*
* Davide Libenzi <davidel@xmailserver.org>
*
+ * Copyright (c) 2013-2014, NVIDIA CORPORATION. All rights reserved.
+ *
*/
#include <linux/init.h>
#include <linux/bitops.h>
#include <linux/mutex.h>
#include <linux/anon_inodes.h>
+#include <linux/device.h>
+#include <linux/freezer.h>
#include <asm/uaccess.h>
-#include <asm/system.h>
#include <asm/io.h>
#include <asm/mman.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/compat.h>
/*
* LOCKING:
* This mutex is acquired by ep_free() during the epoll file
* cleanup path and it is also acquired by eventpoll_release_file()
* if a file has been pushed inside an epoll set and it is then
- * close()d without a previous call toepoll_ctl(EPOLL_CTL_DEL).
+ * close()d without a previous call to epoll_ctl(EPOLL_CTL_DEL).
+ * It is also acquired when inserting an epoll fd onto another epoll
+ * fd. We do this so that we walk the epoll tree and ensure that this
+ * insertion does not create a cycle of epoll file descriptors, which
+ * could lead to deadlock. We need a global mutex to prevent two
+ * simultaneous inserts (A into B and B into A) from racing and
+ * constructing a cycle without either insert observing that it is
+ * going to.
+ * It is necessary to acquire multiple "ep->mtx"es at once in the
+ * case when one epoll fd is added to another. In this case, we
+ * always acquire the locks in the order of nesting (i.e. after
+ * epoll_ctl(e1, EPOLL_CTL_ADD, e2), e1->mtx will always be acquired
+ * before e2->mtx). Since we disallow cycles of epoll file
+ * descriptors, this ensures that the mutexes are well-ordered. In
+ * order to communicate this nesting to lockdep, when walking a tree
+ * of epoll file descriptors, we use the current recursion depth as
+ * the lockdep subkey.
* It is possible to drop the "ep->mtx" and to use the global
* mutex "epmutex" (together with "ep->lock") to have it working,
* but having "ep->mtx" will make the interface more scalable.
*/
/* Epoll private bits inside the event mask */
-#define EP_PRIVATE_BITS (EPOLLONESHOT | EPOLLET)
+#define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET)
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
-/* Maximum msec timeout value storeable in a long int */
-#define EP_MAX_MSTIMEO min(1000ULL * MAX_SCHEDULE_TIMEOUT / HZ, (LONG_MAX - 999ULL) / HZ)
-
#define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event))
#define EP_UNACTIVE_PTR ((void *) -1L)
struct epoll_filefd {
struct file *file;
int fd;
-};
+} __packed;
/*
* Structure used to track possible nested calls, for too deep recursions
/*
* Each file descriptor added to the eventpoll interface will
* have an entry of this type linked to the "rbr" RB tree.
+ * Avoid increasing the size of this struct, there can be many thousands
+ * of these on a server and we do not want this to take another cache line.
*/
struct epitem {
/* RB tree node used to link this structure to the eventpoll RB tree */
/* List header used to link this item to the "struct file" items list */
struct list_head fllink;
+ /* wakeup_source used when EPOLLWAKEUP is set */
+ struct wakeup_source __rcu *ws;
+
/* The structure that describe the interested events and the source fd */
struct epoll_event event;
};
/*
* This structure is stored inside the "private_data" member of the file
- * structure and rapresent the main data sructure for the eventpoll
+ * structure and represents the main data structure for the eventpoll
* interface.
*/
struct eventpoll {
- /* Protect the this structure access */
+ /* Protect the access to this structure */
spinlock_t lock;
/*
/*
* This is a single linked list that chains all the "struct epitem" that
- * happened while transfering ready events to userspace w/out
+ * happened while transferring ready events to userspace w/out
* holding ->lock.
*/
struct epitem *ovflist;
+ /* wakeup_source used when ep_scan_ready_list is running */
+ struct wakeup_source *ws;
+
/* The user that created the eventpoll descriptor */
struct user_struct *user;
+
+ struct file *file;
+
+ /* used to optimize loop detection check */
+ int visited;
+ struct list_head visited_list_link;
};
/* Wait structure used by the poll hooks */
* Configuration options available inside /proc/sys/fs/epoll/
*/
/* Maximum number of epoll watched descriptors, per user */
-static int max_user_watches __read_mostly;
+static long max_user_watches __read_mostly;
/*
* This mutex is used to serialize ep_free() and eventpoll_release_file().
*/
static DEFINE_MUTEX(epmutex);
+/* Used to check for epoll file descriptor inclusion loops */
+static struct nested_calls poll_loop_ncalls;
+
/* Used for safe wake up implementation */
static struct nested_calls poll_safewake_ncalls;
/* Slab cache used to allocate "struct eppoll_entry" */
static struct kmem_cache *pwq_cache __read_mostly;
+/* Visited nodes during ep_loop_check(), so we can unset them when we finish */
+static LIST_HEAD(visited_list);
+
+/*
+ * List of files with newly added links, where we may need to limit the number
+ * of emanating paths. Protected by the epmutex.
