Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Imran Khan <imran.f.khan@oracle.com>
To:     tj@kernel.org, gregkh@linuxfoundation.org, viro@zeniv.linux.org.uk
Cc:     linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org
Subject: [PATCH 0/5] kernfs: Use a per-fs rwsem to protect per-fs list of kernfs_super_info
Date:   Thu, 14 Jul 2022 10:22:19 +1000
Message-Id: <20220714002224.3641629-1-imran.f.khan@oracle.com>
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?7Iib5DgOX4r+AKrrcjtXwcJTytP4vXbNJzBVD3D3fzoAwqH3mtDZwaBL4IXP?=
 =?us-ascii?Q?bTI7Bsbkf5fMFlrDOhVN/NPGnVABNl+HmkZ7TErJRf6RFW8xaEKiztviIIoY?=
 =?us-ascii?Q?DlwPkkP52zKYNo+z7PlEkw+tB92Xf505RcS5O/ubz7IOtucRo0oIdquMiwCz?=
 =?us-ascii?Q?1RvQlqc3ByjojzYdfb+U6ZHaqLMYx3LHgxHLML1jiekCkP4j45TC2f8kOLt3?=
 =?us-ascii?Q?NY8+iuOmPUP8Lw5Nho9UW7jgAHkZqU2uEWlJnbaet9S322864QSW/mERTZTB?=
 =?us-ascii?Q?CxJilVl3P0mkhgJ17vquGb+FwVAUDC1zCYrWLZ7LY+6jyHVKkAk+Sc4oZYU3?=
 =?us-ascii?Q?9ix6nEY//hS5j6bUELIb1YHSDrJOgFJQOHPpfqtTZLZc81RfCxcQ3tkMto7o?=
 =?us-ascii?Q?pAT9UKvWXm7FQ6SuBjE54NINLay9Q4/+EroSrkIxLQDm9gtfnAUm01nqwh1k?=
 =?us-ascii?Q?3VTSxEiPsRN8kCMHd39LxBo6SvH46v4wibNpcslsNqZ11A9fq5aHT04mgPg9?=
 =?us-ascii?Q?VC5BEJfVKtYFVHoN6AFlgCeC7zSbt2saB49guwsnfZIA3M0MNdBBf4P6CCLq?=
 =?us-ascii?Q?Ij54Vqzj0EbryJee+oN/3G7ytD+961hcEgYQMJz7S+6Na9Fm6V+OwvgTlOgL?=
 =?us-ascii?Q?2GUNRdP9nxrgYQ7VSf2L4jWqLPOnTSDUn/c6zMqFXma5vvGInnUt8GsACB6L?=
 =?us-ascii?Q?WOW6Gk0ragNTGiwVoVSEDWhWGPDJDg2X/dmPFdndz4eN6HEo8zdWZgqsJlXK?=
 =?us-ascii?Q?WNn6H41Xwo13ZJ6m2oL8ncqDcYkK+3pfy1A0RRKxo21FwwwzjPUUzgmeoDMb?=
 =?us-ascii?Q?zW58hJt58MSX2vILnSInFxsqS56XnhTZQwo6pNqjLnQ+rCeocYltkUEVdJyl?=
 =?us-ascii?Q?HPoBlHw6+KKSiKZWXAZBnnUmRoO5RHth6+mq1RY+gf9mvzF0Nkeho7shOb8n?=
 =?us-ascii?Q?8JGZkSfFG4Ls6xVz9p+821PU0emAE1CRqgKmkNEk7kXEGMti5awtI34OH6Ep?=
 =?us-ascii?Q?3v0dG5xI0w5jWuyme/tNy9sC47dhdjby9BQ537XwcDbJq/XZuFTPO0ibJx+y?=
 =?us-ascii?Q?eRYL6eBUSorXcoRJJrGdNY/kaR6Mc/JGscAv36z+qBTHtuopPY9MRxCkh6iU?=
 =?us-ascii?Q?/ivP/q+wbJvHWV4DWY0DmeGe8bgv8Tn5ybGEF3PZ/Rxq5IWPzDKmyiaa3szY?=
