linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
* [GIT PULL] Please pull hmm changes
@ 2019-11-25 20:42 Jason Gunthorpe
  2019-11-30 18:03 ` Linus Torvalds
  2019-11-30 18:35 ` Linus Torvalds
  0 siblings, 2 replies; 26+ messages in thread
From: Jason Gunthorpe @ 2019-11-25 20:42 UTC (permalink / raw)
  To: Linus Torvalds
  Cc: Andrew Morton, Dan Williams, Christoph Hellwig, dri-devel,
	linux-mm, David Airlie, Daniel Vetter, amd-gfx, Kuehling, Felix,
	Deucher, Alexander, Ralph Campbell, linux-rdma

[-- Attachment #1: Type: text/plain, Size: 6987 bytes --]

Hi Linus,

Here is this batch of hmm updates, I think we are nearing the end of this
project for now, although I suspect there will be some more patches related to
hmm_range_fault() in the next cycle.

You will probably be most interested in the patch "mm/mmu_notifier: add an
interval tree notifier". The approach here largely pre-exists in the various
drivers, but is honestly kind of complex/ugly. No better idea was found, I'm
hoping putting it all in one place will help improve this over the long
term. At least many bugs were squashed and lines of code eliminated while
consolidating.

Already i915 GPU has posted a series for the next window that also needs this
same approach.

There are two small conflicts I know of, the first is RDMA related with -rc,
the second is a one liner updating a deleted comment in GPU. Both can be
solved by using the hmm.git side of the conflict.

All the big driver changes have been acked and/or tested by their respective
maintainers.

Regards,
Jason

The following changes since commit d6d5df1db6e9d7f8f76d2911707f7d5877251b02:

  Linux 5.4-rc5 (2019-10-27 13:19:19 -0400)

are available in the Git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git tags/for-linus-hmm

for you to fetch changes up to 93f4e735b6d98ee4b7a1252d81e815a983e359f2:

  mm/hmm: remove hmm_range_dma_map and hmm_range_dma_unmap (2019-11-23 19:56:45 -0400)

----------------------------------------------------------------
hmm related patches for 5.5

This is another round of bug fixing and cleanup. This time the focus is on
the driver pattern to use mmu notifiers to monitor a VA range. This code
is lifted out of many drivers and hmm_mirror directly into the
mmu_notifier core and written using the best ideas from all the driver
implementations.

This removes many bugs from the drivers and has a very pleasing
diffstat. More drivers can still be converted, but that is for another
cycle.

- A shared branch with RDMA reworking the RDMA ODP implementation

- New mmu_interval_notifier API. This is focused on the use case of
  monitoring a VA and simplifies the process for drivers

- A common seq-count locking scheme built into the mmu_interval_notifier
  API usable by drivers that call get_user_pages() or hmm_range_fault()
  with the VA range

- Conversion of mlx5 ODP, hfi1, radeon, nouveau, AMD GPU, and Xen GntDev
  drivers to the new API. This deletes a lot of wonky driver code.

- Two improvements for hmm_range_fault(), from testing done by Ralph

----------------------------------------------------------------
Christoph Hellwig (1):
      mm/hmm: remove hmm_range_dma_map and hmm_range_dma_unmap

Jason Gunthorpe (30):
      RDMA/mlx5: Use SRCU properly in ODP prefetch
      RDMA/mlx5: Split sig_err MR data into its own xarray
      RDMA/mlx5: Use a dedicated mkey xarray for ODP
      RDMA/mlx5: Delete struct mlx5_priv->mkey_table
      RDMA/mlx5: Rework implicit_mr_get_data
      RDMA/mlx5: Lift implicit_mr_alloc() into the two routines that call it
      RDMA/mlx5: Set the HW IOVA of the child MRs to their place in the tree
      RDMA/mlx5: Split implicit handling from pagefault_mr
      RDMA/mlx5: Use an xarray for the children of an implicit ODP
      RDMA/mlx5: Reduce locking in implicit_mr_get_data()
      RDMA/mlx5: Avoid double lookups on the pagefault path
      RDMA/mlx5: Rework implicit ODP destroy
      RDMA/mlx5: Do not store implicit children in the odp_mkeys xarray
      RDMA/mlx5: Do not race with mlx5_ib_invalidate_range during create and destroy
      RDMA/odp: Remove broken debugging call to invalidate_range
      Merge branch 'odp_rework' into hmm.git
      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_interval_notifier or hmm_mirror
      mm/hmm: define the pre-processor related parts of hmm.h even if disabled
      RDMA/odp: Use mmu_interval_notifier_insert()
      RDMA/hfi1: Use mmu_interval_notifier_insert for user_exp_rcv
      drm/radeon: use mmu_interval_notifier_insert
      nouveau: use mmu_notifier directly for invalidate_range_start
      nouveau: use mmu_interval_notifier instead of hmm_mirror
      drm/amdgpu: Call find_vma under mmap_sem
      drm/amdgpu: Use mmu_interval_insert instead of hmm_mirror
      drm/amdgpu: Use mmu_interval_notifier instead of hmm_mirror
      mm/hmm: remove hmm_mirror and related
      xen/gntdev: use mmu_interval_notifier_insert