+ */
+static LIST_HEAD(tfile_check_list);
+
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
-static int zero;
+static long zero;
+static long long_max = LONG_MAX;
ctl_table epoll_table[] = {
{
.procname = "max_user_watches",
.data = &max_user_watches,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(max_user_watches),
.mode = 0644,
- .proc_handler = &proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &zero,
+ .extra2 = &long_max,
},
- { .ctl_name = 0 }
+ { }
};
#endif /* CONFIG_SYSCTL */
+static const struct file_operations eventpoll_fops;
+
+static inline int is_file_epoll(struct file *f)
+{
+ return f->f_op == &eventpoll_fops;
+}
/* Setup the structure that is used as key for the RB tree */
static inline void ep_set_ffd(struct epoll_filefd *ffd,
return !list_empty(p);
}
+static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_t *p)
+{
+ return container_of(p, struct eppoll_entry, wait);
+}
+
/* Get the "struct epitem" from a wait queue pointer */
static inline struct epitem *ep_item_from_wait(wait_queue_t *p)
{
spin_lock_init(&ncalls->lock);
}
+/**
+ * ep_events_available - Checks if ready events might be available.
+ *
+ * @ep: Pointer to the eventpoll context.
+ *
+ * Returns: Returns a value different than zero if ready events are available,
+ * or zero otherwise.
+ */
+static inline int ep_events_available(struct eventpoll *ep)
+{
+ return !list_empty(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR;
+}
+
/**
* ep_call_nested - Perform a bound (possibly) nested call, by checking
* that the recursion limit is not exceeded, and that
return error;
}
+/*
+ * As described in commit 0ccf831cb lockdep: annotate epoll
+ * the use of wait queues used by epoll is done in a very controlled
+ * manner. Wake ups can nest inside each other, but are never done
+ * with the same locking. For example:
+ *
+ * dfd = socket(...);
+ * efd1 = epoll_create();
+ * efd2 = epoll_create();
+ * epoll_ctl(efd1, EPOLL_CTL_ADD, dfd, ...);
+ * epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...);
+ *
+ * When a packet arrives to the device underneath "dfd", the net code will
+ * issue a wake_up() on its poll wake list. Epoll (efd1) has installed a
+ * callback wakeup entry on that queue, and the wake_up() performed by the
+ * "dfd" net code will end up in ep_poll_callback(). At this point epoll
+ * (efd1) notices that it may have some event ready, so it needs to wake up
+ * the waiters on its poll wait list (efd2). So it calls ep_poll_safewake()
+ * that ends up in another wake_up(), after having checked about the
+ * recursion constraints. That are, no more than EP_MAX_POLLWAKE_NESTS, to
+ * avoid stack blasting.
+ *
+ * When CONFIG_DEBUG_LOCK_ALLOC is enabled, make sure lockdep can handle
+ * this special case of epoll.
+ */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static inline void ep_wake_up_nested(wait_queue_head_t *wqueue,
unsigned long events, int subclass)
put_cpu();
}
+static void ep_remove_wait_queue(struct eppoll_entry *pwq)
+{
+ wait_queue_head_t *whead;
+
+ rcu_read_lock();
+ /* If it is cleared by POLLFREE, it should be rcu-safe */
+ whead = rcu_dereference(pwq->whead);
+ if (whead)
+ remove_wait_queue(whead, &pwq->wait);
+ rcu_read_unlock();
+}
+
/*
* This function unregisters poll callbacks from the associated file
* descriptor. Must be called with "mtx" held (or "epmutex" if called from
pwq = list_first_entry(lsthead, struct eppoll_entry, llink);
list_del(&pwq->llink);
- remove_wait_queue(pwq->whead, &pwq->wait);
+ ep_remove_wait_queue(pwq);
kmem_cache_free(pwq_cache, pwq);
}
}
+/* call only when ep->mtx is held */
+static inline struct wakeup_source *ep_wakeup_source(struct epitem *epi)
+{
+ return rcu_dereference_check(epi->ws, lockdep_is_held(&epi->ep->mtx));
+}
+
+/* call only when ep->mtx is held */
+static inline void ep_pm_stay_awake(struct epitem *epi)
+{
+ struct wakeup_source *ws = ep_wakeup_source(epi);
+
+ if (ws)
+ __pm_stay_awake(ws);
+}
+
+static inline bool ep_has_wakeup_source(struct epitem *epi)
+{
+ return rcu_access_pointer(epi->ws) ? true : false;
+}
+
+/* call when ep->mtx cannot be held (ep_poll_callback) */
+static inline void ep_pm_stay_awake_rcu(struct epitem *epi)
+{
+ struct wakeup_source *ws;
+
+ rcu_read_lock();
+ ws = rcu_dereference(epi->ws);
+ if (ws)
+ __pm_stay_awake(ws);
+ rcu_read_unlock();
+}
+
/**
* ep_scan_ready_list - Scans the ready list in a way that makes possible for
* the scan code, to call f_op->poll(). Also allows for
* @ep: Pointer to the epoll private data structure.
* @sproc: Pointer to the scan callback.
* @priv: Private opaque data passed to the @sproc callback.
+ * @depth: The current depth of recursive f_op->poll calls.
*
* Returns: The same integer error code returned by the @sproc callback.
*/
static int ep_scan_ready_list(struct eventpoll *ep,
int (*sproc)(struct eventpoll *,
struct list_head *, void *),
- void *priv)
+ void *priv,
+ int depth)
{
int error, pwake = 0;
unsigned long flags;
* We need to lock this because we could be hit by
* eventpoll_release_file() and epoll_ctl().
*/
- mutex_lock(&ep->mtx);
+ mutex_lock_nested(&ep->mtx, depth);
/*
* Steal the ready list, and re-init the original one to the
* queued into ->ovflist but the "txlist" might already
* contain them, and the list_splice() below takes care of them.
*/
- if (!ep_is_linked(&epi->rdllink))
+ if (!ep_is_linked(&epi->rdllink)) {
list_add_tail(&epi->rdllink, &ep->rdllist);
+ ep_pm_stay_awake(epi);
+ }
}
/*
* We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after
* Quickly re-inject items left on "txlist".
