May 2025 - Linux-kselftest-mirror

[PATCH AUTOSEL 6.12 486/486] kernfs: Use RCU to access kernfs_node::parent.

by Sasha Levin

From: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> [ Upstream commit 633488947ef66b194377411322dc9e12aab79b65 ] kernfs_rename_lock is used to obtain stable kernfs_node::{name|parent} pointer. This is a preparation to access kernfs_node::parent under RCU and ensure that the pointer remains stable under the RCU lifetime guarantees. For a complete path, as it is done in kernfs_path_from_node(), the kernfs_rename_lock is still required in order to obtain a stable parent relationship while computing the relevant node depth. This must not change while the nodes are inspected in order to build the path. If the kernfs user never moves the nodes (changes the parent) then the kernfs_rename_lock is not required and the RCU guarantees are sufficient. This "restriction" can be set with KERNFS_ROOT_INVARIANT_PARENT. Otherwise the lock is required. Rename kernfs_node::parent to kernfs_node::__parent to denote the RCU access and use RCU accessor while accessing the node. Make cgroup use KERNFS_ROOT_INVARIANT_PARENT since the parent here can not change. Acked-by: Tejun Heo <tj(a)kernel.org> Cc: Yonghong Song <yonghong.song(a)linux.dev> Signed-off-by: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> Link: https://lore.kernel.org/r/20250213145023.2820193-6-bigeasy@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 65 +++++++++---- fs/kernfs/dir.c | 96 ++++++++++++------- fs/kernfs/kernfs-internal.h | 32 ++++++- fs/kernfs/mount.c | 10 +- fs/kernfs/symlink.c | 23 ++--- fs/sysfs/file.c | 24 +++-- include/linux/kernfs.h | 10 +- kernel/cgroup/cgroup-v1.c | 2 +- kernel/cgroup/cgroup.c | 24 ++++- .../selftests/bpf/progs/profiler.inc.h | 2 +- 10 files changed, 195 insertions(+), 93 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 2d48db66fca85..d4d7ccf1253b8 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -948,10 +948,20 @@ static int rdt_last_cmd_status_show(struct kernfs_open_file *of, return 0; } +static void *rdt_kn_parent_priv(struct kernfs_node *kn) +{ + /* + * The parent pointer is only valid within RCU section since it can be + * replaced. + */ + guard(rcu)(); + return rcu_dereference(kn->__parent)->priv; +} + static int rdt_num_closids_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); seq_printf(seq, "%u\n", s->num_closid); return 0; @@ -960,7 +970,7 @@ static int rdt_num_closids_show(struct kernfs_open_file *of, static int rdt_default_ctrl_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%x\n", r->default_ctrl); @@ -970,7 +980,7 @@ static int rdt_default_ctrl_show(struct kernfs_open_file *of, static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->cache.min_cbm_bits); @@ -980,7 +990,7 @@ static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, static int rdt_shareable_bits_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%x\n", r->cache.shareable_bits); @@ -1004,7 +1014,7 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of, static int rdt_bit_usage_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); /* * Use unsigned long even though only 32 bits are used to ensure * test_bit() is used safely. @@ -1086,7 +1096,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, static int rdt_min_bw_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->membw.min_bw); @@ -1096,7 +1106,7 @@ static int rdt_min_bw_show(struct kernfs_open_file *of, static int rdt_num_rmids_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); seq_printf(seq, "%d\n", r->num_rmid); @@ -1106,7 +1116,7 @@ static int rdt_num_rmids_show(struct kernfs_open_file *of, static int rdt_mon_features_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); struct mon_evt *mevt; list_for_each_entry(mevt, &r->evt_list, list) { @@ -1121,7 +1131,7 @@ static int rdt_mon_features_show(struct kernfs_open_file *of, static int rdt_bw_gran_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->membw.bw_gran); @@ -1131,7 +1141,7 @@ static int rdt_bw_gran_show(struct kernfs_open_file *of, static int rdt_delay_linear_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->membw.delay_linear); @@ -1149,7 +1159,7 @@ static int max_threshold_occ_show(struct kernfs_open_file *of, static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; if (r->membw.throttle_mode == THREAD_THROTTLE_PER_THREAD) @@ -1214,7 +1224,7 @@ static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type) static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks); @@ -1626,7 +1636,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid static int mbm_total_bytes_config_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID); @@ -1636,7 +1646,7 @@ static int mbm_total_bytes_config_show(struct kernfs_open_file *of, static int mbm_local_bytes_config_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID); @@ -1742,7 +1752,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); int ret; /* Valid input requires a trailing newline */ @@ -1768,7 +1778,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); int ret; /* Valid input requires a trailing newline */ @@ -2430,12 +2440,13 @@ static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn) * resource. "info" and its subdirectories don't * have rdtgroup structures, so return NULL here. */ - if (kn == kn_info || kn->parent == kn_info) + if (kn == kn_info || + rcu_access_pointer(kn->__parent) == kn_info) return NULL; else return kn->priv; } else { - return kn->parent->priv; + return rdt_kn_parent_priv(kn); } } @@ -3759,9 +3770,18 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) return 0; } +static struct kernfs_node *rdt_kn_parent(struct kernfs_node *kn) +{ + /* + * Valid within the RCU section it was obtained or while rdtgroup_mutex + * is held. + */ + return rcu_dereference_check(kn->__parent, lockdep_is_held(&rdtgroup_mutex)); +} + static int rdtgroup_rmdir(struct kernfs_node *kn) { - struct kernfs_node *parent_kn = kn->parent; + struct kernfs_node *parent_kn; struct rdtgroup *rdtgrp; cpumask_var_t tmpmask; int ret = 0; @@ -3774,6 +3794,7 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) ret = -EPERM; goto out; } + parent_kn = rdt_kn_parent(kn); /* * If the rdtgroup is a ctrl_mon group and parent directory @@ -3842,6 +3863,7 @@ static void mongrp_reparent(struct rdtgroup *rdtgrp, static int rdtgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name) { + struct kernfs_node *kn_parent; struct rdtgroup *new_prdtgrp; struct rdtgroup *rdtgrp; cpumask_var_t tmpmask; @@ -3876,8 +3898,9 @@ static int rdtgroup_rename(struct kernfs_node *kn, goto out; } - if (rdtgrp->type != RDTMON_GROUP || !kn->parent || - !is_mon_groups(kn->parent, kn->name)) { + kn_parent = rdt_kn_parent(kn); + if (rdtgrp->type != RDTMON_GROUP || !kn_parent || + !is_mon_groups(kn_parent, kn->name)) { rdt_last_cmd_puts("Source must be a MON group\n"); ret = -EPERM; goto out; diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 5a1fea414996e..d2306641b569c 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -17,7 +17,7 @@ #include "kernfs-internal.h" -static DEFINE_RWLOCK(kernfs_rename_lock); /* kn->parent and ->name */ +DEFINE_RWLOCK(kernfs_rename_lock); /* kn->parent and ->name */ /* * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to * call pr_cont() while holding rename_lock. Because sometimes pr_cont() @@ -56,7 +56,7 @@ static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen) if (!kn) return strscpy(buf, "(null)", buflen); - return strscpy(buf, kn->parent ? kn->name : "/", buflen); + return strscpy(buf, rcu_access_pointer(kn->__parent) ? kn->name : "/", buflen); } /* kernfs_node_depth - compute depth from @from to @to */ @@ -64,9 +64,9 @@ static size_t kernfs_depth(struct kernfs_node *from, struct kernfs_node *to) { size_t depth = 0; - while (to->parent && to != from) { + while (rcu_dereference(to->__parent) && to != from) { depth++; - to = to->parent; + to = rcu_dereference(to->__parent); } return depth; } @@ -84,18 +84,18 @@ static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a, db = kernfs_depth(rb->kn, b); while (da > db) { - a = a->parent; + a = rcu_dereference(a->__parent); da--; } while (db > da) { - b = b->parent; + b = rcu_dereference(b->__parent); db--; } /* worst case b and a will be the same at root */ while (b != a) { - b = b->parent; - a = a->parent; + b = rcu_dereference(b->__parent); + a = rcu_dereference(a->__parent); } return a; @@ -168,8 +168,9 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, /* Calculate how many bytes we need for the rest */ for (i = depth_to - 1; i >= 0; i--) { + for (kn = kn_to, j = 0; j < i; j++) - kn = kn->parent; + kn = rcu_dereference(kn->__parent); len += scnprintf(buf + len, buflen - len, "/%s", kn->name); } @@ -226,6 +227,7 @@ int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from, unsigned long flags; int ret; + guard(rcu)(); read_lock_irqsave(&kernfs_rename_lock, flags); ret = kernfs_path_from_node_locked(to, from, buf, buflen); read_unlock_irqrestore(&kernfs_rename_lock, flags); @@ -295,7 +297,7 @@ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) unsigned long