fsnotify: Improve ENOMEM handling
Subsystems (4)
Jan Kara
maintainercover fsnotify: Improve ENOMEM handling
Hello,
these two patches improve ENOMEM handling in fsnotify framework. In particular we queue overflow event if we cannot report some event due to ENOMEM (currently we just silently lose the event). We also make sure fanotify unlimited queues cannot lose events due to ENOMEM. This series is prerequisite for memcg charging of fsnotify events. Comments are welcome!
Honza
Jan Kara
maintainerPATCH 1/2 fanotify: Avoid lost events due to ENOMEM for unlimited queues
Fanotify queues of unlimited length do not expect events can be lost. Since these queues are used for system auditing and other security related tasks, loosing events can even have security implications. So avoid loosing events due to failure to allocate memory by making event allocation use __GFP_NOFAIL. Since the allocation is small (32-bytes), currently there is no practical difference of this change but still it is good to have the expectation explicitely documented.
--- fs/notify/fanotify/fanotify.c | 19 ++++++++++++++----- fs/notify/fanotify/fanotify.h | 3 ++- fs/notify/fanotify/fanotify_user.c | 2 +- 3 files changed, 17 insertions(+), 7 deletions(-)
fs/notify/fanotify/fanotify.c +14 -5
@@ -139,23 +139,32 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,return false; } -struct fanotify_event_info *fanotify_alloc_event (struct inode *inode,u32 mask, +struct fanotify_event_info *fanotify_alloc_event (struct fsnotify_group *group, +struct inode *inode,u32 mask,const struct path *path) {struct fanotify_event_info *event; +gfp_t gfp =GFP_KERNEL ; + +/* +* For queues with unlimited length lost events are not expected and +* can possibly have security implications. Avoid losing events when +* memory is short. +*/ +if (group->max_events ==UINT_MAX ) + gfp |= __GFP_NOFAIL;if (fanotify_is_perm_event (mask)) {struct fanotify_perm_event_info *pevent; - pevent =kmem_cache_alloc (fanotify_perm_event_cachep, -GFP_KERNEL ); + pevent =kmem_cache_alloc (fanotify_perm_event_cachep, gfp);if (!pevent)return NULL ; event = &pevent->fae; pevent->response =0 ; goto init; } - event =kmem_cache_alloc (fanotify_event_cachep,GFP_KERNEL ); + event =kmem_cache_alloc (fanotify_event_cachep, gfp);if (!event)return NULL ; init:__maybe_unused
@@ -210,7 +219,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,return 0 ; } - event =fanotify_alloc_event (inode, mask, data); + event =fanotify_alloc_event (group, inode, mask, data); ret = -ENOMEM ;if (unlikely (!event)) goto finish;
fs/notify/fanotify/fanotify.h +2 -1
@@ -52,5 +52,6 @@ static inline struct fanotify_event_info *FANOTIFY_E(struct fsnotify_event *fse) return container_of(fse, struct fanotify_event_info, fse); } -struct fanotify_event_info *fanotify_alloc_event (struct inode *inode,u32 mask, +struct fanotify_event_info *fanotify_alloc_event (struct fsnotify_group *group, +struct inode *inode,u32 mask,const struct path *path);
fs/notify/fanotify/fanotify_user.c +1 -1
@@ -757,7 +757,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) group->fanotify_data.user = user;atomic_inc (&user->fanotify_listeners); - oevent =fanotify_alloc_event (NULL ,FS_Q_OVERFLOW ,NULL ); + oevent =fanotify_alloc_event (group,NULL ,FS_Q_OVERFLOW ,NULL );if (unlikely (!oevent)) { fd = -ENOMEM ; goto out_destroy_group;
Signature · 1 line
2.13.6
Amir Goldstein
reviewerRe: [PATCH 1/2] fanotify: Avoid lost events due to ENOMEM for unlimited queues
Quoted 2 lines · Jan Kara
Fanotify queues of unlimited length do not expect events can be lost. Since these queues are used for system auditing and other security
Change looks good to me, but the reasoning is going backwards. IMO, you should mention that we are going to change -ENOMEM behavior to result in Q_OVERFLOW and user does not expect Q_OVERFLOW from an UNLIMITED queue.