*/
list_splice(&txlist, &ep->rdllist);
+ __pm_relax(ep->ws);
if (!list_empty(&ep->rdllist)) {
/*
list_del_init(&epi->rdllink);
spin_unlock_irqrestore(&ep->lock, flags);
+ wakeup_source_unregister(ep_wakeup_source(epi));
+
/* At this point it is safe to free the eventpoll item */
kmem_cache_free(epi_cache, epi);
- atomic_dec(&ep->user->epoll_watches);
+ atomic_long_dec(&ep->user->epoll_watches);
return 0;
}
* We do not need to hold "ep->mtx" here because the epoll file
* is on the way to be removed and no one has references to it
* anymore. The only hit might come from eventpoll_release_file() but
- * holding "epmutex" is sufficent here.
+ * holding "epmutex" is sufficient here.
*/
mutex_lock(&epmutex);
* point we are sure no poll callbacks will be lingering around, and also by
* holding "epmutex" we can be sure that no file cleanup code will hit
* us during this operation. So we can avoid the lock on "ep->lock".
+ * We do not need to lock ep->mtx, either, we only do it to prevent
+ * a lockdep warning.
*/
+ mutex_lock(&ep->mtx);
while ((rbp = rb_first(&ep->rbr)) != NULL) {
epi = rb_entry(rbp, struct epitem, rbn);
ep_remove(ep, epi);
}
+ mutex_unlock(&ep->mtx);
mutex_unlock(&epmutex);
mutex_destroy(&ep->mtx);
free_uid(ep->user);
+ wakeup_source_unregister(ep->ws);
kfree(ep);
}
return 0;
}
+static inline unsigned int ep_item_poll(struct epitem *epi, poll_table *pt)
+{
+ pt->_key = epi->event.events;
+
+ return epi->ffd.file->f_op->poll(epi->ffd.file, pt) & epi->event.events;
+}
+
static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
void *priv)
{
struct epitem *epi, *tmp;
+ poll_table pt;
+
+ init_poll_funcptr(&pt, NULL);
list_for_each_entry_safe(epi, tmp, head, rdllink) {
- if (epi->ffd.file->f_op->poll(epi->ffd.file, NULL) &
- epi->event.events)
+ if (ep_item_poll(epi, &pt))
return POLLIN | POLLRDNORM;
else {
/*
* callback, but it's not actually ready, as far as
* caller requested events goes. We can remove it here.
*/
+ __pm_relax(ep_wakeup_source(epi));
list_del_init(&epi->rdllink);
}
}
static int ep_poll_readyevents_proc(void *priv, void *cookie, int call_nests)
{
- return ep_scan_ready_list(priv, ep_read_events_proc, NULL);
+ return ep_scan_ready_list(priv, ep_read_events_proc, NULL, call_nests + 1);
}
static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
return pollflags != -1 ? pollflags : 0;
}
+#ifdef CONFIG_PROC_FS
+static int ep_show_fdinfo(struct seq_file *m, struct file *f)
+{
+ struct eventpoll *ep = f->private_data;
+ struct rb_node *rbp;
+ int ret = 0;
+
+ mutex_lock(&ep->mtx);
+ for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+ struct epitem *epi = rb_entry(rbp, struct epitem, rbn);
+
+ ret = seq_printf(m, "tfd: %8d events: %8x data: %16llx\n",
+ epi->ffd.fd, epi->event.events,
+ (long long)epi->event.data);
+ if (ret)
+ break;
+ }
+ mutex_unlock(&ep->mtx);
+
+ return ret;
+}
+#endif
+
/* File callbacks that implement the eventpoll file behaviour */
static const struct file_operations eventpoll_fops = {
+#ifdef CONFIG_PROC_FS
+ .show_fdinfo = ep_show_fdinfo,
+#endif
.release = ep_eventpoll_release,
- .poll = ep_eventpoll_poll
+ .poll = ep_eventpoll_poll,
+ .llseek = noop_llseek,
};
-/* Fast test to see if the file is an evenpoll file */
-static inline int is_file_epoll(struct file *f)
-{
- return f->f_op == &eventpoll_fops;
-}
-
/*
* This is called from eventpoll_release() to unlink files from the eventpoll
* interface. We need to have this facility to cleanup correctly files that are
/*
* We don't want to get "file->f_lock" because it is not
* necessary. It is not necessary because we're in the "struct file"
- * cleanup path, and this means that noone is using this file anymore.
+ * cleanup path, and this means that no one is using this file anymore.
* So, for example, epoll_ctl() cannot hit here since if we reach this
* point, the file counter already went to zero and fget() would fail.
* The only hit might come from ep_free() but by holding the mutex
ep = epi->ep;
list_del_init(&epi->fllink);
- mutex_lock(&ep->mtx);
+ mutex_lock_nested(&ep->mtx, 0);
ep_remove(ep, epi);
mutex_unlock(&ep->mtx);
}
/*
* This is the callback that is passed to the wait queue wakeup
- * machanism. It is called by the stored file descriptors when they
+ * mechanism. It is called by the stored file descriptors when they
* have events to report.
*/
-static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key)
+int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
int pwake = 0;
unsigned long flags;
struct epitem *epi = ep_item_from_wait(wait);
struct eventpoll *ep = epi->ep;
+ if ((unsigned long)key & POLLFREE) {
+ ep_pwq_from_wait(wait)->whead = NULL;
+ /*
+ * whead = NULL above can race with ep_remove_wait_queue()
+ * which can do another remove_wait_queue() after us, so we
+ * can't use __remove_wait_queue(). whead->lock is held by
+ * the caller.
