Received-SPF: pass (google.com: domain of linux-kernel+bounces-62611-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
Date: Mon, 12 Feb 2024 16:19:17 -0800
Precedence: bulk
Mime-Version: 1.0
Message-ID: <20240213001920.3551772-1-lokeshgidra@google.com>
Subject: [PATCH v5 0/3] per-vma locks in userfaultfd
From: Lokesh Gidra <lokeshgidra@google.com>
To: akpm@linux-foundation.org
Cc: lokeshgidra@google.com, linux-fsdevel@vger.kernel.org, linux-mm@kvack.org, 
	linux-kernel@vger.kernel.org, selinux@vger.kernel.org, surenb@google.com, 
	kernel-team@android.com, aarcange@redhat.com, peterx@redhat.com, 
	david@redhat.com, axelrasmussen@google.com, bgeffon@google.com, 
	willy@infradead.org, jannh@google.com, kaleshsingh@google.com, 
	ngeoffray@google.com, timmurray@google.com, rppt@kernel.org, 
	Liam.Howlett@oracle.com
Content-Type: text/plain; charset="UTF-8"

Performing userfaultfd operations (like copy/move etc.) in critical
section of mmap_lock (read-mode) causes significant contention on the
lock when operations requiring the lock in write-mode are taking place
concurrently. We can use per-vma locks instead to significantly reduce
the contention issue.

Android runtime's Garbage Collector uses userfaultfd for concurrent
compaction. mmap-lock contention during compaction potentially causes
jittery experience for the user. During one such reproducible scenario,
we observed the following improvements with this patch-set:

- Wall clock time of compaction phase came down from ~3s to <500ms
- Uninterruptible sleep time (across all threads in the process) was
  ~10ms (none in mmap_lock) during compaction, instead of >20s

Changes since v4 [4]:
- Fix possible deadlock in find_and_lock_vmas() which may arise if
  lock_vma() is used for both src and dst vmas.
- Ensure we lock vma only once if src and dst vmas are same.
- Fix error handling in move_pages() after successfully locking vmas.
- Introduce helper function for finding dst vma and preparing its
  anon_vma when done in mmap_lock critical section, per Liam Howlett.
- Introduce helper function for finding dst and src vmas when done in
  mmap_lock critical section.

Changes since v3 [3]:
- Rename function names to clearly reflect which lock is being taken,
  per Liam Howlett.
- Have separate functions and abstractions in mm/userfaultfd.c to avoid
  confusion around which lock is being acquired/released, per Liam Howlett.
- Prepare anon_vma for all private vmas, anonymous or file-backed,
  per Jann Horn.

Changes since v2 [2]:
- Implement and use lock_vma() which uses mmap_lock critical section
  to lock the VMA using per-vma lock if lock_vma_under_rcu() fails,
  per Liam R. Howlett. This helps simplify the code and also avoids
  performing the entire userfaultfd operation under mmap_lock.

Changes since v1 [1]:
- rebase patches on 'mm-unstable' branch

[1] https://lore.kernel.org/all/20240126182647.2748949-1-lokeshgidra@google.com/
[2] https://lore.kernel.org/all/20240129193512.123145-1-lokeshgidra@google.com/
[3] https://lore.kernel.org/all/20240206010919.1109005-1-lokeshgidra@google.com/
[4] https://lore.kernel.org/all/20240208212204.2043140-1-lokeshgidra@google.com/

Lokesh Gidra (3):
  userfaultfd: move userfaultfd_ctx struct to header file
  userfaultfd: protect mmap_changing with rw_sem in userfaulfd_ctx
  userfaultfd: use per-vma locks in userfaultfd operations

 fs/userfaultfd.c              |  86 ++-----
 include/linux/userfaultfd_k.h |  75 ++++--
 mm/userfaultfd.c              | 450 ++++++++++++++++++++++++++--------
 3 files changed, 421 insertions(+), 190 deletions(-)

-- 
2.43.0.687.g38aa6559b0-goog