Ralph Campbell (2):
      mm/hmm: allow snapshot of the special zero page
      mm/hmm: make full use of walk_page_range()

 Documentation/vm/hmm.rst                         |  105 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu.h              |    2 +
 drivers/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           |  443 ++--------
 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          |  145 ++--
 drivers/gpu/drm/nouveau/nouveau_svm.c            |  230 +++--
 drivers/gpu/drm/radeon/radeon.h                  |    9 +-
 drivers/gpu/drm/radeon/radeon_mn.c               |  218 +----
 drivers/infiniband/core/device.c                 |    1 -
 drivers/infiniband/core/umem_odp.c               |  341 ++------
 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/cq.c                  |   33 +-
 drivers/infiniband/hw/mlx5/devx.c                |    8 +-
 drivers/infiniband/hw/mlx5/main.c                |   17 +-
 drivers/infiniband/hw/mlx5/mlx5_ib.h             |   29 +-
 drivers/infiniband/hw/mlx5/mr.c                  |  142 ++-
 drivers/infiniband/hw/mlx5/odp.c                 | 1004 +++++++++++-----------
 drivers/net/ethernet/mellanox/mlx5/core/main.c   |    4 -
 drivers/net/ethernet/mellanox/mlx5/core/mr.c     |   28 +-
 drivers/xen/gntdev-common.h                      |    8 +-
 drivers/xen/gntdev.c                             |  179 ++--
 include/linux/hmm.h                              |  190 +---
 include/linux/mlx5/driver.h                      |    4 -
 include/linux/mmu_notifier.h                     |  147 +++-
 include/rdma/ib_umem_odp.h                       |   86 +-
 include/rdma/ib_verbs.h                          |    2 -
 kernel/fork.c                                    |    1 -
 mm/Kconfig                                       |    2 +-
 mm/hmm.c                                         |  523 ++---------
 mm/mmu_notifier.c                                |  557 +++++++++++-
 37 files changed, 1912 insertions(+), 2789 deletions(-)

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply	[flat|nested] 26+ messages in thread
* [GIT PULL] Please pull hmm changes
@ 2020-08-04 15:06 Jason Gunthorpe
  2020-08-05 20:33 ` pr-tracker-bot
  0 siblings, 1 reply; 26+ messages in thread
From: Jason Gunthorpe @ 2020-08-04 15:06 UTC (permalink / raw)
  To: Linus Torvalds; +Cc: linux-kernel, Andrew Morton, linux-mm

[-- Attachment #1: Type: text/plain, Size: 3598 bytes --]

Hi Linus,

Ralph has been working on nouveau's use of hmm_range_fault() and migrate_vma()
which resulted in this small series of improvements.

There are two expected conflicts. Conflict with the kvm-ppc tree:

https://lore.kernel.org/linux-next/20200730191610.204ed02c@canb.auug.org.au/

This is because the kvm-ppc tree moved __kvmppc_svm_page_out() within the
file. To resolve the diff from 5143192cd410 ("mm/migrate: add a flags
parameter to migrate_vma") needs to be applied to the new location:

-       mig.src_owner = &kvmppc_uvmem_pgmap;
++      mig.pgmap_owner = &kvmppc_uvmem_pgmap;
++      mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;

There is an accidental conflict with the DRM tree, due to a confusion the same
patch got applied to both trees and we couldn't undo it in time. Please take
the hmm version of the resolution.

Since neither DRM or kvm-ppc have been merged by you, I've made a very hacky
for-linus-hmm-merged tag with my resolutions for your reference.