+ */
+ list_del_init(&wait->task_list);
+ }
+
spin_lock_irqsave(&ep->lock, flags);
/*
goto out_unlock;
/*
- * If we are trasfering events to userspace, we can hold no locks
+ * If we are transferring events to userspace, we can hold no locks
* (because we're accessing user memory, and because of linux f_op->poll()
- * semantics). All the events that happens during that period of time are
+ * semantics). All the events that happen during that period of time are
* chained in ep->ovflist and requeued later on.
*/
if (unlikely(ep->ovflist != EP_UNACTIVE_PTR)) {
if (epi->next == EP_UNACTIVE_PTR) {
epi->next = ep->ovflist;
ep->ovflist = epi;
+ if (epi->ws) {
+ /*
+ * Activate ep->ws since epi->ws may get
+ * deactivated at any time.
+ */
+ __pm_stay_awake(ep->ws);
+ }
+
}
goto out_unlock;
}
/* If this file is already in the ready list we exit soon */
- if (!ep_is_linked(&epi->rdllink))
+ if (!ep_is_linked(&epi->rdllink)) {
list_add_tail(&epi->rdllink, &ep->rdllist);
+ ep_pm_stay_awake_rcu(epi);
+ }
/*
* Wake up ( if active ) both the eventpoll wait list and the ->poll()
if (epi->nwait >= 0 && (pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL))) {
init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);
+ pwq->wait.private = get_thread_process(current);
pwq->whead = whead;
pwq->base = epi;
add_wait_queue(whead, &pwq->wait);
rb_insert_color(&epi->rbn, &ep->rbr);
}
+
+
+#define PATH_ARR_SIZE 5
+/*
+ * These are the number paths of length 1 to 5, that we are allowing to emanate
+ * from a single file of interest. For example, we allow 1000 paths of length
+ * 1, to emanate from each file of interest. This essentially represents the
+ * potential wakeup paths, which need to be limited in order to avoid massive
+ * uncontrolled wakeup storms. The common use case should be a single ep which
+ * is connected to n file sources. In this case each file source has 1 path
+ * of length 1. Thus, the numbers below should be more than sufficient. These
+ * path limits are enforced during an EPOLL_CTL_ADD operation, since a modify
+ * and delete can't add additional paths. Protected by the epmutex.
+ */
+static const int path_limits[PATH_ARR_SIZE] = { 1000, 500, 100, 50, 10 };
+static int path_count[PATH_ARR_SIZE];
+
+static int path_count_inc(int nests)
+{
+ /* Allow an arbitrary number of depth 1 paths */
+ if (nests == 0)
+ return 0;
+
+ if (++path_count[nests] > path_limits[nests])
+ return -1;
+ return 0;
+}
+
+static void path_count_init(void)
+{
+ int i;
+
+ for (i = 0; i < PATH_ARR_SIZE; i++)
+ path_count[i] = 0;
+}
+
+static int reverse_path_check_proc(void *priv, void *cookie, int call_nests)
+{
+ int error = 0;
+ struct file *file = priv;
+ struct file *child_file;
+ struct epitem *epi;
+
+ list_for_each_entry(epi, &file->f_ep_links, fllink) {
+ child_file = epi->ep->file;
+ if (is_file_epoll(child_file)) {
+ if (list_empty(&child_file->f_ep_links)) {
+ if (path_count_inc(call_nests)) {
+ error = -1;
+ break;
+ }
+ } else {
+ error = ep_call_nested(&poll_loop_ncalls,
+ EP_MAX_NESTS,
+ reverse_path_check_proc,
+ child_file, child_file,
+ current);
+ }
+ if (error != 0)
+ break;
+ } else {
+ printk(KERN_ERR "reverse_path_check_proc: "
+ "file is not an ep!\n");
+ }
+ }
+ return error;
+}
+
+/**
+ * reverse_path_check - The tfile_check_list is list of file *, which have
+ * links that are proposed to be newly added. We need to
+ * make sure that those added links don't add too many
+ * paths such that we will spend all our time waking up
+ * eventpoll objects.
+ *
+ * Returns: Returns zero if the proposed links don't create too many paths,
+ * -1 otherwise.
+ */
+static int reverse_path_check(void)
+{
+ int error = 0;
+ struct file *current_file;
+
+ /* let's call this for all tfiles */
+ list_for_each_entry(current_file, &tfile_check_list, f_tfile_llink) {
+ path_count_init();
+ error = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
+ reverse_path_check_proc, current_file,
+ current_file, current);
+ if (error)
+ break;
+ }
+ return error;
+}
+
+static int ep_create_wakeup_source(struct epitem *epi)
+{
+ const char *name;
+ struct wakeup_source *ws;
+
+ if (!epi->ep->ws) {
+ epi->ep->ws = wakeup_source_register("eventpoll");
+ if (!epi->ep->ws)
+ return -ENOMEM;
+ }
+
+ name = epi->ffd.file->f_path.dentry->d_name.name;
+ ws = wakeup_source_register(name);
+
+ if (!ws)
+ return -ENOMEM;
+ rcu_assign_pointer(epi->ws, ws);
+
+ return 0;
+}
+
+/* rare code path, only used when EPOLL_CTL_MOD removes a wakeup source */
+static noinline void ep_destroy_wakeup_source(struct epitem *epi)
+{
+ struct wakeup_source *ws = ep_wakeup_source(epi);
+
+ RCU_INIT_POINTER(epi->ws, NULL);
+
+ /*
+ * wait for ep_pm_stay_awake_rcu to finish, synchronize_rcu is
+ * used internally by wakeup_source_remove, too (called by
+ * wakeup_source_unregister), so we cannot use call_rcu
+ */
+ synchronize_rcu();
+ wakeup_source_unregister(ws);
+}
+
/*
* Must be called with "mtx" held.
