#include <linux/mutex.h>
#include <linux/anon_inodes.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>
/*
* 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.
/* 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 nested_call_node {
struct list_head llink;
void *cookie;
- int cpu;
+ void *ctx;
};
/*
/*
* 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;
/* 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)
{
}
/**
+ * 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
* the same nested call (by the meaning of same cookie) is
* @nproc: Nested call core function pointer.
* @priv: Opaque data to be passed to the @nproc callback.
* @cookie: Cookie to be used to identify this nested call.
+ * @ctx: This instance context.
*
* Returns: Returns the code returned by the @nproc callback, or -1 if
* the maximum recursion limit has been exceeded.
*/
static int ep_call_nested(struct nested_calls *ncalls, int max_nests,
int (*nproc)(void *, void *, int), void *priv,
- void *cookie)
+ void *cookie, void *ctx)
{
int error, call_nests = 0;
unsigned long flags;
- int this_cpu = get_cpu();
struct list_head *lsthead = &ncalls->tasks_call_list;
struct nested_call_node *tncur;
struct nested_call_node tnode;
* very much limited.
*/
list_for_each_entry(tncur, lsthead, llink) {
- if (tncur->cpu == this_cpu &&
+ if (tncur->ctx == ctx &&
(tncur->cookie == cookie || ++call_nests > max_nests)) {
/*
* Ops ... loop detected or maximum nest level reached.
}
/* Add the current task and cookie to the list */
- tnode.cpu = this_cpu;
+ tnode.ctx = ctx;
tnode.cookie = cookie;
list_add(&tnode.llink, lsthead);
/* Remove the current task from the list */
spin_lock_irqsave(&ncalls->lock, flags);
list_del(&tnode.llink);
- out_unlock:
+out_unlock:
spin_unlock_irqrestore(&ncalls->lock, flags);
- put_cpu();
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)
*/
static void ep_poll_safewake(wait_queue_head_t *wq)
{
+ int this_cpu = get_cpu();
+
ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS,
- ep_poll_wakeup_proc, NULL, wq);
+ ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu);
+
+ 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();
}
/*
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);
}
}
* @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
/* 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);
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) &
+ pt._key = epi->event.events;
+ if (epi->ffd.file->f_op->poll(epi->ffd.file, &pt) &
epi->event.events)
return POLLIN | POLLRDNORM;
else {
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)
* could re-enter here.
*/
pollflags = ep_call_nested(&poll_readywalk_ncalls, EP_MAX_NESTS,
- ep_poll_readyevents_proc, ep, ep);
+ ep_poll_readyevents_proc, ep, ep, current);
return pollflags != -1 ? pollflags : 0;
}
/* File callbacks that implement the eventpoll file behaviour */
static const struct file_operations eventpoll_fops = {
.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)
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)) {
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;
+}
+
/*
* 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;
/* Initialize the poll table using the queue callback */
epq.epi = epi;
init_poll_funcptr(&epq.pt, ep_ptable_queue_proc);
+ epq.pt._key = event->events;
/*
* Attach the item to the poll hooks and get current event bits.
*/
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);
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);
{
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();
* f_op->poll() call and the new event set registering.
*/
epi->event.events = event->events;
+ pt._key = event->events;
epi->event.data = event->data; /* protected by mtx */
/*
* 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 = epi->ffd.file->f_op->poll(epi->ffd.file, &pt);
/*
* If the item is "hot" and it is not registered inside the ready
unsigned int revents;
struct epitem *epi;
struct epoll_event __user *uevent;
+ poll_table pt;
+
+ init_poll_funcptr(&pt, NULL);
/*
* We can loop without lock because we are passed a task private list.
list_del_init(&epi->rdllink);
- revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL) &
+ pt._key = epi->event.events;
+ revents = epi->ffd.file->f_op->poll(epi->ffd.file, &pt) &
epi->event.events;
/*
* 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
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);
+
+ 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;
+ }
-retry:
+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 (!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);
+}
+
/*
* 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;
+ }
+ fd_install(fd, file);
+ ep->file = 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;
*/
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);
*/
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);