[PATCH OLK-5.10 1/7] kernfs: add a revision to identify directory node changes
From: Ian Kent <raven@themaw.net> mainline inclusion from mainline-v5.15-rc1 commit 895adbec302e92086359e6fd92611ac3be6d92c3 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/ICRD6W Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Add a revision counter to kernfs directory nodes so it can be used to detect if a directory node has changed during negative dentry revalidation. There's an assumption that sizeof(unsigned long) <= sizeof(pointer) on all architectures and as far as I know that assumption holds. So adding a revision counter to the struct kernfs_elem_dir variant of the kernfs_node type union won't increase the size of the kernfs_node struct. This is because struct kernfs_elem_dir is at least sizeof(pointer) smaller than the largest union variant. It's tempting to make the revision counter a u64 but that would increase the size of kernfs_node on archs where sizeof(pointer) is smaller than the revision counter. Reviewed-by: Miklos Szeredi <mszeredi@redhat.com> Signed-off-by: Ian Kent <raven@themaw.net> Link: https://lore.kernel.org/r/162642769895.63632.8356662784964509867.stgit@web.m... Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Zizhi Wo <wozizhi@huawei.com> --- fs/kernfs/dir.c | 2 ++ fs/kernfs/kernfs-internal.h | 19 +++++++++++++++++++ include/linux/kernfs.h | 5 +++++ 3 files changed, 26 insertions(+) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 0ba056e06e48..9bc73c8b6e3f 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -380,6 +380,7 @@ static int kernfs_link_sibling(struct kernfs_node *kn) /* successfully added, account subdir number */ if (kernfs_type(kn) == KERNFS_DIR) kn->parent->dir.subdirs++; + kernfs_inc_rev(kn->parent); return 0; } @@ -402,6 +403,7 @@ static bool kernfs_unlink_sibling(struct kernfs_node *kn) if (kernfs_type(kn) == KERNFS_DIR) kn->parent->dir.subdirs--; + kernfs_inc_rev(kn->parent); rb_erase(&kn->rb, &kn->parent->dir.children); RB_CLEAR_NODE(&kn->rb); diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 7ee97ef59184..6a8d0ca26d03 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -81,6 +81,25 @@ static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry) return d_inode(dentry)->i_private; } +static inline void kernfs_set_rev(struct kernfs_node *parent, + struct dentry *dentry) +{ + dentry->d_time = parent->dir.rev; +} + +static inline void kernfs_inc_rev(struct kernfs_node *parent) +{ + parent->dir.rev++; +} + +static inline bool kernfs_dir_changed(struct kernfs_node *parent, + struct dentry *dentry) +{ + if (parent->dir.rev != dentry->d_time) + return true; + return false; +} + extern const struct super_operations kernfs_sops; extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index e2aa4910365d..236240a17017 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -99,6 +99,11 @@ struct kernfs_elem_dir { * better directly in kernfs_node but is here to save space. */ struct kernfs_root *root; + /* + * Monotonic revision counter, used to identify if a directory + * node has changed during negative dentry revalidation. + */ + unsigned long rev; }; struct kernfs_elem_symlink { -- 2.39.2
From: Ian Kent <raven@themaw.net> mainline inclusion from mainline-v5.15-rc1 commit c7e7c04274b13f98f758fb69b03f2ab61976ea80 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/ICRD6W Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- If there are many lookups for non-existent paths these negative lookups can lead to a lot of overhead during path walks. The VFS allows dentries to be created as negative and hashed, and caches them so they can be used to reduce the fairly high overhead alloc/free cycle that occurs during these lookups. Use the kernfs node parent revision to identify if a change has been made to the containing directory so that the negative dentry can be discarded and the lookup redone. Reviewed-by: Miklos Szeredi <mszeredi@redhat.com> Signed-off-by: Ian Kent <raven@themaw.net> Link: https://lore.kernel.org/r/162642770420.63632.15791924970508867106.stgit@web.... Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Zizhi Wo <wozizhi@huawei.com> --- fs/kernfs/dir.c | 55 +++++++++++++++++++++++++++++++------------------ 1 file changed, 35 insertions(+), 20 deletions(-) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 9bc73c8b6e3f..1756f7e43aac 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -565,9 +565,31 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) if (flags & LOOKUP_RCU) return -ECHILD; - /* Always perform fresh lookup for negatives */ - if (d_really_is_negative(dentry)) - goto out_bad_unlocked; + /* Negative hashed dentry? */ + if (d_really_is_negative(dentry)) { + struct kernfs_node *parent; + + /* If the kernfs parent node has changed discard and + * proceed to ->lookup. + */ + mutex_lock(&kernfs_mutex); + spin_lock(&dentry->d_lock); + parent = kernfs_dentry_node(dentry->d_parent); + if (parent) { + if (kernfs_dir_changed(parent, dentry)) { + spin_unlock(&dentry->d_lock); + mutex_unlock(&kernfs_mutex); + return 0; + } + } + spin_unlock(&dentry->d_lock); + mutex_unlock(&kernfs_mutex); + + /* The kernfs parent node hasn't changed, leave the + * dentry negative and return success. + */ + return 1; + } kn = kernfs_dentry_node(dentry); mutex_lock(&kernfs_mutex); @@ -593,7 +615,6 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) return 1; out_bad: mutex_unlock(&kernfs_mutex); -out_bad_unlocked: return 0; } @@ -1104,33 +1125,27 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, struct dentry *ret; struct kernfs_node *parent = dir->i_private; struct kernfs_node *kn; - struct inode *inode; + struct inode *inode = NULL; const void *ns = NULL; mutex_lock(&kernfs_mutex); - if (kernfs_ns_enabled(parent)) ns = kernfs_info(dir->i_sb)->ns; kn = kernfs_find_ns(parent, dentry->d_name.name, ns); - - /* no such entry */ - if (!kn || !kernfs_active(kn)) { - ret = NULL; - goto out_unlock; - } - /* attach dentry and inode */ - inode = kernfs_get_inode(dir->i_sb, kn); - if (!inode) { - ret = ERR_PTR(-ENOMEM); - goto out_unlock; + if (kn && kernfs_active(kn)) { + inode = kernfs_get_inode(dir->i_sb, kn); + if (!inode) + inode = ERR_PTR(-ENOMEM); } - - /* instantiate and hash dentry */ + /* Needed only for negative dentry validation */ + if (!inode) + kernfs_set_rev(parent, dentry); + /* instantiate and hash (possibly negative) dentry */ ret = d_splice_alias(inode, dentry); - out_unlock: mutex_unlock(&kernfs_mutex); + return ret; } -- 2.39.2
From: Ian Kent <raven@themaw.net> mainline inclusion from mainline-v5.15-rc1 commit 7ba0273b2f34a55efe967d3c7381fb1da2ca195f category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/ICRD6W Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- The kernfs global lock restricts the ability to perform kernfs node lookup operations in parallel during path walks. Change the kernfs mutex to an rwsem so that, when opportunity arises, node searches can be done in parallel with path walk lookups. Reviewed-by: Miklos Szeredi <mszeredi@redhat.com> Signed-off-by: Ian Kent <raven@themaw.net> Link: https://lore.kernel.org/r/162642770946.63632.2218304587223241374.stgit@web.m... Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Conflicts: fs/kernfs/dir.c fs/kernfs/inode.c [Simple context conflict, direct adaptation.] Signed-off-by: Zizhi Wo <wozizhi@huawei.com> --- fs/kernfs/dir.c | 100 ++++++++++++++++++------------------ fs/kernfs/file.c | 4 +- fs/kernfs/inode.c | 16 +++--- fs/kernfs/kernfs-internal.h | 5 +- fs/kernfs/mount.c | 12 ++--- fs/kernfs/symlink.c | 4 +- include/linux/kernfs.h | 2 +- 7 files changed, 72 insertions(+), 71 deletions(-) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 1756f7e43aac..0443a9cd72a3 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -17,7 +17,7 @@ #include "kernfs-internal.h" -DEFINE_MUTEX(kernfs_mutex); +DECLARE_RWSEM(kernfs_rwsem); static DEFINE_SPINLOCK(kernfs_rename_lock); /* kn->parent and ->name */ /* * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to @@ -34,7 +34,7 @@ static DEFINE_SPINLOCK(kernfs_idr_lock); /* root->ino_idr */ static bool kernfs_active(struct kernfs_node *kn) { - lockdep_assert_held(&kernfs_mutex); + lockdep_assert_held(&kernfs_rwsem); return