Quoted 6 lines
related tasks, loosing events can even have security implications. So avoid loosing events due to failure to allocate memory by making event allocation use
__GFP_NOFAIL. Since the allocation is small (32-bytes), currently there is no practical difference of this change but still it is good to have the expectation explicitely documented.
But if currently allocations cannot fail, then why do we need patch 2/2 (queue overflow event). It is because small allocations can fail when accounted to non-root memcg?
Thanks,
Amir.
Quoted 85 lines
Signed-off-by Jan Kara <[email protected]>--- fs/notify/fanotify/fanotify.c | 19 ++++++++++++++----- fs/notify/fanotify/fanotify.h | 3 ++- fs/notify/fanotify/fanotify_user.c | 2 +- 3 files changed, 17 insertions(+), 7 deletions(-)fs/notify/fanotify/fanotify.c +14
-5@@ -139,23 +139,32 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,return false; } -struct fanotify_event_info *fanotify_alloc_event (struct inode *inode,u32 mask, +struct fanotify_event_info *fanotify_alloc_event (struct fsnotify_group *group, +struct inode *inode,u32 mask,const struct path *path) {struct fanotify_event_info *event; +gfp_t gfp =GFP_KERNEL ; + +/* +* For queues with unlimited length lost events are not expected and +* can possibly have security implications. Avoid losing events when +* memory is short. +*/ +if (group->max_events ==UINT_MAX ) + gfp |= __GFP_NOFAIL;if (fanotify_is_perm_event (mask)) {struct fanotify_perm_event_info *pevent; - pevent =kmem_cache_alloc (fanotify_perm_event_cachep, -GFP_KERNEL ); + pevent =kmem_cache_alloc (fanotify_perm_event_cachep, gfp);if (!pevent)return NULL ; event = &pevent->fae; pevent->response =0 ; goto init; } - event =kmem_cache_alloc (fanotify_event_cachep,GFP_KERNEL ); + event =kmem_cache_alloc (fanotify_event_cachep, gfp);if (!event)return NULL ; init:__maybe_unused @@ -210,7 +219,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,return 0 ; } - event =fanotify_alloc_event (inode, mask, data); + event =fanotify_alloc_event (group, inode, mask, data); ret = -ENOMEM ;if (unlikely (!event)) goto finish;fs/notify/fanotify/fanotify.h +2
-1@@ -52,5 +52,6 @@ static inline struct fanotify_event_info *FANOTIFY_E(struct fsnotify_event *fse) return container_of(fse, struct fanotify_event_info, fse); } -struct fanotify_event_info *fanotify_alloc_event (struct inode *inode,u32 mask, +struct fanotify_event_info *fanotify_alloc_event (struct fsnotify_group *group, +struct inode *inode,u32 mask,const struct path *path);fs/notify/fanotify/fanotify_user.c +1
-2@@ -757,7 +757,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) group->fanotify_data.user = user;atomic_inc (&user->fanotify_listeners); - oevent =fanotify_alloc_event (NULL ,FS_Q_OVERFLOW ,NULL ); + oevent =fanotify_alloc_event (group,NULL ,FS_Q_OVERFLOW ,NULL );if (unlikely (!oevent)) { fd = -ENOMEM ; goto out_destroy_group; --2.13.6
Jan Kara
maintainerRe: [PATCH 1/2] fanotify: Avoid lost events due to ENOMEM for unlimited queues
Quoted 8 lines · Amir Goldstein
Quoted 2 lines · Jan Kara
Fanotify queues of unlimited length do not expect events can be lost. Since these queues are used for system auditing and other security
Change looks good to me, but the reasoning is going backwards. IMO, you should mention that we are going to change
-ENOMEMbehavior to result inQ_OVERFLOWand user does not expectQ_OVERFLOWfrom an UNLIMITED queue.
