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: Roman Penyaev <rpenyaev@suse.de>,
	Andrew Morton <akpm@linux-foundation.org>,
	Davidlohr Bueso <dbueso@suse.de>, Jason Baron <jbaron@akamai.com>,
	Al Viro <viro@zeniv.linux.org.uk>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andrea Parri <andrea.parri@amarulasolutions.com>,
	linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [RFC PATCH 10/15] epoll: support polling from userspace for ep_insert()
Date: Wed,  9 Jan 2019 17:40:20 +0100
Message-ID: <20190109164025.24554-11-rpenyaev@suse.de> (raw)
In-Reply-To: <20190109164025.24554-1-rpenyaev@suse.de>

When epfd is polled by userspace and new item is inserted:

1. Get free bit for a new item.
2. If expand for user items or user index is required - route all events
   to kernel lists and do expand.
3. If events are ready for newly inserted item - add event to uring,
   if events have been just routed to klists - add item to rdllist.
4. On error path mark user item as freed and route events to klist
   if ready event has not yet been observed by userspace.  That is
   needed to postpone bit put, otherwise newly allocated bit will
   corrupt user item.

Signed-off-by: Roman Penyaev <rpenyaev@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrea Parri <andrea.parri@amarulasolutions.com>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 fs/eventpoll.c | 74 ++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 65 insertions(+), 9 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 36c451c26681..4618db9c077c 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1977,6 +1977,7 @@ 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);
@@ -2002,6 +2003,43 @@ 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 user_epitem *uitem;
+		int bit;
+
+		bit = ep_get_bit(ep);
+		if (unlikely(bit < 0)) {
+			error = bit;
+			goto error_get_bit;
+		}
+		epi->bit = bit;
+		ep->items_nr++;
+
+		if (ep_expand_user_is_required(ep)) {
+			/*
+			 * Expand of user header or user index is required,
+			 * thus reroute all events to klists and then safely
+			 * vrealloc() the memory.
+			 */
+			write_lock_irq(&ep->lock);
+			ep_route_events_to_klists(ep);
+			write_unlock_irq(&ep->lock);
+
+			error = ep_expand_user_items(ep);
+			if (unlikely(error))
+				goto error_expand;
+
+			error = ep_expand_user_index(ep);
+			if (unlikely(error))
+				goto error_expand;
+		}
+
+		/* Now fill-in user item */
+		uitem = &ep->user_header->items[epi->bit];
+		uitem->ready_events = 0;
+		uitem->event = *event;
+	}
+
 	/* Initialize the poll table using the queue callback */
 	epq.epi = epi;
 	init_poll_funcptr(&epq.pt, ep_ptable_queue_proc);
@@ -2046,16 +2084,23 @@ 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_events_routed_to_uring(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);
@@ -2089,6 +2134,17 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 		list_del_init(&epi->rdllink);
 	write_unlock_irq(&ep->lock);
 
+	if (ep_polled_by_user(ep)) {
+error_expand:
+		/*
+		 * No need to check return value: if events are routed to
+		 * klists, that is done by code above, where we've expanded
+		 * memory, but here, on rollback, we do not care.
+		 */
+		(void)ep_free_user_item(epi);
+	}
+
+error_get_bit:
 	wakeup_source_unregister(ep_wakeup_source(epi));
 
 error_create_wakeup_source:
-- 
2.19.1


  parent reply index

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-09 16:40 [RFC 00/15] epoll: support pollable epoll from userspace Roman Penyaev
2019-01-09 16:40 ` [RFC PATCH 01/15] mm/vmalloc: add new 'alignment' field for vm_struct structure Roman Penyaev
2019-01-09 16:40 ` [RFC PATCH 02/15] mm/vmalloc: move common logic from __vmalloc_area_node to a separate func Roman Penyaev
2019-01-09 16:40 ` [RFC PATCH 03/15] mm/vmalloc: introduce new vrealloc() call and its subsidiary reach analog Roman Penyaev
2019-01-09 16:50   ` Matthew Wilcox
2019-01-10 10:08     ` Roman Penyaev
2019-01-09 16:40 ` [RFC PATCH 04/15] epoll: move private helpers from a header to the source Roman Penyaev
2019-01-09 16:40 ` [RFC PATCH 05/15] epoll: introduce user header structure and user index for polling from userspace Roman Penyaev
2019-01-09 16:40 ` [RFC PATCH 06/15] epoll: introduce various of helpers for user structure lengths calculations Roman Penyaev
2019-01-09 16:40 ` [RFC PATCH 07/15] epoll: extend epitem struct with new members for polling from userspace Roman Penyaev
2019-01-09 16:40 ` [RFC PATCH 08/15] epoll: some sanity flags checks for epoll syscalls for polled epfd " Roman Penyaev
2019-01-09 16:40 ` [RFC PATCH 09/15] epoll: introduce stand-alone helpers for polling " Roman Penyaev
2019-01-09 17:29   ` Linus Torvalds
2019-01-10 10:03     ` Roman Penyaev
2019-01-09 16:40 ` Roman Penyaev [this message]
2019-01-09 16:40 ` [RFC PATCH 11/15] epoll: offload polling to a work in case of epfd polled " Roman Penyaev
2019-01-09 16:40 ` [RFC PATCH 12/15] epoll: support polling from userspace for ep_remove() Roman Penyaev
2019-01-09 16:40 ` [RFC PATCH 13/15] epoll: support polling from userspace for ep_modify() Roman Penyaev
2019-01-09 16:40 ` [RFC PATCH 14/15] epoll: support polling from userspace for ep_poll() Roman Penyaev
2019-01-09 16:40 ` [RFC PATCH 15/15] epoll: support mapping for epfd when polled from userspace 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=20190109164025.24554-11-rpenyaev@suse.de \
    --to=rpenyaev@suse.de \
    --cc=akpm@linux-foundation.org \
    --cc=andrea.parri@amarulasolutions.com \
    --cc=dbueso@suse.de \
    --cc=jbaron@akamai.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=paulmck@linux.vnet.ibm.com \
    --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
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.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