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 11/13] epoll: support polling from userspace for ep_poll()
Date: Thu, 16 May 2019 10:58:08 +0200
Message-ID: <20190516085810.31077-12-rpenyaev@suse.de> (raw)
In-Reply-To: <20190516085810.31077-1-rpenyaev@suse.de>

Rule of thumb for epfd polled from userspace is simple: epfd has
events if ->head != ->tail, no traversing of each item is performed.

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 1b7097e58fb2..20c94587488f 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -440,6 +440,12 @@ static inline bool ep_polled_by_user(struct eventpoll *ep)
 	return !!ep->user_header;
 }
 
+static inline bool ep_uring_events_available(struct eventpoll *ep)
+{
+	return ep_polled_by_user(ep) &&
+		ep->user_header->head != ep->user_header->tail;
+}
+
 /**
  * ep_events_available - Checks if ready events might be available.
  *
@@ -451,7 +457,8 @@ static inline bool ep_polled_by_user(struct eventpoll *ep)
 static inline int ep_events_available(struct eventpoll *ep)
 {
 	return !list_empty_careful(&ep->rdllist) ||
-		READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR;
+		READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR ||
+		ep_uring_events_available(ep);
 }
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
@@ -1160,7 +1167,7 @@ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
 static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt,
 				 int depth)
 {
-	struct eventpoll *ep;
+	struct eventpoll *ep, *tep;
 	bool locked;
 
 	pt->_key = epi->event.events;
@@ -1169,6 +1176,26 @@ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt,
 
 	ep = epi->ffd.file->private_data;
 	poll_wait(epi->ffd.file, &ep->poll_wait, pt);
+
+	tep = epi->ffd.file->private_data;
+	if (ep_polled_by_user(tep)) {
+		/*
+		 * The behaviour differs comparing to full scan of ready
+		 * list for original epoll.  If descriptor is pollable
+		 * from userspace we don't do scan of all ready user items:
+		 * firstly because we can't do reverse search of epi by
+		 * uitem bit, secondly this is simply waste of time for
+		 * edge triggered descriptors (user code should be prepared
+		 * to deal with EAGAIN returned from read() or write() on
+		 * inserted file descriptor) and thirdly once event is put
+		 * into user index ring do not touch it from kernel, what
+		 * we do is mark it as EPOLLREMOVED on ep_remove() and
+		 * that's it.
+		 */
+		return ep_uring_events_available(tep) ?
+			EPOLLIN | EPOLLRDNORM : 0;
+	}
+
 	locked = pt && (pt->_qproc == ep_ptable_queue_proc);
 
 	return ep_scan_ready_list(epi->ffd.file->private_data,
@@ -1211,6 +1238,12 @@ static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait)
 	/* Insert inside our poll wait queue */
 	poll_wait(file, &ep->poll_wait, wait);
 
+	if (ep_polled_by_user(ep)) {
+		/* Please read detailed comments inside ep_item_poll() */
+		return ep_uring_events_available(ep) ?
+			EPOLLIN | EPOLLRDNORM : 0;
+	}
+
 	/*
 	 * Proceed to find out if wanted events are really available inside
 	 * the ready list.
@@ -2235,6 +2268,8 @@ static int ep_send_events(struct eventpoll *ep,
 {
 	struct ep_send_events_data esed;
 
+	WARN_ON(ep_polled_by_user(ep));
+
 	esed.maxevents = maxevents;
 	esed.events = events;
 
@@ -2281,6 +2316,12 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 
 	lockdep_assert_irqs_enabled();
 
+	if (ep_polled_by_user(ep)) {
+		if (ep_uring_events_available(ep))
+			/* Firstly all events from ring have to be consumed */
+			return -ESTALE;
+	}
+
 	if (timeout > 0) {
 		struct timespec64 end_time = ep_set_mstimeout(timeout);
 
@@ -2369,14 +2410,21 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 	__set_current_state(TASK_RUNNING);
 
 send_events:
-	/*
-	 * Try to transfer events to user space. In case we get 0 events and
-	 * there's still timeout left over, we go trying again in search of
-	 * more luck.
-	 */
-	if (!res && eavail &&
-	    !(res = ep_send_events(ep, events, maxevents)) && !timed_out)
-		goto fetch_events;
+	if (!res && eavail) {
+		if (!ep_polled_by_user(ep)) {
+			/*
+			 * Try to transfer events to user space. In case we get
+			 * 0 events and there's still timeout left over, we go
+			 * trying again in search of more luck.
+			 */
+			res = ep_send_events(ep, events, maxevents);
+			if (!res && !timed_out)
+				goto fetch_events;
+		} else {
+			/* User has to deal with the ring himself */
+			res = -ESTALE;
+		}
+	}
 
 	if (waiter) {
 		spin_lock_irq(&ep->wq.lock);
-- 
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 ` [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 ` Roman Penyaev [this message]
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=20190516085810.31077-12-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