Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753995Ab0K0KdS (ORCPT ); Sat, 27 Nov 2010 05:33:18 -0500 Received: from ipmail04.adl6.internode.on.net ([150.101.137.141]:34794 "EHLO ipmail04.adl6.internode.on.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752744Ab0K0K0N (ORCPT ); Sat, 27 Nov 2010 05:26:13 -0500 X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: AvsEAO1p8Ex5Lcx2/2dsb2JhbACjC3K9doVHBIph Message-Id: <4e52a88ee4c437d00fc26572ed079dc1d73f9854.1290852959.git.npiggin@kernel.dk> In-Reply-To: References: From: Nick Piggin Date: Sat, 27 Nov 2010 20:44:45 +1100 Subject: [PATCH 15/46] fs: dcache scale subdirs To: linux-fsdevel@vger.kernel.org Cc: linux-kernel@vger.kernel.org Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 38206 Lines: 1314 Protect d_subdirs and d_child with d_lock, except in filesystems that aren't using dcache_lock for these anyway (eg. using i_mutex). Note: if we change the locking rule in future so that ->d_child protection is provided only with ->d_parent->d_lock, it may allow us to reduce some locking. But it would be an exception to an otherwise regular locking scheme, so we'd have to see some good results. Probably not worthwhile. Signed-off-by: Nick Piggin --- drivers/staging/smbfs/cache.c | 4 + drivers/usb/core/inode.c | 8 +- fs/autofs4/autofs_i.h | 11 +++ fs/autofs4/expire.c | 129 +++++++++++++-------------- fs/autofs4/root.c | 18 ++++- fs/ceph/dir.c | 6 +- fs/ceph/inode.c | 8 ++- fs/coda/cache.c | 2 + fs/dcache.c | 195 +++++++++++++++++++++++++++++++---------- fs/libfs.c | 24 ++++-- fs/ncpfs/dir.c | 3 + fs/ncpfs/ncplib_kernel.h | 4 + fs/notify/fsnotify.c | 4 +- include/linux/dcache.h | 1 + kernel/cgroup.c | 19 ++++- security/selinux/selinuxfs.c | 12 ++- 16 files changed, 314 insertions(+), 134 deletions(-) diff --git a/drivers/staging/smbfs/cache.c b/drivers/staging/smbfs/cache.c index dbb9865..29afb05 100644 --- a/drivers/staging/smbfs/cache.c +++ b/drivers/staging/smbfs/cache.c @@ -63,6 +63,7 @@ smb_invalidate_dircache_entries(struct dentry *parent) struct dentry *dentry; spin_lock(&dcache_lock); + spin_lock(&parent->d_lock); next = parent->d_subdirs.next; while (next != &parent->d_subdirs) { dentry = list_entry(next, struct dentry, d_u.d_child); @@ -70,6 +71,7 @@ smb_invalidate_dircache_entries(struct dentry *parent) smb_age_dentry(server, dentry); next = next->next; } + spin_unlock(&parent->d_lock); spin_unlock(&dcache_lock); } @@ -97,6 +99,7 @@ smb_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos) /* If a pointer is invalid, we search the dentry. */ spin_lock(&dcache_lock); + spin_lock(&parent->d_lock); next = parent->d_subdirs.next; while (next != &parent->d_subdirs) { dent = list_entry(next, struct dentry, d_u.d_child); @@ -111,6 +114,7 @@ smb_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos) } dent = NULL; out_unlock: + spin_unlock(&parent->d_lock); spin_unlock(&dcache_lock); return dent; } diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c index e3ab443..89a0e83 100644 --- a/drivers/usb/core/inode.c +++ b/drivers/usb/core/inode.c @@ -344,18 +344,20 @@ static int usbfs_empty (struct dentry *dentry) struct list_head *list; spin_lock(&dcache_lock); - + spin_lock(&dentry->d_lock); list_for_each(list, &dentry->d_subdirs) { struct dentry *de = list_entry(list, struct dentry, d_u.d_child); - spin_lock(&de->d_lock); + + spin_lock_nested(&de->d_lock, DENTRY_D_LOCK_NESTED); if (usbfs_positive(de)) { spin_unlock(&de->d_lock); + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); return 0; } spin_unlock(&de->d_lock); } - + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); return 1; } diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h index 3912dcf..9d2ae9b 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -254,6 +254,17 @@ static inline int simple_positive(struct dentry *dentry) return dentry->d_inode && !d_unhashed(dentry); } +static inline void __autofs4_add_expiring(struct dentry *dentry) +{ + struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_info *ino = autofs4_dentry_ino(dentry); + if (ino) { + if (list_empty(&ino->expiring)) + list_add(&ino->expiring, &sbi->expiring_list); + } + return; +} + static inline void autofs4_add_expiring(struct dentry *dentry) { struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index ee64020..3164802 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -91,24 +91,64 @@ done: } /* - * Calculate next entry in top down tree