atomic_read(&kn->active) >= 0; } @@ -348,7 +348,7 @@ static int kernfs_sd_compare(const struct kernfs_node *left, * @kn->parent->dir.children. * * Locking: - * mutex_lock(kernfs_mutex) + * kernfs_rwsem held exclusive * * RETURNS: * 0 on susccess -EEXIST on failure. @@ -394,7 +394,7 @@ static int kernfs_link_sibling(struct kernfs_node *kn) * removed, %false if @kn wasn't on the rbtree. * * Locking: - * mutex_lock(kernfs_mutex) + * kernfs_rwsem held exclusive */ static bool kernfs_unlink_sibling(struct kernfs_node *kn) { @@ -465,14 +465,14 @@ void kernfs_put_active(struct kernfs_node *kn) * return after draining is complete. */ static void kernfs_drain(struct kernfs_node *kn) - __releases(&kernfs_mutex) __acquires(&kernfs_mutex) + __releases(&kernfs_rwsem) __acquires(&kernfs_rwsem) { struct kernfs_root *root = kernfs_root(kn); - lockdep_assert_held(&kernfs_mutex); + lockdep_assert_held_write(&kernfs_rwsem); WARN_ON_ONCE(kernfs_active(kn)); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); if (kernfs_lockdep(kn)) { rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_); @@ -491,7 +491,7 @@ static void kernfs_drain(struct kernfs_node *kn) kernfs_drain_open_files(kn); - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); } /** @@ -572,18 +572,18 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) /* If the kernfs parent node has changed discard and * proceed to ->lookup. */ - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); spin_lock(&dentry->d_lock); parent = kernfs_dentry_node(dentry->d_parent); if (parent) { if (kernfs_dir_changed(parent, dentry)) { spin_unlock(&dentry->d_lock); - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); return 0; } } spin_unlock(&dentry->d_lock); - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); /* The kernfs parent node hasn't changed, leave the * dentry negative and return success. @@ -592,7 +592,7 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) } kn = kernfs_dentry_node(dentry); - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); /* The kernfs node has been deactivated */ if (!kernfs_active(kn)) @@ -611,10 +611,10 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) kernfs_info(dentry->d_sb)->ns != kn->ns) goto out_bad; - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); return 1; out_bad: - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); return 0; } @@ -809,7 +809,7 @@ int kernfs_add_one(struct kernfs_node *kn) bool has_ns; int ret; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); ret = -EINVAL; has_ns = kernfs_ns_enabled(parent); @@ -840,7 +840,7 @@ int kernfs_add_one(struct kernfs_node *kn) ps_iattr->ia_mtime = ps_iattr->ia_ctime; } - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); /* * Activate the new node unless CREATE_DEACTIVATED is requested. @@ -854,7 +854,7 @@ int kernfs_add_one(struct kernfs_node *kn) return 0; out_unlock: - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); return ret; } @@ -875,7 +875,7 @@ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, bool has_ns = kernfs_ns_enabled(parent); unsigned int hash; - lockdep_assert_held(&kernfs_mutex); + lockdep_assert_held(&kernfs_rwsem); if (has_ns != (bool)ns) { WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", @@ -907,7 +907,7 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, size_t len; char *p, *name; - lockdep_assert_held(&kernfs_mutex); + lockdep_assert_held_read(&kernfs_rwsem); spin_lock_irq(&kernfs_pr_cont_lock); @@ -946,10 +946,10 @@ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, { struct kernfs_node *kn; - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); kn = kernfs_find_ns(parent, name, ns); kernfs_get(kn); - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); return kn; } @@ -970,10 +970,10 @@ struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, { struct kernfs_node *kn; - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); kn = kernfs_walk_ns(parent, path, ns); kernfs_get(kn); - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); return kn; } @@ -1128,7 +1128,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, struct