 =?us-ascii?Q?Fu1Z3tFsxQyb4tKfpcVDzNrhfiSzB85q++/grdnofFXMcnhmj2uR+SyQ1fiz?=
 =?us-ascii?Q?KCp1ZseFmk7QsfPN49YiPJZ1vs2VGZd1FwSsMWAfJR/r+0IMIrJfXDA+1bw4?=
 =?us-ascii?Q?JtW8EB02ZG9+i01tA36/epeWwfMReAQMtM7ilXjSu0ID0hDvuIIjNr6xRnTF?=
 =?us-ascii?Q?/6Pqf/cz99fCD5ok1iOZLbFu52nul5Lkk52tMrgDxV4cL7cNqBwaQej7JnPX?=
 =?us-ascii?Q?07OgNeBUSlOaLNcDG1ksV4L5/D3eqEYEM3IKujFOVgpjbm7ti1K7DgnhkSCW?=
 =?us-ascii?Q?lw8jW0n5FbyUj56ZvRNEpH3x/lt5QqQkw2Dl/ec4rzVEgdEV5+w2MHNuekjE?=
 =?us-ascii?Q?KX3NgeDGfMwd8qfIs/YX1w2ZCGP7/BeVrTLoCPcO4nn5kzi7uK3Af1poKfiI?=
 =?us-ascii?Q?Aw=3D=3D?=
X-OriginatorOrg: oracle.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 36010445-9dab-4294-799b-08da652ef3c6
X-MS-Exchange-CrossTenant-AuthSource: CO1PR10MB4468.namprd10.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 14 Jul 2022 00:22:36.0211
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 4e2c6054-71cb-48f1-bd6c-3a9705aca71b
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: /7VXIe1Phh+n2WEhVLXSfaaBdEyeuLtlk9ZMsXsN3103Lml0A7rggFQVtI9Gv6BZz4qhRuzS1zZIYKu7Snurpw==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BY5PR10MB3986
X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.517,18.0.883
 definitions=2022-07-13_13:2022-07-13,2022-07-13 signatures=0
X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 phishscore=0 malwarescore=0 spamscore=0
 adultscore=0 suspectscore=0 bulkscore=0 mlxlogscore=999 mlxscore=0
 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2206140000
 definitions=main-2207140000
X-Proofpoint-GUID: fI8wkOVnyRhoTdR6fRcs8JwMTYptD-6S
X-Proofpoint-ORIG-GUID: fI8wkOVnyRhoTdR6fRcs8JwMTYptD-6S
X-Spam-Status: No, score=-2.8 required=5.0 tests=BAYES_00,DKIM_SIGNED,
        DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,RCVD_IN_DNSWL_LOW,
        RCVD_IN_MSPIKE_H2,SPF_HELO_NONE,SPF_NONE,T_SCC_BODY_TEXT_LINE
        autolearn=ham autolearn_force=no version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
        lindbergh.monkeyblade.net
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

