#define EP_UNACTIVE_PTR ((void *) -1L)
+#define EP_ITEM_COST (sizeof(struct epitem) + sizeof(struct eppoll_entry))
+
struct epoll_filefd {
struct file *file;
int fd;
* holding ->lock.
*/
struct epitem *ovflist;
+
+ /* The user that created the eventpoll descriptor */
+ struct user_struct *user;
};
/* Wait structure used by the poll hooks */
};
/*
+ * Configuration options available inside /proc/sys/fs/epoll/
+ */
+/* Maximum number of epoll devices, per user */
+static int max_user_instances __read_mostly;
+/* Maximum number of epoll watched descriptors, per user */
+static int max_user_watches __read_mostly;
+
+/*
* This mutex is used to serialize ep_free() and eventpoll_release_file().
*/
-static struct mutex epmutex;
+static DEFINE_MUTEX(epmutex);
/* Safe wake up implementation */
static struct poll_safewake psw;
/* Slab cache used to allocate "struct eppoll_entry" */
static struct kmem_cache *pwq_cache __read_mostly;
+#ifdef CONFIG_SYSCTL
+
+#include <linux/sysctl.h>
+
+static int zero;
+
+ctl_table epoll_table[] = {
+ {
+ .procname = "max_user_instances",
+ .data = &max_user_instances,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .extra1 = &zero,
+ },
+ {
+ .procname = "max_user_watches",
+ .data = &max_user_watches,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .extra1 = &zero,
+ },
+ { .ctl_name = 0 }
+};
+#endif /* CONFIG_SYSCTL */
+
/* Setup the structure that is used as key for the RB tree */
static inline void ep_set_ffd(struct epoll_filefd *ffd,
/* At this point it is safe to free the eventpoll item */
kmem_cache_free(epi_cache, epi);
+ atomic_dec(&ep->user->epoll_watches);
+
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_remove(%p, %p)\n",
current, ep, file));
mutex_unlock(&epmutex);
mutex_destroy(&ep->mtx);
+ atomic_dec(&ep->user->epoll_devs);
+ free_uid(ep->user);
kfree(ep);
}
static int ep_alloc(struct eventpoll **pep)
{
- struct eventpoll *ep = kzalloc(sizeof(*ep), GFP_KERNEL);
+ int error;
+ struct user_struct *user;
+ struct eventpoll *ep;
- if (!ep)
- return -ENOMEM;
+ user = get_current_user();
+ error = -EMFILE;
+ if (unlikely(atomic_read(&user->epoll_devs) >=
+ max_user_instances))
+ goto free_uid;
+ error = -ENOMEM;
+ ep = kzalloc(sizeof(*ep), GFP_KERNEL);
+ if (unlikely(!ep))
+ goto free_uid;
spin_lock_init(&ep->lock);
mutex_init(&ep->mtx);
INIT_LIST_HEAD(&ep->rdllist);
ep->rbr = RB_ROOT;
ep->ovflist = EP_UNACTIVE_PTR;
+ ep->user = user;
*pep = ep;
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_alloc() ep=%p\n",
current, ep));
return 0;
+
+free_uid:
+ free_uid(user);
+ return error;
}
/*
struct epitem *epi;
struct ep_pqueue epq;
- error = -ENOMEM;
+ if (unlikely(atomic_read(&ep->user->epoll_watches) >=
+ max_user_watches))
+ return -ENOSPC;
if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL)))
- goto error_return;
+ return -ENOMEM;
/* Item initialization follow here ... */
INIT_LIST_HEAD(&epi->rdllink);
* install process. Namely an allocation for a wait queue failed due
* high memory pressure.
*/
+ error = -ENOMEM;
if (epi->nwait < 0)
goto error_unregister;
spin_unlock_irqrestore(&ep->lock, flags);
+ atomic_inc(&ep->user->epoll_watches);
+
/* We have to call this outside the lock */
if (pwake)
ep_poll_safewake(&psw, &ep->poll_wait);
spin_unlock_irqrestore(&ep->lock, flags);
kmem_cache_free(epi_cache, epi);
-error_return:
+
return error;
}
/*
* During the time we spent in the loop above, some other events
* might have been queued by the poll callback. We re-insert them
- * here (in case they are not already queued, or they're one-shot).
+ * inside the main ready-list here.
*/
for (nepi = ep->ovflist; (epi = nepi) != NULL;
nepi = epi->next, epi->next = EP_UNACTIVE_PTR) {
- if (!ep_is_linked(&epi->rdllink) &&
- (epi->event.events & ~EP_PRIVATE_BITS))
+ /*
+ * If the above loop quit with errors, the epoll item might still
+ * be linked to "txlist", and the list_splice() done below will
+ * take care of those cases.
+ */
+ if (!ep_is_linked(&epi->rdllink))
list_add_tail(&epi->rdllink, &ep->rdllist);
}
/*
}
/*
- * It opens an eventpoll file descriptor. The "size" parameter is there
- * for historical reasons, when epoll was using an hash instead of an
- * RB tree. With the current implementation, the "size" parameter is ignored
- * (besides sanity checks).
+ * Open an eventpoll file descriptor.
*/
-asmlinkage long sys_epoll_create(int size)
+asmlinkage long sys_epoll_create1(int flags)
{
int error, fd = -1;
struct eventpoll *ep;
+ /* Check the EPOLL_* constant for consistency. */
+ BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);
+
+ if (flags & ~EPOLL_CLOEXEC)
+ return -EINVAL;
+
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d)\n",
- current, size));
+ current, flags));
/*
- * Sanity check on the size parameter, and create the internal data
- * structure ( "struct eventpoll" ).
+ * Create the internal data structure ( "struct eventpoll" ).
*/
- error = -EINVAL;
- if (size <= 0 || (error = ep_alloc(&ep)) < 0) {
+ error = ep_alloc(&ep);
+ if (error < 0) {
fd = error;
goto error_return;
}
* Creates all the items needed to setup an eventpoll file. That is,
* a file structure and a free file descriptor.
*/
- fd = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep);
+ fd = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep,
+ flags & O_CLOEXEC);
if (fd < 0)
ep_free(ep);
+ atomic_inc(&ep->user->epoll_devs);
error_return:
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
- current, size, fd));
+ current, flags, fd));
return fd;
}
+asmlinkage long sys_epoll_create(int size)
+{
+ if (size < 0)
+ return -EINVAL;
+
+ return sys_epoll_create1(0);
+}
+
/*
* The following function implements the controller interface for
* the eventpoll file that enables the insertion/removal/change of
static int __init eventpoll_init(void)
{
- mutex_init(&epmutex);
+ struct sysinfo si;
+
+ si_meminfo(&si);
+ max_user_instances = 128;
+ max_user_watches = (((si.totalram - si.totalhigh) / 32) << PAGE_SHIFT) /
+ EP_ITEM_COST;
/* Initialize the structure used to perform safe poll wait head wake ups */
ep_poll_safewake_init(&psw);