inode *inode = NULL; const void *ns = NULL; - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); if (kernfs_ns_enabled(parent)) ns = kernfs_info(dir->i_sb)->ns; @@ -1144,7 +1144,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, kernfs_set_rev(parent, dentry); /* instantiate and hash (possibly negative) dentry */ ret = d_splice_alias(inode, dentry); - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); return ret; } @@ -1264,7 +1264,7 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos, { struct rb_node *rbn; - lockdep_assert_held(&kernfs_mutex); + lockdep_assert_held_write(&kernfs_rwsem); /* if first iteration, visit leftmost descendant which may be root */ if (!pos) @@ -1300,7 +1300,7 @@ void kernfs_activate(struct kernfs_node *kn) { struct kernfs_node *pos; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); pos = NULL; while ((pos = kernfs_next_descendant_post(pos, kn))) { @@ -1314,14 +1314,14 @@ void kernfs_activate(struct kernfs_node *kn) pos->flags |= KERNFS_ACTIVATED; } - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); } static void __kernfs_remove(struct kernfs_node *kn) { struct kernfs_node *pos; - lockdep_assert_held(&kernfs_mutex); + lockdep_assert_held_write(&kernfs_rwsem); /* * Short-circuit if non-root @kn has already finished removal. @@ -1344,7 +1344,7 @@ static void __kernfs_remove(struct kernfs_node *kn) pos = kernfs_leftmost_descendant(kn); /* - * kernfs_drain() drops kernfs_mutex temporarily and @pos's + * kernfs_drain() drops kernfs_rwsem temporarily and @pos's * base ref could have been put by someone else by the time * the function returns. Make sure it doesn't go away * underneath us. @@ -1391,9 +1391,9 @@ static void __kernfs_remove(struct kernfs_node *kn) */ void kernfs_remove(struct kernfs_node *kn) { - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); __kernfs_remove(kn); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); } /** @@ -1480,17 +1480,17 @@ bool kernfs_remove_self(struct kernfs_node *kn) { bool ret; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); kernfs_break_active_protection(kn); /* * SUICIDAL is used to arbitrate among competing invocations. Only * the first one will actually perform removal. When the removal * is complete, SUICIDED is set and the active ref is restored - * while holding kernfs_mutex. The ones which lost arbitration - * waits for SUICDED && drained which can happen only after the - * enclosing kernfs operation which executed the winning instance - * of kernfs_remove_self() finished. + * while kernfs_rwsem for held exclusive. The ones which lost + * arbitration waits for SUICIDED && drained which can happen only + * after the enclosing kernfs operation which executed the winning + * instance of kernfs_remove_self() finished. */ if (!(kn->flags & KERNFS_SUICIDAL)) { kn->flags |= KERNFS_SUICIDAL; @@ -1508,9 +1508,9 @@ bool kernfs_remove_self(struct kernfs_node *kn) atomic_read(&kn->active) == KN_DEACTIVATED_BIAS) break; - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); schedule(); - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); } finish_wait(waitq, &wait); WARN_ON_ONCE(!RB_EMPTY_NODE(&kn->rb)); @@ -1518,12 +1518,12 @@ bool kernfs_remove_self(struct kernfs_node *kn) } /* - * This must be done while holding kernfs_mutex; otherwise, waiting - * for SUICIDED && deactivated could finish prematurely. + * This must be done while kernfs_rwsem held exclusive; otherwise, + * waiting for SUICIDED && deactivated could finish prematurely. */ kernfs_unbreak_active_protection(kn); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); return ret; } @@ -1547,7 +1547,7 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, return -ENOENT; } - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); kn = kernfs_find_ns(parent, name, ns); if (kn) { @@ -1556,7 +1556,7 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, kernfs_put(kn); } - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); if (kn) return 0; @@ -1582,7 +1582,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, if (!kn->parent) return -EINVAL; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); error = -ENOENT; if (!kernfs_active(kn) || !kernfs_active(new_parent) || @@ -1636,7 +1636,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, error = 0; out: - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); return error; } @@ -1711,7 +1711,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) if (!dir_emit_dots(file, ctx)) return 0; - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); if (kernfs_ns_enabled(parent)) ns = kernfs_info(dentry->d_sb)->ns; @@ -1728,12 +1728,12 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) file->private_data = pos; kernfs_get(pos); - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); if (!dir_emit(ctx, name, len, ino, type)) return 0; - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); } - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); file->private_data = NULL; ctx->pos = INT_MAX; return 0; diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index c75719312147..60e2a86c535e 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -860,7 +860,7 @@ static void kernfs_notify_workfn(struct work_struct *work) spin_unlock_irq(&kernfs_notify_lock); /* kick fsnotify */ - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct kernfs_node *parent; @@ -898,7 +898,7 @@ static void kernfs_notify_workfn(struct work_struct *work) iput(inode); } - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); kernfs_put(kn); goto repeat; } diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index fc2469a20fed..ddaf18198935 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -106,9 +106,9 @@ int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) { int ret; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); ret = __kernfs_setattr(kn, iattr); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); return ret; } @@ -121,7 +121,7 @@ int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr) if (!kn) return -EINVAL; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); error = setattr_prepare(dentry, iattr); if (error) goto out; @@ -134,7 +134,7 @@ int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr) setattr_copy(inode, iattr); out: - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); return error; } @@ -189,9 +189,9 @@ int kernfs_iop_getattr(const struct path *path, struct kstat *stat, struct inode *inode = d_inode(path->dentry); struct kernfs_node *kn = inode->i_private; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); kernfs_refresh_inode(kn, inode); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); generic_fillattr(inode, stat); return 0; @@ -281,9 +281,9 @@ int kernfs_iop_permission(struct inode *inode, int mask) kn = inode->i_private; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); kernfs_refresh_inode(kn, inode); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); return generic_permission(inode, mask); } diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 6a8d0ca26d03..c933d9bd8a78 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -13,6 +13,7 @@ #include <linux/lockdep.h> #include <linux/fs.h> #include <linux/mutex.h> +#include <linux/rwsem.h> #include <linux/xattr.h> #include <linux/kernfs.h> @@ -69,7 +70,7 @@ struct kernfs_super_info { */ const void *ns; - /* anchored at kernfs_root->supers, protected by kernfs_mutex */ + /* anchored at kernfs_root->supers, protected by kernfs_rwsem */ struct list_head node; }; #define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info)) @@ -118,7 +119,7 @@ int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); /* * dir.c */ -extern struct mutex kernfs_mutex; +extern struct rw_semaphore kernfs_rwsem; extern const struct dentry_operations kernfs_dops; extern const struct file_operations kernfs_dir_fops; extern const struct inode_operations kernfs_dir_iops; diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 9dc7e7a64e10..baa4155ba2ed 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -255,9 +255,9 @@ static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *k sb->s_shrink.seeks = 0; /* get root inode, initialize and unlock it */ - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); inode = kernfs_get_inode(sb, info->root->kn); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); if (!inode) { pr_debug("kernfs: could not get root inode\n"); return -ENOMEM; @@ -344,9 +344,9 @@ int kernfs_get_tree(struct fs_context *fc) } sb->s_flags |= SB_ACTIVE; - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); list_add(&info->node, &info->root->supers); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); } fc->root = dget(sb->s_root); @@ -372,9 +372,9 @@ void kernfs_kill_sb(struct super_block *sb) { struct kernfs_super_info *info = kernfs_info(sb); - mutex_lock(&kernfs_mutex); + down_write(&kernfs_rwsem); list_del(&info->node); - mutex_unlock(&kernfs_mutex); + up_write(&kernfs_rwsem); /* * Remove the superblock from fs_supers/s_instances diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index 5432883d819f..c8f8e41b8411 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -116,9 +116,9 @@ static int kernfs_getlink(struct inode *inode, char *path) struct kernfs_node *target = kn->symlink.target_kn; int error; - mutex_lock(&kernfs_mutex); + down_read(&kernfs_rwsem); error = kernfs_get_target_path(parent, target, path); - mutex_unlock(&kernfs_mutex); + up_read(&kernfs_rwsem); return error; } diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 236240a17017..f7dc6bb741a5 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -199,7 +199,7 @@ struct kernfs_root { u32 id_highbits; struct kernfs_syscall_ops *syscall_ops; - /* list of kernfs_super_info of this root, protected by kernfs_mutex */ + /* list of kernfs_super_info of this root, protected by kernfs_rwsem */ struct list_head supers; wait_queue_head_t deactivate_waitq; -- 2.39.2
From: Ian Kent <raven@themaw.net> mainline inclusion from mainline-v5.15-rc1 commit 47b5c64d0ab5e7136db2b78c6ec710e0d8a5a36b category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/ICRD6W Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- The inode operations .permission() and .getattr() use the kernfs node write lock but all that's needed is the read lock to protect against partial updates of these kernfs node fields which are all done under the write lock. And .permission() is called frequently during path walks and can cause quite a bit of contention between kernfs node operations and path walks when the number of concurrent walks is high. To change kernfs_iop_getattr() and kernfs_iop_permission() to take the rw sem read lock instead of the write lock an additional lock is needed to protect against multiple processes concurrently updating the inode attributes and link count in kernfs_refresh_inode(). The inode i_lock seems like the sensible thing to use to protect these inode attribute updates so use it in kernfs_refresh_inode(). The last hunk in the patch, applied to kernfs_fill_super(), is possibly not needed but taking the lock was present originally. I prefer to continue to take it to protect against a partial update of the source kernfs fields during the call to kernfs_refresh_inode() made by kernfs_get_inode(). Reviewed-by: Miklos Szeredi <mszeredi@redhat.com> Signed-off-by: Ian Kent <raven@themaw.net> Link: https://lore.kernel.org/r/162642771474.63632.16295959115893904470.stgit@web.... Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Conflicts: fs/kernfs/inode.c [Simple context conflict, direct adaptation.] Signed-off-by: Zizhi Wo <wozizhi@huawei.com> --- fs/kernfs/inode.c | 17 ++++++++++++----- fs/kernfs/mount.c | 4 ++-- 2 files changed, 14 insertions(+), 7 deletions(-) diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index ddaf18198935..702385efddea 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -189,11 +189,14 @@ int kernfs_iop_getattr(const struct path *path, struct kstat *stat, struct inode *inode = d_inode(path->dentry); struct kernfs_node *kn = inode->i_private; - down_write(&kernfs_rwsem); + down_read(&kernfs_rwsem); + spin_lock(&inode->i_lock); kernfs_refresh_inode(kn, inode); - up_write(&kernfs_rwsem); generic_fillattr(inode, stat); + spin_unlock(&inode->i_lock); + up_read(&kernfs_rwsem); + return 0; } @@ -275,17 +278,21 @@ void kernfs_evict_inode(struct inode *inode) int kernfs_iop_permission(struct inode *inode, int mask) { struct kernfs_node *kn; + int ret; if (mask & MAY_NOT_BLOCK) return -ECHILD; kn = inode->i_private; - down_write(&kernfs_rwsem); + down_read(&kernfs_rwsem); + spin_lock(&inode->i_lock); kernfs_refresh_inode(kn, inode); - up_write(&kernfs_rwsem); + ret = generic_permission(inode, mask); + spin_unlock(&inode->i_lock); + up_read(&kernfs_rwsem); - return generic_permission(inode, mask); + return ret; } int kernfs_xattr_get(struct kernfs_node *kn, const char *name, diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index baa4155ba2ed..f2f909d09f52 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -255,9 +255,9 @@ static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *k sb->s_shrink.seeks = 0; /* get root inode, initialize and unlock it */ - down_write(&kernfs_rwsem); + down_read(&kernfs_rwsem); inode = kernfs_get_inode(sb, info->root->kn); - up_write(&kernfs_rwsem); + up_read(&kernfs_rwsem); if (!inode) { pr_debug("kernfs: could not get root inode\n"); return -ENOMEM; -- 2.39.2
From: Ian Kent <raven@themaw.net> mainline inclusion from mainline-v5.15-rc1 commit df6192f47d2311cf40cd4321cc59863a5853b665 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/ICRD6W Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- The call to d_splice_alias() in kernfs_iop_lookup() doesn't depend on any kernfs node so there's no reason to hold the kernfs node lock when calling it. Reviewed-by: Miklos Szeredi <mszeredi@redhat.com> Signed-off-by: Ian Kent <raven@themaw.net> Link: https://lore.kernel.org/r/162642772000.63632.10672683419693513226.stgit@web.... Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Conflicts: fs/kernfs/dir.c [Simple context conflict, direct adaptation.] Signed-off-by: Zizhi Wo <wozizhi@huawei.com> --- fs/kernfs/dir.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 0443a9cd72a3..f301605d70b0 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1122,7 +1122,6 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { - struct dentry *ret; struct kernfs_node *parent = dir->i_private; struct kernfs_node *kn; struct inode *inode = NULL; @@ -1142,11 +1141,10 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, /* Needed only for negative dentry validation */ if (!inode) kernfs_set_rev(parent, dentry); - /* instantiate and hash (possibly negative) dentry */ - ret = d_splice_alias(inode, dentry); up_read(&kernfs_rwsem); - return ret; + /* instantiate and hash (possibly negative) dentry */ + return d_splice_alias(inode, dentry); } static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry, -- 2.39.2
From: Hou Tao <houtao1@huawei.com> mainline inclusion from mainline-v5.15-rc4 commit df38d852c6814cbbd010d81e84efb9dc057d5ba6 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/ICRD6W Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- A KMSAN warning is reported by Alexander Potapenko: BUG: KMSAN: uninit-value in kernfs_dop_revalidate+0x61f/0x840 fs/kernfs/dir.c:1053 kernfs_dop_revalidate+0x61f/0x840 fs/kernfs/dir.c:1053 d_revalidate fs/namei.c:854 lookup_dcache fs/namei.c:1522 __lookup_hash+0x3a6/0x590 fs/namei.c:1543 filename_create+0x312/0x7c0 fs/namei.c:3657 do_mkdirat+0x103/0x930 fs/namei.c:3900 __do_sys_mkdir fs/namei.c:3931 __se_sys_mkdir fs/namei.c:3929 __x64_sys_mkdir+0xda/0x120 fs/namei.c:3929 do_syscall_x64 arch/x86/entry/common.c:51 It seems a positive dentry in kernfs becomes a negative dentry directly through d_delete() in vfs_rmdir(). dentry->d_time is uninitialized when accessing it in kernfs_dop_revalidate(), because it is only initialized when created as negative dentry in kernfs_iop_lookup(). The problem can be reproduced by the following command: cd /sys/fs/cgroup/pids && mkdir hi && stat hi && rmdir hi && stat hi A simple fixes seems to be initializing d->d_time for positive dentry in kernfs_iop_lookup() as well. The downside is the negative dentry will be revalidated again after it becomes negative in d_delete(), because the revison of its parent must have been increased due to its removal. Alternative solution is implement .d_iput for kernfs, and assign d_time for the newly-generated negative dentry in it. But we may need to take kernfs_rwsem to protect again the concurrent kernfs_link_sibling() on the parent directory, it is a little over-killing. Now the simple fix is chosen. Link: https://marc.info/?l=linux-fsdevel&m=163249838610499 Fixes: c7e7c04274b1 ("kernfs: use VFS negative dentry caching") Reported-by: Alexander Potapenko <glider@google.com> Signed-off-by: Hou Tao <houtao1@huawei.com> Link: https://lore.kernel.org/r/20210928140750.1274441-1-houtao1@huawei.