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>
This commit is contained in:
@@ -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;
|
||||
|
Reference in New Issue
Block a user