Thanks,
Jason

The following changes since commit dcb7fd82c75ee2d6e6f9d8cc71c52519ed52e258:

  Linux 5.8-rc4 (2020-07-05 16:20:22 -0700)

are available in the Git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git tags/for-linus-hmm

for you to fetch changes up to 7d17e83abec1be3355260b3e4812044c65c32907:

  mm/hmm/test: use the new migration invalidation (2020-07-28 16:20:33 -0300)

----------------------------------------------------------------
hmm related patches for 5.9

This series adds reporting of the page table order from hmm_range_fault()
and some optimization of migrate_vma():

- Report the size of the page table mapping out of hmm_range_fault(). This
  makes it easier to establish a large/huge/etc mapping in the device's
  page table.

- Allow devices to ignore the invalidations during migration in cases
  where the migration is not going to change pages. For instance migrating
  pages to a device does not require the device to invalidate pages
  already in the device.

- Update nouveau and hmm_tests to use the above

----------------------------------------------------------------
Ralph Campbell (10):
      mm/hmm: provide the page mapping order in hmm_range_fault()
      mm/hmm: add tests for hmm_pfn_to_map_order()
      nouveau/hmm: fault one page at a time
      nouveau: fix mapping 2MB sysmem pages
      nouveau/hmm: support mapping large sysmem pages
      nouveau: fix storing invalid ptes
      mm/migrate: add a flags parameter to migrate_vma
      mm/notifier: add migration invalidation type
      nouveau/svm: use the new migration invalidation
      mm/hmm/test: use the new migration invalidation

 arch/powerpc/kvm/book3s_hv_uvmem.c                 |   4 +-
 drivers/gpu/drm/nouveau/nouveau_dmem.c             |  19 +-
 drivers/gpu/drm/nouveau/nouveau_svm.c              | 257 +++++++++------------
 drivers/gpu/drm/nouveau/nouveau_svm.h              |  13 +-
 drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c      |   5 +-
 drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c |  91 +++++++-
 include/linux/hmm.h                                |  24 +-
 include/linux/migrate.h                            |  16 +-
 include/linux/mmu_notifier.h                       |   6 +
 lib/test_hmm.c                                     |  47 ++--
 lib/test_hmm_uapi.h                                |   4 +
 mm/hmm.c                                           |  16 +-
 mm/migrate.c                                       |  14 +-
 tools/testing/selftests/vm/hmm-tests.c             |  94 +++++++-
 14 files changed, 410 insertions(+), 200 deletions(-)

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply	[flat|nested] 26+ messages in thread
* [GIT PULL] Please pull hmm changes
@ 2020-06-01 18:25 Jason Gunthorpe
  2020-06-02 22:20 ` pr-tracker-bot
  0 siblings, 1 reply; 26+ messages in thread
From: Jason Gunthorpe @ 2020-06-01 18:25 UTC (permalink / raw)
  To: Linus Torvalds, linux-kernel, Andrew Morton, linux-mm
  Cc: linux-rdma, linux-kernel

[-- Attachment #1: Type: text/plain, Size: 2698 bytes --]

Hi Linus,

This is a small update for 5.8 mainly including the selftest from
Ralph and finishing the hmm_range_fault() simplification started in
the last merge window.

Regards,
Jason

The following changes since commit 0e698dfa282211e414076f9dc7e83c1c288314fd:

  Linux 5.7-rc4 (2020-05-03 14:56:04 -0700)

are available in the Git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git tags/for-linus-hmm

for you to fetch changes up to f07e2f6be37a750737b93f5635485171ad459eb9:

  MAINTAINERS: add HMM selftests (2020-05-19 16:48:31 -0300)

----------------------------------------------------------------
hmm related patches for 5.8

This series adds a selftest for hmm_range_fault() and several of the
DEVICE_PRIVATE migration related actions, and another simplification for
hmm_range_fault()'s API.

