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 08/13] epoll: support polling from userspace for ep_insert()
Date: Thu, 16 May 2019 10:58:05 +0200
Message-ID: <20190516085810.31077-9-rpenyaev@suse.de> (raw)
In-Reply-To: <20190516085810.31077-1-rpenyaev@suse.de>

When epfd is polled by userspace and new item is inserted new bit
should be get from a bitmap and then user item is set accordingly.

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 55612da9651e..f1ffccfcca67 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -865,6 +865,23 @@ static void epi_rcu_free(struct rcu_head *head)
 	kmem_cache_free(epi_cache, epi);
 }
 
+static inline int ep_get_bit(struct eventpoll *ep)
+{
+	bool was_set;
+	int bit;
+
+	lockdep_assert_held(&ep->mtx);
+
+	bit = find_first_zero_bit(ep->items_bm, ep->max_items_nr);
+	if (bit >= ep->max_items_nr)
+		return -ENOSPC;
+
+	was_set = test_and_set_bit(bit, ep->items_bm);
+	WARN_ON(was_set);
+
+	return bit;
+}
+
 #define atomic_set_unless_zero(ptr, flags)			\
 ({								\
 	typeof(ptr) _ptr = (ptr);				\
@@ -1875,6 +1892,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 	struct epitem *epi;
 	struct ep_pqueue epq;
 
+	lockdep_assert_held(&ep->mtx);
 	lockdep_assert_irqs_enabled();
 
 	user_watches = atomic_long_read(&ep->user->epoll_watches);
@@ -1901,6 +1919,29 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 		RCU_INIT_POINTER(epi->ws, NULL);
 	}
 
+	if (ep_polled_by_user(ep)) {
+		struct epoll_uitem *uitem;
+		int bit;
+
+		bit = ep_get_bit(ep);
+		if (unlikely(bit < 0)) {
+			error = bit;
+			goto error_get_bit;
+		}
+		epi->bit = bit;
+
+		/*
+		 * Now fill-in user item.  Do not touch ready_events, since
+		 * it can be EPOLLREMOVED (has been set by previous user
+		 * item), thus user index entry can be not yet consumed
+		 * by userspace.  See ep_remove_user_item() and
+		 * ep_add_event_to_uring() for details.
+		 */
+		uitem = &ep->user_header->items[epi->bit];
+		uitem->events = event->events;
+		uitem->data = event->data;
+	}
+
 	/* Initialize the poll table using the queue callback */
 	epq.epi = epi;
 	init_poll_funcptr(&epq.pt, ep_ptable_queue_proc);
@@ -1945,16 +1986,23 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 	/* record NAPI ID of new item if present */
 	ep_set_busy_poll_napi_id(epi);
 
-	/* If the file is already "ready" we drop it inside the ready list */
-	if (revents && !ep_is_linked(epi)) {
-		list_add_tail(&epi->rdllink, &ep->rdllist);
-		ep_pm_stay_awake(epi);
+	if (revents) {
+		bool added = false;
 
-		/* Notify waiting tasks that events are available */
-		if (waitqueue_active(&ep->wq))
-			wake_up(&ep->wq);
-		if (waitqueue_active(&ep->poll_wait))
-			pwake++;
+		if (ep_polled_by_user(ep)) {
+			added = ep_add_event_to_uring(epi, revents);
+		} else if (!ep_is_linked(epi)) {
+			list_add_tail(&epi->rdllink, &ep->rdllist);
+			ep_pm_stay_awake(epi);
+			added = true;
+		}
+		if (added) {
+			/* Notify waiting tasks that events are available */
+			if (waitqueue_active(&ep->wq))
+				wake_up(&ep->wq);
+			if (waitqueue_active(&ep->poll_wait))
+				pwake++;
+		}
 	}
 
 	write_unlock_irq(&ep->lock);
@@ -1983,11 +2031,16 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 	 * list, since that is used/cleaned only inside a section bound by "mtx".
 	 * And ep_insert() is called with "mtx" held.
 	 */
-	write_lock_irq(&ep->lock);
-	if (ep_is_linked(epi))
-		list_del_init(&epi->rdllink);
-	write_unlock_irq(&ep->lock);
+	if (ep_polled_by_user(ep)) {
+		ep_remove_user_item(epi);
+	} else {
+		write_lock_irq(&ep->lock);
+		if (ep_is_linked(epi))
+			list_del_init(&epi->rdllink);
+		write_unlock_irq(&ep->lock);
+	}
 
+error_get_bit:
 	wakeup_source_unregister(ep_wakeup_source(epi));
 
 error_create_wakeup_source:
-- 
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 ` [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 ` Roman Penyaev [this message]
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=20190516085810.31077-9-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