*/
{
int error, revents, pwake = 0;
unsigned long flags;
+ long user_watches;
struct epitem *epi;
struct ep_pqueue epq;
- if (unlikely(atomic_read(&ep->user->epoll_watches) >=
- max_user_watches))
+ user_watches = atomic_long_read(&ep->user->epoll_watches);
+ if (unlikely(user_watches >= max_user_watches))
return -ENOSPC;
if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL)))
return -ENOMEM;
epi->event = *event;
epi->nwait = 0;
epi->next = EP_UNACTIVE_PTR;
+ if (epi->event.events & EPOLLWAKEUP) {
+ error = ep_create_wakeup_source(epi);
+ if (error)
+ goto error_create_wakeup_source;
+ } else {
+ RCU_INIT_POINTER(epi->ws, NULL);
+ }
/* Initialize the poll table using the queue callback */
epq.epi = epi;
* this operation completes, the poll callback can start hitting
* the new item.
*/
- revents = tfile->f_op->poll(tfile, &epq.pt);
+ revents = ep_item_poll(epi, &epq.pt);
/*
* We have to check if something went wrong during the poll wait queue
spin_lock(&tfile->f_lock);
list_add_tail(&epi->fllink, &tfile->f_ep_links);
spin_unlock(&tfile->f_lock);
+ if (tfile->f_path.dentry->d_inode->i_private == NULL)
+ tfile->f_path.dentry->d_inode->i_private =
+ get_thread_process(current);
/*
* Add the current item to the RB tree. All RB tree operations are
*/
ep_rbtree_insert(ep, epi);
+ /* now check if we've created too many backpaths */
+ error = -EINVAL;
+ if (reverse_path_check())
+ goto error_remove_epi;
+
/* We have to drop the new item inside our item list to keep track of it */
spin_lock_irqsave(&ep->lock, flags);
/* If the file is already "ready" we drop it inside the ready list */
if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {
list_add_tail(&epi->rdllink, &ep->rdllist);
+ ep_pm_stay_awake(epi);
/* Notify waiting tasks that events are available */
if (waitqueue_active(&ep->wq))
spin_unlock_irqrestore(&ep->lock, flags);
- atomic_inc(&ep->user->epoll_watches);
+ atomic_long_inc(&ep->user->epoll_watches);
/* We have to call this outside the lock */
if (pwake)
return 0;
+error_remove_epi:
+ spin_lock(&tfile->f_lock);
+ if (ep_is_linked(&epi->fllink))
+ list_del_init(&epi->fllink);
+ spin_unlock(&tfile->f_lock);
+
+ rb_erase(&epi->rbn, &ep->rbr);
+
error_unregister:
ep_unregister_pollwait(ep, epi);
list_del_init(&epi->rdllink);
spin_unlock_irqrestore(&ep->lock, flags);
+ wakeup_source_unregister(ep_wakeup_source(epi));
+
+error_create_wakeup_source:
kmem_cache_free(epi_cache, epi);
return error;
{
int pwake = 0;
unsigned int revents;
+ poll_table pt;
+
+ init_poll_funcptr(&pt, NULL);
/*
* Set the new event interest mask before calling f_op->poll();
* otherwise we might miss an event that happens between the
* f_op->poll() call and the new event set registering.
*/
- epi->event.events = event->events;
+ epi->event.events = event->events; /* need barrier below */
epi->event.data = event->data; /* protected by mtx */
+ if (epi->event.events & EPOLLWAKEUP) {
+ if (!ep_has_wakeup_source(epi))
+ ep_create_wakeup_source(epi);
+ } else if (ep_has_wakeup_source(epi)) {
+ ep_destroy_wakeup_source(epi);
+ }
+
+ /*
+ * The following barrier has two effects:
+ *
+ * 1) Flush epi changes above to other CPUs. This ensures
+ * we do not miss events from ep_poll_callback if an
+ * event occurs immediately after we call f_op->poll().
+ * We need this because we did not take ep->lock while
+ * changing epi above (but ep_poll_callback does take
+ * ep->lock).
+ *
+ * 2) We also need to ensure we do not miss _past_ events
+ * when calling f_op->poll(). This barrier also
+ * pairs with the barrier in wq_has_sleeper (see
+ * comments for wq_has_sleeper).
+ *
+ * This barrier will now guarantee ep_poll_callback or f_op->poll
+ * (or both) will notice the readiness of an item.
+ */
+ smp_mb();
/*
* Get current event bits. We can safely use the file* here because
* its usage count has been increased by the caller of this function.
*/
- revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL);
+ revents = ep_item_poll(epi, &pt);
/*
* If the item is "hot" and it is not registered inside the ready
spin_lock_irq(&ep->lock);
if (!ep_is_linked(&epi->rdllink)) {
list_add_tail(&epi->rdllink, &ep->rdllist);
+ ep_pm_stay_awake(epi);
/* Notify waiting tasks that events are available */
if (waitqueue_active(&ep->wq))
unsigned int revents;
struct epitem *epi;
struct epoll_event __user *uevent;
+ struct wakeup_source *ws;
+ poll_table pt;
+
+ init_poll_funcptr(&pt, NULL);
/*
* We can loop without lock because we are passed a task private list.