- Simplify hmm_range_fault() with a simpler return code, no
  HMM_PFN_SPECIAL, and no customizable output PFN format

- Add a selftest for hmm_range_fault() and DEVICE_PRIVATE related
  functionality

----------------------------------------------------------------
Jason Gunthorpe (4):
      mm/hmm: make hmm_range_fault return 0 or -1
      drm/amdgpu: remove dead code after hmm_range_fault()
      mm/hmm: remove HMM_PFN_SPECIAL
      mm/hmm: remove the customizable pfn format from hmm_range_fault

Ralph Campbell (3):
      mm/hmm/test: add selftest driver for HMM
      mm/hmm/test: add selftests for HMM
      MAINTAINERS: add HMM selftests

 Documentation/vm/hmm.rst                |   30 +-
 MAINTAINERS                             |    2 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c |   56 +-
 drivers/gpu/drm/nouveau/nouveau_dmem.c  |   27 +-
 drivers/gpu/drm/nouveau/nouveau_dmem.h  |    3 +-
 drivers/gpu/drm/nouveau/nouveau_svm.c   |   94 ++-
 include/linux/hmm.h                     |  111 +--
 lib/Kconfig.debug                       |   13 +
 lib/Makefile                            |    1 +
 lib/test_hmm.c                          | 1164 ++++++++++++++++++++++++++
 lib/test_hmm_uapi.h                     |   59 ++
 mm/hmm.c                                |  185 ++---
 tools/testing/selftests/vm/.gitignore   |    1 +
 tools/testing/selftests/vm/Makefile     |    3 +
 tools/testing/selftests/vm/config       |    2 +
 tools/testing/selftests/vm/hmm-tests.c  | 1359 +++++++++++++++++++++++++++++++
 tools/testing/selftests/vm/run_vmtests  |   16 +
 tools/testing/selftests/vm/test_hmm.sh  |   97 +++
 18 files changed, 2934 insertions(+), 289 deletions(-)
 create mode 100644 lib/test_hmm.c
 create mode 100644 lib/test_hmm_uapi.h
 create mode 100644 tools/testing/selftests/vm/hmm-tests.c
 create mode 100755 tools/testing/selftests/vm/test_hmm.sh

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply	[flat|nested] 26+ messages in thread
* [GIT PULL] Please pull HMM changes
@ 2020-03-30 17:57 Jason Gunthorpe
  2020-03-30 19:54 ` Nathan Chancellor
  0 siblings, 1 reply; 26+ messages in thread
From: Jason Gunthorpe @ 2020-03-30 17:57 UTC (permalink / raw)
  To: Linus Torvalds; +Cc: linux-kernel, Andrew Morton, linux-mm

[-- Attachment #1: Type: text/plain, Size: 4017 bytes --]

Hi Linus,

This series arose from a review of hmm_range_fault() by Christoph, Ralph and
myself. Several bug fixes and some general clarity.

hmm_range_fault() is being used by these 'SVM' style drivers to
non-destructively read the page tables. It is very similar to get_user_pages()
except that the output is an array of PFNs and per-pfn flags, and it has
various modes of reading.

This is necessary before RDMA ODP can be converted, as we don't want to have
weird corner case regressions, which is still a looking forward item. Ralph
has a nice tester for this routine, but it is waiting for feedback from the
selftests maintainers.

Regards,
Jason

The following changes since commit f8788d86ab28f61f7b46eb6be375f8a726783636:

  Linux 5.6-rc3 (2020-02-23 16:17:42 -0800)

are available in the Git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git tags/for-linus-hmm

for you to fetch changes up to 9cee0e8c6f1eb4b5e56d3eb7f5d47b05637bab4f:

  mm/hmm: return error for non-vma snapshots (2020-03-27 20:19:25 -0300)

----------------------------------------------------------------
hmm related patches for 5.7

This series focuses on corner case bug fixes and general clarity
improvements to hmm_range_fault().

- 9 bug fixes

- Allow pgmap to track the 'owner' of a DEVICE_PRIVATE - in this case the
  owner tells the driver if it can understand the DEVICE_PRIVATE page or
  not. Use this to resolve a bug in nouveau where it could touch
  DEVICE_PRIVATE pages from other drivers.

