From: Ian Kent raven@themaw.net

Commit c7e7c04274b13f98f758fb69b03f2ab61976ea80 upstream.

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 --- 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; }

From: Ian Kent raven@themaw.net

Commit 7ba0273b2f34a55efe967d3c7381fb1da2ca195f upstream.

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 --- 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 195afa63ab1c..95e1948379d0 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -193,7 +193,7 @@ 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;

From: Ian Kent raven@themaw.net

Commit 47b5c64d0ab5e7136db2b78c6ec710e0d8a5a36b upstream.

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 --- fs/kernfs/inode.c | 18 ++++++++++++------ fs/kernfs/mount.c | 4 ++-- 2 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index ddaf18198935..73d7d4a24c51 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -189,11 +189,13 @@ 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 +277,21 @@ 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;

From: Ian Kent raven@themaw.net

Commit df6192f47d2311cf40cd4321cc59863a5853b665 upstream.

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 --- 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,