epoll: convert max_user_watches to long

On a 16TB machine, max_user_watches has an integer overflow.  Convert it
to use a long and handle the associated fallout.

Signed-off-by: Robin Holt <holt@sgi.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 8cf0724..cc8a9b7 100644 (file)
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -217,7 +217,7 @@ struct ep_send_events_data {
  * 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().
@@ -240,16 +240,18 @@ static struct kmem_cache *pwq_cache __read_mostly;
 
 #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,
        },
        { }
 };
@@ -561,7 +563,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *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;
 }
@@ -898,11 +900,12 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 {
        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;
@@ -966,7 +969,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 
        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)
@@ -1426,6 +1429,7 @@ 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 safe poll wait head wake ups */
        ep_nested_calls_init(&poll_safewake_ncalls);

diff --git a/include/linux/sched.h b/include/linux/sched.h
index abc527a..96e2321 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -683,7 +683,7 @@ struct user_struct {
        atomic_t fanotify_listeners;
 #endif
 #ifdef CONFIG_EPOLL
-       atomic_t epoll_watches; /* The number of file descriptors currently watched */
+       atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
 #endif
 #ifdef CONFIG_POSIX_MQUEUE
        /* protected by mq_lock */