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, 30 insertions, 12 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7c7362dd2faa..0205aee44ded 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1289,8 +1289,8 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp,
 }
 #endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */
 
-void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
-		unsigned long start, unsigned long end);
+int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+		unsigned long start, unsigned long end, bool blockable);
 
 #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE
 int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu);
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 392e6af82701..133ba78820ee 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -151,13 +151,15 @@ struct mmu_notifier_ops {
 	 * address space but may still be referenced by sptes until
 	 * the last refcount is dropped.
 	 *
-	 * If both of these callbacks cannot block, and invalidate_range
-	 * cannot block, mmu_notifier_ops.flags should have
-	 * MMU_INVALIDATE_DOES_NOT_BLOCK set.
+	 * If blockable argument is set to false then the callback cannot
+	 * sleep and has to return with -EAGAIN. 0 should be returned
+	 * otherwise.
+	 *
 	 */
-	void (*invalidate_range_start)(struct mmu_notifier *mn,
+	int (*invalidate_range_start)(struct mmu_notifier *mn,
 				       struct mm_struct *mm,
-				       unsigned long start, unsigned long end);
+				       unsigned long start, unsigned long end,
+				       bool blockable);
 	void (*invalidate_range_end)(struct mmu_notifier *mn,
 				     struct mm_struct *mm,
 				     unsigned long start, unsigned long end);
@@ -229,8 +231,9 @@ extern int __mmu_notifier_test_young(struct mm_struct *mm,
 				     unsigned long address);
 extern void __mmu_notifier_change_pte(struct mm_struct *mm,
 				      unsigned long address, pte_t pte);
-extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
-				  unsigned long start, unsigned long end);
+extern int __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
+				  unsigned long start, unsigned long end,
+				  bool blockable);
 extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 				  unsigned long start, unsigned long end,
 				  bool only_end);
@@ -281,7 +284,15 @@ static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm,
 				  unsigned long start, unsigned long end)
 {
 	if (mm_has_notifiers(mm))
-		__mmu_notifier_invalidate_range_start(mm, start, end);
+		__mmu_notifier_invalidate_range_start(mm, start, end, true);
+}
+
+static inline int mmu_notifier_invalidate_range_start_nonblock(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+	if (mm_has_notifiers(mm))
+		return __mmu_notifier_invalidate_range_start(mm, start, end, false);
+	return 0;
 }
 
 static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm,
@@ -461,6 +472,12 @@ static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm,
 {
 }
 
+static inline int mmu_notifier_invalidate_range_start_nonblock(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+	return 0;
+}
+
 static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 				  unsigned long start, unsigned long end)
 {
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 6adac113e96d..92f70e4c6252 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -95,7 +95,7 @@ static inline int check_stable_address_space(struct mm_struct *mm)
 	return 0;
 }
 
-void __oom_reap_task_mm(struct mm_struct *mm);
+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,
diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h
index 6a17f856f841..381cdf5a9bd1 100644
--- a/include/rdma/ib_umem_odp.h
+++ b/include/rdma/ib_umem_odp.h
@@ -119,7 +119,8 @@ typedef int (*umem_call_back)(struct ib_umem *item, u64 start, u64 end,
  */
 int rbt_ib_umem_for_each_in_range(struct rb_root_cached *root,
 				  u64 start, u64 end,
-				  umem_call_back cb, void *cookie);
+				  umem_call_back cb,
+				  bool blockable, void *cookie);
 
 /*
  * Find first region intersecting with address range.