Re: [PATCH v4 0/1] Use HMM for ODP v4

From: Jerome Glisse
Date: Wed May 22 2019 - 18:07:10 EST


On Wed, May 22, 2019 at 05:12:47PM -0300, Jason Gunthorpe wrote:
> On Wed, May 22, 2019 at 01:48:52PM -0400, Jerome Glisse wrote:
>
> > static void put_per_mm(struct ib_umem_odp *umem_odp)
> > {
> > struct ib_ucontext_per_mm *per_mm = umem_odp->per_mm;
> > @@ -325,9 +283,10 @@ static void put_per_mm(struct ib_umem_odp *umem_odp)
> > up_write(&per_mm->umem_rwsem);
> >
> > WARN_ON(!RB_EMPTY_ROOT(&per_mm->umem_tree.rb_root));
> > - mmu_notifier_unregister_no_release(&per_mm->mn, per_mm->mm);
> > + hmm_mirror_unregister(&per_mm->mirror);
> > put_pid(per_mm->tgid);
> > - mmu_notifier_call_srcu(&per_mm->rcu, free_per_mm);
> > +
> > + kfree(per_mm);
>
> Notice that mmu_notifier only uses SRCU to fence in-progress ops
> callbacks, so I think hmm internally has the bug that this ODP
> approach prevents.
>
> hmm should follow the same pattern ODP has and 'kfree_srcu' the hmm
> struct, use container_of in the mmu_notifier callbacks, and use the
> otherwise vestigal kref_get_unless_zero() to bail:
>
> From 0cb536dc0150ba964a1d655151d7b7a84d0f915a Mon Sep 17 00:00:00 2001
> From: Jason Gunthorpe <jgg@xxxxxxxxxxxx>
> Date: Wed, 22 May 2019 16:52:52 -0300
> Subject: [PATCH] hmm: Fix use after free with struct hmm in the mmu notifiers
>
> mmu_notifier_unregister_no_release() is not a fence and the mmu_notifier
> system will continue to reference hmm->mn until the srcu grace period
> expires.
>
> CPU0 CPU1
> __mmu_notifier_invalidate_range_start()
> srcu_read_lock
> hlist_for_each ()
> // mn == hmm->mn
> hmm_mirror_unregister()
> hmm_put()
> hmm_free()
> mmu_notifier_unregister_no_release()
> hlist_del_init_rcu(hmm-mn->list)
> mn->ops->invalidate_range_start(mn, range);
> mm_get_hmm()
> mm->hmm = NULL;
> kfree(hmm)
> mutex_lock(&hmm->lock);
>
> Use SRCU to kfree the hmm memory so that the notifiers can rely on hmm
> existing. Get the now-safe hmm struct through container_of and directly
> check kref_get_unless_zero to lock it against free.

It is already badly handled with BUG_ON(), i just need to convert
those to return and to use mmu_notifier_call_srcu() to free hmm
struct.

The way race is avoided is because mm->hmm will either be NULL or
point to another hmm struct before an existing hmm is free. Also
if range_start/range_end use kref_get_unless_zero() but right now
this is BUG_ON if it turn out to be NULL, it should just return
on NULL.

>
> Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxxxx>
> ---
> include/linux/hmm.h | 1 +
> mm/hmm.c | 25 +++++++++++++++++++------
> 2 files changed, 20 insertions(+), 6 deletions(-)
>
> diff --git a/include/linux/hmm.h b/include/linux/hmm.h
> index 51ec27a8466816..8b91c90d3b88cb 100644
> --- a/include/linux/hmm.h
> +++ b/include/linux/hmm.h
> @@ -102,6 +102,7 @@ struct hmm {
> struct mmu_notifier mmu_notifier;
> struct rw_semaphore mirrors_sem;
> wait_queue_head_t wq;
> + struct rcu_head rcu;
> long notifiers;
> bool dead;
> };
> diff --git a/mm/hmm.c b/mm/hmm.c
> index 816c2356f2449f..824e7e160d8167 100644
> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -113,6 +113,11 @@ static struct hmm *hmm_get_or_create(struct mm_struct *mm)
> return NULL;
> }
>
> +static void hmm_fee_rcu(struct rcu_head *rcu)
> +{
> + kfree(container_of(rcu, struct hmm, rcu));
> +}
> +
> static void hmm_free(struct kref *kref)
> {
> struct hmm *hmm = container_of(kref, struct hmm, kref);
> @@ -125,7 +130,7 @@ static void hmm_free(struct kref *kref)
> mm->hmm = NULL;
> spin_unlock(&mm->page_table_lock);
>
> - kfree(hmm);
> + mmu_notifier_call_srcu(&hmm->rcu, hmm_fee_rcu);
> }
>
> static inline void hmm_put(struct hmm *hmm)
> @@ -153,10 +158,14 @@ void hmm_mm_destroy(struct mm_struct *mm)
>
> static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
> {
> - struct hmm *hmm = mm_get_hmm(mm);
> + struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
> struct hmm_mirror *mirror;
> struct hmm_range *range;
>
> + /* hmm is in progress to free */
> + if (!kref_get_unless_zero(&hmm->kref))
> + return;
> +
> /* Report this HMM as dying. */
> hmm->dead = true;
>
> @@ -194,13 +203,15 @@ static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
> static int hmm_invalidate_range_start(struct mmu_notifier *mn,
> const struct mmu_notifier_range *nrange)
> {
> - struct hmm *hmm = mm_get_hmm(nrange->mm);
> + struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
> struct hmm_mirror *mirror;
> struct hmm_update update;
> struct hmm_range *range;
> int ret = 0;
>
> - VM_BUG_ON(!hmm);
> + /* hmm is in progress to free */
> + if (!kref_get_unless_zero(&hmm->kref))
> + return 0;
>
> update.start = nrange->start;
> update.end = nrange->end;
> @@ -248,9 +259,11 @@ static int hmm_invalidate_range_start(struct mmu_notifier *mn,
> static void hmm_invalidate_range_end(struct mmu_notifier *mn,
> const struct mmu_notifier_range *nrange)
> {
> - struct hmm *hmm = mm_get_hmm(nrange->mm);
> + struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
>
> - VM_BUG_ON(!hmm);
> + /* hmm is in progress to free */
> + if (!kref_get_unless_zero(&hmm->kref))
> + return;
>
> mutex_lock(&hmm->lock);
> hmm->notifiers--;
> --
> 2.21.0
>