flags; read_lock_irqsave(&kernfs_rename_lock, flags); - parent = kn->parent; + parent = kernfs_parent(kn); kernfs_get(parent); read_unlock_irqrestore(&kernfs_rename_lock, flags); @@ -360,8 +362,12 @@ static int kernfs_sd_compare(const struct kernfs_node *left, */ static int kernfs_link_sibling(struct kernfs_node *kn) { - struct rb_node **node = &kn->parent->dir.children.rb_node; struct rb_node *parent = NULL; + struct kernfs_node *kn_parent; + struct rb_node **node; + + kn_parent = kernfs_parent(kn); + node = &kn_parent->dir.children.rb_node; while (*node) { struct kernfs_node *pos; @@ -380,13 +386,13 @@ static int kernfs_link_sibling(struct kernfs_node *kn) /* add new node and rebalance the tree */ rb_link_node(&kn->rb, parent, node); - rb_insert_color(&kn->rb, &kn->parent->dir.children); + rb_insert_color(&kn->rb, &kn_parent->dir.children); /* successfully added, account subdir number */ down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); if (kernfs_type(kn) == KERNFS_DIR) - kn->parent->dir.subdirs++; - kernfs_inc_rev(kn->parent); + kn_parent->dir.subdirs++; + kernfs_inc_rev(kn_parent); up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); return 0; @@ -407,16 +413,19 @@ static int kernfs_link_sibling(struct kernfs_node *kn) */ static bool kernfs_unlink_sibling(struct kernfs_node *kn) { + struct kernfs_node *kn_parent; + if (RB_EMPTY_NODE(&kn->rb)) return false; + kn_parent = kernfs_parent(kn); down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); if (kernfs_type(kn) == KERNFS_DIR) - kn->parent->dir.subdirs--; - kernfs_inc_rev(kn->parent); + kn_parent->dir.subdirs--; + kernfs_inc_rev(kn_parent); up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); - rb_erase(&kn->rb, &kn->parent->dir.children); + rb_erase(&kn->rb, &kn_parent->dir.children); RB_CLEAR_NODE(&kn->rb); return true; } @@ -562,7 +571,7 @@ void kernfs_put(struct kernfs_node *kn) * Moving/renaming is always done while holding reference. * kn->parent won't change beneath us. */ - parent = kn->parent; + parent = kernfs_parent(kn); WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS, "kernfs_put: %s/%s: released with incorrect active_ref %d\n", @@ -701,7 +710,7 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, name, mode, uid, gid, flags); if (kn) { kernfs_get(parent); - kn->parent = parent; + rcu_assign_pointer(kn->__parent, parent); } return kn; } @@ -769,13 +778,14 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, */ int kernfs_add_one(struct kernfs_node *kn) { - struct kernfs_node *parent = kn->parent; - struct kernfs_root *root = kernfs_root(parent); + struct kernfs_root *root = kernfs_root(kn); struct kernfs_iattrs *ps_iattr; + struct kernfs_node *parent; bool has_ns; int ret; down_write(&root->kernfs_rwsem); + parent = kernfs_parent(kn); ret = -EINVAL; has_ns = kernfs_ns_enabled(parent); @@ -949,6 +959,11 @@ struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, return kn; } +unsigned int kernfs_root_flags(struct kernfs_node *kn) +{ + return kernfs_root(kn)->flags; +} + /** * kernfs_create_root - create a new kernfs hierarchy * @scops: optional syscall operations for the hierarchy @@ -1111,7 +1126,7 @@ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) { - struct kernfs_node *kn; + struct kernfs_node *kn, *parent; struct kernfs_root *root; if (flags & LOOKUP_RCU) @@ -1162,8 +1177,9 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) if (!kernfs_active(kn)) goto out_bad; + parent = kernfs_parent(kn); /* The kernfs node has been moved? */ - if (kernfs_dentry_node(dentry->d_parent) != kn->parent) + if (kernfs_dentry_node(dentry->d_parent) != parent) goto out_bad; /* The kernfs node has been renamed */ @@ -1171,7 +1187,7 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) goto out_bad; /* The kernfs node has been moved to a different namespace */ - if (kn->parent && kernfs_ns_enabled(kn->parent) && + if (parent && kernfs_ns_enabled(parent) && kernfs_info(dentry->d_sb)->ns != kn->ns) goto out_bad; @@ -1364,7 +1380,7 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos, return kernfs_leftmost_descendant(rb_to_kn(rbn)); /* no sibling left, visit parent */ - return pos->parent; + return kernfs_parent(pos); } static void kernfs_activate_one(struct kernfs_node *kn) @@ -1376,7 +1392,7 @@ static void kernfs_activate_one(struct kernfs_node *kn) if (kernfs_active(kn) || (kn->flags & (KERNFS_HIDDEN | KERNFS_REMOVING))) return; - WARN_ON_ONCE(kn->parent && RB_EMPTY_NODE(&kn->rb)); + WARN_ON_ONCE(rcu_access_pointer(kn->__parent) && RB_EMPTY_NODE(&kn->rb)); WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS); atomic_sub(KN_DEACTIVATED_BIAS, &kn->active); @@ -1446,7 +1462,7 @@ void kernfs_show(struct kernfs_node *kn, bool show) static void __kernfs_remove(struct kernfs_node *kn) { - struct kernfs_node *pos; + struct kernfs_node *pos, *parent; /* Short-circuit if non-root @kn has already finished removal. */ if (!kn) @@ -1458,7 +1474,7 @@ static void __kernfs_remove(struct kernfs_node *kn) * This is for kernfs_remove_self() which plays with active ref * after removal. */ - if (kn->parent && RB_EMPTY_NODE(&kn->rb)) + if (kernfs_parent(kn) && RB_EMPTY_NODE(&kn->rb)) return; pr_debug("kernfs %s: removing\n", kn->name); @@ -1484,14 +1500,14 @@ static void __kernfs_remove(struct kernfs_node *kn) kernfs_get(pos); kernfs_drain(pos); - + parent = kernfs_parent(pos); /* * kernfs_unlink_sibling() succeeds once per node. Use it * to decide who's responsible for cleanups. */ - if (!pos->parent || kernfs_unlink_sibling(pos)) { + if (!parent || kernfs_unlink_sibling(pos)) { struct kernfs_iattrs *ps_iattr = - pos->parent ? pos->parent->iattr : NULL; + parent ? parent->iattr : NULL; /* update timestamps on the parent */ down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); @@ -1721,7 +1737,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, int error; /* can't move or rename root */ - if (!kn->parent) + if (!rcu_access_pointer(kn->__parent)) return -EINVAL; root = kernfs_root(kn); @@ -1732,8 +1748,15 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, (new_parent->flags & KERNFS_EMPTY_DIR)) goto out; + old_parent = kernfs_parent(kn); + if (root->flags & KERNFS_ROOT_INVARIANT_PARENT) { + error = -EINVAL; + if (WARN_ON_ONCE(old_parent != new_parent)) + goto out; + } + error = 0; - if ((kn->parent == new_parent) && (kn->ns == new_ns) && + if ((old_parent == new_parent) && (kn->ns == new_ns) && (strcmp(kn->name, new_name) == 0)) goto out; /* nothing to rename */ @@ -1760,8 +1783,8 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, /* rename_lock protects ->parent and ->name accessors */ write_lock_irq(&kernfs_rename_lock); - old_parent = kn->parent; - kn->parent = new_parent; + old_parent = kernfs_parent(kn); + rcu_assign_pointer(kn->__parent, new_parent); kn->ns = new_ns; if (new_name) { @@ -1794,7 +1817,8 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns, { if (pos) { int valid = kernfs_active(pos) && - pos->parent == parent && hash == pos->hash; + rcu_access_pointer(pos->__parent) == parent && + hash == pos->hash; kernfs_put(pos); if (!valid) pos = NULL; diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index b42ee6547cdc1..c43bee18b79f7 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -19,6 +19,8 @@ #include <linux/kernfs.h> #include <linux/fs_context.h> +extern rwlock_t kernfs_rename_lock; + struct kernfs_iattrs { kuid_t ia_uid; kgid_t ia_gid; @@ -64,11 +66,14 @@ struct kernfs_root { * * Return: the kernfs_root @kn belongs to. */ -static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn) +static inline struct kernfs_root *kernfs_root(const struct kernfs_node *kn) { + const struct kernfs_node *knp; /* if parent exists, it's always a dir; otherwise, @sd is a dir */ - if (kn->parent) - kn = kn->parent; + guard(rcu)(); + knp = rcu_dereference(kn->__parent); + if (knp) + kn = knp; return kn->dir.root; } @@ -97,6 +102,27 @@ struct kernfs_super_info { }; #define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info)) +static inline bool kernfs_root_is_locked(const struct kernfs_node *kn) +{ + return lockdep_is_held(&kernfs_root(kn)->kernfs_rwsem); +} + +static inline struct kernfs_node *kernfs_parent(const struct kernfs_node *kn) +{ + /* + * The kernfs_node::__parent remains valid within a RCU section. The kn + * can be reparented (and renamed) which changes the entry. This can be + * avoided by locking kernfs_root::kernfs_rwsem or kernfs_rename_lock. + * Both locks can be used to obtain a reference on __parent. Once the + * reference count reaches 0 then the node is about to be freed + * and can not be renamed (or become a different parent) anymore. + */ + return rcu_dereference_check(kn->__parent, + kernfs_root_is_locked(kn) || + lockdep_is_held(&kernfs_rename_lock) || + !atomic_read(&kn->count)); +} + static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry) { if (d_really_is_negative(dentry)) diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 4a0ff08d589ca..2252b16e6ef0b 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -148,7 +148,7 @@ static struct dentry *kernfs_get_parent_dentry(struct dentry *child) struct kernfs_root *root = kernfs_root(kn); guard(rwsem_read)(&root->kernfs_rwsem); - return d_obtain_alias(kernfs_get_inode(child->d_sb, kn->parent)); + return d_obtain_alias(kernfs_get_inode(child->d_sb, kernfs_parent(kn))); } static const struct export_operations kernfs_export_ops = { @@ -188,10 +188,10 @@ static struct kernfs_node *find_next_ancestor(struct kernfs_node *child, return NULL; } - while (child->parent != parent) { - if (!child->parent) + while (kernfs_parent(child) != parent) { + child = kernfs_parent(child); + if (!child) return NULL; - child = child->parent; } return child; @@ -216,7 +216,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, dentry = dget(sb->s_root); /* Check if this is the root kernfs_node */ - if (!kn->parent) + if (!rcu_access_pointer(kn->__parent)) return dentry; root = kernfs_root(kn); diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index 45371a70caa71..05c62ca93c53d 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -62,10 +62,10 @@ static int kernfs_get_target_path(struct kernfs_node *parent, /* go up to the root, stop at the base */ base = parent; - while (base->parent) { - kn = target->parent; - while (kn->parent && base != kn) - kn = kn->parent; + while (kernfs_parent(base)) { + kn = kernfs_parent(target); + while (kernfs_parent(kn) && base != kn) + kn = kernfs_parent(kn); if (base == kn) break; @@ -75,14 +75,14 @@ static int kernfs_get_target_path(struct kernfs_node *parent, strcpy(s, "../"); s += 3; - base = base->parent; + base = kernfs_parent(base); } /* determine end of target string for reverse fillup */ kn = target; - while (kn->parent && kn != base) { + while (kernfs_parent(kn) && kn != base) { len += strlen(kn->name) + 1; - kn = kn->parent; + kn = kernfs_parent(kn); } /* check limits */ @@ -94,7 +94,7 @@ static int kernfs_get_target_path(struct kernfs_node *parent, /* reverse fillup of target string from target to base */ kn = target; - while (kn->parent && kn != base) { + while (kernfs_parent(kn) && kn != base) { int slen = strlen(kn->name); len -= slen; @@ -102,7 +102,7 @@ static int kernfs_get_target_path(struct kernfs_node *parent, if (len) s[--len] = '/'; - kn = kn->parent; + kn = kernfs_parent(kn); } return 0; @@ -111,12 +111,13 @@ static int kernfs_get_target_path(struct kernfs_node *parent, static int kernfs_getlink(struct inode *inode, char *path) { struct kernfs_node *kn = inode->i_private; - struct kernfs_node *parent = kn->parent; + struct kernfs_node *parent; struct kernfs_node *target = kn->symlink.target_kn; - struct kernfs_root *root = kernfs_root(parent); + struct kernfs_root *root = kernfs_root(kn); int error; down_read(&root->kernfs_rwsem); + parent = kernfs_parent(kn); error = kernfs_get_target_path(parent, target, path); up_read(&root->kernfs_rwsem); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index d1995e2d6c943..3671a3fd60198 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -19,13 +19,19 @@ #include "sysfs.h" +static struct kobject *sysfs_file_kobj(struct kernfs_node *kn) +{ + guard(rcu)(); + return rcu_dereference(kn->__parent)->priv; +} + /* * Determine ktype->sysfs_ops for the given kernfs_node. This function * must be called while holding an active reference. */ static const struct sysfs_ops *sysfs_file_ops(struct kernfs_node *kn) { - struct kobject *kobj = kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(kn); if (kn->flags & KERNFS_LOCKDEP) lockdep_assert_held(kn); @@ -40,7 +46,7 @@ static const struct sysfs_ops *sysfs_file_ops(struct kernfs_node *kn) static int sysfs_kf_seq_show(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); const struct sysfs_ops *ops = sysfs_file_ops(of->kn); ssize_t count; char *buf; @@ -78,7 +84,7 @@ static ssize_t sysfs_kf_bin_read(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { struct bin_attribute *battr = of->kn->priv; - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); loff_t size = file_inode(of->file)->i_size; if (!count) @@ -102,7 +108,7 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); ssize_t len; /* @@ -128,7 +134,7 @@ static ssize_t sysfs_kf_write(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); if (!count) return 0; @@ -141,7 +147,7 @@ static ssize_t sysfs_kf_bin_write(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { struct bin_attribute *battr = of->kn->priv; - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); loff_t size = file_inode(of->file)->i_size; if (size) { @@ -162,7 +168,7 @@ static int sysfs_kf_bin_mmap(struct kernfs_open_file *of, struct vm_area_struct *vma) { struct bin_attribute *battr = of->kn->priv; - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); return battr->mmap(of->file, kobj, battr, vma); } @@ -171,7 +177,7 @@ static loff_t sysfs_kf_bin_llseek(struct kernfs_open_file *of, loff_t offset, int whence) { struct bin_attribute *battr = of->kn->priv; - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); if (battr->llseek) return battr->llseek(of->file, kobj, battr, offset, whence); @@ -482,7 +488,7 @@ EXPORT_SYMBOL_GPL(sysfs_break_active_protection); */ void sysfs_unbreak_active_protection(struct kernfs_node *kn) { - struct kobject *kobj = kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(kn); kernfs_unbreak_active_protection(kn); kernfs_put(kn); diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 87c79d076d6d7..5dda9a268e44c 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -147,6 +147,11 @@ enum kernfs_root_flag { * Support user xattrs to be written to nodes rooted at this root. */ KERNFS_ROOT_SUPPORT_USER_XATTR = 0x0008, + + /* + * Renames must not change the parent node. + */ + KERNFS_ROOT_INVARIANT_PARENT = 0x0010, }; /* type-specific structures for kernfs_node union members */ @@ -199,8 +204,8 @@ struct kernfs_node { * never moved to a different parent, it is safe to access the * parent directly. */ - struct kernfs_node *parent; const char *name; + struct kernfs_node __rcu *__parent; struct rb_node rb; @@ -416,6 +421,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv); void kernfs_destroy_root(struct kernfs_root *root); +unsigned int kernfs_root_flags(struct kernfs_node *kn); struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, @@ -514,6 +520,8 @@ kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, { return ERR_PTR(-ENOSYS); } static inline void kernfs_destroy_root(struct kernfs_root *root) { } +static inline unsigned int kernfs_root_flags(struct kernfs_node *kn) +{ return 0; } static inline struct kernfs_node * kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index e28d5f0d20ed0..c9752eb607ec9 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -844,7 +844,7 @@ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent if (kernfs_type(kn) != KERNFS_DIR) return -ENOTDIR; - if (kn->parent != new_parent) + if (rcu_access_pointer(kn->__parent) != new_parent) return -EIO; /* diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index e63d6f3b00470..fc152691a6b42 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -633,9 +633,22 @@ int cgroup_task_count(const struct cgroup *cgrp) return count; } +static struct cgroup *kn_priv(struct kernfs_node *kn) +{ + struct kernfs_node *parent; + /* + * The parent can not be replaced due to KERNFS_ROOT_INVARIANT_PARENT. + * Therefore it is always safe to dereference this pointer outside of a + * RCU section. + */ + parent = rcu_dereference_check(kn->__parent, + kernfs_root_flags(kn) & KERNFS_ROOT_INVARIANT_PARENT); + return parent->priv; +} + struct cgroup_subsys_state *of_css(struct kernfs_open_file *of) { - struct cgroup *cgrp = of->kn->parent->priv; + struct cgroup *cgrp = kn_priv(of->kn); struct cftype *cft = of_cft(of); /* @@ -1612,7 +1625,7 @@ void cgroup_kn_unlock(struct kernfs_node *kn) if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else - cgrp = kn->parent->priv; + cgrp = kn_priv(kn); cgroup_unlock(); @@ -1644,7 +1657,7 @@ struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline) if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else - cgrp = kn->parent->priv; + cgrp = kn_priv(kn); /* * We're gonna grab cgroup_mutex which nests outside kernfs @@ -2118,7 +2131,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) root->kf_root = kernfs_create_root(kf_sops, KERNFS_ROOT_CREATE_DEACTIVATED | KERNFS_ROOT_SUPPORT_EXPORTOP | - KERNFS_ROOT_SUPPORT_USER_XATTR, + KERNFS_ROOT_SUPPORT_USER_XATTR | + KERNFS_ROOT_INVARIANT_PARENT, root_cgrp); if (IS_ERR(root->kf_root)) { ret = PTR_ERR(root->kf_root); @@ -4144,7 +4158,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup_file_ctx *ctx = of->priv; - struct cgroup *cgrp = of->kn->parent->priv; + struct cgroup *cgrp = kn_priv(of->kn); struct cftype *cft = of_cft(of); struct cgroup_subsys_state *css; int ret; diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index 8bd1ebd7d6afd..813143b4985dc 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -223,7 +223,7 @@ static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node, if (bpf_cmp_likely(filepart_length, <=, MAX_PATH)) { payload += filepart_length; } - cgroup_node = BPF_CORE_READ(cgroup_node, parent); + cgroup_node = BPF_CORE_READ(cgroup_node, __parent); } return payload; } -- 2.39.5

