mm, oom: distinguish blockable mode for mmu notifiers

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>

4 files changed, 35 insertions, 22 deletions

diff --git a/mm/hmm.c b/mm/hmm.c
index 76e7a058b32f..0b0554591610 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -177,16 +177,19 @@ static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 	up_write(&hmm->mirrors_sem);
 }
 
-static void hmm_invalidate_range_start(struct mmu_notifier *mn,
+static int hmm_invalidate_range_start(struct mmu_notifier *mn,
 				       struct mm_struct *mm,
 				       unsigned long start,
-				       unsigned long end)
+				       unsigned long end,
+				       bool blockable)
 {
 	struct hmm *hmm = mm->hmm;
 
 	VM_BUG_ON(!hmm);
 
 	atomic_inc(&hmm->sequence);
+
+	return 0;
 }
 
 static void hmm_invalidate_range_end(struct mmu_notifier *mn,
diff --git a/mm/mmap.c b/mm/mmap.c
index 8d6449e74431..bb2a7e097c7d 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3064,7 +3064,7 @@ void exit_mmap(struct mm_struct *mm)
 		 * reliably test it.
 		 */
 		mutex_lock(&oom_lock);
-		__oom_reap_task_mm(mm);
+		(void)__oom_reap_task_mm(mm);
 		mutex_unlock(&oom_lock);
 
 		set_bit(MMF_OOM_SKIP, &mm->flags);
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index eff6b88a993f..82bb1a939c0e 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -174,18 +174,29 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
 	srcu_read_unlock(&srcu, id);
 }
 
-void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
-				  unsigned long start, unsigned long end)
+int __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
+				  unsigned long start, unsigned long end,
+				  bool blockable)
 {
 	struct mmu_notifier *mn;
+	int ret = 0;
 	int id;
 
 	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
-		if (mn->ops->invalidate_range_start)
-			mn->ops->invalidate_range_start(mn, mm, start, end);
+		if (mn->ops->invalidate_range_start) {
+			int _ret = mn->ops->invalidate_range_start(mn, mm, start, end, blockable);
+			if (_ret) {
+				pr_info("%pS callback failed with %d in %sblockable context.\n",
+						mn->ops->invalidate_range_start, _ret,
+						!blockable ? "non-" : "");
+				ret = _ret;
+			}
+		}
 	}
 	srcu_read_unlock(&srcu, id);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_start);
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 412f43453a68..be31a1e0fe78 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -487,9 +487,10 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);
 static struct task_struct *oom_reaper_list;
 static DEFINE_SPINLOCK(oom_reaper_lock);
 
-void __oom_reap_task_mm(struct mm_struct *mm)
+bool __oom_reap_task_mm(struct mm_struct *mm)
 {
 	struct vm_area_struct *vma;
+	bool ret = true;
 
 	/*
 	 * Tell all users of get_user/copy_from_user etc... that the content
@@ -519,12 +520,17 @@ void __oom_reap_task_mm(struct mm_struct *mm)
 			struct mmu_gather tlb;
 
 			tlb_gather_mmu(&tlb, mm, start, end);
-			mmu_notifier_invalidate_range_start(mm, start, end);
+			if (mmu_notifier_invalidate_range_start_nonblock(mm, start, end)) {
+				ret = false;
+				continue;
+			}
 			unmap_page_range(&tlb, vma, start, end, NULL);
 			mmu_notifier_invalidate_range_end(mm, start, end);
 			tlb_finish_mmu(&tlb, start, end);
 		}
 	}
+
+	return ret;
 }
 
 static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
@@ -554,18 +560,6 @@ static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 	}
 
 	/*
-	 * If the mm has invalidate_{start,end}() notifiers that could block,
-	 * sleep to give the oom victim some more time.
-	 * TODO: we really want to get rid of this ugly hack and make sure that
-	 * notifiers cannot block for unbounded amount of time
-	 */
-	if (mm_has_blockable_invalidate_notifiers(mm)) {
-		up_read(&mm->mmap_sem);
-		schedule_timeout_idle(HZ);
-		goto unlock_oom;
-	}
-
-	/*
 	 * MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't
 	 * work on the mm anymore. The check for MMF_OOM_SKIP must run
 	 * under mmap_sem for reading because it serializes against the
@@ -579,7 +573,12 @@ static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 
 	trace_start_task_reaping(tsk->pid);
 
-	__oom_reap_task_mm(mm);
+	/* failed to reap part of the address space. Try again later */
+	if (!__oom_reap_task_mm(mm)) {
+		up_read(&mm->mmap_sem);
+		ret = false;
+		goto unlock_oom;
+	}
 
 	pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
 			task_pid_nr(tsk), tsk->comm,