Return-Path: linux-nfs-owner@vger.kernel.org Received: from cantor2.suse.de ([195.135.220.15]:53415 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751661AbaGNBbL (ORCPT ); Sun, 13 Jul 2014 21:31:11 -0400 From: NeilBrown To: Trond Myklebust Date: Mon, 14 Jul 2014 11:28:20 +1000 Subject: [PATCH 2/7] NFS: prepare for RCU-walk support but pushing tests later in code. Cc: linux-nfs@vger.kernel.org Message-ID: <20140714012820.12562.1238.stgit@notabene.brown> In-Reply-To: <20140714011630.12562.1940.stgit@notabene.brown> References: <20140714011630.12562.1940.stgit@notabene.brown> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Sender: linux-nfs-owner@vger.kernel.org List-ID: nfs_lookup_revalidate, nfs4_lookup_revalidate, and nfs_permission all need to understand and handle RCU-walk for NFS to gain the benefits of RCU-walk for cached information. Currently these functions all immediately return -ECHILD if the relevant flag (LOOKUP_RCU or MAY_NOT_BLOCK) is set. This patch pushes those tests later in the code so that we only abort immediately before we enter rcu-unsafe code. As subsequent patches make that rcu-unsafe code rcu-safe, several of these new tests will disappear. With this patch there are several paths through the code which will no longer return -ECHILD during an RCU-walk. However these are mostly error paths or other uninteresting cases. A noteworthy change in nfs_lookup_revalidate is that we don't take (or put) the reference to ->d_parent when LOOKUP_RCU is set. Rather we rcu_dereference ->d_parent, and check that ->d_inode is not NULL. We also check that ->d_parent hasn't changed after all the tests. In nfs4_lookup_revalidate we simply avoid testing LOOKUP_RCU on the path that only calls nfs_lookup_revalidate() as that function already performs the required test. Signed-off-by: NeilBrown --- fs/nfs/dir.c | 45 +++++++++++++++++++++++++++++++++------------ 1 file changed, 33 insertions(+), 12 deletions(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index c5a4a89637fb..3c2b36acf291 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1088,21 +1088,30 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) struct nfs4_label *label = NULL; int error; - if (flags & LOOKUP_RCU) - return -ECHILD; - - parent = dget_parent(dentry); - dir = parent->d_inode; + if (flags & LOOKUP_RCU) { + parent = rcu_dereference(dentry->d_parent); + dir = ACCESS_ONCE(parent->d_inode); + if (!dir) + return -ECHILD; + } else { + parent = dget_parent(dentry); + dir = parent->d_inode; + } nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE); inode = dentry->d_inode; if (!inode) { + if (flags & LOOKUP_RCU) + return -ECHILD; + if (nfs_neg_need_reval(dir, dentry, flags)) goto out_bad; goto out_valid_noent; } if (is_bad_inode(inode)) { + if (flags & LOOKUP_RCU) + return -ECHILD; dfprintk(LOOKUPCACHE, "%s: %pd2 has dud inode\n", __func__, dentry); goto out_bad; @@ -1111,6 +1120,9 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ)) goto out_set_verifier; + if (flags & LOOKUP_RCU) + return -ECHILD; + /* Force a full look up iff the parent directory has changed */ if (!nfs_is_exclusive_create(dir, flags) && nfs_check_verifier(dir, dentry)) { if (nfs_lookup_verify_inode(inode, flags)) @@ -1153,13 +1165,18 @@ out_set_verifier: /* Success: notify readdir to use READDIRPLUS */ nfs_advise_use_readdirplus(dir); out_valid_noent: - dput(parent); + if (flags & LOOKUP_RCU) { + if (parent != rcu_dereference(dentry->d_parent)) + return -ECHILD; + } else + dput(parent); dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is valid\n", __func__, dentry); return 1; out_zap_parent: nfs_zap_caches(dir); out_bad: + WARN_ON(flags & LOOKUP_RCU); nfs_free_fattr(fattr); nfs_free_fhandle(fhandle); nfs4_label_free(label); @@ -1185,6 +1202,7 @@ out_zap_parent: __func__, dentry); return 0; out_error: + WARN_ON(flags & LOOKUP_RCU); nfs_free_fattr(fattr); nfs_free_fhandle(fhandle); nfs4_label_free(label); @@ -1532,9 +1550,6 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) struct inode *inode; int ret = 0; - if (flags & LOOKUP_RCU) - return -ECHILD; - if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY)) goto no_open; if (d_mountpoint(dentry)) @@ -1551,6 +1566,9 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) struct dentry *parent; struct inode *dir; + if (flags & LOOKUP_RCU) + return -ECHILD; + parent = dget_parent(dentry); dir = parent->d_inode; if (!nfs_neg_need_reval(dir, dentry, flags)) @@ -2320,9 +2338,6 @@ int nfs_permission(struct inode *inode, int mask) struct rpc_cred *cred; int res = 0; - if (mask & MAY_NOT_BLOCK) - return -ECHILD; - nfs_inc_stats(inode, NFSIOS_VFSACCESS); if ((mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0) @@ -2349,6 +2364,9 @@ force_lookup: if (!NFS_PROTO(inode)->access) goto out_notsup; + if (mask & MAY_NOT_BLOCK) + return -ECHILD; + cred = rpc_lookup_cred(); if (!IS_ERR(cred)) { res = nfs_do_access(inode, cred, mask); @@ -2363,6 +2381,9 @@ out: inode->i_sb->s_id, inode->i_ino, mask, res); return res; out_notsup: + if (mask & MAY_NOT_BLOCK) + return -ECHILD; + res = nfs_revalidate_inode(NFS_SERVER(inode), inode); if (res == 0) res = generic_permission(inode, mask);