LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Roman Penyaev <rpenyaev@suse.de>
Cc: azat@libevent.org, rpenyaev@suse.de, akpm@linux-foundation.org,
	viro@zeniv.linux.org.uk, torvalds@linux-foundation.org,
	linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v3 00/13] epoll: support pollable epoll from userspace
Date: Fri, 31 May 2019 18:33:12 +0200
Message-ID: <20190531163312.GW2650@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20190516085810.31077-1-rpenyaev@suse.de>

On Thu, May 16, 2019 at 10:57:57AM +0200, Roman Penyaev wrote:
> When new event comes for some epoll item kernel does the following:
> 
>  struct epoll_uitem *uitem;
> 
>  /* Each item has a bit (index in user items array), discussed later */
>  uitem = user_header->items[epi->bit];
> 
>  if (!atomic_fetch_or(uitem->ready_events, pollflags)) {
>      i = atomic_add(&ep->user_header->tail, 1);

So this is where you increment tail

> 
>      item_idx = &user_index[i & index_mask];
> 
>      /* Signal with a bit, user spins on index expecting value > 0 */
>      *item_idx = idx + 1;

IUC, this is where you write the idx into shared memory, which is
_after_ tail has already been incremented.

>  }
> 
> Important thing here is that ring can't infinitely grow and corrupt other
> elements, because kernel always checks that item was marked as ready, so
> userspace has to clear ready_events field.
> 
> On userside events the following code should be used in order to consume
> events:
> 
>  tail = READ_ONCE(header->tail);
>  for (i = 0; header->head != tail; header->head++) {
>      item_idx_ptr = &index[idx & indeces_mask];
> 
>      /*
>       * Spin here till we see valid index
>       */
>      while (!(idx = __atomic_load_n(item_idx_ptr, __ATOMIC_ACQUIRE)))
>          ;

Which you then try and fix up by busy waiting for @idx to become !0 ?!

Why not write the idx first, then increment the ->tail, such that when
we see ->tail, we already know idx must be correct?

> 
>      item = &header->items[idx - 1];
> 
>      /*
>       * Mark index as invalid, that is for userspace only, kernel does not care
>       * and will refill this pointer only when observes that event is cleared,
>       * which happens below.
>       */
>      *item_idx_ptr = 0;

That avoids this store too.

> 
>      /*
>       * Fetch data first, if event is cleared by the kernel we drop the data
>       * returning false.
>       */
>      event->data = item->event.data;
>      event->events = __atomic_exchange_n(&item->ready_events, 0,
>                          __ATOMIC_RELEASE);
> 
>  }

Aside from that, you have to READ/WRITE_ONCE() on ->head, to avoid
load/store tearing.


That would give something like:

kernel:

	slot = atomic_fetch_inc(&ep->slot);
	item_idx = &user_index[slot & idx_mask];
	WRITE_ONCE(*item_idx, idx);
	smp_store_release(&ep->user_header->tail, slot);

userspace:

	tail = smp_load_acquire(&header->tail);
	for (head = READ_ONCE(header->head); head != tail; head++) {
		idx = READ_ONCE(index[head & idx_mask]);
		itemp = &header->items[idx];

		...
	}
	smp_store_release(&header->head, head);



  parent reply index

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-16  8:57 Roman Penyaev
2019-05-16  8:57 ` [PATCH v3 01/13] epoll: move private helpers from a header to the source Roman Penyaev
2019-05-16  8:57 ` [PATCH v3 02/13] epoll: introduce user structures for polling from userspace Roman Penyaev
2019-05-16  8:58 ` [PATCH v3 03/13] epoll: allocate user header and user events ring " Roman Penyaev
2019-05-16  8:58 ` [PATCH v3 04/13] epoll: some sanity flags checks for epoll syscalls " Roman Penyaev
2019-05-16  8:58 ` [PATCH v3 05/13] epoll: offload polling to a work in case of epfd polled " Roman Penyaev
2019-05-21  7:51   ` Eric Wong
2019-05-22 12:54     ` Roman Penyaev
2019-05-16  8:58 ` [PATCH v3 06/13] epoll: introduce helpers for adding/removing events to uring Roman Penyaev
2019-05-31  9:55   ` Peter Zijlstra
2019-05-31 11:24     ` Roman Penyaev
2019-05-31 13:11       ` Peter Zijlstra
2019-05-31  9:56   ` Peter Zijlstra
2019-05-31 11:15     ` Roman Penyaev
2019-05-31 12:53       ` Peter Zijlstra
2019-05-31 14:28         ` Roman Penyaev
2019-05-31 16:53           ` Peter Zijlstra
2019-05-31 12:56       ` Peter Zijlstra
2019-05-31 14:21         ` Roman Penyaev
2019-05-31 16:51           ` Peter Zijlstra
2019-05-31 18:58             ` Roman Penyaev
2019-06-03  9:09               ` Peter Zijlstra
2019-06-03 10:02                 ` Roman Penyaev
2019-05-16  8:58 ` [PATCH v3 07/13] epoll: call ep_add_event_to_uring() from ep_poll_callback() Roman Penyaev
2019-05-31  9:56   ` Peter Zijlstra
2019-05-31 11:22     ` Roman Penyaev
2019-05-31 13:05       ` Peter Zijlstra
2019-05-31 15:05         ` Roman Penyaev
2019-05-16  8:58 ` [PATCH v3 08/13] epoll: support polling from userspace for ep_insert() Roman Penyaev
2019-05-16  8:58 ` [PATCH v3 09/13] epoll: support polling from userspace for ep_remove() Roman Penyaev
2019-05-16  8:58 ` [PATCH v3 10/13] epoll: support polling from userspace for ep_modify() Roman Penyaev
2019-05-16  8:58 ` [PATCH v3 11/13] epoll: support polling from userspace for ep_poll() Roman Penyaev
2019-05-16  8:58 ` [PATCH v3 12/13] epoll: support mapping for epfd when polled from userspace Roman Penyaev
2019-05-16  8:58 ` [PATCH v3 13/13] epoll: implement epoll_create2() syscall Roman Penyaev
2019-05-16 10:03   ` Arnd Bergmann
2019-05-16 10:20     ` Roman Penyaev
2019-05-16 10:57       ` Arnd Bergmann
2019-05-22  2:33       ` Andrew Morton
2019-05-22  9:11         ` Roman Penyaev
2019-05-22 11:14         ` Arnd Bergmann
2019-05-22 18:36           ` Andrew Morton
2019-05-31  9:55 ` [PATCH v3 00/13] epoll: support pollable epoll from userspace Peter Zijlstra
2019-05-31 14:48 ` Jens Axboe
2019-05-31 16:02   ` Roman Penyaev
2019-05-31 16:54     ` Jens Axboe
2019-05-31 19:45       ` Roman Penyaev
2019-05-31 21:09         ` Jens Axboe
2019-06-05  6:17           ` Roman Penyaev
2019-05-31 16:33 ` Peter Zijlstra [this message]
2019-05-31 18:50   ` Roman Penyaev

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=20190531163312.GW2650@hirez.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=akpm@linux-foundation.org \
    --cc=azat@libevent.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rpenyaev@suse.de \
    --cc=torvalds@linux-foundation.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: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git