From 7e360c38abe2c70eae3ba5a8a17f17671d8b77c5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Oct 2010 09:32:55 +0200 Subject: 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 : 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. 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 Signed-off-by: Eric Dumazet Acked-by: David Miller Reviewed-by: Robin Holt Tested-by: Robin Holt Signed-off-by: Al Viro --- kernel/sysctl.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3a45c224770f..694b140852c2 100644 --- 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", -- cgit v1.2.3 From cffbc8aa334f55c9ed42d25202eb3ebf3a97c195 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Sat, 23 Oct 2010 05:03:02 -0400 Subject: fs: Convert nr_inodes and nr_unused to per-cpu counters The number of inodes allocated does not need to be tied to the addition or removal of an inode to/from a list. If we are not tied to a list lock, we could update the counters when inodes are initialised or destroyed, but to do that we need to convert the counters to be per-cpu (i.e. independent of a lock). This means that we have the freedom to change the list/locking implementation without needing to care about the counters. Based on a patch originally from Eric Dumazet. [AV: cleaned up a bit, fixed build breakage on weird configs Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Al Viro --- kernel/sysctl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 694b140852c2..99a510cbfbb3 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1340,14 +1340,14 @@ static struct ctl_table fs_table[] = { .data = &inodes_stat, .maxlen = 2*sizeof(int), .mode = 0444, - .proc_handler = proc_dointvec, + .proc_handler = proc_nr_inodes, }, { .procname = "inode-state", .data = &inodes_stat, .maxlen = 7*sizeof(int), .mode = 0444, - .proc_handler = proc_dointvec, + .proc_handler = proc_nr_inodes, }, { .procname = "file-nr", -- cgit v1.2.3 From 7de9c6ee3ecffd99e1628e81a5ea5468f7581a1f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 23 Oct 2010 11:11:40 -0400 Subject: new helper: ihold() Clones an existing reference to inode; caller must already hold one. Signed-off-by: Al Viro --- kernel/futex.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index a118bf160e0b..6c683b37f2ce 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -169,7 +169,7 @@ static void get_futex_key_refs(union futex_key *key) switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: - atomic_inc(&key->shared.inode->i_count); + ihold(key->shared.inode); break; case FUT_OFF_MMSHARED: atomic_inc(&key->private.mm->mm_count); -- cgit v1.2.3 From 85fe4025c616a7c0ed07bc2fc8c5371b07f3888c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 Oct 2010 11:19:54 -0400 Subject: fs: do not assign default i_ino in new_inode Instead of always assigning an increasing inode number in new_inode move the call to assign it into those callers that actually need it. For now callers that need it is estimated conservatively, that is the call is added to all filesystems that do not assign an i_ino by themselves. For a few more filesystems we can avoid assigning any inode number given that they aren't user visible, and for others it could be done lazily when an inode number is actually needed, but that's left for later patches. Signed-off-by: Christoph Hellwig Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- kernel/cgroup.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 7b69b8d0313d..9270d532ec3c 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -777,6 +777,7 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) struct inode *inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); -- cgit v1.2.3 From 312d3ca856d369bb04d0443846b85b4cdde6fa8a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 10 Oct 2010 05:36:23 -0400 Subject: fs: use percpu counter for nr_dentry and nr_dentry_unused The nr_dentry stat is a globally touched cacheline and atomic operation twice over the lifetime of a dentry. It is used for the benfit of userspace only. Turn it into a per-cpu counter and always decrement it in d_free instead of doing various batching operations to reduce lock hold times in the callers. Based on an earlier patch from Nick Piggin . Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- kernel/sysctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 99a510cbfbb3..8b77ff5c502c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1377,7 +1377,7 @@ static struct ctl_table fs_table[] = { .data = &dentry_stat, .maxlen = 6*sizeof(int), .mode = 0444, - .proc_handler = proc_dointvec, + .proc_handler = proc_nr_dentry, }, { .procname = "overflowuid", -- cgit v1.2.3