2019-02-12 23:19 ` Jens Axboe 2019-02-12 23:19 ` Jens Axboe 2019-02-12 23:28 ` Jann Horn 2019-02-12 23:28 ` Jann Horn 2019-02-12 23:46 ` Jens Axboe 2019-02-12 23:46 ` Jens Axboe 2019-02-12 23:53 ` Jens Axboe 2019-02-12 23:53 ` Jens Axboe 2019-02-13 0:07 ` Andy Lutomirski 2019-02-13 0:07 ` Andy Lutomirski 2019-02-13 0:14 ` Jann Horn 2019-02-13 0:14 ` Jann Horn 2019-02-13 0:24 ` Jens Axboe 2019-02-13 0:24 ` Jens Axboe 2019-02-09 9:35 ` Hannes Reinecke 2019-02-09 9:35 ` Hannes Reinecke
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=alpine.DEB.2.21.1902101048100.8784@nanos.tec.linutronix.de \ --to=tglx@linutronix.de \ --cc=avi@scylladb.com \ --cc=axboe@kernel.dk \ --cc=hch@lst.de \ --cc=jannh@google.com \ --cc=jmoyer@redhat.com \ --cc=linux-aio@kvack.org \ --cc=linux-api@vger.kernel.org \ --cc=linux-block@vger.kernel.org \ --cc=viro@ZenIV.linux.org.uk \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.