diff options
author | Michal Hocko <mhocko@suse.com> | 2018-08-21 21:52:33 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-22 10:52:44 -0700 |
commit | 93065ac753e4443840a057bfef4be71ec766fde9 (patch) | |
tree | 6293538251b5e62affb5cdbe56a4d2f7257fc656 /drivers/infiniband | |
parent | c2343d2761f86ae1b857f78c7cdb9f51e5fa1641 (diff) | |
download | linux-93065ac753e4443840a057bfef4be71ec766fde9.tar.gz linux-93065ac753e4443840a057bfef4be71ec766fde9.tar.bz2 linux-93065ac753e4443840a057bfef4be71ec766fde9.zip |
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>
Diffstat (limited to 'drivers/infiniband')
-rw-r--r-- | drivers/infiniband/core/umem_odp.c | 33 | ||||
-rw-r--r-- | drivers/infiniband/hw/hfi1/mmu_rb.c | 11 | ||||
-rw-r--r-- | drivers/infiniband/hw/mlx5/odp.c | 2 |
3 files changed, 34 insertions, 12 deletions
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index 182436b92ba9..6ec748eccff7 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -186,6 +186,7 @@ static void ib_umem_notifier_release(struct mmu_notifier *mn, rbt_ib_umem_for_each_in_range(&context->umem_tree, 0, ULLONG_MAX, ib_umem_notifier_release_trampoline, + true, NULL); up_read(&context->umem_rwsem); } @@ -207,22 +208,31 @@ static int invalidate_range_start_trampoline(struct ib_umem *item, u64 start, return 0; } -static void ib_umem_notifier_invalidate_range_start(struct mmu_notifier *mn, +static int ib_umem_notifier_invalidate_range_start(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, - unsigned long end) + unsigned long end, + bool blockable) { struct ib_ucontext *context = container_of(mn, struct ib_ucontext, mn); + int ret; if (!context->invalidate_range) - return; + return 0; + + if (blockable) + down_read(&context->umem_rwsem); + else if (!down_read_trylock(&context->umem_rwsem)) + return -EAGAIN; ib_ucontext_notifier_start_account(context); - down_read(&context->umem_rwsem); - rbt_ib_umem_for_each_in_range(&context->umem_tree, start, + ret = rbt_ib_umem_for_each_in_range(&context->umem_tree, start, end, - invalidate_range_start_trampoline, NULL); + invalidate_range_start_trampoline, + blockable, NULL); up_read(&context->umem_rwsem); + + return ret; } static int invalidate_range_end_trampoline(struct ib_umem *item, u64 start, @@ -242,10 +252,15 @@ static void ib_umem_notifier_invalidate_range_end(struct mmu_notifier *mn, if (!context->invalidate_range) return; + /* + * TODO: we currently bail out if there is any sleepable work to be done + * in ib_umem_notifier_invalidate_range_start so we shouldn't really block + * here. But this is ugly and fragile. + */ down_read(&context->umem_rwsem); rbt_ib_umem_for_each_in_range(&context->umem_tree, start, end, - invalidate_range_end_trampoline, NULL); + invalidate_range_end_trampoline, true, NULL); up_read(&context->umem_rwsem); ib_ucontext_notifier_end_account(context); } @@ -798,6 +813,7 @@ EXPORT_SYMBOL(ib_umem_odp_unmap_dma_pages); int rbt_ib_umem_for_each_in_range(struct rb_root_cached *root, u64 start, u64 last, umem_call_back cb, + bool blockable, void *cookie) { int ret_val = 0; @@ -809,6 +825,9 @@ int rbt_ib_umem_for_each_in_range(struct rb_root_cached *root, for (node = rbt_ib_umem_iter_first(root, start, last - 1); node; node = next) { + /* TODO move the blockable decision up to the callback */ + if (!blockable) + return -EAGAIN; next = rbt_ib_umem_iter_next(node, start, last - 1); umem = container_of(node, struct ib_umem_odp, interval_tree); ret_val = cb(umem->umem, start, last, cookie) || ret_val; diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index 70aceefe14d5..e1c7996c018e 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -67,9 +67,9 @@ struct mmu_rb_handler { static unsigned long mmu_node_start(struct mmu_rb_node *); static unsigned long mmu_node_last(struct mmu_rb_node *); -static void mmu_notifier_range_start(struct mmu_notifier *, +static int mmu_notifier_range_start(struct mmu_notifier *, struct mm_struct *, - unsigned long, unsigned long); + unsigned long, unsigned long, bool); static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *, unsigned long, unsigned long); static void do_remove(struct mmu_rb_handler *handler, @@ -284,10 +284,11 @@ void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler, handler->ops->remove(handler->ops_arg, node); } -static void mmu_notifier_range_start(struct mmu_notifier *mn, +static int mmu_notifier_range_start(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, - unsigned long end) + unsigned long end, + bool blockable) { struct mmu_rb_handler *handler = container_of(mn, struct mmu_rb_handler, mn); @@ -313,6 +314,8 @@ static void mmu_notifier_range_start(struct mmu_notifier *mn, if (added) queue_work(handler->wq, &handler->del_work); + + return 0; } /* diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index f1a87a690a4c..d216e0d2921d 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -488,7 +488,7 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) down_read(&ctx->umem_rwsem); rbt_ib_umem_for_each_in_range(&ctx->umem_tree, 0, ULLONG_MAX, - mr_leaf_free, imr); + mr_leaf_free, true, imr); up_read(&ctx->umem_rwsem); wait_event(imr->q_leaf_free, !atomic_read(&imr->num_leaf_free)); |