From patchwork Thu Mar 9 11:09:30 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Imran Khan X-Patchwork-Id: 13167253 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id F31C1C61DA4 for ; Thu, 9 Mar 2023 11:15:20 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231372AbjCILPT (ORCPT ); Thu, 9 Mar 2023 06:15:19 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43874 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231460AbjCILOd (ORCPT ); Thu, 9 Mar 2023 06:14:33 -0500 Received: from mx0a-00069f02.pphosted.com (mx0a-00069f02.pphosted.com [205.220.165.32]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 6040CEE77B; Thu, 9 Mar 2023 03:09:51 -0800 (PST) Received: from pps.filterd (m0246629.ppops.net [127.0.0.1]) by mx0b-00069f02.pphosted.com (8.17.1.19/8.17.1.19) with ESMTP id 3297f2Sf010892; Thu, 9 Mar 2023 11:09:42 GMT DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=oracle.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-transfer-encoding; s=corp-2022-7-12; bh=CeyDZipp/ufRAN71ci8Y49vLa1a0i3SMVyGK2lSK0xQ=; b=nImGf20piFb7whiKJSzNHZLlrAqM/afb16CTwLp5HXJhwk31qrGHahgCIt11SIqX38SL BiqZWmoTIMfT6rp6zBrNo9/kFzQn7t18512V0r2FXQLiX6S/0dzZ5VQtFaLjUDseOLwj +kVVyMBFjkmItYNFwDiWOfl1UBf09O2QsatxexSUdAp0MOCGU4+mzSi/n2kUGObcHAJj FPqGnlJ5r0t9zWG3j/DUtbQ7w1gzn3k2w0YYSSsyYba4gwEvH3LVLSTMkzntau+gmr67 E8tfXYC1sRW3Qllz+6DcbSfSlS/qzhHmVJ/bx7gewtY1wtYhu8+SxK/UGSOLoFZZAEzH vg== Received: from phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (phxpaimrmta02.appoci.oracle.com [147.154.114.232]) by mx0b-00069f02.pphosted.com (PPS) with ESMTPS id 3p41622arr-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Thu, 09 Mar 2023 11:09:42 +0000 Received: from pps.filterd (phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com [127.0.0.1]) by phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (8.17.1.5/8.17.1.5) with ESMTP id 329A7OgB020771; Thu, 9 Mar 2023 11:09:41 GMT Received: from pps.reinject (localhost [127.0.0.1]) by phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (PPS) with ESMTPS id 3p6fu9b76k-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Thu, 09 Mar 2023 11:09:41 +0000 Received: from phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com [127.0.0.1]) by pps.reinject (8.17.1.5/8.17.1.5) with ESMTP id 329B70tK021817; Thu, 9 Mar 2023 11:09:41 GMT Received: from localhost.localdomain (dhcp-10-191-129-247.vpn.oracle.com [10.191.129.247]) by phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (PPS) with ESMTP id 3p6fu9b73f-2; Thu, 09 Mar 2023 11:09:40 +0000 From: Imran Khan To: tj@kernel.org, gregkh@linuxfoundation.org, viro@zeniv.linux.org.uk, willy@infradead.org Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, joe.jin@oracle.com Subject: [PATCH v2 1/3] kernfs: Introduce separate rwsem to protect inode attributes. Date: Thu, 9 Mar 2023 22:09:30 +1100 Message-Id: <20230309110932.2889010-2-imran.f.khan@oracle.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230309110932.2889010-1-imran.f.khan@oracle.com> References: <20230309110932.2889010-1-imran.f.khan@oracle.com> MIME-Version: 1.0 X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.254,Aquarius:18.0.942,Hydra:6.0.573,FMLib:17.11.170.22 definitions=2023-03-09_06,2023-03-08_03,2023-02-09_01 X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 mlxlogscore=869 adultscore=0 phishscore=0 suspectscore=0 malwarescore=0 spamscore=0 bulkscore=0 mlxscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2212070000 definitions=main-2303090088 X-Proofpoint-GUID: l_cfXc36h-HKfFpk9aoyD9a_vvYcoi0Z X-Proofpoint-ORIG-GUID: l_cfXc36h-HKfFpk9aoyD9a_vvYcoi0Z Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Right now a global per-fs rwsem (kernfs_rwsem) synchronizes multiple kernfs operations. On a large system with few hundred CPUs and few hundred applications simultaneoulsy trying to access sysfs, this results in multiple sys_open(s) contending on kernfs_rwsem via kernfs_iop_permission and kernfs_dop_revalidate. 