lkml.org 
[lkml]   [2019]   [Jan]   [21]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[RFC PATCH v2 05/13] epoll: offload polling to a work in case of epfd polled from userspace
Date
Not every device reports pollflags on wake_up(), expecting that it will be
polled later. vfs_poll() can't be called from ep_poll_callback(), because
ep_poll_callback() is called under the spinlock. Obviously userspace can't
call vfs_poll(), thus epoll has to offload vfs_poll() to a work and then to
call ep_poll_callback() with pollflags in a hand.

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 | 108 +++++++++++++++++++++++++++++++++++--------------
1 file changed, 78 insertions(+), 30 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 9c9283e4a073..891cc7db8f8d 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -44,6 +44,7 @@
#include <linux/seq_file.h>
#include <linux/compat.h>
#include <linux/rculist.h>
+#include <linux/workqueue.h>
#include <net/busy_poll.h>

/*
@@ -185,6 +186,9 @@ struct epitem {

/* The structure that describe the interested events and the source fd */
struct epoll_event event;
+
+ /* Work for offloading event callback */
+ struct work_struct work;
};

/*
@@ -696,6 +700,14 @@ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
ep_remove_wait_queue(pwq);
kmem_cache_free(pwq_cache, pwq);
}
+ if (ep_polled_by_user(ep)) {
+ /*
+ * Events polled by user require offloading to a work,
+ * thus we have to be sure everything which was queued
+ * has run to a completion.
+ */
+ flush_work(&epi->work);
+ }
}

/* call only when ep->mtx is held */
@@ -1339,9 +1351,8 @@ static inline bool chain_epi_lockless(struct epitem *epi)
}

/*
- * This is the callback that is passed to the wait queue wakeup
- * mechanism. It is called by the stored file descriptors when they
- * have events to report.
+ * This is the callback that is called directly from wake queue wakeup or
+ * from a work.
*
* This callback takes a read lock in order not to content with concurrent
* events from another file descriptors, thus all modifications to ->rdllist
@@ -1356,14 +1367,11 @@ static inline bool chain_epi_lockless(struct epitem *epi)
* queues are used should be detected accordingly. This is detected using
* cmpxchg() operation.
*/
-static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
+static int ep_poll_callback(struct epitem *epi, __poll_t pollflags)
{
- int pwake = 0;
- struct epitem *epi = ep_item_from_wait(wait);
struct eventpoll *ep = epi->ep;
- __poll_t pollflags = key_to_poll(key);
+ int pwake = 0, ewake = 0;
unsigned long flags;
- int ewake = 0;

read_lock_irqsave(&ep->lock, flags);

@@ -1381,8 +1389,9 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
/*
* Check the events coming with the callback. At this stage, not
* every device reports the events in the "key" parameter of the
- * callback. We need to be able to handle both cases here, hence the
- * test for "key" != NULL before the event match test.
+ * callback (for ep_poll_callback() case special worker is used).
+ * We need to be able to handle both cases here, hence the test
+ * for "key" != NULL before the event match test.
*/
if (pollflags && !(pollflags & epi->event.events))
goto out_unlock;
@@ -1442,23 +1451,67 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
if (!(epi->event.events & EPOLLEXCLUSIVE))
ewake = 1;

- if (pollflags & POLLFREE) {
- /*
- * If we race with ep_remove_wait_queue() it can miss
- * ->whead = NULL and do another remove_wait_queue() after
- * us, so we can't use __remove_wait_queue().
- */
- list_del_init(&wait->entry);
+ return ewake;
+}
+
+static void ep_poll_callback_work(struct work_struct *work)
+{
+ struct epitem *epi = container_of(work, typeof(*epi), work);
+ __poll_t pollflags;
+ poll_table pt;
+
+ WARN_ON(!ep_polled_by_user(epi->ep));
+
+ init_poll_funcptr(&pt, NULL);
+ pollflags = ep_item_poll(epi, &pt, 1);
+
+ (void)ep_poll_callback(epi, pollflags);
+}
+
+/*
+ * This is the callback that is passed to the wait queue wakeup
+ * mechanism. It is called by the stored file descriptors when they
+ * have events to report.
+ */
+static int ep_poll_wakeup(wait_queue_entry_t *wait, unsigned int mode,
+ int sync, void *key)
+{
+
+ struct epitem *epi = ep_item_from_wait(wait);
+ struct eventpoll *ep = epi->ep;
+ __poll_t pollflags = key_to_poll(key);
+ int rc;
+
+ if (!ep_polled_by_user(ep) || pollflags) {
+ rc = ep_poll_callback(epi, pollflags);
+
+ if (pollflags & POLLFREE) {
+ /*
+ * If we race with ep_remove_wait_queue() it can miss
+ * ->whead = NULL and do another remove_wait_queue()
+ * after us, so we can't use __remove_wait_queue().
+ */
+ list_del_init(&wait->entry);
+ /*
+ * ->whead != NULL protects us from the race with
+ * ep_free() or ep_remove(), ep_remove_wait_queue()
+ * takes whead->lock held by the caller. Once we nullify
+ * it, nothing protects ep/epi or even wait.
+ */
+ smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL);
+ }
+ } else {
+ schedule_work(&epi->work);
+
/*
- * ->whead != NULL protects us from the race with ep_free()
- * or ep_remove(), ep_remove_wait_queue() takes whead->lock
- * held by the caller. Once we nullify it, nothing protects
- * ep/epi or even wait.
+ * Here on this path we are absolutely sure that for file
+ * descriptors* which are pollable from userspace we do not
+ * support EPOLLEXCLUSIVE, so it is safe to return 1.
*/
- smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL);
+ rc = 1;
}

- return ewake;
+ return rc;
}

/*
@@ -1472,7 +1525,7 @@ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
struct eppoll_entry *pwq;

if (epi->nwait >= 0 && (pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL))) {
- init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);
+ init_waitqueue_func_entry(&pwq->wait, ep_poll_wakeup);
pwq->whead = whead;
pwq->base = epi;
if (epi->event.events & EPOLLEXCLUSIVE)
@@ -1666,6 +1719,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
INIT_LIST_HEAD(&epi->rdllink);
INIT_LIST_HEAD(&epi->fllink);
INIT_LIST_HEAD(&epi->pwqlist);
+ INIT_WORK(&epi->work, ep_poll_callback_work);
epi->ep = ep;
ep_set_ffd(&epi->ffd, tfile, fd);
epi->event = *event;
@@ -2546,12 +2600,6 @@ static int __init eventpoll_init(void)
ep_nested_calls_init(&poll_safewake_ncalls);
#endif

- /*
- * We can have many thousands of epitems, so prevent this from
- * using an extra cache line on 64-bit (and smaller) CPUs
- */
- BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128);
-
/* Allocates slab cache used to allocate "struct epitem" items */
epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem),
0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL);
--
2.19.1
\
 
 \ /
  Last update: 2019-01-21 21:16    [W:0.069 / U:55.756 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site