When booting a 16TB system, unix_create1 fails due to integer overflow.
Subsystems (5)
I do not know which direction to take, but here is the summary of the problem.
We recently started trying to boot a customer's two new machines which are configured with 384GB short of 16TB of memory.
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.
We came up with a few possible solutions:
Our first response was to limit max_files to (INT_MAX / 2) This at least got us past the problem and seemed reasonable.
We could also have changed the 2 * get_max_files() to 2UL * get_max_files() and gotten past this point in boot. That was not tested.
We could also have changed the definition of max_files to at least an unsigned int instead of an int and gotten past the problem, but again, not tested.
Any suggestions for a direction would be appreciated.
Thank you,
Robin Holt
Quoted 33 lines · Robin Holt
I do not know which direction to take, but here is the summary of the problem.
We recently started trying to boot a customer's two new machines which are configured with 384GB short of 16TB of memory.
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'sfiles_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 leavesmax_filesat approximately 1,503,238,553. This causes 2 *get_max_files()to integer overflow.We came up with a few possible solutions:
Our first response was to limit
max_filesto (INT_MAX/ 2) This at least got us past the problem and seemed reasonable.We could also have changed the 2 *
get_max_files()to 2UL *get_max_files()and gotten past this point in boot. That was not tested.
Quoted 6 lines
We could also have changed the definition of
max_filesto at least an unsigned int instead of an int and gotten past the problem, but again, not tested.Any suggestions for a direction would be appreciated.
Hi Robin
I would say : We can use atomic_long_t instead of atomic_t
And make get_max_files(void) return a long ?
Something like :
fs/file_table.c | 10 +++++----- include/linux/fs.h | 2 +- net/unix/af_unix.c | 14 +++++++------- 3 files changed, 13 insertions(+), 13 deletions(-)
fs/file_table.c +5 -5
@@ -68,9 +68,9 @@ 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; +return (unsigned long )(unsigned int )files_stat.max_files; }EXPORT_SYMBOL_GPL (get_max_files);
@@ -140,7 +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" , +printk (KERN_INFO "VFS: file-max limit %lu reached\n" ,get_max_files ()); old_max =get_nr_files (); }
@@ -487,7 +487,7 @@ 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 );
@@ -498,7 +498,7 @@ void __init files_init(unsigned long mempages)*/ n = (mempages * (PAGE_SIZE /1024 )) /10 ; - files_stat.max_files = n; + files_stat.max_files =min (n,0x7FFFFFFFUL );if (files_stat.max_files <NR_FILE ) files_stat.max_files =NR_FILE ;files_defer_init ();
include/linux/fs.h +1 -1
@@ -404,7 +404,7 @@ 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;
net/unix/af_unix.c +7 -7
@@ -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 =ATOMIC_INIT (0 );#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 );
Quoted 6 lines · Eric Dumazet
Hi Robin
I would say : We can use
atomic_long_tinstead ofatomic_tAnd make
get_max_files(void)return a long ?
AFAIK we can move to long everywhere (/proc/sys/fs/file-nr & /proc/sys/fs/file-max) ...
So you can open more than 2^31 files ;)
Here is the patch I tested (unfortunately not on a 16TB machine )
[PATCH] 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.
before patch :
# 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
--- fs/file_table.c | 15 ++++++--------- include/linux/fs.h | 8 ++++---- kernel/sysctl.c | 8 ++++---- net/unix/af_unix.c | 14 +++++++------- 4 files changed, 21 insertions(+), 24 deletions(-)
fs/file_table.c +6 -9
@@ -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; }
@@ -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 );
include/linux/fs.h +4 -4
@@ -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 {
@@ -404,7 +404,7 @@ 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;
kernel/sysctl.c +4 -4
@@ -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, + .proc_handler = proc_doulongvec_minmax, }, { .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",
net/unix/af_unix.c +7 -7
@@ -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 =ATOMIC_INIT (0 );#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 );
Quoted 31 lines · Eric Dumazet
Quoted 6 lines · Robin Holt
I do not know which direction to take, but here is the summary of the problem.
We recently started trying to boot a customer's two new machines which are configured with 384GB short of 16TB of memory.