- Remove a bunch of dead, redundant or unused code and flags

- Clarity improvements to hmm_range_fault()

----------------------------------------------------------------
Christoph Hellwig (9):
      mm/hmm: don't provide a stub for hmm_range_fault()
      mm/hmm: remove the unused HMM_FAULT_ALLOW_RETRY flag
      mm/hmm: simplify hmm_vma_walk_hugetlb_entry()
      mm/hmm: don't handle the non-fault case in hmm_vma_walk_hole_()
      mm: merge hmm_vma_do_fault into into hmm_vma_walk_hole_
      memremap: add an owner field to struct dev_pagemap
      mm: handle multiple owners of device private pages in migrate_vma
      mm: simplify device private page handling in hmm_range_fault
      mm/hmm: check the device private page owner in hmm_range_fault()

Jason Gunthorpe (17):
      mm/hmm: add missing unmaps of the ptep during hmm_vma_handle_pte()
      mm/hmm: do not call hmm_vma_walk_hole() while holding a spinlock
      mm/hmm: add missing pfns set to hmm_vma_walk_pmd()
      mm/hmm: add missing call to hmm_range_need_fault() before returning EFAULT
      mm/hmm: reorganize how !pte_present is handled in hmm_vma_handle_pte()
      mm/hmm: return -EFAULT when setting HMM_PFN_ERROR on requested valid pages
      mm/hmm: add missing call to hmm_pte_need_fault in HMM_PFN_SPECIAL handling
      mm/hmm: do not check pmd_protnone twice in hmm_vma_handle_pmd()
      mm/hmm: remove pgmap checking for devmap pages
      mm/hmm: return the fault type from hmm_pte_need_fault()
      mm/hmm: remove unused code and tidy comments
      mm/hmm: remove HMM_FAULT_SNAPSHOT
      mm/hmm: remove the CONFIG_TRANSPARENT_HUGEPAGE #ifdef
      mm/hmm: use device_private_entry_to_pfn()
      mm/hmm: do not unconditionally set pfns when returning EBUSY
      mm/hmm: do not set pfns when returning an error code
      mm/hmm: return error for non-vma snapshots

 Documentation/vm/hmm.rst                |  12 +-
 arch/powerpc/kvm/book3s_hv_uvmem.c      |   3 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c |   3 +-
 drivers/gpu/drm/nouveau/nouveau_dmem.c  |  19 +-
 drivers/gpu/drm/nouveau/nouveau_svm.c   |   3 +-
 include/linux/hmm.h                     | 125 +--------
 include/linux/memremap.h                |   4 +
 include/linux/migrate.h                 |   8 +
 mm/hmm.c                                | 476 +++++++++++++-------------------
 mm/memremap.c                           |   4 +
 mm/migrate.c                            |   9 +-
 11 files changed, 227 insertions(+), 439 deletions(-)

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply	[flat|nested] 26+ messages in thread
* [GIT PULL] Please pull hmm changes
@ 2019-07-30 11:58 Jason Gunthorpe
  2019-07-30 20:40 ` pr-tracker-bot
  0 siblings, 1 reply; 26+ messages in thread
From: Jason Gunthorpe @ 2019-07-30 11:58 UTC (permalink / raw)
  To: Linus Torvalds, Andrew Morton
  Cc: Christoph Hellwig, dri-devel, linux-mm, David Airlie,
	Daniel Vetter, amd-gfx, Kuehling, Felix, Deucher, Alexander,
	linux-kernel

[-- Attachment #1: Type: text/plain, Size: 1982 bytes --]

Hi Linus,

Locking fix for nouveau's use of HMM

This small series was posted by Christoph before the merge window, but didn't
make it in time for the PR. It fixes various locking errors in the nouveau
driver's use of the hmm_range_* functions.

The diffstat is a bit big as Christoph did a comprehensive job to move the
obsolete API from the core header and into the driver before fixing its flow,
but the risk of regression from this code motion is low.

I don't intend to often send -rc patches for hmm, but this is entangled with
other changes already, so it is simpler to keep it on the hmm git branch.

Thanks,
Jason

The following changes since commit 5f9e832c137075045d15cd6899ab0505cfb2ca4b:

  Linus 5.3-rc1 (2019-07-21 14:05:38 -0700)

are available in the Git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git tags/for-linus-hmm

for you to fetch changes up to de4ee728465f7c0c29241550e083139b2ce9159c:

  nouveau: unlock mmap_sem on all errors from nouveau_range_fault (2019-07-25 16:14:40 -0300)

----------------------------------------------------------------
HMM patches for 5.3-rc

Fix the locking around nouveau's use of the hmm_range_* APIs. It works
correctly in the success case, but many of the the edge cases have missing
unlocks or double unlocks.