See below.
Quoted 10 lines
Quoted 6 lines
related tasks, loosing events can even have security implications. So avoid loosing events due to failure to allocate memory by making event allocation use
__GFP_NOFAIL. Since the allocation is small (32-bytes), currently there is no practical difference of this change but still it is good to have the expectation explicitely documented.But if currently allocations cannot fail, then why do we need patch 2/2 (queue overflow event). It is because small allocations can fail when accounted to non-root memcg?
Yes. So how about changelog like:
Fanotify queues of unlimited length do not expect events can be lost. Since these queues are used for system auditing and other security related tasks, loosing events can even have security implications. Currently, since the allocation is small (32-bytes), it cannot fail however when we start accounting events in memcgs, allocation can start failing. So avoid loosing events due to failure to allocate memory by making event allocation use __GFP_NOFAIL.
Thanks for review!
Honza
Signature · 2 lines
Jan Kara <[email protected]> SUSE Labs, CR
Amir Goldstein
reviewerRe: [PATCH 1/2] fanotify: Avoid lost events due to ENOMEM for unlimited queues
Quoted 25 lines · Jan Kara
Quoted 8 lines · Amir Goldstein
Quoted 2 lines · Jan Kara
Fanotify queues of unlimited length do not expect events can be lost. Since these queues are used for system auditing and other security
Change looks good to me, but the reasoning is going backwards. IMO, you should mention that we are going to change
-ENOMEMbehavior to result inQ_OVERFLOWand user does not expectQ_OVERFLOWfrom an UNLIMITED queue.See below.
Quoted 10 lines
Quoted 6 lines
related tasks, loosing events can even have security implications. So avoid loosing events due to failure to allocate memory by making event allocation use
__GFP_NOFAIL. Since the allocation is small (32-bytes), currently there is no practical difference of this change but still it is good to have the expectation explicitely documented.But if currently allocations cannot fail, then why do we need patch 2/2 (queue overflow event). It is because small allocations can fail when accounted to non-root memcg?
Yes. So how about changelog like:
Quoted 8 lines
Fanotify queues of unlimited length do not expect events can be lost. Since these queues are used for system auditing and other security related tasks, loosing events can even have security implications. Currently, since the allocation is small (32-bytes), it cannot fail however when we start accounting events in memcgs, allocation can start failing. So avoid loosing events due to failure to allocate memory by making event allocation use
__GFP_NOFAIL.
Very good.
Thanks,
Amir.
Jan Kara
maintainerRe: [PATCH 1/2] fanotify: Avoid lost events due to ENOMEM for unlimited queues
Quoted 35 lines · Amir Goldstein
Quoted 25 lines · Jan Kara
Quoted 8 lines · Amir Goldstein
Quoted 2 lines · Jan Kara
Fanotify queues of unlimited length do not expect events can be lost. Since these queues are used for system auditing and other security
Change looks good to me, but the reasoning is going backwards. IMO, you should mention that we are going to change
-ENOMEMbehavior to result inQ_OVERFLOWand user does not expectQ_OVERFLOWfrom an UNLIMITED queue.See below.
Quoted 10 lines
Quoted 6 lines
related tasks, loosing events can even have security implications. So avoid loosing events due to failure to allocate memory by making event allocation use
__GFP_NOFAIL. Since the allocation is small (32-bytes), currently there is no practical difference of this change but still it is good to have the expectation explicitely documented.But if currently allocations cannot fail, then why do we need patch 2/2 (queue overflow event). It is because small allocations can fail when accounted to non-root memcg?
Yes. So how about changelog like:
Quoted 8 lines
Fanotify queues of unlimited length do not expect events can be lost. Since these queues are used for system auditing and other security related tasks, loosing events can even have security implications. Currently, since the allocation is small (32-bytes), it cannot fail however when we start accounting events in memcgs, allocation can start failing. So avoid loosing events due to failure to allocate memory by making event allocation use
__GFP_NOFAIL.
Quoted 1 line
Very good.