1 month, 1 week

1
0
0 0

[PATCH AUTOSEL 6.12 428/486] bridge: mdb: Allow replace of a host-joined group

by Sasha Levin

From: Petr Machata <petrm(a)nvidia.com> [ Upstream commit d9e9f6d7b7d0c520bb87f19d2cbc57aeeb2091d5 ] Attempts to replace an MDB group membership of the host itself are currently bounced: # ip link add name br up type bridge vlan_filtering 1 # bridge mdb replace dev br port br grp 239.0.0.1 vid 2 # bridge mdb replace dev br port br grp 239.0.0.1 vid 2 Error: bridge: Group is already joined by host. A similar operation done on a member port would succeed. Ignore the check for replacement of host group memberships as well. The bit of code that this enables is br_multicast_host_join(), which, for already-joined groups only refreshes the MC group expiration timer, which is desirable; and a userspace notification, also desirable. Change a selftest that exercises this code path from expecting a rejection to expecting a pass. The rest of MDB selftests pass without modification. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Ido Schimmel <idosch(a)nvidia.com> Acked-by: Nikolay Aleksandrov <razor(a)blackwall.org> Link: https://patch.msgid.link/e5c5188b9787ae806609e7ca3aa2a0a501b9b5c4.173868564… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- net/bridge/br_mdb.c | 2 +- tools/testing/selftests/net/forwarding/bridge_mdb.sh | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 1a52a0bca086d..7e1ad229e1330 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -1040,7 +1040,7 @@ static int br_mdb_add_group(const struct br_mdb_config *cfg, /* host join */ if (!port) { - if (mp->host_joined) { + if (mp->host_joined && !(cfg->nlflags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "Group is already joined by host"); return -EEXIST; } diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index d9d587454d207..8c1597ebc2d38 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -149,7 +149,7 @@ cfg_test_host_common() check_err $? "Failed to add $name host entry" bridge mdb replace dev br0 port br0 grp $grp $state vid 10 &> /dev/null - check_fail $? "Managed to replace $name host entry" + check_err $? "Failed to replace $name host entry" bridge mdb del dev br0 port br0 grp $grp $state vid 10 bridge mdb get dev br0 grp $grp vid 10 &> /dev/null -- 2.39.5