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 see contention around kernfs_rwsem as follows: path_openat | |----link_path_walk.part.0.constprop.0 | | | |--49.92%--inode_permission | | | | | --48.69%--kernfs_iop_permission | | | | | |--18.16%--down_read | | | | | |--15.38%--up_read | | | | | --14.58%--_raw_spin_lock | | | | | ----- | | | |--29.08%--walk_component | | | | | --29.02%--lookup_fast | | | | | |--24.26%--kernfs_dop_revalidate | | | | | | | |--14.97%--down_read | | | | | | | --9.01%--up_read | | | | | --4.74%--__d_lookup | | | | | --4.64%--_raw_spin_lock | | | | | ---- Having a separate per-fs rwsem to protect kernfs inode attributes, will avoid the above mentioned contention and result in better performance as can bee seen below: path_openat | |----link_path_walk.part.0.constprop.0 | | | | | |--27.06%--inode_permission | | | | | --25.84%--kernfs_iop_permission | | | | | |--9.29%--up_read | | | | | |--8.19%--down_read | | | | | --7.89%--_raw_spin_lock | | | | | ---- | | | |--22.42%--walk_component | | | | | --22.36%--lookup_fast | | | | | |--16.07%--__d_lookup | | | | | | | --16.01%--_raw_spin_lock | | | | | | | ---- | | | | | --6.28%--kernfs_dop_revalidate | | | | | |--3.76%--down_read | | | | | --2.26%--up_read As can be seen from the above data the overhead due to both kerfs_iop_permission and kernfs_dop_revalidate have gone down and this also reduces overall run time of the earlier mentioned loop. Signed-off-by: Imran Khan --- fs/kernfs/dir.c | 7 +++++++ fs/kernfs/inode.c | 16 ++++++++-------- fs/kernfs/kernfs-internal.h | 1 + 3 files changed, 16 insertions(+), 8 deletions(-) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index ef00b5fe8ceea..953b2717c60e6 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -770,12 +770,15 @@ int kernfs_add_one(struct kernfs_node *kn) goto out_unlock; /* Update timestamps on the parent */ + down_write(&root->kernfs_iattr_rwsem); + ps_iattr = parent->iattr; if (ps_iattr) { ktime_get_real_ts64(&ps_iattr->ia_ctime); ps_iattr->ia_mtime = ps_iattr->ia_ctime; } + up_write(&root->kernfs_iattr_rwsem); up_write(&root->kernfs_rwsem); /* @@ -940,6 +943,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, idr_init(&root->ino_idr); init_rwsem(&root->kernfs_rwsem); + init_rwsem(&root->kernfs_iattr_rwsem); INIT_LIST_HEAD(&root->supers); /* @@ -1462,11 +1466,14 @@ static void __kernfs_remove(struct kernfs_node *kn) pos->parent ? pos->parent->iattr : NULL; /* update timestamps on the parent */ + down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); + if (ps_iattr) { ktime_get_real_ts64(&ps_iattr->ia_ctime); ps_iattr->ia_mtime = ps_iattr->ia_ctime; } + up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); kernfs_put(pos); } diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 30494dcb0df34..b22b74d1a1150 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -101,9 +101,9 @@ int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) int ret; struct kernfs_root *root = kernfs_root(kn); - down_write(&root->kernfs_rwsem); + down_write(&root->kernfs_iattr_rwsem); ret = __kernfs_setattr(kn, iattr); - up_write(&root->kernfs_rwsem); + up_write(&root->kernfs_iattr_rwsem); return ret; } @@ -119,7 +119,7 @@ int kernfs_iop_setattr(struct mnt_idmap *idmap, struct dentry *dentry, return -EINVAL; root = kernfs_root(kn); - down_write(&root->kernfs_rwsem); + down_write(&root->kernfs_iattr_rwsem); error = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (error) goto out; @@ -132,7 +132,7 @@ int kernfs_iop_setattr(struct mnt_idmap *idmap, struct dentry *dentry, setattr_copy(&nop_mnt_idmap, inode, iattr); out: - up_write(&root->kernfs_rwsem); + up_write(&root->kernfs_iattr_rwsem); return error; } @@ -189,10 +189,10 @@ int kernfs_iop_getattr(struct mnt_idmap *idmap, struct kernfs_node *kn = inode->i_private; struct kernfs_root *root = kernfs_root(kn); - down_read(&root->kernfs_rwsem); + down_read(&root->kernfs_iattr_rwsem); kernfs_refresh_inode(kn, inode); generic_fillattr(&nop_mnt_idmap, inode, stat); - up_read(&root->kernfs_rwsem); + up_read(&root->kernfs_iattr_rwsem); return 0; } @@ -285,10 +285,10 @@ int kernfs_iop_permission(struct mnt_idmap *idmap, kn = inode->i_private; root = kernfs_root(kn); - down_read(&root->kernfs_rwsem); + down_read(&root->kernfs_iattr_rwsem); kernfs_refresh_inode(kn, inode); ret = generic_permission(&nop_mnt_idmap, inode, mask); - up_read(&root->kernfs_rwsem); + up_read(&root->kernfs_iattr_rwsem); return ret; } diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 236c3a6113f1e..3297093c920de 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -47,6 +47,7 @@ struct kernfs_root { wait_queue_head_t deactivate_waitq; struct rw_semaphore kernfs_rwsem; + struct rw_semaphore kernfs_iattr_rwsem; }; /* +1 to avoid triggering overflow warning when negating it */ From patchwork Thu Mar 9 11:09:31 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Imran Khan X-Patchwork-Id: 13167254 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 4728EC64EC4 for ; Thu, 9 Mar 2023 11:15:24 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229895AbjCILPW (ORCPT ); Thu, 9 Mar 2023 06:15:22 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43814 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231461AbjCILOd (ORCPT ); Thu, 9 Mar 2023 06:14:33 -0500 Received: from mx0a-00069f02.pphosted.com (mx0a-00069f02.pphosted.com [205.220.165.32]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 2CEA3F249F; Thu, 9 Mar 2023 03:09:52 -0800 (PST) Received: from pps.filterd (m0333521.ppops.net [127.0.0.1]) by mx0b-00069f02.pphosted.com (8.17.1.19/8.17.1.19) with ESMTP id 3297eXL3024061; Thu, 9 Mar 2023 11:09:45 GMT DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=oracle.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-transfer-encoding; s=corp-2022-7-12; bh=AVwrVBC1YwXBtnFMwHYdJTjiEZ0n8RKNs2clD1tsk+o=; b=hJ2FhyCe5DXrPvwddAl8lklGBSjBnAjNvXgloTpXMEaImw/tTUhSRMr5RQ/W2jxoC30o b581DQxrQQAska5XlZn5Eb1mY48FFqN+Ua/mRObMKXsAoUsHx3HnbKbN7jYlw2nLwKRo fXX9dqiKz4YuGWQ56uTtQ9qKrND9sL2YZtFKGt7aOBeUhznA47t9FyQkcFyM5rvLeuRi uSUJSw2WsLhb04UFSuBiYzoGJEe0Vy0+WPcnGnalNam3gI2Lq7Z5aKSq/hu3yw6eeUQw 2ynfY/AyQsaX4+Fa67iPvl20g8z2QYT5sdzkd239KZb+xA7QNHV1f/9YEdcsMXDBypl2 jA== Received: from phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (phxpaimrmta02.appoci.oracle.com [147.154.114.232]) by mx0b-00069f02.pphosted.com (PPS) with ESMTPS id 3p418y2fj4-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Thu, 09 Mar 2023 11:09:45 +0000 Received: from pps.filterd (phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com [127.0.0.1]) by phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (8.17.1.5/8.17.1.5) with ESMTP id 329AckMf020762; Thu, 9 Mar 2023 11:09:44 GMT Received: from pps.reinject (localhost [127.0.0.1]) by phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (PPS) with ESMTPS id 3p6fu9b77c-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Thu, 09 Mar 2023 11:09:44 +0000 Received: from phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com [127.0.0.1]) by pps.reinject (8.17.1.5/8.17.1.5) with ESMTP id 329B70tM021817; Thu, 9 Mar 2023 11:09:43 GMT Received: from localhost.localdomain (dhcp-10-191-129-247.vpn.oracle.com [10.191.129.247]) by phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (PPS) with ESMTP id 3p6fu9b73f-3; Thu, 09 Mar 2023 11:09:43 +0000 From: Imran Khan To: tj@kernel.org, gregkh@linuxfoundation.org, viro@zeniv.linux.org.uk, willy@infradead.org Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, joe.jin@oracle.com Subject: [PATCH v2 2/3] kernfs: Use a per-fs rwsem to protect per-fs list of kernfs_super_info. Date: Thu, 9 Mar 2023 22:09:31 +1100 Message-Id: <20230309110932.2889010-3-imran.f.khan@oracle.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230309110932.2889010-1-imran.f.khan@oracle.com> References: <20230309110932.2889010-1-imran.f.khan@oracle.com> MIME-Version: 1.0 X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.254,Aquarius:18.0.942,Hydra:6.0.573,FMLib:17.11.170.22 definitions=2023-03-09_06,2023-03-08_03,2023-02-09_01 X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 mlxlogscore=999 adultscore=0 phishscore=0 suspectscore=0 malwarescore=0 spamscore=0 bulkscore=0 mlxscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2212070000 definitions=main-2303090088 X-Proofpoint-GUID: ZS6LNlr80EJgBb5lZJSH0USiaGC6dNHy X-Proofpoint-ORIG-GUID: ZS6LNlr80EJgBb5lZJSH0USiaGC6dNHy Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org Right now per-fs kernfs_rwsem protects list of kernfs_super_info instances for a kernfs_root. Since kernfs_rwsem is used to synchronize several other operations across kernfs and since most of these operations don't impact kernfs_super_info, we can use a separate per-fs rwsem to synchronize access to list of kernfs_super_info. This helps in reducing contention around kernfs_rwsem and also allows operations that change/access list of kernfs_super_info to proceed without contending for kernfs_rwsem. Signed-off-by: Imran Khan --- fs/kernfs/dir.c | 1 + fs/kernfs/file.c | 4 ++-- fs/kernfs/kernfs-internal.h | 1 + fs/kernfs/mount.c | 8 ++++---- 4 files changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 953b2717c60e6..2cdb8516e5287 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -944,6 +944,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, idr_init(&root->ino_idr); init_rwsem(&root->kernfs_rwsem); init_rwsem(&root->kernfs_iattr_rwsem); + init_rwsem(&root->kernfs_supers_rwsem); INIT_LIST_HEAD(&root->supers); /* diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index e4a50e4ff0d23..40c4661f15b7c 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -922,8 +922,8 @@ static void kernfs_notify_workfn(struct work_struct *work) root = kernfs_root(kn); /* kick fsnotify */ - down_write(&root->kernfs_rwsem); + down_read(&root->kernfs_supers_rwsem); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct kernfs_node *parent; struct inode *p_inode = NULL; @@ -960,7 +960,7 @@ static void kernfs_notify_workfn(struct work_struct *work) iput(inode); } - up_write(&root->kernfs_rwsem); + up_read(&root->kernfs_supers_rwsem); kernfs_put(kn); goto repeat; } diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 3297093c920de..a9b854cdfdb5f 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -48,6 +48,7 @@ struct kernfs_root { wait_queue_head_t