Can I add your reviewed-by to the patch then?
Honza
Signature · 2 lines
Jan Kara <[email protected]> SUSE Labs, CR
Amir Goldstein
reviewerRe: [PATCH 1/2] fanotify: Avoid lost events due to ENOMEM for unlimited queues
Quoted 36 lines · Jan Kara
Quoted 35 lines · Amir Goldstein
Quoted 33 lines · Jan Kara
Quoted 8 lines · Amir Goldstein
Quoted 2 lines · Jan Kara
Fanotify queues of unlimited length do not expect events can be lost. Since these queues are used for system auditing and other security
Change looks good to me, but the reasoning is going backwards. IMO, you should mention that we are going to change
-ENOMEMbehavior to result inQ_OVERFLOWand user does not expectQ_OVERFLOWfrom an UNLIMITED queue.See below.
Quoted 10 lines
Quoted 6 lines
related tasks, loosing events can even have security implications. So avoid loosing events due to failure to allocate memory by making event allocation use
__GFP_NOFAIL. Since the allocation is small (32-bytes), currently there is no practical difference of this change but still it is good to have the expectation explicitely documented.But if currently allocations cannot fail, then why do we need patch 2/2 (queue overflow event). It is because small allocations can fail when accounted to non-root memcg?
Yes. So how about changelog like:
Fanotify queues of unlimited length do not expect events can be lost. Since these queues are used for system auditing and other security related tasks, loosing events can even have security implications. Currently, since the allocation is small (32-bytes), it cannot fail however when we start accounting events in memcgs, allocation can start failing. So avoid loosing events due to failure to allocate memory by making event allocation use
__GFP_NOFAIL.
Quoted 4 lines
Quoted 1 line
Very good.
Can I add your reviewed-by to the patch then?
Yes, of course.
Thanks,
Amir.
Jan Kara
maintainerPATCH 2/2 fsnotify: Let userspace know about lost events due to ENOMEM
In reply to Jan KaraCurrently if notification event is lost due to event allocation failing we ENOMEM, we just silently continue (except for fanotify permission events where we deny the access). This is undesirable as userspace has no way of knowing whether the notifications it got are complete or not. Treat lost events due to ENOMEM the same way as lost events due to queue overflow so that userspace knows something bad happened and it likely needs to rescan the filesystem.
--- fs/notify/fanotify/fanotify.c | 9 ++++++++- fs/notify/inotify/inotify_fsnotify.c | 8 +++++++- fs/notify/notification.c | 3 ++- include/linux/fsnotify_backend.h | 6 ++++++ 4 files changed, 23 insertions(+), 3 deletions(-)
fs/notify/fanotify/fanotify.c +8 -1
@@ -221,8 +221,15 @@ static int fanotify_handle_event(struct fsnotify_group *group, event =fanotify_alloc_event (group, inode, mask, data); ret = -ENOMEM ; -if (unlikely (!event)) +if (unlikely (!event)) { +/* +* We don't queue overflow events for permission events as +* there the access is denied and so no event is in fact lost. +*/ +if (!fanotify_is_perm_event (mask)) +fsnotify_queue_overflow (group); goto finish; + } fsn_event = &event->fse; ret =fsnotify_add_event (group, fsn_event, fanotify_merge);
fs/notify/inotify/inotify_fsnotify.c +7 -1
@@ -99,8 +99,14 @@ int inotify_handle_event(struct fsnotify_group *group, fsn_mark); event =kmalloc (alloc_len,GFP_KERNEL ); -if (unlikely (!event)) +if (unlikely (!event)) { +/* +* Treat lost event due to ENOMEM the same way as queue +* overflow to let userspace know event was lost. +*/ +fsnotify_queue_overflow (group);return -ENOMEM ; + } fsn_event = &event->fse;fsnotify_init_event (fsn_event, inode, mask);
fs/notify/notification.c +2 -1