1 month, 1 week

1
0
0 0

[PATCH AUTOSEL 6.12 334/486] kunit: tool: Use qboot on QEMU x86_64

by Sasha Levin

From: Brendan Jackman <jackmanb(a)google.com> [ Upstream commit 08fafac4c9f289a9d9a22d838921e4b3eb22c664 ] As noted in [0], SeaBIOS (QEMU default) makes a mess of the terminal, qboot does not. It turns out this is actually useful with kunit.py, since the user is exposed to this issue if they set --raw_output=all. qboot is also faster than SeaBIOS, but it's is marginal for this usecase. [0] https://lore.kernel.org/all/CA+i-1C0wYb-gZ8Mwh3WSVpbk-LF-Uo+njVbASJPe1WXDUR… Both SeaBIOS and qboot are x86-specific. Link: https://lore.kernel.org/r/20250124-kunit-qboot-v1-1-815e4d4c6f7c@google.com Signed-off-by: Brendan Jackman <jackmanb(a)google.com> Reviewed-by: David Gow <davidgow(a)google.com> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/kunit/qemu_configs/x86_64.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/kunit/qemu_configs/x86_64.py b/tools/testing/kunit/qemu_configs/x86_64.py index dc79490768630..4a6bf4e048f5b 100644 --- a/tools/testing/kunit/qemu_configs/x86_64.py +++ b/tools/testing/kunit/qemu_configs/x86_64.py @@ -7,4 +7,6 @@ CONFIG_SERIAL_8250_CONSOLE=y''', qemu_arch='x86_64', kernel_path='arch/x86/boot/bzImage', kernel_command_line='console=ttyS0', - extra_qemu_params=[]) + # qboot is faster than SeaBIOS and doesn't mess up + # the terminal. + extra_qemu_params=['-bios', 'qboot.rom']) -- 2.39.5

1 month, 1 week

1
0
0 0

[PATCH AUTOSEL 6.12 239/486] selftests/net: have `gro.sh -t` return a correct exit code

by Sasha Levin

From: Kevin Krakauer <krakauer(a)google.com> [ Upstream commit 784e6abd99f24024a8998b5916795f0bec9d2fd9 ] Modify gro.sh to return a useful exit code when the -t flag is used. It formerly returned 0 no matter what. Tested: Ran `gro.sh -t large` and verified that test failures return 1. Signed-off-by: Kevin Krakauer <krakauer(a)google.com> Reviewed-by: Willem de Bruijn <willemb(a)google.com> Link: https://patch.msgid.link/20250226192725.621969-2-krakauer@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/net/gro.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh index 02c21ff4ca81f..aabd6e5480b8e 100755 --- a/tools/testing/selftests/net/gro.sh +++ b/tools/testing/selftests/net/gro.sh @@ -100,5 +100,6 @@ trap cleanup EXIT if [[ "${test}" == "all" ]]; then run_all_tests else - run_test "${proto}" "${test}" + exit_code=$(run_test "${proto}" "${test}") + exit $exit_code fi; -- 2.39.5

1 month, 1 week

1
0
0 0

[PATCH AUTOSEL 6.12 210/486] iommufd: Disallow allocating nested parent domain with fault ID

by Sasha Levin

From: Yi Liu <yi.l.liu(a)intel.com> [ Upstream commit 1062d81086156e42878d701b816d2f368b53a77c ] Allocating a domain with a fault ID indicates that the domain is faultable. However, there is a gap for the nested parent domain to support PRI. Some hardware lacks the capability to distinguish whether PRI occurs at stage 1 or stage 2. This limitation may require software-based page table walking to resolve. Since no in-tree IOMMU driver currently supports this functionality, it is disallowed. For more details, refer to the related discussion at [1]. [1] https://lore.kernel.org/linux-iommu/bd1655c6-8b2f-4cfa-adb1-badc00d01811@in… Link: https://patch.msgid.link/r/20250226104012.82079-1-yi.l.liu@intel.com Suggested-by: Lu Baolu <baolu.lu(a)linux.intel.com> Signed-off-by: Yi Liu <yi.l.liu(a)intel.com> Reviewed-by: Kevin Tian <kevin.tian(a)intel.com> Reviewed-by: Lu Baolu <baolu.lu(a)linux.intel.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/iommu/iommufd/hw_pagetable.c | 3 +++ tools/testing/selftests/iommu/iommufd.c | 4 ++++ 2 files changed, 7 insertions(+) diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index d06bf6e6c19fd..2454627a8b61b 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -122,6 +122,9 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, if ((flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING) && !device_iommu_capable(idev->dev, IOMMU_CAP_DIRTY_TRACKING)) return ERR_PTR(-EOPNOTSUPP); + if ((flags & IOMMU_HWPT_FAULT_ID_VALID) && + (flags & IOMMU_HWPT_ALLOC_NEST_PARENT)) + return ERR_PTR(-EOPNOTSUPP); hwpt_paging = __iommufd_object_alloc( ictx, hwpt_paging, IOMMUFD_OBJ_HWPT_PAGING, common.obj); diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 4927b9add5add..06f252733660a 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -289,6 +289,10 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested) &test_hwpt_id); test_err_hwpt_alloc(EINVAL, self->device_id, self->device_id, 0, &test_hwpt_id); + test_err_hwpt_alloc(EOPNOTSUPP, self->device_id, self->ioas_id, + IOMMU_HWPT_ALLOC_NEST_PARENT | + IOMMU_HWPT_FAULT_ID_VALID, + &test_hwpt_id); test_cmd_hwpt_alloc(self->device_id, self->ioas_id, IOMMU_HWPT_ALLOC_NEST_PARENT, -- 2.39.5

1 month, 1 week

1
0
0 0

[PATCH AUTOSEL 6.14 633/642] kernfs: Use RCU to access kernfs_node::parent.

