![Michal Hocko](/assets/img/avatar_default.png)
There are several blockable mmu notifiers which might sleep in mmu_notifier_invalidate_range_start and that is a problem for the oom_reaper because it needs to guarantee a forward progress so it cannot depend on any sleepable locks. Currently we simply back off and mark an oom victim with blockable mmu notifiers as done after a short sleep. That can result in selecting a new oom victim prematurely because the previous one still hasn't torn its memory down yet. We can do much better though. Even if mmu notifiers use sleepable locks there is no reason to automatically assume those locks are held. Moreover majority of notifiers only care about a portion of the address space and there is absolutely zero reason to fail when we are unmapping an unrelated range. Many notifiers do really block and wait for HW which is harder to handle and we have to bail out though. This patch handles the low hanging fruit. __mmu_notifier_invalidate_range_start gets a blockable flag and callbacks are not allowed to sleep if the flag is set to false. This is achieved by using trylock instead of the sleepable lock for most callbacks and continue as long as we do not block down the call chain. I think we can improve that even further because there is a common pattern to do a range lookup first and then do something about that. The first part can be done without a sleeping lock in most cases AFAICS. The oom_reaper end then simply retries if there is at least one notifier which couldn't make any progress in !blockable mode. A retry loop is already implemented to wait for the mmap_sem and this is basically the same thing. The simplest way for driver developers to test this code path is to wrap userspace code which uses these notifiers into a memcg and set the hard limit to hit the oom. This can be done e.g. after the test faults in all the mmu notifier managed memory and set the hard limit to something really small. Then we are looking for a proper process tear down. [akpm@linux-foundation.org: coding style fixes] [akpm@linux-foundation.org: minor code simplification] Link: http://lkml.kernel.org/r/20180716115058.5559-1-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Christian König <christian.koenig@amd.com> # AMD notifiers Acked-by: Leon Romanovsky <leonro@mellanox.com> # mlx and umem_odp Reported-by: David Rientjes <rientjes@google.com> Cc: "David (ChunMing) Zhou" <David1.Zhou@amd.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: David Airlie <airlied@linux.ie> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Doug Ledford <dledford@redhat.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Mike Marciniszyn <mike.marciniszyn@intel.com> Cc: Dennis Dalessandro <dennis.dalessandro@intel.com> Cc: Sudeep Dutt <sudeep.dutt@intel.com> Cc: Ashutosh Dixit <ashutosh.dixit@intel.com> Cc: Dimitri Sivanich <sivanich@sgi.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
121 lines
3.1 KiB
C
121 lines
3.1 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __INCLUDE_LINUX_OOM_H
|
|
#define __INCLUDE_LINUX_OOM_H
|
|
|
|
|
|
#include <linux/sched/signal.h>
|
|
#include <linux/types.h>
|
|
#include <linux/nodemask.h>
|
|
#include <uapi/linux/oom.h>
|
|
#include <linux/sched/coredump.h> /* MMF_* */
|
|
#include <linux/mm.h> /* VM_FAULT* */
|
|
|
|
struct zonelist;
|
|
struct notifier_block;
|
|
struct mem_cgroup;
|
|
struct task_struct;
|
|
|
|
/*
|
|
* Details of the page allocation that triggered the oom killer that are used to
|
|
* determine what should be killed.
|
|
*/
|
|
struct oom_control {
|
|
/* Used to determine cpuset */
|
|
struct zonelist *zonelist;
|
|
|
|
/* Used to determine mempolicy */
|
|
nodemask_t *nodemask;
|
|
|
|
/* Memory cgroup in which oom is invoked, or NULL for global oom */
|
|
struct mem_cgroup *memcg;
|
|
|
|
/* Used to determine cpuset and node locality requirement */
|
|
const gfp_t gfp_mask;
|
|
|
|
/*
|
|
* order == -1 means the oom kill is required by sysrq, otherwise only
|
|
* for display purposes.
|
|
*/
|
|
const int order;
|
|
|
|
/* Used by oom implementation, do not set */
|
|
unsigned long totalpages;
|
|
struct task_struct *chosen;
|
|
unsigned long chosen_points;
|
|
};
|
|
|
|
extern struct mutex oom_lock;
|
|
|
|
static inline void set_current_oom_origin(void)
|
|
{
|
|
current->signal->oom_flag_origin = true;
|
|
}
|
|
|
|
static inline void clear_current_oom_origin(void)
|
|
{
|
|
current->signal->oom_flag_origin = false;
|
|
}
|
|
|
|
static inline bool oom_task_origin(const struct task_struct *p)
|
|
{
|
|
return p->signal->oom_flag_origin;
|
|
}
|
|
|
|
static inline bool tsk_is_oom_victim(struct task_struct * tsk)
|
|
{
|
|
return tsk->signal->oom_mm;
|
|
}
|
|
|
|
/*
|
|
* Use this helper if tsk->mm != mm and the victim mm needs a special
|
|
* handling. This is guaranteed to stay true after once set.
|
|
*/
|
|
static inline bool mm_is_oom_victim(struct mm_struct *mm)
|
|
{
|
|
return test_bit(MMF_OOM_VICTIM, &mm->flags);
|
|
}
|
|
|
|
/*
|
|
* Checks whether a page fault on the given mm is still reliable.
|
|
* This is no longer true if the oom reaper started to reap the
|
|
* address space which is reflected by MMF_UNSTABLE flag set in
|
|
* the mm. At that moment any !shared mapping would lose the content
|
|
* and could cause a memory corruption (zero pages instead of the
|
|
* original content).
|
|
*
|
|
* User should call this before establishing a page table entry for
|
|
* a !shared mapping and under the proper page table lock.
|
|
*
|
|
* Return 0 when the PF is safe VM_FAULT_SIGBUS otherwise.
|
|
*/
|
|
static inline int check_stable_address_space(struct mm_struct *mm)
|
|
{
|
|
if (unlikely(test_bit(MMF_UNSTABLE, &mm->flags)))
|
|
return VM_FAULT_SIGBUS;
|
|
return 0;
|
|
}
|
|
|
|
bool __oom_reap_task_mm(struct mm_struct *mm);
|
|
|
|
extern unsigned long oom_badness(struct task_struct *p,
|
|
struct mem_cgroup *memcg, const nodemask_t *nodemask,
|
|
unsigned long totalpages);
|
|
|
|
extern bool out_of_memory(struct oom_control *oc);
|
|
|
|
extern void exit_oom_victim(void);
|
|
|
|
extern int register_oom_notifier(struct notifier_block *nb);
|
|
extern int unregister_oom_notifier(struct notifier_block *nb);
|
|
|
|
extern bool oom_killer_disable(signed long timeout);
|
|
extern void oom_killer_enable(void);
|
|
|
|
extern struct task_struct *find_lock_task_mm(struct task_struct *p);
|
|
|
|
/* sysctls */
|
|
extern int sysctl_oom_dump_tasks;
|
|
extern int sysctl_oom_kill_allocating_task;
|
|
extern int sysctl_panic_on_oom;
|
|
#endif /* _INCLUDE_LINUX_OOM_H */
|