inotify: Convert to using per-namespace limits

This patchset converts inotify to using the newly introduced
per-userns sysctl infrastructure.

Currently the inotify instances/watches are being accounted in the
user_struct structure. This means that in setups where multiple
users in unprivileged containers map to the same underlying
real user (i.e. pointing to the same user_struct) the inotify limits
are going to be shared as well, allowing one user(or application) to exhaust
all others limits.

Fix this by switching the inotify sysctls to using the
per-namespace/per-user limits. This will allow the server admin to
set sensible global limits, which can further be tuned inside every
individual user namespace. Additionally, in order to preserve the
sysctl ABI make the existing inotify instances/watches sysctls
modify the values of the initial user namespace.

Signed-off-by: Nikolay Borisov <n.borisov.lkml@gmail.com>
Acked-by: Jan Kara <jack@suse.cz>
Acked-by: Serge Hallyn <serge@hallyn.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
This commit is contained in:
Nikolay Borisov
2016-12-14 15:56:33 +02:00
committed by Eric W. Biederman
parent 880a38547f
commit 1cce1eea0a
7 changed files with 47 additions and 27 deletions

View File

@@ -44,10 +44,8 @@
#include <asm/ioctls.h>
/* these are configurable via /proc/sys/fs/inotify/ */
static int inotify_max_user_instances __read_mostly;
/* configurable via /proc/sys/fs/inotify/ */
static int inotify_max_queued_events __read_mostly;
static int inotify_max_user_watches __read_mostly;
static struct kmem_cache *inotify_inode_mark_cachep __read_mostly;
@@ -60,7 +58,7 @@ static int zero;
struct ctl_table inotify_table[] = {
{
.procname = "max_user_instances",
.data = &inotify_max_user_instances,
.data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES],
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
@@ -68,7 +66,7 @@ struct ctl_table inotify_table[] = {
},
{
.procname = "max_user_watches",
.data = &inotify_max_user_watches,
.data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES],
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
@@ -500,7 +498,7 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
/* remove this mark from the idr */
inotify_remove_from_idr(group, i_mark);
atomic_dec(&group->inotify_data.user->inotify_watches);
dec_inotify_watches(group->inotify_data.ucounts);
}
/* ding dong the mark is dead */
@@ -584,14 +582,17 @@ static int inotify_new_watch(struct fsnotify_group *group,
tmp_i_mark->fsn_mark.mask = mask;
tmp_i_mark->wd = -1;
ret = -ENOSPC;
if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches)
goto out_err;
ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark);
if (ret)
goto out_err;
/* increment the number of watches the user has */
if (!inc_inotify_watches(group->inotify_data.ucounts)) {
inotify_remove_from_idr(group, tmp_i_mark);
ret = -ENOSPC;
goto out_err;
}
/* we are on the idr, now get on the inode */
ret = fsnotify_add_mark_locked(&tmp_i_mark->fsn_mark, group, inode,
NULL, 0);
@@ -601,8 +602,6 @@ static int inotify_new_watch(struct fsnotify_group *group,
goto out_err;
}
/* increment the number of watches the user has */
atomic_inc(&group->inotify_data.user->inotify_watches);
/* return the watch descriptor for this new mark */
ret = tmp_i_mark->wd;
@@ -653,10 +652,11 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
spin_lock_init(&group->inotify_data.idr_lock);
idr_init(&group->inotify_data.idr);
group->inotify_data.user = get_current_user();
group->inotify_data.ucounts = inc_ucount(current_user_ns(),
current_euid(),
UCOUNT_INOTIFY_INSTANCES);
if (atomic_inc_return(&group->inotify_data.user->inotify_devs) >
inotify_max_user_instances) {
if (!group->inotify_data.ucounts) {
fsnotify_destroy_group(group);
return ERR_PTR(-EMFILE);
}
@@ -819,8 +819,8 @@ static int __init inotify_user_setup(void)
inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark, SLAB_PANIC);
inotify_max_queued_events = 16384;
inotify_max_user_instances = 128;
inotify_max_user_watches = 8192;
init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128;
init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = 8192;
return 0;
}