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>

diff --git a/fs/file_table.c b/fs/file_table.c
index a04bdd8..c3dee38 100644 (file)
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -60,7 +60,7 @@ static inline void file_free(struct file *f)
 /*
  * Return the total number of open files in the system
  */
-static int get_nr_files(void)
+static long get_nr_files(void)
 {
        return percpu_counter_read_positive(&nr_files);
 }
@@ -68,7 +68,7 @@ static int get_nr_files(void)
 /*
  * Return the maximum number of open files in the system
  */
-int get_max_files(void)
+unsigned long get_max_files(void)
 {
        return files_stat.max_files;
 }
@@ -82,7 +82,7 @@ int proc_nr_files(ctl_table *table, int write,
                      void __user *buffer, size_t *lenp, loff_t *ppos)
 {
        files_stat.nr_files = get_nr_files();
-       return proc_dointvec(table, write, buffer, lenp, ppos);
+       return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 #else
 int proc_nr_files(ctl_table *table, int write,
@@ -105,7 +105,7 @@ int proc_nr_files(ctl_table *table, int write,
 struct file *get_empty_filp(void)
 {
        const struct cred *cred = current_cred();
-       static int old_max;
+       static long old_max;
        struct file * f;
 
        /*
@@ -140,8 +140,7 @@ struct file *get_empty_filp(void)
 over:
        /* Ran out of filps - report that */
        if (get_nr_files() > old_max) {
-               printk(KERN_INFO "VFS: file-max limit %d reached\n",
-                                       get_max_files());
+               pr_info("VFS: file-max limit %lu reached\n", get_max_files());
                old_max = get_nr_files();
        }
        goto fail;
@@ -487,7 +486,7 @@ retry:
 
 void __init files_init(unsigned long mempages)
 { 
-       int n; 
+       unsigned long n;
 
        filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
                        SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
@@ -498,9 +497,7 @@ void __init files_init(unsigned long mempages)
         */ 
 
        n = (mempages * (PAGE_SIZE / 1024)) / 10;
-       files_stat.max_files = n; 
-       if (files_stat.max_files < NR_FILE)
-               files_stat.max_files = NR_FILE;
+       files_stat.max_files = max_t(unsigned long, n, NR_FILE);
        files_defer_init();
        lg_lock_init(files_lglock);
        percpu_counter_init(&nr_files, 0);

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0a5d836..0cd6821 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -34,9 +34,9 @@
 
 /* And dynamically-tunable limits and defaults: */
 struct files_stat_struct {
-       int nr_files;           /* read only */
-       int nr_free_files;      /* read only */
-       int max_files;          /* tunable */
+       unsigned long nr_files;         /* read only */
+       unsigned long nr_free_files;    /* read only */
+       unsigned long max_files;                /* tunable */
 };
 
 struct inodes_stat_t {
@@ -400,7 +400,7 @@ extern void __init inode_init_early(void);
 extern void __init files_init(unsigned long);
 
 extern struct files_stat_struct files_stat;
-extern int get_max_files(void);
+extern unsigned long get_max_files(void);
 extern int sysctl_nr_open;
 extern struct inodes_stat_t inodes_stat;
 extern int leases_enable, lease_break_time;

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 3a45c22..694b140 100644 (file)
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1352,16 +1352,16 @@ static struct ctl_table fs_table[] = {
        {
                .procname       = "file-nr",
                .data           = &files_stat,
-               .maxlen         = 3*sizeof(int),
+               .maxlen         = sizeof(files_stat),
                .mode           = 0444,
                .proc_handler   = proc_nr_files,
        },
        {
                .procname       = "file-max",
                .data           = &files_stat.max_files,
-               .maxlen         = sizeof(int),
+               .maxlen         = sizeof(files_stat.max_files),
                .mode           = 0644,
-               .proc_handler   = proc_dointvec,
+               .proc_handler   = proc_doulongvec_minmax,
        },
        {
                .procname       = "nr_open",

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 0ebc777..3c95304 100644 (file)
--- 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);