traversal. - * From next_mnt in namespace.c - elegant. + * Calculate and dget next entry in top down tree traversal. */ -static struct dentry *next_dentry(struct dentry *p, struct dentry *root) +static struct dentry *get_next_positive_dentry(struct dentry *prev, + struct dentry *root) { - struct list_head *next = p->d_subdirs.next; + struct list_head *next; + struct dentry *p, *ret; + + if (prev == NULL) + return dget(prev); + spin_lock(&dcache_lock); +relock: + p = prev; + spin_lock(&p->d_lock); +again: + next = p->d_subdirs.next; if (next == &p->d_subdirs) { while (1) { - if (p == root) + struct dentry *parent; + + if (p == root) { + spin_unlock(&p->d_lock); + spin_unlock(&dcache_lock); + dput(prev); return NULL; + } + + parent = p->d_parent; + if (!spin_trylock(&parent->d_lock)) { + spin_unlock(&p->d_lock); + cpu_relax(); + goto relock; + } + spin_unlock(&p->d_lock); next = p->d_u.d_child.next; - if (next != &p->d_parent->d_subdirs) + p = parent; + if (next != &parent->d_subdirs) break; - p = p->d_parent; } } - return list_entry(next, struct dentry, d_u.d_child); + ret = list_entry(next, struct dentry, d_u.d_child); + + spin_lock_nested(&ret->d_lock, DENTRY_D_LOCK_NESTED); + /* Negative dentry - try next */ + if (!simple_positive(ret)) { + spin_unlock(&ret->d_lock); + p = ret; + goto again; + } + dget_dlock(ret); + spin_unlock(&ret->d_lock); + spin_unlock(&p->d_lock); + spin_unlock(&dcache_lock); + + dput(prev); + + return ret; } /* @@ -158,22 +198,11 @@ static int autofs4_tree_busy(struct vfsmount *mnt, if (!simple_positive(top)) return 1; - spin_lock(&dcache_lock); - for (p = top; p; p = next_dentry(p, top)) { - spin_lock(&p->d_lock); - /* Negative dentry - give up */ - if (!simple_positive(p)) { - spin_unlock(&p->d_lock); - continue; - } - + p = NULL; + while ((p = get_next_positive_dentry(p, top))) { DPRINTK("dentry %p %.*s", p, (int) p->d_name.len, p->d_name.name); - p = dget_dlock(p); - spin_unlock(&p->d_lock); - spin_unlock(&dcache_lock); - /* * Is someone visiting anywhere in the subtree ? * If there's no mount we need to check the usage @@ -208,10 +237,7 @@ static int autofs4_tree_busy(struct vfsmount *mnt, return 1; } } - dput(p); - spin_lock(&dcache_lock); } - spin_unlock(&dcache_lock); /* Timeout of a tree mount is ultimately determined by its top dentry */ if (!autofs4_can_expire(top, timeout, do_now)) @@ -230,36 +256,21 @@ static struct dentry *autofs4_check_leaves(struct vfsmount *mnt, DPRINTK("parent %p %.*s", parent, (int)parent->d_name.len, parent->d_name.name); - spin_lock(&dcache_lock); - for (p = parent; p; p = next_dentry(p, parent)) { - spin_lock(&p->d_lock); - /* Negative dentry - give up */ - if (!simple_positive(p)) { - spin_unlock(&p->d_lock); - continue; - } - + p = NULL; + while ((p = get_next_positive_dentry(p, parent))) { DPRINTK("dentry %p %.*s", p, (int) p->d_name.len, p->d_name.name); - p = dget_dlock(p); - spin_unlock(&p->d_lock); - spin_unlock(&dcache_lock); - if (d_mountpoint(p)) { /* Can we umount this guy */ if (autofs4_mount_busy(mnt, p)) - goto cont; + continue; /* Can we expire this guy */ if (autofs4_can_expire(p, timeout, do_now)) return p; } -cont: - dput(p); - spin_lock(&dcache_lock); } - spin_unlock(&dcache_lock); return NULL; } @@ -310,8 +321,8 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, { unsigned long timeout; struct dentry *root = sb->s_root; + struct dentry *dentry; struct dentry *expired = NULL; - struct list_head *next; int do_now = how & AUTOFS_EXP_IMMEDIATE; int exp_leaves = how & AUTOFS_EXP_LEAVES; struct autofs_info *ino; @@ -323,26 +334,8 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, now = jiffies; timeout = sbi->exp_timeout; - spin_lock(&dcache_lock); - next = root->d_subdirs.next; - - /* On exit from the loop expire is set to a dgot dentry - * to expire or it's NULL */ - while ( next != &root->d_subdirs ) { - struct dentry *dentry = list_entry(next, struct dentry, d_u.d_child); - - /* Negative dentry - give up */ - spin_lock(&dentry->d_lock); - if (!simple_positive(dentry)) { - next = next->next; - spin_unlock(&dentry->d_lock); - continue; - } - - dentry = dget_dlock(dentry); - spin_unlock(&dentry->d_lock); - spin_unlock(&dcache_lock); - + dentry = NULL; + while ((dentry = get_next_positive_dentry(dentry, root))) { spin_lock(&sbi->fs_lock); ino = autofs4_dentry_ino(dentry); @@ -405,11 +398,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, } next: spin_unlock(&sbi->fs_lock); - dput(dentry); - spin_lock(&dcache_lock); - next = next->next; } - spin_unlock(&dcache_lock); return NULL; found: @@ -420,7 +409,11 @@ found: init_completion(&ino->expire_complete); spin_unlock(&sbi->fs_lock); spin_lock(&dcache_lock); - list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child); + spin_lock(&expired->d_parent->d_lock); + spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED); + list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child); + spin_unlock(&expired->d_lock); + spin_unlock(&expired->d_parent->d_lock); spin_unlock(&dcache_lock); return expired; } diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index dc7e64b..a185e7e 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -143,10 +143,13 @@ static int autofs4_dir_open(struct inode *inode, struct file *file) * it. */ spin_lock(&dcache_lock); + spin_lock(&dentry->d_lock); if (!d_mountpoint(dentry) && list_empty(&dentry->d_subdirs)) { + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); return -ENOENT; } + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); out: @@ -253,7 +256,9 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd) lookup_type = autofs4_need_mount(nd->flags); spin_lock(&sbi->fs_lock); spin_lock(&dcache_lock); + spin_lock(&dentry->d_lock); if (!(lookup_type || ino->flags & AUTOFS_INF_PENDING)) { + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); spin_unlock(&sbi->fs_lock); goto follow; @@ -266,6 +271,7 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd) */ if (ino->flags & AUTOFS_INF_PENDING || (!d_mountpoint(dentry) && list_empty(&dentry->d_subdirs))) { + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); spin_unlock(&sbi->fs_lock); @@ -275,6 +281,7 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd) goto follow; } + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); spin_unlock(&sbi->fs_lock); follow: @@ -347,10 +354,12 @@ static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd) /* Check for a non-mountpoint directory with no contents */ spin_lock(&dcache_lock); + spin_lock(&dentry->d_lock); if (S_ISDIR(dentry->d_inode->i_mode) && !d_mountpoint(dentry) && list_empty(&dentry->d_subdirs)) { DPRINTK("dentry=%p %.*s, emptydir", dentry, dentry->d_name.len, dentry->d_name.name); + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); /* The daemon never causes a mount to trigger */ @@ -367,6 +376,7 @@ static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd) return status; } + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); return 1; @@ -776,12 +786,16 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry) return -EACCES; spin_lock(&dcache_lock); + spin_lock(&sbi->lookup_lock); + spin_lock(&dentry->d_lock); if (!list_empty(&dentry->d_subdirs)) { + spin_unlock(&dentry->d_lock); + spin_unlock(&sbi->lookup_lock); spin_unlock(&dcache_lock); return -ENOTEMPTY; } - autofs4_add_expiring(dentry); - spin_lock(&dentry->d_lock); + __autofs4_add_expiring(dentry); + spin_unlock(&sbi->lookup_lock); __d_drop(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 9d52531..4c81ae5 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -112,6 +112,7 @@ static int __dcache_readdir(struct file *filp, last); spin_lock(&dcache_lock); + spin_lock(&parent->d_lock); /* start at beginning? */ if (filp->f_pos == 2 || (last && @@ -135,7 +136,7 @@ more: fi->at_end = 1; goto out_unlock; } - spin_lock(&dentry->d_lock); + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); if (!d_unhashed(dentry) && dentry->d_inode && ceph_snap(dentry->d_inode) != CEPH_SNAPDIR && ceph_ino(dentry->d_inode) != CEPH_INO_CEPH && @@ -153,6 +154,7 @@ more: dget_dlock(dentry); spin_unlock(&dentry->d_lock); + spin_unlock(&parent->d_lock); spin_unlock(&dcache_lock); dout(" %llu (%llu) dentry %p %.*s %p\n", di->offset, filp->f_pos, @@ -187,10 +189,12 @@ more: } spin_lock(&dcache_lock); + spin_lock(&parent->d_lock); p = p->prev; /* advance to next dentry */ goto more; out_unlock: + spin_unlock(&parent->d_lock); spin_unlock(&dcache_lock); out: if (last) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index bb68c79..2c69444 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -842,11 +842,13 @@ static void ceph_set_dentry_offset(struct dentry *dn) spin_unlock(&inode->i_lock); spin_lock(&dcache_lock); - spin_lock(&dn->d_lock); + spin_lock(&dir->d_lock); + spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED); list_move(&dn->d_u.d_child, &dir->d_subdirs); dout("set_dentry_offset %p %lld (%p %p)\n", dn, di->offset, dn->d_u.d_child.prev, dn->d_u.d_child.next); spin_unlock(&dn->d_lock); + spin_unlock(&dir->d_lock); spin_unlock(&dcache_lock); } @@ -1232,9 +1234,11 @@ retry_lookup: } else { /* reorder parent's d_subdirs */ spin_lock(&dcache_lock); - spin_lock(&dn->d_lock); + spin_lock(&parent->d_lock); + spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED); list_move(&dn->d_u.d_child, &parent->d_subdirs); spin_unlock(&dn->d_lock); + spin_unlock(&parent->d_lock); spin_unlock(&dcache_lock); } diff --git a/fs/coda/cache.c b/fs/coda/cache.c index 9060f08..859393f 100644 --- a/fs/coda/cache.c +++ b/fs/coda/cache.c @@ -94,6 +94,7 @@ static void coda_flag_children(struct dentry *parent, int flag) struct dentry *de; spin_lock(&dcache_lock); + spin_lock(&parent->d_lock); list_for_each(child, &parent->d_subdirs) { de = list_entry(child, struct dentry, d_u.d_child); @@ -102,6 +103,7 @@ static void coda_flag_children(struct dentry *parent, int flag) continue; coda_flag_inode(de->d_inode, flag); } + spin_unlock(&parent->d_lock); spin_unlock(&dcache_lock); return; } diff --git a/fs/dcache.c b/fs/dcache.c index 05b2257..c79f3d4 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -47,6 +47,8 @@ * - d_lru * - d_count * - d_unhashed() + * - d_parent and d_subdirs + * - childrens' d_child and d_parent * * Ordering: * dcache_lock @@ -217,24 +219,22 @@ static void dentry_lru_move_tail(struct dentry *dentry) * * If this is the root of the dentry tree, return NULL. * - * dcache_lock and d_lock must be held by caller, are dropped by d_kill. + * dcache_lock and d_lock and d_parent->d_lock must be held by caller, and + * are dropped by d_kill. */ -static struct dentry *d_kill(struct dentry *dentry) +static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent) __releases(dentry->d_lock) + __releases(parent->d_lock) __releases(dcache_lock) { - struct dentry *parent; - list_del(&dentry->d_u.d_child); + if (parent) + spin_unlock(&parent->d_lock); dentry_iput(dentry); /* * dentry_iput drops the locks, at which point nobody (except * transient RCU lookups) can reach this dentry. */ - if (IS_ROOT(dentry)) - parent = NULL; - else - parent = dentry->d_parent; d_free(dentry); return parent; } @@ -270,6 +270,7 @@ static struct dentry *d_kill(struct dentry *dentry) void dput(struct dentry *dentry) { + struct dentry *parent; if (!dentry) return; @@ -277,6 +278,10 @@ repeat: if (dentry->d_count == 1) might_sleep(); spin_lock(&dentry->d_lock); + if (IS_ROOT(dentry)) + parent = NULL; + else + parent = dentry->d_parent; if (dentry->d_count == 1) { if (!spin_trylock(&dcache_lock)) { /* @@ -288,10 +293,17 @@ repeat: spin_unlock(&dentry->d_lock); goto repeat; } + if (parent && !spin_trylock(&parent->d_lock)) { + spin_unlock(&dentry->d_lock); + spin_unlock(&dcache_lock); + goto repeat; + } } dentry->d_count--; if (dentry->d_count) { spin_unlock(&dentry->d_lock); + if (parent) + spin_unlock(&parent->d_lock); spin_unlock(&dcache_lock); return; } @@ -313,6 +325,8 @@ repeat: dentry_lru_add(dentry); spin_unlock(&dentry->d_lock); + if (parent) + spin_unlock(&parent->d_lock); spin_unlock(&dcache_lock); return; @@ -321,7 +335,7 @@ unhash_it: kill_it: /* if dentry was on the d_lru list delete it from there */ dentry_lru_del(dentry); - dentry = d_kill(dentry); + dentry = d_kill(dentry, parent); if (dentry) goto repeat; } @@ -547,12 +561,13 @@ EXPORT_SYMBOL(d_prune_aliases); * quadratic behavior of shrink_dcache_parent(), but is also expected * to be beneficial in reducing dentry cache fragmentation. */ -static void prune_one_dentry(struct dentry * dentry) +static void prune_one_dentry(struct dentry *dentry, struct dentry *parent) __releases(dentry->d_lock) + __releases(parent->d_lock) __releases(dcache_lock) { __d_drop(dentry); - dentry = d_kill(dentry); + dentry = d_kill(dentry, parent); /* * Prune ancestors. Locking is simpler than in dput(), @@ -560,9 +575,20 @@ static void prune_one_dentry(struct dentry * dentry) */ while (dentry) { spin_lock(&dcache_lock); +again: spin_lock(&dentry->d_lock); + if (IS_ROOT(dentry)) + parent = NULL; + else + parent = dentry->d_parent; + if (parent && !spin_trylock(&parent->d_lock)) { + spin_unlock(&dentry->d_lock); + goto again; + } dentry->d_count--; if (dentry->d_count) { + if (parent) + spin_unlock(&parent->d_lock); spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); return; @@ -570,7 +596,7 @@ static