This patchset contains second subset of patches (after addressing review
comments) discussed at [1]. As per [2], the patches of [1] were divided
into 2 parts so that they can be reviewed feature by feature.
Patches of [2] are now in linux-next. So this patchset is for resuming
review (after addressing latest review comments) of rest of the patches
of [1].

The patches in this change set are as follows:

PATCH-1: Use a per-fs rwsem to protect per-fs list of kernfs_super_info.

PATCH-2: Change kernfs_rename_lock into a read-write lock.

PATCH-3: Introduce interface to access per-fs rwsem.

PATCH-4: Replace per-fs rwsem with hashed rwsems.

PATCH-5: Add a document to describe hashed locks used in kernfs.


    Original cover letter
---------------------------------------------------------------
Reduce contention around global locks used in kernfs.

The current kernfs design makes use of 3 global locks to synchronize
various operations. There are a few other global locks as well but
they are used for specific cases and hence don't cause severe contention.

The above mentioned 3 main global locks used in kernfs are:

1. A global mutex, kernfs_open_file_mutex, to protect the list of
kernfs_open_file instances correspondng to a sysfs attribute.

2. A global spinlock, kernfs_open_node_lock, to protect
kernfs_node->attr.open which points to kernfs_open_node instance
corresponding to a kernfs_node.

3. A global per-fs rw semaphore, root->kernfs_rwsem, to synchronize most
of the other operations like adding, removing, renaming etc. of a file
or directory.

Since these locks are global, they can cause contention when multiple
(for example few hundred) applications try to access sysfs (or other kernfs
based file system) files in parallel, even if the applications are
accessing different and unrelated files.

For example on a system with 384 cores, if I run 200 instances of an
application which is mostly executing the following loop:

  for (int loop = 0; loop <100 ; loop++)
  {
    for (int port_num = 1; port_num < 2; port_num++)
    {
      for (int gid_index = 0; gid_index < 254; gid_index++ )
      {
        char ret_buf[64], ret_buf_lo[64];
        char gid_file_path[1024];

        int      ret_len;
        int      ret_fd;
        ssize_t  ret_rd;

        ub4  i, saved_errno;

        memset(ret_buf, 0, sizeof(ret_buf));
        memset(gid_file_path, 0, sizeof(gid_file_path));

        ret_len = snprintf(gid_file_path, sizeof(gid_file_path),
                           "/sys/class/infiniband/%s/ports/%d/gids/%d",
                           dev_name,
                           port_num,
                           gid_index);

        ret_fd = open(gid_file_path, O_RDONLY | O_CLOEXEC);
        if (ret_fd < 0)
        {
          printf("Failed to open %s\n", gid_file_path);
          continue;
        }

        /* Read the GID */
        ret_rd = read(ret_fd, ret_buf, 40);

        if (ret_rd == -1)
        {
          printf("Failed to read from file %s, errno: %u\n",
                 gid_file_path, saved_errno);

          continue;
        }

        close(ret_fd);
      }
    }

I can see contention around above mentioned locks as follows:

-   54.07%    53.60%  showgids         [kernel.kallsyms]       [k] osq_lock
   - 53.60% __libc_start_main
      - 32.29% __GI___libc_open
           entry_SYSCALL_64_after_hwframe
           do_syscall_64
           sys_open
           do_sys_open
           do_filp_open
           path_openat
           vfs_open
           do_dentry_open
           kernfs_fop_open
           mutex_lock
         - __mutex_lock_slowpath
            - 32.23% __mutex_lock.isra.5
                 osq_lock
      - 21.31% __GI___libc_close
           entry_SYSCALL_64_after_hwframe
           do_syscall_64
           exit_to_usermode_loop
           task_work_run
           ____fput
           __fput
           kernfs_fop_release
           kernfs_put_open_node.isra.8
           mutex_lock
         - __mutex_lock_slowpath
            - 21.28% __mutex_lock.isra.5
                 osq_lock

-   10.49%    10.39%  showgids         [kernel.kallsyms]      [k] down_read
     10.39% __libc_start_main
        __GI___libc_open
        entry_SYSCALL_64_after_hwframe
        do_syscall_64
        sys_open
        do_sys_open
        do_filp_open
      - path_openat
         - 9.72% link_path_walk
            - 5.21% inode_permission
               - __inode_permission
                  - 5.21% kernfs_iop_permission
                       down_read
            - 4.08% walk_component
                 lookup_fast
               - d_revalidate.part.24
                  - 4.08% kernfs_dop_revalidate

-    7.48%     7.41%  showgids         [kernel.kallsyms]       [k] up_read
     7.41% __libc_start_main
        __GI___libc_open
        entry_SYSCALL_64_after_hwframe
        do_syscall_64
        sys_open
        do_sys_open
        do_filp_open
      - path_openat
         - 7.01% link_path_walk
            - 4.12% inode_permission
               - __inode_permission
                  - 4.12% kernfs_iop_permission
                       up_read
            - 2.61% walk_component
                 lookup_fast
               - d_revalidate.part.24
                  - 2.61% kernfs_dop_revalidate

Moreover this run of 200 application isntances takes 32-34 secs. to
complete.                                                     

This patch set is reducing the above mentioned contention by replacing
these global locks with hashed locks. 

