LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Roman Penyaev <rpenyaev@suse.de>
To: unlisted-recipients:; (no To-header on input)
Cc: Azat Khuzhin <azat@libevent.org>,
	Roman Penyaev <rpenyaev@suse.de>,
	Andrew Morton <akpm@linux-foundation.org>,
	Al Viro <viro@zeniv.linux.org.uk>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v3 06/13] epoll: introduce helpers for adding/removing events to uring
Date: Thu, 16 May 2019 10:58:03 +0200
Message-ID: <20190516085810.31077-7-rpenyaev@suse.de> (raw)
In-Reply-To: <20190516085810.31077-1-rpenyaev@suse.de>

Both add and remove events are lockless and can be called in parallel.

ep_add_event_to_uring():
	o user item is marked atomically as ready
	o if on previous stem user item was observed as not ready,
	  then new entry is created for the index uring.

ep_remove_user_item():
	o user item is marked as EPOLLREMOVED only if it was ready,
	  thus userspace will obseve previously added entry in index
	  uring and correct "removed" state of the item.

Signed-off-by: Roman Penyaev <rpenyaev@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 9d3905c0afbf..2f551c005640 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -189,6 +189,9 @@ struct epitem {
 
 	/* Work for offloading event callback */
 	struct work_struct work;
+
+	/* Bit in user bitmap for user polling */
+	unsigned int bit;
 };
 
 /*
@@ -427,6 +430,11 @@ static inline unsigned int ep_to_items_bm_length(unsigned int nr)
 	return PAGE_ALIGN(ALIGN(nr, 8) >> 3);
 }
 
+static inline unsigned int ep_max_index_nr(struct eventpoll *ep)
+{
+	return ep->index_length >> ilog2(sizeof(*ep->user_index));
+}
+
 static inline bool ep_polled_by_user(struct eventpoll *ep)
 {
 	return !!ep->user_header;
@@ -857,6 +865,127 @@ static void epi_rcu_free(struct rcu_head *head)
 	kmem_cache_free(epi_cache, epi);
 }
 
+#define atomic_set_unless_zero(ptr, flags)			\
+({								\
+	typeof(ptr) _ptr = (ptr);				\
+	typeof(flags) _flags = (flags);				\
+	typeof(*_ptr) _old, _val = READ_ONCE(*_ptr);		\
+								\
+	for (;;) {						\
+		if (!_val)					\
+			break;					\
+		_old = cmpxchg(_ptr, _val, _flags);		\
+		if (_old == _val)				\
+			break;					\
+		_val = _old;					\
+	}							\
+	_val;							\
+})
+
+static inline void ep_remove_user_item(struct epitem *epi)
+{
+	struct eventpoll *ep = epi->ep;
+	struct epoll_uitem *uitem;
+
+	lockdep_assert_held(&ep->mtx);
+
+	/* Event should not have any attached queues */
+	WARN_ON(!list_empty(&epi->pwqlist));
+
+	uitem = &ep->user_header->items[epi->bit];
+
+	/*
+	 * User item can be in two states: signaled (read_events is set
+	 * and userspace has not yet consumed this event) and not signaled
+	 * (no events yet fired or already consumed by userspace).
+	 * We reset ready_events to EPOLLREMOVED only if ready_events is
+	 * in signaled state (we expect that userspace will come soon and
+	 * fetch this event).  In case of not signaled leave read_events
+	 * as 0.
+	 *
+	 * Why it is important to mark read_events as EPOLLREMOVED in case
+	 * of already signaled state?  ep_insert() op can be immediately
+	 * called after ep_remove(), thus the same bit can be reused and
+	 * then new event comes, which corresponds to the same entry inside
+	 * user items array.  For this particular case ep_add_event_to_uring()
+	 * does not allocate a new index entry, but simply masks EPOLLREMOVED,
+	 * and userspace uses old index entry, but meanwhile old user item
+	 * has been removed, new item has been added and event updated.
+	 */
+	atomic_set_unless_zero(&uitem->ready_events, EPOLLREMOVED);
+	clear_bit(epi->bit, ep->items_bm);
+}
+
+#define atomic_or_with_mask(ptr, flags, mask)			\
+({								\
+	typeof(ptr) _ptr = (ptr);				\
+	typeof(flags) _flags = (flags);				\
+	typeof(flags) _mask = (mask);				\
+	typeof(*_ptr) _old, _new, _val = READ_ONCE(*_ptr);	\
+								\
+	for (;;) {						\
+		_new = (_val & ~_mask) | _flags;		\
+		_old = cmpxchg(_ptr, _val, _new);		\
+		if (_old == _val)				\
+			break;					\
+		_val = _old;					\
+	}							\
+	_val;							\
+})
+
+static inline bool ep_add_event_to_uring(struct epitem *epi, __poll_t pollflags)
+{
+	struct eventpoll *ep = epi->ep;
+	struct epoll_uitem *uitem;
+	bool added = false;
+
+	if (WARN_ON(!pollflags))
+		return false;
+
+	uitem = &ep->user_header->items[epi->bit];
+	/*
+	 * Can be represented as:
+	 *
+	 *    was_ready = uitem->ready_events;
+	 *    uitem->ready_events &= ~EPOLLREMOVED;
+	 *    uitem->ready_events |= pollflags;
+	 *    if (!was_ready) {
+	 *         // create index entry
+	 *    }
+	 *
+	 * See the big comment inside ep_remove_user_item(), why it is
+	 * important to mask EPOLLREMOVED.
+	 */
+	if (!atomic_or_with_mask(&uitem->ready_events,
+				 pollflags, EPOLLREMOVED)) {
+		unsigned int i, *item_idx, index_mask;
+
+		/*
+		 * Item was not ready before, thus we have to insert
+		 * new index to the ring.
+		 */
+
+		index_mask = ep_max_index_nr(ep) - 1;
+		i = __atomic_fetch_add(&ep->user_header->tail, 1,
+				       __ATOMIC_ACQUIRE);
+		item_idx = &ep->user_index[i & index_mask];
+
+		/* Signal with a bit, which is > 0 */
+		*item_idx = epi->bit + 1;
+
+		/*
+		 * Want index update be flushed from CPU write buffer and
+		 * immediately visible on userspace side to avoid long busy
+		 * loops.
+		 */
+		smp_wmb();
+
+		added = true;
+	}
+
+	return added;
+}
+
 /*
  * Removes a "struct epitem" from the eventpoll RB tree and deallocates
  * all the associated resources. Must be called with "mtx" held.
diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h
index 95ac0b564529..70aa80ddff25 100644
--- a/include/uapi/linux/eventpoll.h
+++ b/include/uapi/linux/eventpoll.h
@@ -42,6 +42,9 @@
 #define EPOLLMSG	(__force __poll_t)0x00000400
 #define EPOLLRDHUP	(__force __poll_t)0x00002000
 
+/* User item marked as removed for EPOLL_USERPOLL */
+#define EPOLLREMOVED	((__force __poll_t)(1U << 27))
+
 /* Set exclusive wakeup mode for the target file descriptor */
 #define EPOLLEXCLUSIVE	((__force __poll_t)(1U << 28))
 
-- 
2.21.0


  parent reply index

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-16  8:57 [PATCH v3 00/13] epoll: support pollable epoll from userspace 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 ` Roman Penyaev [this message]
2019-05-31  9:55   ` [PATCH v3 06/13] epoll: introduce helpers for adding/removing events to uring 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
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=20190516085810.31077-7-rpenyaev@suse.de \
    --to=rpenyaev@suse.de \
    --cc=akpm@linux-foundation.org \
    --cc=azat@libevent.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --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