Quoted 8 lines
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;Hi Robin
I would say : We can use
atomic_long_tinstead ofatomic_tAnd make
get_max_files(void)return a long ?Something like :
fs/file_table.c | 10 +++++----- include/linux/fs.h | 2 +- net/unix/af_unix.c | 14 +++++++------- 3 files changed, 13 insertions(+), 13 deletions(-)
fs/file_table.c void __init files_init(unsigned long mempages) · line 501
Quoted 4 lines
fs/file_table.c +1
-1n = (mempages * (PAGE_SIZE /1024 )) /10 ; - files_stat.max_files = n; + files_stat.max_files =min (n,0x7FFFFFFFUL );
It may be cleaner to just convert both the file counters and the file limits to usnsigned long.
Other than that, this seems like a reasonable thing to do.
Thanks
Dipankar
David Miller
maintainerFrom: Dipankar Sarma <[email protected]>
Date: Thu, 23 Sep 2010 19:40:37 +0530
Quoted 33 lines · Eric Dumazet
Quoted 32 lines · Robin Holt
Quoted 6 lines
I do not know which direction to take, but here is the summary of the problem.
We recently started trying to boot a customer's two new machines which are configured with 384GB short of 16TB of memory.
Quoted 8 lines
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;Hi Robin
I would say : We can use
atomic_long_tinstead ofatomic_tAnd make
get_max_files(void)return a long ?Something like :
fs/file_table.c | 10 +++++----- include/linux/fs.h | 2 +- net/unix/af_unix.c | 14 +++++++------- 3 files changed, 13 insertions(+), 13 deletions(-)fs/file_table.c +0
-0
Quoted 8 lines
fs/file_table.c void __init files_init(unsigned long mempages) · line 501
Quoted 3 lines
fs/file_table.c +1
-1n = (mempages * (PAGE_SIZE /1024 )) /10 ; - files_stat.max_files = n; + files_stat.max_files =min (n,0x7FFFFFFFUL );It may be cleaner to just convert both the file counters and the file limits to usnsigned long.
Other than that, this seems like a reasonable thing to do.
Is someone following up on integrating this upstream so this thing gets fixed?
Thanks.
PATCH v3 1/1 fs: allow for more than 2^31 files
Quoted 3 lines · David Miller
Is someone following up on integrating this upstream so this thing gets fixed?
Thanks for the heads-up.
I am not sure V2 of my patch was reviewed, maybe it did not reach the list.
Here is V3 of it. I removed the ATOMIC_INIT(0) I left in V2. It should be an ATOMIC_LONG_INIT(0), but then, it can be avoided.
CC netdev
Thanks
[PATCH V3] 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
--- fs/file_table.c | 15 ++++++--------- include/linux/fs.h | 8 ++++---- kernel/sysctl.c | 8 ++++---- net/unix/af_unix.c | 14 +++++++------- 4 files changed, 21 insertions(+), 24 deletions(-)
fs/file_table.c +6 -9
@@ -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; }
@@ -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 );
include/linux/fs.h +4 -4
@@ -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 {
@@ -404,7 +404,7 @@ 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;
kernel/sysctl.c +4 -4
@@ -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, + .proc_handler = proc_doulongvec_minmax, }, { .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",
net/unix/af_unix.c +7 -7
@@ -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 );
Re: [PATCH V3] fs: allow for more than 2^31 files
From: Eric Dumazet <[email protected]>
Date: Tue, 28 Sep 2010 05:46:51 +0200
Quoted 1 line
[PATCH V3] fs: allow for more than 2^31 files
...
Quoted 2 lines
Reported-by Robin Holt <[email protected]>Signed-off-by Eric Dumazet <[email protected]>
Re: [PATCH V3] fs: allow for more than 2^31 files
In reply to Eric DumazetQuoted 1 line · Eric Dumazet
Le lundi 27 septembre 2010 à 15:36 -0700, David Miller a écrit :
...
Quoted 5 lines
Fix is to let
/proc/sys/fs/file-nr&/proc/sys/fs/file-maxuse long integers, and changeaf_unixto use anatomic_long_tinstead ofatomic_t.
get_max_files()is changed to return an unsigned long.
