linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
* [PATCH v2 00/15] Consolidate the mmu notifier interval_tree and locking
@ 2019-10-28 20:10 Jason Gunthorpe
  2019-10-28 20:10 ` [PATCH v2 01/15] mm/mmu_notifier: define the header pre-processor parts even if disabled Jason Gunthorpe
                   ` (16 more replies)
  0 siblings, 17 replies; 70+ messages in thread
From: Jason Gunthorpe @ 2019-10-28 20:10 UTC (permalink / raw)
  To: linux-mm, Jerome Glisse, Ralph Campbell, John Hubbard, Felix.Kuehling
  Cc: linux-rdma, dri-devel, amd-gfx, Alex Deucher, Ben Skeggs,
	Boris Ostrovsky, Christian König, David Zhou,
	Dennis Dalessandro, Juergen Gross, Mike Marciniszyn,
	Oleksandr Andrushchenko, Petr Cvek, Stefano Stabellini, nouveau,
	xen-devel, Christoph Hellwig, Jason Gunthorpe

From: Jason Gunthorpe <jgg@mellanox.com>

8 of the mmu_notifier using drivers (i915_gem, radeon_mn, umem_odp, hfi1,
scif_dma, vhost, gntdev, hmm) drivers are using a common pattern where
they only use invalidate_range_start/end and immediately check the
invalidating range against some driver data structure to tell if the
driver is interested. Half of them use an interval_tree, the others are
simple linear search lists.

Of the ones I checked they largely seem to have various kinds of races,
bugs and poor implementation. This is a result of the complexity in how
the notifier interacts with get_user_pages(). It is extremely difficult to
use it correctly.

Consolidate all of this code together into the core mmu_notifier and
provide a locking scheme similar to hmm_mirror that allows the user to
safely use get_user_pages() and reliably know if the page list still
matches the mm.

This new arrangment plays nicely with the !blockable mode for
OOM. Scanning the interval tree is done such that the intersection test
will always succeed, and since there is no invalidate_range_end exposed to
drivers the scheme safely allows multiple drivers to be subscribed.

Four places are converted as an example of how the new API is used.
Four are left for future patches:
 - i915_gem has complex locking around destruction of a registration,
   needs more study
 - hfi1 (2nd user) needs access to the rbtree
 - scif_dma has a complicated logic flow
 - vhost's mmu notifiers are already being rewritten

This series, and the other code it depends on is available on my github:

https://github.com/jgunthorpe/linux/commits/mmu_notifier

v2 changes:
- Add mmu_range_set_seq() to set the mrn sequence number under the driver
  lock and make the locking more understandable
- Add some additional comments around locking/READ_ONCe
- Make the WARN_ON flow in mn_itree_invalidate a bit easier to follow
- Fix wrong WARN_ON

Jason Gunthorpe (15):
  mm/mmu_notifier: define the header pre-processor parts even if
    disabled
  mm/mmu_notifier: add an interval tree notifier
  mm/hmm: allow hmm_range to be used with a mmu_range_notifier or
    hmm_mirror
  mm/hmm: define the pre-processor related parts of hmm.h even if
    disabled
  RDMA/odp: Use mmu_range_notifier_insert()
  RDMA/hfi1: Use mmu_range_notifier_inset for user_exp_rcv
  drm/radeon: use mmu_range_notifier_insert
  xen/gntdev: Use select for DMA_SHARED_BUFFER
  xen/gntdev: use mmu_range_notifier_insert
  nouveau: use mmu_notifier directly for invalidate_range_start
  nouveau: use mmu_range_notifier instead of hmm_mirror
  drm/amdgpu: Call find_vma under mmap_sem
  drm/amdgpu: Use mmu_range_insert instead of hmm_mirror
  drm/amdgpu: Use mmu_range_notifier instead of hmm_mirror
  mm/hmm: remove hmm_mirror and related