----------------------------------------------------------------
Christoph Hellwig (4):
      mm/hmm: always return EBUSY for invalid ranges in hmm_range_{fault,snapshot}
      mm/hmm: move hmm_vma_range_done and hmm_vma_fault to nouveau
      nouveau: remove the block parameter to nouveau_range_fault
      nouveau: unlock mmap_sem on all errors from nouveau_range_fault

 Documentation/vm/hmm.rst              |  2 +-
 drivers/gpu/drm/nouveau/nouveau_svm.c | 47 ++++++++++++++++++++++++++++--
 include/linux/hmm.h                   | 54 -----------------------------------
 mm/hmm.c                              | 10 +++----
 4 files changed, 49 insertions(+), 64 deletions(-)

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply	[flat|nested] 26+ messages in thread
* [GIT PULL] Please pull hmm changes
@ 2019-07-09 19:24 Jason Gunthorpe
  2019-07-15  2:48 ` Linus Torvalds
  2019-07-15  3:00 ` pr-tracker-bot
  0 siblings, 2 replies; 26+ messages in thread
From: Jason Gunthorpe @ 2019-07-09 19:24 UTC (permalink / raw)
  To: Linus Torvalds, Andrew Morton
  Cc: Dan Williams, Christoph Hellwig, dri-devel, linux-mm,
	David Airlie, Daniel Vetter, amd-gfx, Kuehling, Felix, Deucher,
	Alexander, linux-rdma, linux-kernel

[-- Attachment #1: Type: text/plain, Size: 9266 bytes --]

Hi Linus,

As was discussed some time ago here are the mostly -mm patches related
to hmm functions. In agreement with Andrew we split this out from
quilt into a git topic branch so it can be shared between the DRM and
RDMA git trees. However, this cycle did not see dependencies with work
in DRM or RDMA that required a topic merge. I expect that work will
start to get ready next cycle and we will see a need for a cross-tree
topic merge then.

I'm sending it early as it is now a dependency for several patches in
mm's quilt.

This has been an exciting topic branch for conflicts, you'll need the
below simple resolution in the merge commit to make it compile
(lockdep_assert_held_exclusive() was renamed to
lockdep_assert_held_write())

Otherwise, for reference to all parties, here is how the conflicts were
handled:

- Several small patches from -mm quilt were moved to this tree to simplify
  conflict management, only Ira's 'fix release_pages()' patch was not hmm
  related.

- DRM introduced a new users of the hmm_range_register() API. We worked
  with AMDGPU to ensure that their new user could use the revised API via
  the below trivial merge fixup with DRM:

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -783,7 +783,7 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
                                0 : range->flags[HMM_PFN_WRITE];
        range->pfn_flags_mask = 0;
        range->pfns = pfns;
 -     hmm_range_register(range, mm, start,
 +     hmm_range_register(range, mirror, start,
                           start + ttm->num_pages * PAGE_SIZE, PAGE_SHIFT);

   retry:

- ARM64 has a patch series going through -mm with a trivial
  conflict ("Devmap cleanups + arm64 support"), Andrew has re-applied this
  in quilt onto linux-next and will send it

- The memreap sub-section changes in -mm has 5 hunk conflict with the
  memremap changes here. Andrew reapplied Dan's series ontop of
  Christoph's series in linux-next and will send it.

The tag for-linus-hmm-merged with my merge resolution to your tree is
also available to pull.

Thanks,
Jason

diff --cc mm/hmm.c
index d48b9283725a90,f702a3895d05d8..e1eedef129cf5c
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@@ -42,16 -54,11 +42,16 @@@ static const struct mmu_notifier_ops hm
   */
  static struct hmm *hmm_get_or_create(struct mm_struct *mm)
  {
 -	struct hmm *hmm = mm_get_hmm(mm);
 -	bool cleanup = false;
 +	struct hmm *hmm;

- 	lockdep_assert_held_exclusive(&mm->mmap_sem);
 -	if (hmm)
 -		return hmm;
++	lockdep_assert_held_write(&mm->mmap_sem);
 +
 +	/* Abuse the page_table_lock to also protect mm->hmm. */
 +	spin_lock(&mm->page_table_lock);
 +	hmm = mm->hmm;
 +	if (mm->hmm && kref_get_unless_zero(&mm->hmm->kref))
 +		goto out_unlock;
 +	spin_unlock(&mm->page_table_lock);

  	hmm = kmalloc(sizeof(*hmm), GFP_KERNEL);
  	if (!hmm)
@@@ -245,8 -277,8 +245,8 @@@ static const struct mmu_notifier_ops hm
   */
  int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm)
  {
- 	lockdep_assert_held_exclusive(&mm->mmap_sem);
++	lockdep_assert_held_write(&mm->mmap_sem);
 +
  	/* Sanity check */
  	if (!mm || !mirror || !mirror->ops)
  		return -EINVAL;