!list_empty(head) && eventcnt < esed->maxevents;) {
epi = list_first_entry(head, struct epitem, rdllink);
+ /*
+ * Activate ep->ws before deactivating epi->ws to prevent
+ * triggering auto-suspend here (in case we reactive epi->ws
+ * below).
+ *
+ * This could be rearranged to delay the deactivation of epi->ws
+ * instead, but then epi->ws would temporarily be out of sync
+ * with ep_is_linked().
+ */
+ ws = ep_wakeup_source(epi);
+ if (ws) {
+ if (ws->active)
+ __pm_stay_awake(ep->ws);
+ __pm_relax(ws);
+ }
+
list_del_init(&epi->rdllink);
- revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL) &
- epi->event.events;
+ revents = ep_item_poll(epi, &pt);
/*
* If the event mask intersect the caller-requested one,
if (__put_user(revents, &uevent->events) ||
__put_user(epi->event.data, &uevent->data)) {
list_add(&epi->rdllink, head);
+ ep_pm_stay_awake(epi);
return eventcnt ? eventcnt : -EFAULT;
}
eventcnt++;
* Trigger mode, we need to insert back inside
* the ready list, so that the next call to
* epoll_wait() will check again the events
- * availability. At this point, noone can insert
+ * availability. At this point, no one can insert
* into ep->rdllist besides us. The epoll_ctl()
* callers are locked out by
* ep_scan_ready_list() holding "mtx" and the
* poll callback will queue them in ep->ovflist.
*/
list_add_tail(&epi->rdllink, &ep->rdllist);
+ ep_pm_stay_awake(epi);
}
}
}
esed.maxevents = maxevents;
esed.events = events;
- return ep_scan_ready_list(ep, ep_send_events_proc, &esed);
+ return ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0);
}
+static inline struct timespec ep_set_mstimeout(long ms)
+{
+ struct timespec now, ts = {
+ .tv_sec = ms / MSEC_PER_SEC,
+ .tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC),
+ };
+
+ ktime_get_ts(&now);
+ return timespec_add_safe(now, ts);
+}
+
+/**
+ * ep_poll - Retrieves ready events, and delivers them to the caller supplied
+ * event buffer.
+ *
+ * @ep: Pointer to the eventpoll context.
+ * @events: Pointer to the userspace buffer where the ready events should be
+ * stored.
+ * @maxevents: Size (in terms of number of events) of the caller event buffer.
+ * @timeout: Maximum timeout for the ready events fetch operation, in
+ * milliseconds. If the @timeout is zero, the function will not block,
+ * while if the @timeout is less than zero, the function will block
+ * until at least one event has been retrieved (or an error
+ * occurred).
+ *
+ * Returns: Returns the number of ready events which have been fetched, or an
+ * error code, in case of error.
+ */
static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
int maxevents, long timeout)
{
- int res, eavail;
+ int res = 0, eavail, timed_out = 0;
unsigned long flags;
- long jtimeout;
+ long slack = 0;
wait_queue_t wait;
+ ktime_t expires, *to = NULL;
- /*
- * Calculate the timeout by checking for the "infinite" value (-1)
- * and the overflow condition. The passed timeout is in milliseconds,
- * that why (t * HZ) / 1000.
- */
- jtimeout = (timeout < 0 || timeout >= EP_MAX_MSTIMEO) ?
- MAX_SCHEDULE_TIMEOUT : (timeout * HZ + 999) / 1000;
+ if (timeout > 0) {
+ struct timespec end_time = ep_set_mstimeout(timeout);
-retry:
+ slack = select_estimate_accuracy(&end_time);
+ to = &expires;
+ *to = timespec_to_ktime(end_time);
+ } else if (timeout == 0) {
+ /*
+ * Avoid the unnecessary trip to the wait queue loop, if the
+ * caller specified a non blocking operation.
+ */
+ timed_out = 1;
+ spin_lock_irqsave(&ep->lock, flags);
+ goto check_events;
+ }
+
+fetch_events:
spin_lock_irqsave(&ep->lock, flags);
- res = 0;
- if (list_empty(&ep->rdllist)) {
+ if (!ep_events_available(ep)) {
/*
* We don't have any available event to return to the caller.
* We need to sleep here, and we will be wake up by
* ep_poll_callback() when events will become available.
*/
init_waitqueue_entry(&wait, current);
- wait.flags |= WQ_FLAG_EXCLUSIVE;
- __add_wait_queue(&ep->wq, &wait);
+ __add_wait_queue_exclusive(&ep->wq, &wait);
for (;;) {
/*
* to TASK_INTERRUPTIBLE before doing the checks.
*/
set_current_state(TASK_INTERRUPTIBLE);
- if (!list_empty(&ep->rdllist) || !jtimeout)
+ if (ep_events_available(ep) || timed_out)
break;
if (signal_pending(current)) {
res = -EINTR;
}
spin_unlock_irqrestore(&ep->lock, flags);
- jtimeout = schedule_timeout(jtimeout);
+ if (!freezable_schedule_hrtimeout_range(to, slack,
+ HRTIMER_MODE_ABS))
+ timed_out = 1;
+
spin_lock_irqsave(&ep->lock, flags);
}
__remove_wait_queue(&ep->wq, &wait);
set_current_state(TASK_RUNNING);
}
+check_events:
/* Is it worth to try to dig for events ? */
- eavail = !list_empty(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR;
+ eavail = ep_events_available(ep);
spin_unlock_irqrestore(&ep->lock, flags);
* more luck.
