fs: allow for more than 2^31 files

Andrew,

Could you please review this patch, you probably are the right guy to
take it, because it crosses fs and net trees.

Note : /proc/sys/fs/file-nr is a read-only file, so this patch doesnt
depend on previous patch (sysctl: fix min/max handling in
__do_proc_doulongvec_minmax())

Thanks !

[PATCH V4] fs: allow for more than 2^31 files

Robin Holt tried to boot a 16TB system and found af_unix was overflowing
a 32bit value :

<quote>

We were seeing a failure which prevented boot.  The kernel was incapable
of creating either a named pipe or unix domain socket.  This comes down
to a common kernel function called unix_create1() which does:

        atomic_inc(&unix_nr_socks);
        if (atomic_read(&unix_nr_socks) > 2 * get_max_files())
                goto out;

The function get_max_files() is a simple return of files_stat.max_files.
files_stat.max_files is a signed integer and is computed in
fs/file_table.c's files_init().

        n = (mempages * (PAGE_SIZE / 1024)) / 10;
        files_stat.max_files = n;

In our case, mempages (total_ram_pages) is approx 3,758,096,384
(0xe0000000).  That leaves max_files at approximately 1,503,238,553.
This causes 2 * get_max_files() to integer overflow.

</quote>

Fix is to let /proc/sys/fs/file-nr & /proc/sys/fs/file-max use long
integers, and change af_unix to use an atomic_long_t instead of
atomic_t.

get_max_files() is changed to return an unsigned long.
get_nr_files() is changed to return a long.

unix_nr_socks is changed from atomic_t to atomic_long_t, while not
strictly needed to address Robin problem.

Before patch (on a 64bit kernel) :
# echo 2147483648 >/proc/sys/fs/file-max
# cat /proc/sys/fs/file-max
-18446744071562067968

After patch:
# echo 2147483648 >/proc/sys/fs/file-max
# cat /proc/sys/fs/file-max
2147483648
# cat /proc/sys/fs/file-nr
704     0       2147483648

Reported-by: Robin Holt <holt@sgi.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: David Miller <davem@davemloft.net>
Reviewed-by: Robin Holt <holt@sgi.com>
Tested-by: Robin Holt <holt@sgi.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 7 insertions, 7 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 0ebc777a6660..3c95304a0817 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -117,7 +117,7 @@
 
 static struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
 static DEFINE_SPINLOCK(unix_table_lock);
-static atomic_t unix_nr_socks = ATOMIC_INIT(0);
+static atomic_long_t unix_nr_socks;
 
 #define unix_sockets_unbound    (&unix_socket_table[UNIX_HASH_SIZE])
 
@@ -360,13 +360,13 @@ static void unix_sock_destructor(struct sock *sk)
         if (u->addr)
                 unix_release_addr(u->addr);
 
-        atomic_dec(&unix_nr_socks);
+        atomic_long_dec(&unix_nr_socks);
         local_bh_disable();
         sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
         local_bh_enable();
 #ifdef UNIX_REFCNT_DEBUG
-        printk(KERN_DEBUG "UNIX %p is destroyed, %d are still alive.\n", sk,
-                atomic_read(&unix_nr_socks));
+        printk(KERN_DEBUG "UNIX %p is destroyed, %ld are still alive.\n", sk,
+                atomic_long_read(&unix_nr_socks));
 #endif
 }
 
@@ -606,8 +606,8 @@ static struct sock *unix_create1(struct net *net, struct socket *sock)
         struct sock *sk = NULL;
         struct unix_sock *u;
 
-        atomic_inc(&unix_nr_socks);
-        if (atomic_read(&unix_nr_socks) > 2 * get_max_files())
+        atomic_long_inc(&unix_nr_socks);
+        if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files())
                 goto out;
 
         sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto);
@@ -632,7 +632,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock)
         unix_insert_socket(unix_sockets_unbound, sk);
 out:
         if (sk == NULL)
-                atomic_dec(&unix_nr_socks);
+                atomic_long_dec(&unix_nr_socks);
         else {
                 local_bh_disable();
                 sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);