The following changes since commit 6fbc7275c7a9ba97877050335f290341a1fd8dbf:

  Linux 5.2-rc7 (2019-06-30 11:25:36 +0800)

are available in the Git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git tags/for-linus-hmm

for you to fetch changes up to cc5dfd59e375f4d0f2b64643723d16b38b2f2d78:

  Merge branch 'hmm-devmem-cleanup.4' into rdma.git hmm (2019-07-02 15:10:45 -0300)

----------------------------------------------------------------
HMM patches for 5.3

Improvements and bug fixes for the hmm interface in the kernel:

- Improve clarity, locking and APIs related to the 'hmm mirror' feature
  merged last cycle. In linux-next we now see AMDGPU and nouveau to be
  using this API.

- Remove old or transitional hmm APIs. These are hold overs from the past
  with no users, or APIs that existed only to manage cross tree conflicts.
  There are still a few more of these cleanups that didn't make the merge
  window cut off.

- Improve some core mm APIs:
  * export alloc_pages_vma() for driver use
  * refactor into devm_request_free_mem_region() to manage
    DEVICE_PRIVATE resource reservations
  * refactor duplicative driver code into the core dev_pagemap
    struct

- Remove hmm wrappers of improved core mm APIs, instead have drivers use
  the simplified API directly

- Remove DEVICE_PUBLIC

- Simplify the kconfig flow for the hmm users and core code

----------------------------------------------------------------
Christoph Hellwig (24):
      mm: remove the unused ARCH_HAS_HMM_DEVICE Kconfig option
      mm: remove the struct hmm_device infrastructure
      mm: remove MEMORY_DEVICE_PUBLIC support
      mm: don't clear ->mapping in hmm_devmem_free
      mm: export alloc_pages_vma
      mm: factor out a devm_request_free_mem_region helper
      memremap: validate the pagemap type passed to devm_memremap_pages
      memremap: move dev_pagemap callbacks into a separate structure
      memremap: pass a struct dev_pagemap to ->kill and ->cleanup
      memremap: lift the devmap_enable manipulation into devm_memremap_pages
      memremap: add a migrate_to_ram method to struct dev_pagemap_ops
      memremap: remove the data field in struct dev_pagemap
      memremap: replace the altmap_valid field with a PGMAP_ALTMAP_VALID flag
      memremap: provide an optional internal refcount in struct dev_pagemap
      device-dax: use the dev_pagemap internal refcount
      PCI/P2PDMA: use the dev_pagemap internal refcount
      nouveau: use alloc_page_vma directly
      nouveau: use devm_memremap_pages directly
      mm: remove hmm_vma_alloc_locked_page
      mm: remove hmm_devmem_add
      mm: simplify ZONE_DEVICE page private data
      mm: sort out the DEVICE_PRIVATE Kconfig mess
      mm: remove the HMM config option
      mm: don't select MIGRATE_VMA_HELPER from HMM_MIRROR

Ira Weiny (1):
      mm/swap: fix release_pages() when releasing devmap pages

Jason Gunthorpe (15):
      mm/hmm.c: suppress compilation warnings when CONFIG_HUGETLB_PAGE is not set
      mm/hmm: fix use after free with struct hmm in the mmu notifiers
      mm/hmm: Use hmm_mirror not mm as an argument for hmm_range_register
      mm/hmm: Hold a mmgrab from hmm to mm
      mm/hmm: Simplify hmm_get_or_create and make it reliable
      mm/hmm: Remove duplicate condition test before wait_event_timeout
      mm/hmm: Do not use list*_rcu() for hmm->ranges
      mm/hmm: Hold on to the mmget for the lifetime of the range
      mm/hmm: Use lockdep instead of comments
      mm/hmm: Remove racy protection against double-unregistration
      mm/hmm: Poison hmm_range during unregister
      mm/hmm: Remove confusing comment and logic from hmm_release
      mm/hmm: Fix error flows in hmm_invalidate_range_start
      Merge tag 'v5.2-rc7' into rdma.git hmm
      Merge branch 'hmm-devmem-cleanup.4' into rdma.git hmm