void prune_one_dentry(struct dentry * dentry) dentry_lru_del(dentry); __d_drop(dentry); - dentry = d_kill(dentry); + dentry = d_kill(dentry, parent); } } @@ -579,29 +605,40 @@ static void shrink_dentry_list(struct list_head *list) struct dentry *dentry; while (!list_empty(list)) { + struct dentry *parent; + dentry = list_entry(list->prev, struct dentry, d_lru); if (!spin_trylock(&dentry->d_lock)) { +relock: spin_unlock(&dcache_lru_lock); cpu_relax(); spin_lock(&dcache_lru_lock); continue; } - __dentry_lru_del(dentry); - /* * We found an inuse dentry which was not removed from * the LRU because of laziness during lookup. Do not free * it - just keep it off the LRU list. */ if (dentry->d_count) { + __dentry_lru_del(dentry); spin_unlock(&dentry->d_lock); continue; } + if (IS_ROOT(dentry)) + parent = NULL; + else + parent = dentry->d_parent; + if (parent && !spin_trylock(&parent->d_lock)) { + spin_unlock(&dentry->d_lock); + goto relock; + } + __dentry_lru_del(dentry); spin_unlock(&dcache_lru_lock); - prune_one_dentry(dentry); + prune_one_dentry(dentry, parent); /* dcache_lock and dentry->d_lock dropped */ spin_lock(&dcache_lock); spin_lock(&dcache_lru_lock); @@ -796,14 +833,16 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) /* this is a branch with children - detach all of them * from the system in one go */ spin_lock(&dcache_lock); + spin_lock(&dentry->d_lock); list_for_each_entry(loop, &dentry->d_subdirs, d_u.d_child) { - spin_lock(&loop->d_lock); + spin_lock_nested(&loop->d_lock, + DENTRY_D_LOCK_NESTED); dentry_lru_del(loop); __d_drop(loop); spin_unlock(&loop->d_lock); - cond_resched_lock(&dcache_lock); } + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); /* move to the first child */ @@ -831,16 +870,17 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) BUG(); } - if (IS_ROOT(dentry)) + if (IS_ROOT(dentry)) { parent = NULL; - else { + list_del(&dentry->d_u.d_child); + } else { parent = dentry->d_parent; spin_lock(&parent->d_lock); parent->d_count--; + list_del(&dentry->d_u.d_child); spin_unlock(&parent->d_lock); } - list_del(&dentry->d_u.d_child); detached++; inode = dentry->d_inode; @@ -921,6 +961,7 @@ int have_submounts(struct dentry *parent) spin_lock(&dcache_lock); if (d_mountpoint(parent)) goto positive; + spin_lock(&this_parent->d_lock); repeat: next = this_parent->d_subdirs.next; resume: @@ -928,22 +969,34 @@ resume: struct list_head *tmp = next; struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child); next = tmp->next; + + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); /* Have we found a mount point ? */ - if (d_mountpoint(dentry)) + if (d_mountpoint(dentry)) { + spin_unlock(&dentry->d_lock); + spin_unlock(&this_parent->d_lock); goto positive; + } if (!list_empty(&dentry->d_subdirs)) { + spin_unlock(&this_parent->d_lock); + spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_); this_parent = dentry; + spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); goto repeat; } + spin_unlock(&dentry->d_lock); } /* * All done at this level ... ascend and resume the search. */ if (this_parent != parent) { next = this_parent->d_u.d_child.next; + spin_unlock(&this_parent->d_lock); this_parent = this_parent->d_parent; + spin_lock(&this_parent->d_lock); goto resume; } + spin_unlock(&this_parent->d_lock); spin_unlock(&dcache_lock); return 0; /* No mount points found in tree */ positive: @@ -973,6 +1026,7 @@ static int select_parent(struct dentry * parent) int found = 0; spin_lock(&dcache_lock); + spin_lock(&this_parent->d_lock); repeat: next = this_parent->d_subdirs.next; resume: @@ -980,8 +1034,9 @@ resume: struct list_head *tmp = next; struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child); next = tmp->next; + BUG_ON(this_parent == dentry); - spin_lock(&dentry->d_lock); + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); /* * move only zero ref count dentries to the end @@ -994,33 +1049,44 @@ resume: dentry_lru_del(dentry); } - spin_unlock(&dentry->d_lock); - /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ - if (found && need_resched()) + if (found && need_resched()) { + spin_unlock(&dentry->d_lock); goto out; + } /* * Descend a level if the d_subdirs list is non-empty. */ if (!list_empty(&dentry->d_subdirs)) { + spin_unlock(&this_parent->d_lock); + spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_); this_parent = dentry; + spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); goto