@@ -111,7 +111,8 @@ int fsnotify_add_event(struct fsnotify_group *group,return 2 ; } -if (group->q_len >= group->max_events) { +if (event == group->overflow_event || + group->q_len >= group->max_events) { ret =2 ;/* Queue overflow event only if it isn't already queued */ if (!list_empty (&group->overflow_event->list)) {
include/linux/fsnotify_backend.h +6 -0
@@ -331,6 +331,12 @@ extern int fsnotify_add_event(struct fsnotify_group *group,struct fsnotify_event *event, int (*merge)(struct list_head *, struct fsnotify_event *)); +/* Queue overflow event to a notification group */ +static inline void fsnotify_queue_overflow (struct fsnotify_group *group) +{ +fsnotify_add_event (group, group->overflow_event,NULL ); +} +/* true if the group notification queue is empty */ extern bool fsnotify_notify_queue_is_empty (struct fsnotify_group *group);/* return, but do not dequeue the first event on the notification queue */
Signature · 1 line
2.13.6
Re: [PATCH 2/2] fsnotify: Let userspace know about lost events due to ENOMEM
Quoted 9 lines · Jan Kara
Currently if notification event is lost due to event allocation failing we ENOMEM, we just silently continue (except for fanotify permission events where we deny the access). This is undesirable as userspace has no way of knowing whether the notifications it got are complete or not. Treat lost events due to ENOMEM the same way as lost events due to queue overflow so that userspace knows something bad happened and it likely needs to rescan the filesystem.
Signed-off-by Jan Kara <[email protected]>
Quoted 82 lines
--- fs/notify/fanotify/fanotify.c | 9 ++++++++- fs/notify/inotify/inotify_fsnotify.c | 8 +++++++- fs/notify/notification.c | 3 ++- include/linux/fsnotify_backend.h | 6 ++++++ 4 files changed, 23 insertions(+), 3 deletions(-)fs/notify/fanotify/fanotify.c +8
-1@@ -221,8 +221,15 @@ static int fanotify_handle_event(struct fsnotify_group *group, event =fanotify_alloc_event (group, inode, mask, data); ret = -ENOMEM ; -if (unlikely (!event)) +if (unlikely (!event)) { +/* +* We don't queue overflow events for permission events as +* there the access is denied and so no event is in fact lost. +*/ +if (!fanotify_is_perm_event (mask)) +fsnotify_queue_overflow (group); goto finish; + } fsn_event = &event->fse; ret =fsnotify_add_event (group, fsn_event, fanotify_merge);fs/notify/inotify/inotify_fsnotify.c +7
-1@@ -99,8 +99,14 @@ int inotify_handle_event(struct fsnotify_group *group, fsn_mark); event =kmalloc (alloc_len,GFP_KERNEL ); -if (unlikely (!event)) +if (unlikely (!event)) { +/* +* Treat lost event due to ENOMEM the same way as queue +* overflow to let userspace know event was lost. +*/ +fsnotify_queue_overflow (group);return -ENOMEM ; + } fsn_event = &event->fse;fsnotify_init_event (fsn_event, inode, mask);fs/notify/notification.c +2
-1@@ -111,7 +111,8 @@ int fsnotify_add_event(struct fsnotify_group *group,return 2 ; } -if (group->q_len >= group->max_events) { +if (event == group->overflow_event || + group->q_len >= group->max_events) { ret =2 ;/* Queue overflow event only if it isn't already queued */ if (!list_empty (&group->overflow_event->list)) {include/linux/fsnotify_backend.h +6
-1@@ -331,6 +331,12 @@ extern int fsnotify_add_event(struct fsnotify_group *group,struct fsnotify_event *event, int (*merge)(struct list_head *, struct fsnotify_event *)); +/* Queue overflow event to a notification group */ +static inline void fsnotify_queue_overflow (struct fsnotify_group *group) +{ +fsnotify_add_event (group, group->overflow_event,NULL ); +} +/* true if the group notification queue is empty */ extern bool fsnotify_notify_queue_is_empty (struct fsnotify_group *group);/* return, but do not dequeue the first event on the notification queue */ --2.13.6