*/
if (!res && eavail &&
- !(res = ep_send_events(ep, events, maxevents)) && jtimeout)
- goto retry;
+ !(res = ep_send_events(ep, events, maxevents)) && !timed_out)
+ goto fetch_events;
return res;
}
+/**
+ * ep_loop_check_proc - Callback function to be passed to the @ep_call_nested()
+ * API, to verify that adding an epoll file inside another
+ * epoll structure, does not violate the constraints, in
+ * terms of closed loops, or too deep chains (which can
+ * result in excessive stack usage).
+ *
+ * @priv: Pointer to the epoll file to be currently checked.
+ * @cookie: Original cookie for this call. This is the top-of-the-chain epoll
+ * data structure pointer.
+ * @call_nests: Current dept of the @ep_call_nested() call stack.
+ *
+ * Returns: Returns zero if adding the epoll @file inside current epoll
+ * structure @ep does not violate the constraints, or -1 otherwise.
+ */
+static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
+{
+ int error = 0;
+ struct file *file = priv;
+ struct eventpoll *ep = file->private_data;
+ struct eventpoll *ep_tovisit;
+ struct rb_node *rbp;
+ struct epitem *epi;
+
+ mutex_lock_nested(&ep->mtx, call_nests + 1);
+ ep->visited = 1;
+ list_add(&ep->visited_list_link, &visited_list);
+ for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+ epi = rb_entry(rbp, struct epitem, rbn);
+ if (unlikely(is_file_epoll(epi->ffd.file))) {
+ ep_tovisit = epi->ffd.file->private_data;
+ if (ep_tovisit->visited)
+ continue;
+ error = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
+ ep_loop_check_proc, epi->ffd.file,
+ ep_tovisit, current);
+ if (error != 0)
+ break;
+ } else {
+ /*
+ * If we've reached a file that is not associated with
+ * an ep, then we need to check if the newly added
+ * links are going to add too many wakeup paths. We do
+ * this by adding it to the tfile_check_list, if it's
+ * not already there, and calling reverse_path_check()
+ * during ep_insert().
+ */
+ if (list_empty(&epi->ffd.file->f_tfile_llink))
+ list_add(&epi->ffd.file->f_tfile_llink,
+ &tfile_check_list);
+ }
+ }
+ mutex_unlock(&ep->mtx);
+
+ return error;
+}
+
+/**
+ * ep_loop_check - Performs a check to verify that adding an epoll file (@file)
+ * another epoll file (represented by @ep) does not create
+ * closed loops or too deep chains.
+ *
+ * @ep: Pointer to the epoll private data structure.
+ * @file: Pointer to the epoll file to be checked.
+ *
+ * Returns: Returns zero if adding the epoll @file inside current epoll
+ * structure @ep does not violate the constraints, or -1 otherwise.
+ */
+static int ep_loop_check(struct eventpoll *ep, struct file *file)
+{
+ int ret;
+ struct eventpoll *ep_cur, *ep_next;
+
+ ret = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
+ ep_loop_check_proc, file, ep, current);
+ /* clear visited list */
+ list_for_each_entry_safe(ep_cur, ep_next, &visited_list,
+ visited_list_link) {
+ ep_cur->visited = 0;
+ list_del(&ep_cur->visited_list_link);
+ }
+ return ret;
+}
+
+static void clear_tfile_check_list(void)
+{
+ struct file *file;
+
+ /* first clear the tfile_check_list */
+ while (!list_empty(&tfile_check_list)) {
+ file = list_first_entry(&tfile_check_list, struct file,
+ f_tfile_llink);
+ list_del_init(&file->f_tfile_llink);
+ }
+ INIT_LIST_HEAD(&tfile_check_list);
+}
+
+struct task_struct *get_epoll_file_task(struct file *file)
+{
+ struct list_head *lh;
+ struct epitem *epi = NULL;
+ struct eppoll_entry *pwq = NULL;
+ struct task_struct *task = NULL;
+ wait_queue_t *wq = NULL;
+
+ lh = &file->f_ep_links;
+ if (!list_empty(lh)) {
+ lh = lh->next;
+ epi = list_entry(lh, struct epitem, fllink);
+ lh = &epi->pwqlist;
+ if (!list_empty(lh)) {
+ lh = lh->next;
+ pwq = list_entry(lh, struct eppoll_entry, llink);
+ lh = &pwq->whead->task_list;
+ if (!list_empty(lh)) {
+ lh = lh->next;
+ wq = list_entry(lh, wait_queue_t, task_list);
+ task = wq->private;
+ }
+ }
+ }
+
+ return task;
+}
+
/*
* Open an eventpoll file descriptor.
*/
SYSCALL_DEFINE1(epoll_create1, int, flags)
{
- int error;
+ int error, fd;
struct eventpoll *ep = NULL;
+ struct file *file;
/* Check the EPOLL_* constant for consistency. */
BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);
* Creates all the items needed to setup an eventpoll file. That is,
* a file structure and a free file descriptor.