repeat; } + + spin_unlock(&dentry->d_lock); } /* * All done at this level ... ascend and resume the search. */ if (this_parent != parent) { + struct dentry *tmp; next = this_parent->d_u.d_child.next; - this_parent = this_parent->d_parent; + tmp = this_parent->d_parent; + spin_unlock(&this_parent->d_lock); + BUG_ON(tmp == this_parent); + this_parent = tmp; + spin_lock(&this_parent->d_lock); goto resume; } out: + spin_unlock(&this_parent->d_lock); spin_unlock(&dcache_lock); return found; } @@ -1121,18 +1187,19 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) INIT_LIST_HEAD(&dentry->d_lru); INIT_LIST_HEAD(&dentry->d_subdirs); INIT_LIST_HEAD(&dentry->d_alias); + INIT_LIST_HEAD(&dentry->d_u.d_child); if (parent) { - dentry->d_parent = dget(parent); + spin_lock(&dcache_lock); + spin_lock(&parent->d_lock); + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + dentry->d_parent = dget_dlock(parent); dentry->d_sb = parent->d_sb; - } else { - INIT_LIST_HEAD(&dentry->d_u.d_child); - } - - spin_lock(&dcache_lock); - if (parent) list_add(&dentry->d_u.d_child, &parent->d_subdirs); - spin_unlock(&dcache_lock); + spin_unlock(&dentry->d_lock); + spin_unlock(&parent->d_lock); + spin_unlock(&dcache_lock); + } percpu_counter_inc(&nr_dentry); @@ -1650,13 +1717,18 @@ int d_validate(struct dentry *dentry, struct dentry *dparent) struct dentry *child; spin_lock(&dcache_lock); + spin_lock(&dparent->d_lock); list_for_each_entry(child, &dparent->d_subdirs, d_u.d_child) { if (dentry == child) { - __dget_locked(dentry); + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + __dget_locked_dlock(dentry); + spin_unlock(&dentry->d_lock); + spin_unlock(&dparent->d_lock); spin_unlock(&dcache_lock); return 1; } } + spin_unlock(&dparent->d_lock); spin_unlock(&dcache_lock); return 0; @@ -1822,15 +1894,26 @@ static void d_move_locked(struct dentry * dentry, struct dentry * target) /* * XXXX: do we really need to take target->d_lock? */ - if (d_ancestor(dentry, target)) { - spin_lock(&dentry->d_lock); - spin_lock_nested(&target->d_lock, DENTRY_D_LOCK_NESTED); - } else if (d_ancestor(target, dentry) || target < dentry) { - spin_lock(&target->d_lock); - spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - } else { - spin_lock(&dentry->d_lock); - spin_lock_nested(&target->d_lock, DENTRY_D_LOCK_NESTED); + BUG_ON(d_ancestor(dentry, target)); + BUG_ON(d_ancestor(target, dentry)); + + if (IS_ROOT(dentry) || dentry->d_parent == target->d_parent) + spin_lock(&target->d_parent->d_lock); + else { + if (d_ancestor(dentry->d_parent, target->d_parent)) { + spin_lock(&dentry->d_parent->d_lock); + spin_lock_nested(&target->d_parent->d_lock, DENTRY_D_LOCK_NESTED); + } else { + spin_lock(&target->d_parent->d_lock); + spin_lock_nested(&dentry->d_parent->d_lock, DENTRY_D_LOCK_NESTED); + } + } + if (target < dentry) { + spin_lock_nested(&target->d_lock, 2); + spin_lock_nested(&dentry->d_lock, 3); + } else { + spin_lock_nested(&dentry->d_lock, 2); + spin_lock_nested(&target->d_lock, 3); } /* Move the dentry to the target hash queue, if on different bucket */ @@ -1863,6 +1946,10 @@ static void d_move_locked(struct dentry * dentry, struct dentry * target) } list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs); + if (target->d_parent != dentry->d_parent) + spin_unlock(&dentry->d_parent->d_lock); + if (target->d_parent != target) + spin_unlock(&target->d_parent->d_lock); spin_unlock(&target->d_lock); fsnotify_d_move(dentry); spin_unlock(&dentry->d_lock); @@ -1963,6 +2050,13 @@ static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon) dparent = dentry->d_parent; aparent = anon->d_parent; + /* XXX: hack */ + /* returns with anon->d_lock held! */ + spin_lock(&aparent->d_lock); + spin_lock(&dparent->d_lock); + spin_lock(&dentry->d_lock); + spin_lock(&anon->d_lock); + dentry->d_parent = (aparent == anon) ? dentry : aparent; list_del(&dentry->d_u.d_child); if (!IS_ROOT(dentry)) @@ -1977,6 +2071,10 @@ static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon) else INIT_LIST_HEAD(&anon->d_u.d_child); + spin_unlock(&dentry->d_lock); + spin_unlock(&dparent->d_lock); + spin_unlock(&aparent->d_lock); + anon->d_flags &= ~DCACHE_DISCONNECTED; } @@ -2012,7 +2110,6 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode) /* Is this an anonymous mountpoint that we could splice * into our tree? */ if (IS_ROOT(alias)) { - spin_lock(&alias->d_lock); __d_materialise_dentry(dentry, alias); __d_drop(alias); goto found; @@ -2497,6 +2594,7 @@ void d_genocide(struct dentry *root) struct list_head *next; spin_lock(&dcache_lock); + spin_lock(&this_parent->d_lock); repeat: next = this_parent->d_subdirs.next; resume: @@ -2510,8 +2608,10 @@ resume: continue; } if (!list_empty(&dentry->d_subdirs)) { - spin_unlock(&dentry->d_lock); + spin_unlock(&this_parent->d_lock); + spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_); this_parent = dentry; + spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); goto repeat; } dentry->d_count--; @@ -2519,12 +2619,13 @@ resume: } if (this_parent != root) { next = this_parent->d_u.d_child.next; - spin_lock(&this_parent->d_lock); this_parent->d_count--; spin_unlock(&this_parent->d_lock); this_parent = this_parent->d_parent; + spin_lock(&this_parent->d_lock); goto resume; } + spin_unlock(&this_parent->d_lock); spin_unlock(&dcache_lock); } diff --git a/fs/libfs.c b/fs/libfs.c index 433e713..cc47949 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -81,7 +81,8 @@ int dcache_dir_close(struct inode *inode, struct file *file) loff_t dcache_dir_lseek(struct file *file, loff_t offset, int origin) { - mutex_lock(&file->f_path.dentry->d_inode->i_mutex); + struct dentry *dentry = file->f_path.dentry; + mutex_lock(&dentry->d_inode->i_mutex); switch (origin) { case 1: offset += file->f_pos; @@ -89,7 +90,7 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int origin) if (offset >= 0) break; default: - mutex_unlock(&file->f_path.dentry->d_inode->i_mutex); + mutex_unlock(&dentry->d_inode->i_mutex); return -EINVAL; } if (offset != file->f_pos) { @@ -100,22 +101,25 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int origin) loff_t n = file->f_pos - 2; spin_lock(&dcache_lock); + spin_lock(&dentry->d_lock); + /* d_lock not required for cursor */ list_del(&cursor->d_u.d_child); - p = file->f_path.dentry->d_subdirs.next; - while (n && p != &file->f_path.dentry->d_subdirs) { + p = dentry->d_subdirs.next; + while (n && p != &dentry->d_subdirs) { struct dentry *next; next = list_entry(p, struct dentry, d_u.d_child); - spin_lock(&next->d_lock); + spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(next)) n--; spin_unlock(&next->d_lock); p = p->next; } list_add_tail(&cursor->d_u.d_child, p); + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); } } - mutex_unlock(&file->f_path.dentry->d_inode->i_mutex); + mutex_unlock(&dentry->d_inode->i_mutex); return offset; } @@ -156,6 +160,7 @@ int dcache_readdir(struct file * filp, void * dirent, filldir_t filldir) /* fallthrough */ default: spin_lock(&dcache_lock); + spin_lock(&dentry->d_lock); if (filp->f_pos == 2) list_move(q, &dentry->d_subdirs); @@ -169,6 +174,7 @@ int dcache_readdir(struct file * filp, void * dirent, filldir_t filldir) } spin_unlock(&next->d_lock); + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); if (filldir(dirent, next->d_name.name, next->d_name.len, filp->f_pos, @@ -176,11 +182,15 @@ int dcache_readdir(struct file * filp, void * dirent, filldir_t filldir) dt_type(next->d_inode)) < 0) return 0; spin_lock(&dcache_lock); + spin_lock(&dentry->d_lock); + spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED); /* next is still alive */ list_move(q, p); + spin_unlock(&next->d_lock); p = q; filp->f_pos++; } + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); } return 0; @@ -276,6 +286,7 @@ int simple_empty(struct dentry *dentry) int ret = 0; spin_lock(&dcache_lock); + spin_lock(&dentry->d_lock); list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { @@ -286,6 +297,7 @@ int simple_empty(struct dentry *dentry) } ret = 1; out: + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); return ret; } diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index ecb25c6..ce65f29 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -394,6 +394,7 @@ ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos) /* If a pointer is invalid, we search the dentry. */ spin_lock(&dcache_lock); + spin_lock(&parent->d_lock); next = parent->d_subdirs.next; while (next != &parent->d_subdirs) { dent = list_entry(next, struct dentry, d_u.d_child); @@ -402,11 +403,13 @@ ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos) dget_locked(dent); else dent = NULL; + spin_unlock(&parent->d_lock); spin_unlock(&dcache_lock); goto out; } next = next->next; } + spin_unlock(&parent->d_lock); spin_unlock(&dcache_lock); return NULL; diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h index 244d1b7..c4b718f 