 Documentation/vm/hmm.rst                      | 105 +---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h           |   2 +
 .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c  |   9 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c        |  14 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c    |   1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c        | 457 +++------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h        |  53 --
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.h    |  13 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c       | 111 ++--
 drivers/gpu/drm/nouveau/nouveau_svm.c         | 231 +++++---
 drivers/gpu/drm/radeon/radeon.h               |   9 +-
 drivers/gpu/drm/radeon/radeon_mn.c            | 219 ++-----
 drivers/infiniband/core/device.c              |   1 -
 drivers/infiniband/core/umem_odp.c            | 288 +--------
 drivers/infiniband/hw/hfi1/file_ops.c         |   2 +-
 drivers/infiniband/hw/hfi1/hfi.h              |   2 +-
 drivers/infiniband/hw/hfi1/user_exp_rcv.c     | 146 ++---
 drivers/infiniband/hw/hfi1/user_exp_rcv.h     |   3 +-
 drivers/infiniband/hw/mlx5/mlx5_ib.h          |   7 +-
 drivers/infiniband/hw/mlx5/mr.c               |   3 +-
 drivers/infiniband/hw/mlx5/odp.c              |  50 +-
 drivers/xen/Kconfig                           |   3 +-
 drivers/xen/gntdev-common.h                   |   8 +-
 drivers/xen/gntdev.c                          | 180 ++----
 include/linux/hmm.h                           | 195 +------
 include/linux/mmu_notifier.h                  | 144 ++++-
 include/rdma/ib_umem_odp.h                    |  65 +--
 include/rdma/ib_verbs.h                       |   2 -
 kernel/fork.c                                 |   1 -
 mm/Kconfig                                    |   2 +-
 mm/hmm.c                                      | 275 +--------
 mm/mmu_notifier.c                             | 546 +++++++++++++++++-
 32 files changed, 1225 insertions(+), 1922 deletions(-)

-- 
2.23.0



^ permalink raw reply	[flat|nested] 70+ messages in thread

end of thread, other threads:[~2019-11-08 20:19 UTC | newest]