I _THINK_ we actually want get_max_files to return a long and have the files_stat_struct definitions be longs. If we do not have it that way, we could theoretically open enough files on a single cpu to make get_nr_files return a negative without overflowing max_files. That, of course, would require an insane amount of memory, but I think it is technically more correct.
kernel/sysctl.c static struct ctl_table fs_table[] = { · line 1357
Quoted 11 lines
kernel/sysctl.c +2
-2@@ -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, + .proc_handler = proc_doulongvec_minmax,
With this change, don't we lose the current nr_files value? I think you need proc_nr_files to stay as it was. If you disagree, we should probably eliminate the definitions for proc_nr_files as I don't believe they are used anywhere else.
Thanks,
Robin
Re: [PATCH V3] fs: allow for more than 2^31 files
Quoted 8 lines · Robin Holt
Quoted 1 line · Eric Dumazet
Le lundi 27 septembre 2010 à 15:36 -0700, David Miller a écrit :
...
Quoted 4 lines
Fix is to let
/proc/sys/fs/file-nr&/proc/sys/fs/file-maxuse long integers, and changeaf_unixto use anatomic_long_tinstead ofatomic_t.
Quoted 9 lines
Quoted 1 line
get_max_files()is changed to return an unsigned long.I _THINK_ we actually want
get_max_filesto return a long and have thefiles_stat_structdefinitions be longs. If we do not have it that way, we could theoretically open enough files on a single cpu to makeget_nr_filesreturn a negative without overflowingmax_files. That, of course, would require an insane amount of memory, but I think it is technically more correct.
Number of opened file is technically a positive (or null) value, I have no idea why you want it being signed.
Quoted 18 lines
kernel/sysctl.c static struct ctl_table fs_table[] = { · line 1357
Quoted 12 lines
kernel/sysctl.c +2
-2@@ -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, + .proc_handler = proc_doulongvec_minmax,With this change, don't we lose the current
nr_filesvalue? I think you needproc_nr_filesto stay as it was. If you disagree, we should probably eliminate the definitions forproc_nr_filesas I don't believe they are used anywhere else.
I have no idea why you think I changed something. I only made the value use 64bit on 64bit arches, so that we are not anymore limited to 2^31 files.
Re: [PATCH V3] fs: allow for more than 2^31 files
Quoted 41 lines · Eric Dumazet
Quoted 8 lines · Robin Holt
Quoted 1 line · Eric Dumazet
Le lundi 27 septembre 2010 à 15:36 -0700, David Miller a écrit :
...
Quoted 4 lines
Fix is to let
/proc/sys/fs/file-nr&/proc/sys/fs/file-maxuse long integers, and changeaf_unixto use anatomic_long_tinstead ofatomic_t.Quoted 9 lines
Quoted 1 line
get_max_files()is changed to return an unsigned long.I _THINK_ we actually want
get_max_filesto return a long and have thefiles_stat_structdefinitions be longs. If we do not have it that way, we could theoretically open enough files on a single cpu to makeget_nr_filesreturn a negative without overflowingmax_files. That, of course, would require an insane amount of memory, but I think it is technically more correct.Number of opened file is technically a positive (or null) value, I have no idea why you want it being signed.
Quoted 18 lines
kernel/sysctl.c static struct ctl_table fs_table[] = { · line 1357
Quoted 12 lines
kernel/sysctl.c +2
-2@@ -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, + .proc_handler = proc_doulongvec_minmax,With this change, don't we lose the current
nr_filesvalue? I think you needproc_nr_filesto stay as it was. If you disagree, we should probably eliminate the definitions forproc_nr_filesas I don't believe they are used anywhere else.
Quoted 3 lines
I have no idea why you think I changed something. I only made the value use 64bit on 64bit arches, so that we are not anymore limited to 2^31 files.
The proc_handler used to be proc_nr_files() which would call get_nr_files() and deposit the result in files_stat.nr_files then cascade to proc_dointvec() which would dump the 3 values. Now it will dump the three values, but not update the middle (nr_files) value first.
Robin
Re: [PATCH V3] fs: allow for more than 2^31 files
Quoted 5 lines · Robin Holt
The
proc_handlerused to beproc_nr_files()which would callget_nr_files()and deposit the result in files_stat.nr_files then cascade toproc_dointvec()which would dump the 3 values. Now it will dump the three values, but not update the middle (nr_files) value first.