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Zizhi Wo <wozizhi@huawei.com> --- fs/kernfs/dir.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index f301605d70b0..abb45820396c 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1138,8 +1138,13 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, if (!inode) inode = ERR_PTR(-ENOMEM); } - /* Needed only for negative dentry validation */ - if (!inode) + /* + * Needed for negative dentry validation. + * The negative dentry can be created in kernfs_iop_lookup() + * or transforms from positive dentry in dentry_unlink_inode() + * called from vfs_rmdir(). + */ + if (!IS_ERR(inode)) kernfs_set_rev(parent, dentry); up_read(&kernfs_rwsem); -- 2.39.2
From: Ian Kent <raven@themaw.net> mainline inclusion from mainline-v5.15-rc6 commit 410d591a19543f1347bc2b4b4ec3399cb548ba47 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/ICRD6W Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- It's been reported that doing stress test for module insertion and removal can result in an ENOENT from libkmod for a valid module. In kernfs_iop_lookup() a negative dentry is created if there's no kernfs node associated with the dentry or the node is inactive. But inactive kernfs nodes are meant to be invisible to the VFS and creating a negative dentry for these can have unexpected side effects when the node transitions to an active state. The point of creating negative dentries is to avoid the expensive alloc/free cycle that occurs if there are frequent lookups for kernfs attributes that don't exist. So kernfs nodes that are not yet active should not result in a negative dentry being created so when they transition to an active state VFS lookups can create an associated dentry is a natural way. It's also been reported that https://github.com/osandov/blktests.git test block/001 hangs during the test. It was suggested that recent changes to blktests might have caused it but applying this patch resolved the problem without change to blktests. Fixes: c7e7c04274b1 ("kernfs: use VFS negative dentry caching") Tested-by: Yi Zhang <yi.zhang@redhat.com> ACKed-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Ian Kent <raven@themaw.net> Link: https://lore.kernel.org/r/163330943316.19450.15056895533949392922.stgit@mick... Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Zizhi Wo <wozizhi@huawei.com> --- fs/kernfs/dir.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index abb45820396c..1ea4763824c7 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1133,7 +1133,14 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, kn = kernfs_find_ns(parent, dentry->d_name.name, ns); /* attach dentry and inode */ - if (kn && kernfs_active(kn)) { + if (kn) { + /* Inactive nodes are invisible to the VFS so don't + * create a negative. + */ + if (!kernfs_active(kn)) { + up_read(&kernfs_rwsem); + return NULL; + } inode = kernfs_get_inode(dir->i_sb, kn); if (!inode) inode = ERR_PTR(-ENOMEM); -- 2.39.2
反馈: 您发送到kernel@openeuler.org的补丁/补丁集，转换为PR失败！ 邮件列表地址：https://mailweb.openeuler.org/archives/list/kernel@openeuler.org/message/DYK... 失败原因：补丁集缺失封面信息 建议解决方法：请提供补丁集并重新发送您的补丁集到邮件列表 FeedBack: The patch(es) which you have sent to kernel@openeuler.org has been converted to PR failed! Mailing list address: https://mailweb.openeuler.org/archives/list/kernel@openeuler.org/message/DYK... Failed Reason: the cover of the patches is missing Suggest Solution: please checkout and apply the patches' cover and send all again
participants (2)
-
patchwork bot -
Zizhi Wo