Thread overview: 70+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-10-28 20:10 [PATCH v2 00/15] Consolidate the mmu notifier interval_tree and locking Jason Gunthorpe
2019-10-28 20:10 ` [PATCH v2 01/15] mm/mmu_notifier: define the header pre-processor parts even if disabled Jason Gunthorpe
2019-11-05 21:23   ` John Hubbard
2019-11-06 13:36     ` Jason Gunthorpe
2019-10-28 20:10 ` [PATCH v2 02/15] mm/mmu_notifier: add an interval tree notifier Jason Gunthorpe
2019-10-29 22:04   ` Kuehling, Felix
2019-10-29 22:56     ` Jason Gunthorpe
2019-11-07  0:23   ` John Hubbard
2019-11-07  2:08     ` Jerome Glisse
2019-11-07 20:11       ` Jason Gunthorpe
2019-11-07 21:04         ` Jerome Glisse
2019-11-08  0:32           ` Jason Gunthorpe
2019-11-08  2:00             ` Jerome Glisse
2019-11-08 20:19               ` Jason Gunthorpe
2019-11-07 20:06     ` Jason Gunthorpe
2019-11-07 20:53       ` John Hubbard
2019-11-08 15:26         ` Jason Gunthorpe
2019-11-08  6:33       ` Christoph Hellwig
2019-11-08 13:43         ` Jerome Glisse
2019-10-28 20:10 ` [PATCH v2 03/15] mm/hmm: allow hmm_range to be used with a mmu_range_notifier or hmm_mirror Jason Gunthorpe
2019-10-28 20:10 ` [PATCH v2 04/15] mm/hmm: define the pre-processor related parts of hmm.h even if disabled Jason Gunthorpe
2019-10-28 20:10 ` [PATCH v2 05/15] RDMA/odp: Use mmu_range_notifier_insert() Jason Gunthorpe
2019-10-28 20:10 ` [PATCH v2 06/15] RDMA/hfi1: Use mmu_range_notifier_inset for user_exp_rcv Jason Gunthorpe
2019-10-29 12:19   ` Dennis Dalessandro
2019-10-29 12:51     ` Jason Gunthorpe
2019-10-28 20:10 ` [PATCH v2 07/15] drm/radeon: use mmu_range_notifier_insert Jason Gunthorpe
2019-10-29  7:48   ` Koenig, Christian
2019-10-28 20:10 ` [PATCH v2 08/15] xen/gntdev: Use select for DMA_SHARED_BUFFER Jason Gunthorpe
2019-11-01 18:26   ` Jason Gunthorpe
2019-11-05 14:44     ` Jürgen Groß
2019-11-07  9:39   ` Jürgen Groß
2019-10-28 20:10 ` [PATCH v2 09/15] xen/gntdev: use mmu_range_notifier_insert Jason Gunthorpe
2019-10-30 16:55   ` Boris Ostrovsky
2019-11-01 17:48     ` Jason Gunthorpe
2019-11-01 18:51       ` Boris Ostrovsky
2019-11-01 19:17         ` Jason Gunthorpe
2019-11-04 22:03   ` Boris Ostrovsky
2019-11-05  2:31     ` Jason Gunthorpe
2019-11-05 15:16       ` Boris Ostrovsky
2019-11-07 20:36         ` Jason Gunthorpe
2019-11-07 22:54           ` Boris Ostrovsky
2019-11-08 14:53             ` Jason Gunthorpe
2019-10-28 20:10 ` [PATCH v2 10/15] nouveau: use mmu_notifier directly for invalidate_range_start Jason Gunthorpe
2019-10-28 20:10 ` [PATCH v2 11/15] nouveau: use mmu_range_notifier instead of hmm_mirror Jason Gunthorpe
2019-10-28 20:10 ` [PATCH v2 13/15] drm/amdgpu: Use mmu_range_insert " Jason Gunthorpe
2019-10-29  7:51   ` Koenig, Christian
2019-10-29 13:59     ` Jason Gunthorpe
2019-10-29 22:14   ` Kuehling, Felix
2019-10-29 23:09     ` Jason Gunthorpe
2019-10-28 20:10 ` [PATCH v2 14/15] drm/amdgpu: Use mmu_range_notifier " Jason Gunthorpe
2019-10-29 19:22   ` Yang, Philip
2019-10-29 19:25     ` Jason Gunthorpe
2019-11-01 14:44       ` Yang, Philip
2019-11-01 15:12         ` Jason Gunthorpe
2019-11-01 15:59           ` Yang, Philip
2019-11-01 17:42             ` Jason Gunthorpe
2019-11-01 19:19               ` Jason Gunthorpe
2019-11-01 19:45               ` Yang, Philip
2019-11-01 19:50                 ` Yang, Philip
2019-11-01 19:51                 ` Jason Gunthorpe
2019-11-01 18:21         ` Jason Gunthorpe
2019-11-01 18:34         ` [PATCH v2a " Jason Gunthorpe
2019-10-28 20:10 ` [PATCH v2 15/15] mm/hmm: remove hmm_mirror and related Jason Gunthorpe
     [not found] ` <20191028201032.6352-13-jgg@ziepe.ca>
2019-10-29  7:49   ` [PATCH v2 12/15] drm/amdgpu: Call find_vma under mmap_sem Koenig, Christian
2019-10-29 16:28   ` Kuehling, Felix
2019-10-29 13:07     ` Christian König
2019-10-29 17:19     ` Jason Gunthorpe
2019-11-01 19:54 ` [PATCH v2 00/15] Consolidate the mmu notifier interval_tree and locking Jason Gunthorpe
2019-11-01 20:54 ` Ralph Campbell
2019-11-04 20:40   ` Jason Gunthorpe

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).