deactivate_waitq; struct rw_semaphore kernfs_rwsem; struct rw_semaphore kernfs_iattr_rwsem; + struct rw_semaphore kernfs_supers_rwsem; }; /* +1 to avoid triggering overflow warning when negating it */ diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index e08e8d9998070..d49606accb07b 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -351,9 +351,9 @@ int kernfs_get_tree(struct fs_context *fc) } sb->s_flags |= SB_ACTIVE; - down_write(&root->kernfs_rwsem); + down_write(&root->kernfs_supers_rwsem); list_add(&info->node, &info->root->supers); - up_write(&root->kernfs_rwsem); + up_write(&root->kernfs_supers_rwsem); } fc->root = dget(sb->s_root); @@ -380,9 +380,9 @@ void kernfs_kill_sb(struct super_block *sb) struct kernfs_super_info *info = kernfs_info(sb); struct kernfs_root *root = info->root; - down_write(&root->kernfs_rwsem); + down_write(&root->kernfs_supers_rwsem); list_del(&info->node); - up_write(&root->kernfs_rwsem); + up_write(&root->kernfs_supers_rwsem); /* * Remove the superblock from fs_supers/s_instances From patchwork Thu Mar 9 11:09:32 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Imran Khan X-Patchwork-Id: 13167251 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id BE009C64EC4 for ; Thu, 9 Mar 2023 11:15:17 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229702AbjCILPP (ORCPT ); Thu, 9 Mar 2023 06:15:15 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:40678 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231473AbjCILOf (ORCPT ); Thu, 9 Mar 2023 06:14:35 -0500 Received: from mx0a-00069f02.pphosted.com (mx0a-00069f02.pphosted.com [205.220.165.32]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 6364AF24A1; Thu, 9 Mar 2023 03:09:52 -0800 (PST) Received: from pps.filterd (m0246627.ppops.net [127.0.0.1]) by mx0b-00069f02.pphosted.com (8.17.1.19/8.17.1.19) with ESMTP id 3297ehhf018305; Thu, 9 Mar 2023 11:09:48 GMT DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=oracle.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-transfer-encoding; s=corp-2022-7-12; bh=sM2f8KUGw2ieEok7xffWn1NRPRHy+6lIt8O7z1nqwUA=; b=TSnSEGn5fb0r5OLvOmUoycnnvxGcMtkvj/9K5fXfjPDk9H8e+BsRTw2uEkMU64l1vELt aKRdI2H/G4dZsIpo3IJXtA0+sTk8iJzlIig9WYSj42yiRC20iPnTLAfw7xbxFk4NGbsv fAUU1a0c9ZPPgIOYiCw0zCAnLYMpgsH90fLJ4ilnFoqXLDpeP+0PxTuAJ8Ka31WQUpKD BSQ1H4dQ7EgM8MFHSHQNhxHF2vEp/QZLOagIHzUsYu/NtfarilnJfAQ1za8URmfhtyeU aWG/rkqYpVFuOzgPtj5XzP90WmFP17XqbXdCEgdU+QlDiVNQamF5pJCX1cuYikzzwo4B ig== Received: from phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (phxpaimrmta02.appoci.oracle.com [147.154.114.232]) by mx0b-00069f02.pphosted.com (PPS) with ESMTPS id 3p5nn96r6y-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Thu, 09 Mar 2023 11:09:48 +0000 Received: from pps.filterd (phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com [127.0.0.1]) by phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (8.17.1.5/8.17.1.5) with ESMTP id 3299XM3J020822; Thu, 9 Mar 2023 11:09:47 GMT Received: from pps.reinject (localhost [127.0.0.1]) by phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (PPS) with ESMTPS id 3p6fu9b78j-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Thu, 09 Mar 2023 11:09:47 +0000 Received: from phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com [127.0.0.1]) by pps.reinject (8.17.1.5/8.17.1.5) with ESMTP id 329B70tO021817; Thu, 9 Mar 2023 11:09:46 GMT Received: from localhost.localdomain (dhcp-10-191-129-247.vpn.oracle.com [10.191.129.247]) by phxpaimrmta02.imrmtpd1.prodappphxaev1.oraclevcn.com (PPS) with ESMTP id 3p6fu9b73f-4; Thu, 09 Mar 2023 11:09:46 +0000 From: Imran Khan To: tj@kernel.org, gregkh@linuxfoundation.org, viro@zeniv.linux.org.uk, willy@infradead.org Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, joe.jin@oracle.com Subject: [PATCH v2 3/3] kernfs: change kernfs_rename_lock into a read-write lock. Date: Thu, 9 Mar 2023 22:09:32 +1100 Message-Id: <20230309110932.2889010-4-imran.f.khan@oracle.