Ah I get it now, thanks !
I'll send a V4 shortly.
PATCH v4 1/1 fs: allow for more than 2^31 files
Quoted 8 lines · Eric Dumazet
Quoted 5 lines · Robin Holt
The
proc_handlerused to beproc_nr_files()which would callget_nr_files()and deposit the result in files_stat.nr_files then cascade toproc_dointvec()which would dump the 3 values. Now it will dump the three values, but not update the middle (nr_files) value first.
Quoted 5 lines
Ah I get it now, thanks !
I'll send a V4 shortly.
In this v4, I call proc_nr_files() again, and proc_nr_files() calls proc_doulongvec_minmax() instead of proc_dointvec()
Added the "cat /proc/sys/fs/file-nr" in Changelog
Thanks again Robin
[PATCH V3] 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
--- fs/file_table.c | 17 +++++++---------- include/linux/fs.h | 8 ++++---- kernel/sysctl.c | 6 +++--- net/unix/af_unix.c | 14 +++++++------- 4 files changed, 21 insertions(+), 24 deletions(-)
fs/file_table.c +7 -10
@@ -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 );
include/linux/fs.h +4 -4
@@ -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 {
@@ -404,7 +404,7 @@ 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;
kernel/sysctl.c +3 -3
@@ -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",
net/unix/af_unix.c +7 -7
@@ -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 );
Re: [PATCH V4] fs: allow for more than 2^31 files
Looks good.
I don't mean to flood this with my name, merely that I do find this patch acceptable, worthy, and have tested it. Feel free to lop off any of these lines that are offensive.
Robin
Quoted 259 lines · Eric Dumazet
Quoted 8 lines · Eric Dumazet
Quoted 5 lines · Robin Holt
The
proc_handlerused to beproc_nr_files()which would callget_nr_files()and deposit the result in files_stat.nr_files then cascade toproc_dointvec()which would dump the 3 values. Now it will dump the three values, but not update the middle (nr_files) value first.Quoted 5 lines
Ah I get it now, thanks !
I'll send a V4 shortly.
In this v4, I call
proc_nr_files()again, andproc_nr_files()callsproc_doulongvec_minmax()instead ofproc_dointvec()Added the "cat
/proc/sys/fs/file-nr" in ChangelogThanks again Robin
[PATCH V3] fs: allow for more than 2^31 files
Robin Holt tried to boot a 16TB system and found
af_unixwas 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'sfiles_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 leavesmax_filesat 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-maxuse long integers, and changeaf_unixto use anatomic_long_tinstead ofatomic_t.
get_max_files()is changed to return an unsigned long.get_nr_files()is changed to return a long.
unix_nr_socksis changed fromatomic_ttoatomic_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 -18446744071562067968After patch:
# echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max 2147483648 # cat /proc/sys/fs/file-nr 704 0 2147483648Reported-by Robin Holt <[email protected]>Signed-off-by Eric Dumazet <[email protected]>--- fs/file_table.c | 17 +++++++---------- include/linux/fs.h | 8 ++++---- kernel/sysctl.c | 6 +++--- net/unix/af_unix.c | 14 +++++++------- 4 files changed, 21 insertions(+), 24 deletions(-)fs/file_table.c +7
-10@@ -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 );include/linux/fs.h +4
-4@@ -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 {@@ -404,7 +404,7 @@ 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;kernel/sysctl.c +3
-3@@ -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",net/unix/af_unix.c +7
-8@@ -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 ); --To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
PATCH v4 1/1 fs: allow for more than 2^31 files
In reply to Eric DumazetAndrew,
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
--- fs/file_table.c | 17 +++++++---------- include/linux/fs.h | 8 ++++---- kernel/sysctl.c | 6 +++--- net/unix/af_unix.c | 14 +++++++------- 4 files changed, 21 insertions(+), 24 deletions(-)
fs/file_table.c +7 -10
@@ -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 );
include/linux/fs.h +4 -4
@@ -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 {
@@ -404,7 +404,7 @@ 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;
kernel/sysctl.c +3 -3
@@ -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",
net/unix/af_unix.c +7 -7
@@ -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 );