For example with the patched kernel and on the same test setup, we no
longer see contention around osq_lock (i.e kernfs_open_file_mutex) and also
contention around per-fs kernfs_rwsem has reduced significantly as well.
This can be seen in the following perf snippet:

-    1.66%     1.65%  showgids         [kernel.kallsyms]      [k] down_read
     1.65% __libc_start_main
        __GI___libc_open
        entry_SYSCALL_64_after_hwframe
        do_syscall_64
        sys_open
        do_sys_open
        do_filp_open
      - path_openat
         - 1.62% link_path_walk
            - 0.98% inode_permission
               - __inode_permission
                  + 0.98% kernfs_iop_permission
            - 0.52% walk_component
                 lookup_fast
               - d_revalidate.part.24
                  - 0.52% kernfs_dop_revalidate

-    1.12%     1.11%  showgids         [kernel.kallsyms]      [k] up_read
     1.11% __libc_start_main
        __GI___libc_open
        entry_SYSCALL_64_after_hwframe
        do_syscall_64
        sys_open
        do_sys_open
        do_filp_open
      - path_openat
         - 1.11% link_path_walk
            - 0.69% inode_permission
               - __inode_permission
                  - 0.69% kernfs_iop_permission
                       up_read

Moreover the test execution time has reduced from 32-34 secs to 15-16 secs.

The patches of this patchset introduce following changes:

PATCH-1: Remove reference counting from kernfs_open_node.

PATCH-2: Make kernfs_open_node->attr.open RCU protected.

PATCH-3: Change kernfs_notify_list to llist.

PATCH-4: Introduce interface to access kernfs_open_file_mutex.

PATCH-5: Replace global kernfs_open_file_mutex with hashed mutexes.

PATCH-6: Use a per-fs rwsem to protect per-fs list of kernfs_super_info.

PATCH-7: Change kernfs_rename_lock into a read-write lock.

PATCH-8: Introduce interface to access per-fs rwsem.

PATCH-9: Replace per-fs rwsem with hashed rwsems.

PATCH-10: Add a document to describe hashed locks used in kernfs.

------------------------------------------------------------------

Imran Khan (5):
  kernfs: Use a per-fs rwsem to protect per-fs list of
    kernfs_super_info.
  kernfs: Change kernfs_rename_lock into a read-write lock.
  kernfs: Introduce interface to access per-fs rwsem.
  kernfs: Replace per-fs rwsem with hashed rwsems.
  kernfs: Add a document to describe hashed locks used in kernfs.

 .../filesystems/kernfs-hashed-locks.rst       | 214 ++++++++++++++
 fs/kernfs/Makefile                            |   2 +-
 fs/kernfs/dir.c                               | 269 ++++++++++++------
 fs/kernfs/file.c                              |   7 +-
 fs/kernfs/inode.c                             |  48 +++-
 fs/kernfs/kernfs-internal.c                   | 259 +++++++++++++++++
 fs/kernfs/kernfs-internal.h                   | 122 +++++++-
 fs/kernfs/mount.c                             |  23 +-
 fs/kernfs/symlink.c                           |  13 +-
 include/linux/kernfs.h                        |   1 +
 10 files changed, 845 insertions(+), 113 deletions(-)
 create mode 100644 Documentation/filesystems/kernfs-hashed-locks.rst
 create mode 100644 fs/kernfs/kernfs-internal.c


base-commit: 4112a8699ae2eac797415b9be1d7901b3f79e772

[1]: https://lore.kernel.org/lkml/20220410023719.1752460-1-imran.f.khan@oracle.com/
[2]: https://lore.kernel.org/lkml/20220428055431.3826852-1-imran.f.khan@oracle.com/
-- 
2.30.2