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230309110932.2889010-1-imran.f.khan@oracle.com> References: <20230309110932.2889010-1-imran.f.khan@oracle.com> MIME-Version: 1.0 X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.254,Aquarius:18.0.942,Hydra:6.0.573,FMLib:17.11.170.22 definitions=2023-03-09_06,2023-03-08_03,2023-02-09_01 X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 mlxlogscore=999 adultscore=0 phishscore=0 suspectscore=0 malwarescore=0 spamscore=0 bulkscore=0 mlxscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2212070000 definitions=main-2303090088 X-Proofpoint-GUID: ZO8p4MktoRctYaJuWOGPKLN1rJZ9us9T X-Proofpoint-ORIG-GUID: ZO8p4MktoRctYaJuWOGPKLN1rJZ9us9T Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org kernfs_rename_lock protects a node's ->parent and thus kernfs topology. Thus it can be used in cases that rely on a stable kernfs topology. Change it to a read-write lock for better scalability. Suggested by: Al Viro Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Imran Khan --- fs/kernfs/dir.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 2cdb8516e5287..06e27b36216fe 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -17,7 +17,7 @@ #include "kernfs-internal.h" -static DEFINE_SPINLOCK(kernfs_rename_lock); /* kn->parent and ->name */ +static DEFINE_RWLOCK(kernfs_rename_lock); /* kn->parent and ->name */ /* * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to * call pr_cont() while holding rename_lock. Because sometimes pr_cont() @@ -196,9 +196,9 @@ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) unsigned long flags; int ret; - spin_lock_irqsave(&kernfs_rename_lock, flags); + read_lock_irqsave(&kernfs_rename_lock, flags); ret = kernfs_name_locked(kn, buf, buflen); - spin_unlock_irqrestore(&kernfs_rename_lock, flags); + read_unlock_irqrestore(&kernfs_rename_lock, flags); return ret; } @@ -224,9 +224,9 @@ int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from, unsigned long flags; int ret; - spin_lock_irqsave(&kernfs_rename_lock, flags); + read_lock_irqsave(&kernfs_rename_lock, flags); ret = kernfs_path_from_node_locked(to, from, buf, buflen); - spin_unlock_irqrestore(&kernfs_rename_lock, flags); + read_unlock_irqrestore(&kernfs_rename_lock, flags); return ret; } EXPORT_SYMBOL_GPL(kernfs_path_from_node); @@ -294,10 +294,10 @@ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) struct kernfs_node *parent; unsigned long flags; - spin_lock_irqsave(&kernfs_rename_lock, flags); + read_lock_irqsave(&kernfs_rename_lock, flags); parent = kn->parent; kernfs_get(parent); - spin_unlock_irqrestore(&kernfs_rename_lock, flags); + read_unlock_irqrestore(&kernfs_rename_lock, flags); return parent; } @@ -1731,7 +1731,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, kernfs_get(new_parent); /* rename_lock protects ->parent and ->name accessors */ - spin_lock_irq(&kernfs_rename_lock); + write_lock_irq(&kernfs_rename_lock); old_parent = kn->parent; kn->parent = new_parent; @@ -1742,7 +1742,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, kn->name = new_name; } - spin_unlock_irq(&kernfs_rename_lock); + write_unlock_irq(&kernfs_rename_lock); kn->hash = kernfs_name_hash(kn->name, kn->ns); kernfs_link_sibling(kn);