100644 --- a/fs/ncpfs/ncplib_kernel.h +++ b/fs/ncpfs/ncplib_kernel.h @@ -194,6 +194,7 @@ ncp_renew_dentries(struct dentry *parent) struct dentry *dentry; spin_lock(&dcache_lock); + spin_lock(&parent->d_lock); next = parent->d_subdirs.next; while (next != &parent->d_subdirs) { dentry = list_entry(next, struct dentry, d_u.d_child); @@ -205,6 +206,7 @@ ncp_renew_dentries(struct dentry *parent) next = next->next; } + spin_unlock(&parent->d_lock); spin_unlock(&dcache_lock); } @@ -216,6 +218,7 @@ ncp_invalidate_dircache_entries(struct dentry *parent) struct dentry *dentry; spin_lock(&dcache_lock); + spin_lock(&parent->d_lock); next = parent->d_subdirs.next; while (next != &parent->d_subdirs) { dentry = list_entry(next, struct dentry, d_u.d_child); @@ -223,6 +226,7 @@ ncp_invalidate_dircache_entries(struct dentry *parent) ncp_age_dentry(server, dentry); next = next->next; } + spin_unlock(&parent->d_lock); spin_unlock(&dcache_lock); } diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 20dc218..aa4f25e 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -68,17 +68,19 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode) /* run all of the children of the original inode and fix their * d_flags to indicate parental interest (their parent is the * original inode) */ + spin_lock(&alias->d_lock); list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) { if (!child->d_inode) continue; - spin_lock(&child->d_lock); + spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (watched) child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; else child->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; spin_unlock(&child->d_lock); } + spin_unlock(&alias->d_lock); } spin_unlock(&dcache_lock); } diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 06f6f58..16d6ecf 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -337,6 +337,7 @@ static inline struct dentry *dget_dlock(struct dentry *dentry) } return dentry; } + static inline struct dentry *dget(struct dentry *dentry) { if (dentry) { diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 7ead732..54f3442 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -875,23 +875,31 @@ static void cgroup_clear_directory(struct dentry *dentry) BUG_ON(!mutex_is_locked(&dentry->d_inode->i_mutex)); spin_lock(&dcache_lock); + spin_lock(&dentry->d_lock); node = dentry->d_subdirs.next; while (node != &dentry->d_subdirs) { struct dentry *d = list_entry(node, struct dentry, d_u.d_child); + + spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); list_del_init(node); if (d->d_inode) { /* This should never be called on a cgroup * directory with child cgroups */ BUG_ON(d->d_inode->i_mode & S_IFDIR); - d = dget_locked(d); + dget_locked_dlock(d); + spin_unlock(&d->d_lock); + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); d_delete(d); simple_unlink(dentry->d_inode, d); dput(d); spin_lock(&dcache_lock); - } + spin_lock(&dentry->d_lock); + } else + spin_unlock(&d->d_lock); node = dentry->d_subdirs.next; } + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); } @@ -900,10 +908,17 @@ static void cgroup_clear_directory(struct dentry *dentry) */ static void cgroup_d_remove_dir(struct dentry *dentry) { + struct dentry *parent; + cgroup_clear_directory(dentry); spin_lock(&dcache_lock); + parent = dentry->d_parent; + spin_lock(&parent->d_lock); + spin_lock(&dentry->d_lock); list_del_init(&dentry->d_u.d_child); + spin_unlock(&dentry->d_lock); + spin_unlock(&parent->d_lock); spin_unlock(&dcache_lock); remove_dir(dentry); } diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 073fd5b..017ec09 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -1146,22 +1146,30 @@ static void sel_remove_entries(struct dentry *de) struct list_head *node; spin_lock(&dcache_lock); + spin_lock(&de->d_lock); node = de->d_subdirs.next; while (node != &de->d_subdirs) { struct dentry *d = list_entry(node, struct dentry, d_u.d_child); + + spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); list_del_init(node); if (d->d_inode) { - d = dget_locked(d); + dget_locked_dlock(d); + spin_unlock(&de->d_lock); + spin_unlock(&d->d_lock); spin_unlock(&dcache_lock); d_delete(d); simple_unlink(de->d_inode, d); dput(d); spin_lock(&dcache_lock); - } + spin_lock(&de->d_lock); + } else + spin_unlock(&d->d_lock); node = de->d_subdirs.next; } + spin_unlock(&de->d_lock); spin_unlock(&dcache_lock); } -- 1.7.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/