Kuehling, Felix (1):
      mm/hmm: Only set FAULT_FLAG_ALLOW_RETRY for non-blocking

Philip Yang (1):
      mm/hmm: support automatic NUMA balancing

Ralph Campbell (2):
      mm/hmm: update HMM documentation
      mm/hmm: clean up some coding style and comments

 Documentation/vm/hmm.rst               | 166 ++++------
 arch/powerpc/mm/mem.c                  |  10 +-
 arch/x86/mm/init_64.c                  |   8 +-
 drivers/dax/dax-private.h              |   4 -
 drivers/dax/device.c                   |  41 +--
 drivers/dax/pmem/core.c                |   2 +-
 drivers/gpu/drm/nouveau/Kconfig        |   6 +-
 drivers/gpu/drm/nouveau/nouveau_dmem.c | 103 +++---
 drivers/gpu/drm/nouveau/nouveau_svm.c  |   2 +-
 drivers/nvdimm/pfn_devs.c              |   3 +-
 drivers/nvdimm/pmem.c                  |  51 ++-
 drivers/pci/p2pdma.c                   |  52 +--
 fs/proc/task_mmu.c                     |   2 +-
 include/linux/hmm.h                    | 302 ++---------------
 include/linux/ioport.h                 |   3 +-
 include/linux/memremap.h               |  75 +++--
 include/linux/mm.h                     |  28 +-
 include/linux/mm_types.h               |   4 +-
 include/linux/swapops.h                |  15 -
 kernel/fork.c                          |   1 -
 kernel/memremap.c                      | 194 ++++++-----
 kernel/resource.c                      |  39 +++
 mm/Kconfig                             |  50 +--
 mm/Makefile                            |   2 +-
 mm/gup.c                               |   7 -
 mm/hmm.c                               | 587 ++++++++-------------------------
 mm/madvise.c                           |   2 +-
 mm/memcontrol.c                        |  13 +-
 mm/memory-failure.c                    |   6 +-
 mm/memory.c                            |  49 +--
 mm/memory_hotplug.c                    |   6 +-
 mm/mempolicy.c                         |   1 +
 mm/migrate.c                           |  28 +-
 mm/page_alloc.c                        |  13 +-
 mm/swap.c                              |  13 +-
 tools/testing/nvdimm/test/iomap.c      |  57 +++-
 36 files changed, 619 insertions(+), 1326 deletions(-)
(diffstat from tag for-linus-hmm-merged)

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply	[flat|nested] 26+ messages in thread

end of thread, other threads:[~2020-08-05 20:33 UTC | newest]

Thread overview: 26+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-11-25 20:42 [GIT PULL] Please pull hmm changes Jason Gunthorpe
2019-11-30 18:03 ` Linus Torvalds
2019-11-30 18:23   ` Linus Torvalds
2019-12-03  2:42     ` Jason Gunthorpe
2019-12-05 16:03       ` Jerome Glisse
2019-12-11 22:57         ` Jason Gunthorpe
2019-12-13 10:19           ` Daniel Vetter
2019-12-18 14:59             ` Jason Gunthorpe
2019-12-18 16:53               ` Linus Torvalds
2019-12-18 18:37                 ` Jason Gunthorpe
2019-12-18 19:33                   ` Linus Torvalds
2019-12-05 23:03       ` John Hubbard
2019-12-11 22:47         ` Jason Gunthorpe
2019-11-30 18:35 ` Linus Torvalds
  -- strict thread matches above, loose matches on Subject: below --
2020-08-04 15:06 Jason Gunthorpe
2020-08-05 20:33 ` pr-tracker-bot
2020-06-01 18:25 Jason Gunthorpe
2020-06-02 22:20 ` pr-tracker-bot
2020-03-30 17:57 [GIT PULL] Please pull HMM changes Jason Gunthorpe
2020-03-30 19:54 ` Nathan Chancellor
2020-03-30 20:08   ` Jason Gunthorpe
2019-07-30 11:58 [GIT PULL] Please pull hmm changes Jason Gunthorpe
2019-07-30 20:40 ` pr-tracker-bot
2019-07-09 19:24 Jason Gunthorpe
2019-07-15  2:48 ` Linus Torvalds
2019-07-15  3:00 ` pr-tracker-bot

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).