*/
- error = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep,
- flags & O_CLOEXEC);
- if (error < 0)
- ep_free(ep);
-
+ fd = get_unused_fd_flags(O_RDWR | (flags & O_CLOEXEC));
+ if (fd < 0) {
+ error = fd;
+ goto out_free_ep;
+ }
+ file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep,
+ O_RDWR | (flags & O_CLOEXEC));
+ if (IS_ERR(file)) {
+ error = PTR_ERR(file);
+ goto out_free_fd;
+ }
+ ep->file = file;
+ fd_install(fd, file);
+ return fd;
+
+out_free_fd:
+ put_unused_fd(fd);
+out_free_ep:
+ ep_free(ep);
return error;
}
struct epoll_event __user *, event)
{
int error;
+ int did_lock_epmutex = 0;
struct file *file, *tfile;
struct eventpoll *ep;
struct epitem *epi;
if (!tfile->f_op || !tfile->f_op->poll)
goto error_tgt_fput;
+ /* Check if EPOLLWAKEUP is allowed */
+ if ((epds.events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND))
+ epds.events &= ~EPOLLWAKEUP;
+
/*
* We have to check that the file structure underneath the file descriptor
* the user passed to us _is_ an eventpoll file. And also we do not permit
*/
ep = file->private_data;
- mutex_lock(&ep->mtx);
+ /*
+ * When we insert an epoll file descriptor, inside another epoll file
+ * descriptor, there is the change of creating closed loops, which are
+ * better be handled here, than in more critical paths. While we are
+ * checking for loops we also determine the list of files reachable
+ * and hang them on the tfile_check_list, so we can check that we
+ * haven't created too many possible wakeup paths.
+ *
+ * We need to hold the epmutex across both ep_insert and ep_remove
+ * b/c we want to make sure we are looking at a coherent view of
+ * epoll network.
+ */
+ if (op == EPOLL_CTL_ADD || op == EPOLL_CTL_DEL) {
+ mutex_lock(&epmutex);
+ did_lock_epmutex = 1;
+ }
+ if (op == EPOLL_CTL_ADD) {
+ if (is_file_epoll(tfile)) {
+ error = -ELOOP;
+ if (ep_loop_check(ep, tfile) != 0) {
+ clear_tfile_check_list();
+ goto error_tgt_fput;
+ }
+ } else
+ list_add(&tfile->f_tfile_llink, &tfile_check_list);
+ }
+
+ mutex_lock_nested(&ep->mtx, 0);
/*
* Try to lookup the file inside our RB tree, Since we grabbed "mtx"
error = ep_insert(ep, &epds, tfile, fd);
} else
error = -EEXIST;
+ clear_tfile_check_list();
break;
case EPOLL_CTL_DEL:
if (epi)
mutex_unlock(&ep->mtx);
error_tgt_fput:
+ if (did_lock_epmutex)
+ mutex_unlock(&epmutex);
+
fput(tfile);
error_fput:
fput(file);
int, maxevents, int, timeout)
{
int error;
- struct file *file;
+ struct fd f;
struct eventpoll *ep;
/* The maximum number of event must be greater than zero */
return -EINVAL;
/* Verify that the area passed by the user is writeable */
- if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event))) {
- error = -EFAULT;
- goto error_return;
- }
+ if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event)))
+ return -EFAULT;
/* Get the "struct file *" for the eventpoll file */
- error = -EBADF;
- file = fget(epfd);
- if (!file)
- goto error_return;
+ f = fdget(epfd);
+ if (!f.file)
+ return -EBADF;
/*
* We have to check that the file structure underneath the fd
* the user passed to us _is_ an eventpoll file.
*/
error = -EINVAL;
- if (!is_file_epoll(file))
+ if (!is_file_epoll(f.file))
goto error_fput;
/*
* At this point it is safe to assume that the "private_data" contains
* our own data structure.
*/
- ep = file->private_data;
+ ep = f.file->private_data;
/* Time to fish for events ... */
error = ep_poll(ep, events, maxevents, timeout);
error_fput:
- fput(file);
-error_return:
-
+ fdput(f);
return error;
}
-#ifdef HAVE_SET_RESTORE_SIGMASK
-
/*
* Implement the event wait interface for the eventpoll file. It is the kernel
* part of the user space epoll_pwait(2).
return error;
}
-#endif /* HAVE_SET_RESTORE_SIGMASK */
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd,
+ struct epoll_event __user *, events,
+ int, maxevents, int, timeout,
+ const compat_sigset_t __user *, sigmask,
+ compat_size_t, sigsetsize)
+{
+ long err;
+ compat_sigset_t csigmask;
+ sigset_t ksigmask, sigsaved;
+
+ /*
+ * If the caller wants a certain signal mask to be set during the wait,
+ * we apply it here.
+ */
+ if (sigmask) {
+ if (sigsetsize != sizeof(compat_sigset_t))
+ return -EINVAL;
+ if (copy_from_user(&csigmask, sigmask, sizeof(csigmask)))
+ return -EFAULT;
+ sigset_from_compat(&ksigmask, &csigmask);
+ sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+ sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+ }
+
+ err = sys_epoll_wait(epfd, events, maxevents, timeout);
+
+ /*
+ * If we changed the signal mask, we need to restore the original one.
+ * In case we've got a signal while waiting, we do not restore the
+ * signal mask yet, and we allow do_signal() to deliver the signal on
+ * the way back to userspace, before the signal mask is restored.
+ */
+ if (sigmask) {
+ if (err == -EINTR) {
+ memcpy(¤t->saved_sigmask, &sigsaved,
+ sizeof(sigsaved));
+ set_restore_sigmask();
+ } else
+ sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ }
+
+ return err;
+}
+#endif
static int __init eventpoll_init(void)
{
*/
max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) /
EP_ITEM_COST;
+ BUG_ON(max_user_watches < 0);
+
+ /*
+ * Initialize the structure used to perform epoll file descriptor
+ * inclusion loops checks.
+ */
+ ep_nested_calls_init(&poll_loop_ncalls);
/* Initialize the structure used to perform safe poll wait head wake ups */
ep_nested_calls_init(&poll_safewake_ncalls);
/* Initialize the structure used to perform file's f_op->poll() calls */
ep_nested_calls_init(&poll_readywalk_ncalls);
+ /*
+ * 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, NULL);
Code Review / linux-3.10.git / blobdiff