by Sasha Levin

From: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> [ Upstream commit 633488947ef66b194377411322dc9e12aab79b65 ] kernfs_rename_lock is used to obtain stable kernfs_node::{name|parent} pointer. This is a preparation to access kernfs_node::parent under RCU and ensure that the pointer remains stable under the RCU lifetime guarantees. For a complete path, as it is done in kernfs_path_from_node(), the kernfs_rename_lock is still required in order to obtain a stable parent relationship while computing the relevant node depth. This must not change while the nodes are inspected in order to build the path. If the kernfs user never moves the nodes (changes the parent) then the kernfs_rename_lock is not required and the RCU guarantees are sufficient. This "restriction" can be set with KERNFS_ROOT_INVARIANT_PARENT. Otherwise the lock is required. Rename kernfs_node::parent to kernfs_node::__parent to denote the RCU access and use RCU accessor while accessing the node. Make cgroup use KERNFS_ROOT_INVARIANT_PARENT since the parent here can not change. Acked-by: Tejun Heo <tj(a)kernel.org> Cc: Yonghong Song <yonghong.song(a)linux.dev> Signed-off-by: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> Link: https://lore.kernel.org/r/20250213145023.2820193-6-bigeasy@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Stable-dep-of: 6ef5b6fae304 ("kernfs: Drop kernfs_rwsem while invoking lookup_positive_unlocked().") Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 65 +++++++++---- fs/kernfs/dir.c | 96 ++++++++++++------- fs/kernfs/kernfs-internal.h | 32 ++++++- fs/kernfs/mount.c | 10 +- fs/kernfs/symlink.c | 23 ++--- fs/sysfs/file.c | 24 +++-- include/linux/kernfs.h | 10 +- kernel/cgroup/cgroup-v1.c | 2 +- kernel/cgroup/cgroup.c | 24 ++++- .../selftests/bpf/progs/profiler.inc.h | 2 +- 10 files changed, 195 insertions(+), 93 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 04b653d613e88..3d2a850ea737d 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -957,10 +957,20 @@ static int rdt_last_cmd_status_show(struct kernfs_open_file *of, return 0; } +static void *rdt_kn_parent_priv(struct kernfs_node *kn) +{ + /* + * The parent pointer is only valid within RCU section since it can be + * replaced. + */ + guard(rcu)(); + return rcu_dereference(kn->__parent)->priv; +} + static int rdt_num_closids_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); seq_printf(seq, "%u\n", s->num_closid); return 0; @@ -969,7 +979,7 @@ static int rdt_num_closids_show(struct kernfs_open_file *of, static int rdt_default_ctrl_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%x\n", r->default_ctrl); @@ -979,7 +989,7 @@ static int rdt_default_ctrl_show(struct kernfs_open_file *of, static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->cache.min_cbm_bits); @@ -989,7 +999,7 @@ static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, static int rdt_shareable_bits_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%x\n", r->cache.shareable_bits); @@ -1013,7 +1023,7 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of, static int rdt_bit_usage_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); /* * Use unsigned long even though only 32 bits are used to ensure * test_bit() is used safely. @@ -1095,7 +1105,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, static int rdt_min_bw_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->membw.min_bw); @@ -1105,7 +1115,7 @@ static int rdt_min_bw_show(struct kernfs_open_file *of, static int rdt_num_rmids_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); seq_printf(seq, "%d\n", r->num_rmid); @@ -1115,7 +1125,7 @@ static int rdt_num_rmids_show(struct kernfs_open_file *of, static int rdt_mon_features_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); struct mon_evt *mevt; list_for_each_entry(mevt, &r->evt_list, list) { @@ -1130,7 +1140,7 @@ static int rdt_mon_features_show(struct kernfs_open_file *of, static int rdt_bw_gran_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->membw.bw_gran); @@ -1140,7 +1150,7 @@ static int rdt_bw_gran_show(struct kernfs_open_file *of, static int rdt_delay_linear_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->membw.delay_linear); @@ -1158,7 +1168,7 @@ static int max_threshold_occ_show(struct kernfs_open_file *of, static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; if (r->membw.throttle_mode == THREAD_THROTTLE_PER_THREAD) @@ -1223,7 +1233,7 @@ static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type) static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct resctrl_schema *s = of->kn->parent->priv; + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); struct rdt_resource *r = s->res; seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks); @@ -1635,7 +1645,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid static int mbm_total_bytes_config_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID); @@ -1645,7 +1655,7 @@ static int mbm_total_bytes_config_show(struct kernfs_open_file *of, static int mbm_local_bytes_config_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID); @@ -1751,7 +1761,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); int ret; /* Valid input requires a trailing newline */ @@ -1777,7 +1787,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - struct rdt_resource *r = of->kn->parent->priv; + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); int ret; /* Valid input requires a trailing newline */ @@ -2441,12 +2451,13 @@ static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn) * resource. "info" and its subdirectories don't * have rdtgroup structures, so return NULL here. */ - if (kn == kn_info || kn->parent == kn_info) + if (kn == kn_info || + rcu_access_pointer(kn->__parent) == kn_info) return NULL; else return kn->priv; } else { - return kn->parent->priv; + return rdt_kn_parent_priv(kn); } } @@ -3772,9 +3783,18 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) return 0; } +static struct kernfs_node *rdt_kn_parent(struct kernfs_node *kn) +{ + /* + * Valid within the RCU section it was obtained or while rdtgroup_mutex + * is held. + */ + return rcu_dereference_check(kn->__parent, lockdep_is_held(&rdtgroup_mutex)); +} + static int rdtgroup_rmdir(struct kernfs_node *kn) { - struct kernfs_node *parent_kn = kn->parent; + struct kernfs_node *parent_kn; struct rdtgroup *rdtgrp; cpumask_var_t tmpmask; int ret = 0; @@ -3787,6 +3807,7 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) ret = -EPERM; goto out; } + parent_kn = rdt_kn_parent(kn); /* * If the rdtgroup is a ctrl_mon group and parent directory @@ -3855,6 +3876,7 @@ static void mongrp_reparent(struct rdtgroup *rdtgrp, static int rdtgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name) { + struct kernfs_node *kn_parent; struct rdtgroup *new_prdtgrp; struct rdtgroup *rdtgrp; cpumask_var_t tmpmask; @@ -3889,8 +3911,9 @@ static int rdtgroup_rename(struct kernfs_node *kn, goto out; } - if (rdtgrp->type != RDTMON_GROUP || !kn->parent || - !is_mon_groups(kn->parent, kn->name)) { + kn_parent = rdt_kn_parent(kn); + if (rdtgrp->type != RDTMON_GROUP || !kn_parent || + !is_mon_groups(kn_parent, kn->name)) { rdt_last_cmd_puts("Source must be a MON group\n"); ret = -EPERM; goto out; diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 43fbada678381..1d370c497e8a3 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -17,7 +17,7 @@ #include "kernfs-internal.h" -static DEFINE_RWLOCK(kernfs_rename_lock); /* kn->parent and ->name */ +DEFINE_RWLOCK(kernfs_rename_lock); /* kn->parent and ->name */ /* * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to * call pr_cont() while holding rename_lock. Because sometimes pr_cont() @@ -56,7 +56,7 @@ static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen) if (!kn) return strscpy(buf, "(null)", buflen); - return strscpy(buf, kn->parent ? kn->name : "/", buflen); + return strscpy(buf, rcu_access_pointer(kn->__parent) ? kn->name : "/", buflen); } /* kernfs_node_depth - compute depth from @from to @to */ @@ -64,9 +64,9 @@ static size_t kernfs_depth(struct kernfs_node *from, struct kernfs_node *to) { size_t depth = 0; - while (to->parent && to != from) { + while (rcu_dereference(to->__parent) && to != from) { depth++; - to = to->parent; + to = rcu_dereference(to->__parent); } return depth; } @@ -84,18 +84,18 @@ static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a, db = kernfs_depth(rb->kn, b); while (da > db) { - a = a->parent; + a = rcu_dereference(a->__parent); da--; } while (db > da) { - b = b->parent; + b = rcu_dereference(b->__parent); db--; } /* worst case b and a will be the same at root */ while (b != a) { - b = b->parent; - a = a->parent; + b = rcu_dereference(b->__parent); + a = rcu_dereference(a->__parent); } return a; @@ -168,8 +168,9 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, /* Calculate how many bytes we need for the rest */ for (i = depth_to - 1; i >= 0; i--) { + for (kn = kn_to, j = 0; j < i; j++) - kn = kn->parent; + kn = rcu_dereference(kn->__parent); len += scnprintf(buf + len, buflen - len, "/%s", kn->name); } @@ -226,6 +227,7 @@ int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from, unsigned long flags; int ret; + guard(rcu)(); read_lock_irqsave(&kernfs_rename_lock, flags); ret = kernfs_path_from_node_locked(to, from, buf, buflen); read_unlock_irqrestore(&kernfs_rename_lock, flags); @@ -295,7 +297,7 @@ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) unsigned long flags; read_lock_irqsave(&kernfs_rename_lock, flags); - parent = kn->parent; + parent = kernfs_parent(kn); kernfs_get(parent); read_unlock_irqrestore(&kernfs_rename_lock, flags); @@ -360,8 +362,12 @@ static int kernfs_sd_compare(const struct kernfs_node *left, */ static int kernfs_link_sibling(struct kernfs_node *kn) { - struct rb_node **node = &kn->parent->dir.children.rb_node; struct rb_node *parent = NULL; + struct kernfs_node *kn_parent; + struct rb_node **node; + + kn_parent = kernfs_parent(kn); + node = &kn_parent->dir.children.rb_node; while (*node) { struct kernfs_node *pos; @@ -380,13 +386,13 @@ static int kernfs_link_sibling(struct kernfs_node *kn) /* add new node and rebalance the tree */ rb_link_node(&kn->rb, parent, node); - rb_insert_color(&kn->rb, &kn->parent->dir.children); + rb_insert_color(&kn->rb, &kn_parent->dir.children); /* successfully added, account subdir number */ down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); if (kernfs_type(kn) == KERNFS_DIR) - kn->parent->dir.subdirs++; - kernfs_inc_rev(kn->parent); + kn_parent->dir.subdirs++; + kernfs_inc_rev(kn_parent); up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); return 0; @@ -407,16 +413,19 @@ static int kernfs_link_sibling(struct kernfs_node *kn) */ static bool kernfs_unlink_sibling(struct kernfs_node *kn) { + struct kernfs_node *kn_parent; + if (RB_EMPTY_NODE(&kn->rb)) return false; + kn_parent = kernfs_parent(kn); down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); if (kernfs_type(kn) == KERNFS_DIR) - kn->parent->dir.subdirs--; - kernfs_inc_rev(kn->parent); + kn_parent->dir.subdirs--; + kernfs_inc_rev(kn_parent); up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); - rb_erase(&kn->rb, &kn->parent->dir.children); + rb_erase(&kn->rb, &kn_parent->dir.children); RB_CLEAR_NODE(&kn->rb); return true; } @@ -562,7 +571,7 @@ void kernfs_put(struct kernfs_node *kn) * Moving/renaming is always done while holding reference. * kn->parent won't change beneath us. */ - parent = kn->parent; + parent = kernfs_parent(kn); WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS, "kernfs_put: %s/%s: released with incorrect active_ref %d\n", @@ -701,7 +710,7 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, name, mode, uid, gid, flags); if (kn) { kernfs_get(parent); - kn->parent = parent; + rcu_assign_pointer(kn->__parent, parent); } return kn; } @@ -769,13 +778,14 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, */ int kernfs_add_one(struct kernfs_node *kn) { - struct kernfs_node *parent = kn->parent; - struct kernfs_root *root = kernfs_root(parent); + struct kernfs_root *root = kernfs_root(kn); struct kernfs_iattrs *ps_iattr; + struct kernfs_node *parent; bool has_ns; int ret; down_write(&root->kernfs_rwsem); + parent = kernfs_parent(kn); ret = -EINVAL; has_ns = kernfs_ns_enabled(parent); @@ -949,6 +959,11 @@ struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, return kn; } +unsigned int kernfs_root_flags(struct kernfs_node *kn) +{ + return kernfs_root(kn)->flags; +} + /** * kernfs_create_root - create a new kernfs hierarchy * @scops: optional syscall operations for the hierarchy @@ -1112,7 +1127,7 @@ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, static int kernfs_dop_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { - struct kernfs_node *kn; + struct kernfs_node *kn, *parent; struct kernfs_root *root; if (flags & LOOKUP_RCU) @@ -1163,8 +1178,9 @@ static int kernfs_dop_revalidate(struct inode *dir, const struct qstr *name, if (!kernfs_active(kn)) goto out_bad; + parent = kernfs_parent(kn); /* The kernfs node has been moved? */ - if (kernfs_dentry_node(dentry->d_parent) != kn->parent) + if (kernfs_dentry_node(dentry->d_parent) != parent) goto out_bad; /* The kernfs node has been renamed */ @@ -1172,7 +1188,7 @@ static int kernfs_dop_revalidate(struct inode *dir, const struct qstr *name, goto out_bad; /* The kernfs node has been moved to a different namespace */ - if (kn->parent && kernfs_ns_enabled(kn->parent) && + if (parent && kernfs_ns_enabled(parent) && kernfs_info(dentry->d_sb)->ns != kn->ns) goto out_bad; @@ -1365,7 +1381,7 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos, return kernfs_leftmost_descendant(rb_to_kn(rbn)); /* no sibling left, visit parent */ - return pos->parent; + return kernfs_parent(pos); } static void kernfs_activate_one(struct kernfs_node *kn) @@ -1377,7 +1393,7 @@ static void kernfs_activate_one(struct kernfs_node *kn) if (kernfs_active(kn) || (kn->flags & (KERNFS_HIDDEN | KERNFS_REMOVING))) return; - WARN_ON_ONCE(kn->parent && RB_EMPTY_NODE(&kn->rb)); + WARN_ON_ONCE(rcu_access_pointer(kn->__parent) && RB_EMPTY_NODE(&kn->rb)); WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS); atomic_sub(KN_DEACTIVATED_BIAS, &kn->active); @@ -1447,7 +1463,7 @@ void kernfs_show(struct kernfs_node *kn, bool show) static void __kernfs_remove(struct kernfs_node *kn) { - struct kernfs_node *pos; + struct kernfs_node *pos, *parent; /* Short-circuit if non-root @kn has already finished removal. */ if (!kn) @@ -1459,7 +1475,7 @@ static void __kernfs_remove(struct kernfs_node *kn) * This is for kernfs_remove_self() which plays with active ref * after removal. */ - if (kn->parent && RB_EMPTY_NODE(&kn->rb)) + if (kernfs_parent(kn) && RB_EMPTY_NODE(&kn->rb)) return; pr_debug("kernfs %s: removing\n", kn->name); @@ -1485,14 +1501,14 @@ static void __kernfs_remove(struct kernfs_node *kn) kernfs_get(pos); kernfs_drain(pos); - + parent = kernfs_parent(pos); /* * kernfs_unlink_sibling() succeeds once per node. Use it * to decide who's responsible for cleanups. */ - if (!pos->parent || kernfs_unlink_sibling(pos)) { + if (!parent || kernfs_unlink_sibling(pos)) { struct kernfs_iattrs *ps_iattr = - pos->parent ? pos->parent->iattr : NULL; + parent ? parent->iattr : NULL; /* update timestamps on the parent */ down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); @@ -1722,7 +1738,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, int error; /* can't move or rename root */ - if (!kn->parent) + if (!rcu_access_pointer(kn->__parent)) return -EINVAL; root = kernfs_root(kn); @@ -1733,8 +1749,15 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, (new_parent->flags & KERNFS_EMPTY_DIR)) goto out; + old_parent = kernfs_parent(kn); + if (root->flags & KERNFS_ROOT_INVARIANT_PARENT) { + error = -EINVAL; + if (WARN_ON_ONCE(old_parent != new_parent)) + goto out; + } + error = 0; - if ((kn->parent == new_parent) && (kn->ns == new_ns) && + if ((old_parent == new_parent) && (kn->ns == new_ns) && (strcmp(kn->name, new_name) == 0)) goto out; /* nothing to rename */ @@ -1761,8 +1784,8 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, /* rename_lock protects ->parent and ->name accessors */ write_lock_irq(&kernfs_rename_lock); - old_parent = kn->parent; - kn->parent = new_parent; + old_parent = kernfs_parent(kn); + rcu_assign_pointer(kn->__parent, new_parent); kn->ns = new_ns; if (new_name) { @@ -1795,7 +1818,8 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns, { if (pos) { int valid = kernfs_active(pos) && - pos->parent == parent && hash == pos->hash; + rcu_access_pointer(pos->__parent) == parent && + hash == pos->hash; kernfs_put(pos); if (!valid) pos = NULL; diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index b42ee6547cdc1..c43bee18b79f7 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -19,6 +19,8 @@ #include <linux/kernfs.h> #include <linux/fs_context.h> +extern rwlock_t kernfs_rename_lock; + struct kernfs_iattrs { kuid_t ia_uid; kgid_t ia_gid; @@ -64,11 +66,14 @@ struct kernfs_root { * * Return: the kernfs_root @kn belongs to. */ -static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn) +static inline struct kernfs_root *kernfs_root(const struct kernfs_node *kn) { + const struct kernfs_node *knp; /* if parent exists, it's always a dir; otherwise, @sd is a dir */ - if (kn->parent) - kn = kn->parent; + guard(rcu)(); + knp = rcu_dereference(kn->__parent); + if (knp) + kn = knp; return kn->dir.root; } @@ -97,6 +102,27 @@ struct kernfs_super_info { }; #define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info)) +static inline bool kernfs_root_is_locked(const struct kernfs_node *kn) +{ + return lockdep_is_held(&kernfs_root(kn)->kernfs_rwsem); +} + +static inline struct kernfs_node *kernfs_parent(const struct kernfs_node *kn) +{ + /* + * The kernfs_node::__parent remains valid within a RCU section. The kn + * can be reparented (and renamed) which changes the entry. This can be + * avoided by locking kernfs_root::kernfs_rwsem or kernfs_rename_lock. + * Both locks can be used to obtain a reference on __parent. Once the + * reference count reaches 0 then the node is about to be freed + * and can not be renamed (or become a different parent) anymore. + */ + return rcu_dereference_check(kn->__parent, + kernfs_root_is_locked(kn) || + lockdep_is_held(&kernfs_rename_lock) || + !atomic_read(&kn->count)); +} + static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry) { if (d_really_is_negative(dentry)) diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 4a0ff08d589ca..2252b16e6ef0b 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -148,7 +148,7 @@ static struct dentry *kernfs_get_parent_dentry(struct dentry *child) struct kernfs_root *root = kernfs_root(kn); guard(rwsem_read)(&root->kernfs_rwsem); - return d_obtain_alias(kernfs_get_inode(child->d_sb, kn->parent)); + return d_obtain_alias(kernfs_get_inode(child->d_sb, kernfs_parent(kn))); } static const struct export_operations kernfs_export_ops = { @@ -188,10 +188,10 @@ static struct kernfs_node *find_next_ancestor(struct kernfs_node *child, return NULL; } - while (child->parent != parent) { - if (!child->parent) + while (kernfs_parent(child) != parent) { + child = kernfs_parent(child); + if (!child) return NULL; - child = child->parent; } return child; @@ -216,7 +216,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, dentry = dget(sb->s_root); /* Check if this is the root kernfs_node */ - if (!kn->parent) + if (!rcu_access_pointer(kn->__parent)) return dentry; root = kernfs_root(kn); diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index 45371a70caa71..05c62ca93c53d 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -62,10 +62,10 @@ static int kernfs_get_target_path(struct kernfs_node *parent, /* go up to the root, stop at the base */ base = parent; - while (base->parent) { - kn = target->parent; - while (kn->parent && base != kn) - kn = kn->parent; + while (kernfs_parent(base)) { + kn = kernfs_parent(target); + while (kernfs_parent(kn) && base != kn) + kn = kernfs_parent(kn); if (base == kn) break; @@ -75,14 +75,14 @@ static int kernfs_get_target_path(struct kernfs_node *parent, strcpy(s, "../"); s += 3; - base = base->parent; + base = kernfs_parent(base); } /* determine end of target string for reverse fillup */ kn = target; - while (kn->parent && kn != base) { + while (kernfs_parent(kn) && kn != base) { len += strlen(kn->name) + 1; - kn = kn->parent; + kn = kernfs_parent(kn); } /* check limits */ @@ -94,7 +94,7 @@ static int kernfs_get_target_path(struct kernfs_node *parent, /* reverse fillup of target string from target to base */ kn = target; - while (kn->parent && kn != base) { + while (kernfs_parent(kn) && kn != base) { int slen = strlen(kn->name); len -= slen; @@ -102,7 +102,7 @@ static int kernfs_get_target_path(struct kernfs_node *parent, if (len) s[--len] = '/'; - kn = kn->parent; + kn = kernfs_parent(kn); } return 0; @@ -111,12 +111,13 @@ static int kernfs_get_target_path(struct kernfs_node *parent, static int kernfs_getlink(struct inode *inode, char *path) { struct kernfs_node *kn = inode->i_private; - struct kernfs_node *parent = kn->parent; + struct kernfs_node *parent; struct kernfs_node *target = kn->symlink.target_kn; - struct kernfs_root *root = kernfs_root(parent); + struct kernfs_root *root = kernfs_root(kn); int error; down_read(&root->kernfs_rwsem); + parent = kernfs_parent(kn); error = kernfs_get_target_path(parent, target, path); up_read(&root->kernfs_rwsem); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 6931308876c4a..c3d3b079aedde 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -19,13 +19,19 @@ #include "sysfs.h" +static struct kobject *sysfs_file_kobj(struct kernfs_node *kn) +{ + guard(rcu)(); + return rcu_dereference(kn->__parent)->priv; +} + /* * Determine ktype->sysfs_ops for the given kernfs_node. This function * must be called while holding an active reference. */ static const struct sysfs_ops *sysfs_file_ops(struct kernfs_node *kn) { - struct kobject *kobj = kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(kn); if (kn->flags & KERNFS_LOCKDEP) lockdep_assert_held(kn); @@ -40,7 +46,7 @@ static const struct sysfs_ops *sysfs_file_ops(struct kernfs_node *kn) static int sysfs_kf_seq_show(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); const struct sysfs_ops *ops = sysfs_file_ops(of->kn); ssize_t count; char *buf; @@ -78,7 +84,7 @@ static ssize_t sysfs_kf_bin_read(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { struct bin_attribute *battr = of->kn->priv; - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); loff_t size = file_inode(of->file)->i_size; if (!count) @@ -105,7 +111,7 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); ssize_t len; /* @@ -131,7 +137,7 @@ static ssize_t sysfs_kf_write(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); if (!count) return 0; @@ -144,7 +150,7 @@ static ssize_t sysfs_kf_bin_write(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { struct bin_attribute *battr = of->kn->priv; - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); loff_t size = file_inode(of->file)->i_size; if (size) { @@ -168,7 +174,7 @@ static int sysfs_kf_bin_mmap(struct kernfs_open_file *of, struct vm_area_struct *vma) { struct bin_attribute *battr = of->kn->priv; - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); return battr->mmap(of->file, kobj, battr, vma); } @@ -177,7 +183,7 @@ static loff_t sysfs_kf_bin_llseek(struct kernfs_open_file *of, loff_t offset, int whence) { struct bin_attribute *battr = of->kn->priv; - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); if (battr->llseek) return battr->llseek(of->file, kobj, battr, offset, whence); @@ -494,7 +500,7 @@ EXPORT_SYMBOL_GPL(sysfs_break_active_protection); */ void sysfs_unbreak_active_protection(struct kernfs_node *kn) { - struct kobject *kobj = kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(kn); kernfs_unbreak_active_protection(kn); kernfs_put(kn); diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 87c79d076d6d7..5dda9a268e44c 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -147,6 +147,11 @@ enum kernfs_root_flag { * Support user xattrs to be written to nodes rooted at this root. */ KERNFS_ROOT_SUPPORT_USER_XATTR = 0x0008, + + /* + * Renames must not change the parent node. + */ + KERNFS_ROOT_INVARIANT_PARENT = 0x0010, }; /* type-specific structures for kernfs_node union members */ @@ -199,8 +204,8 @@ struct kernfs_node { * never moved to a different parent, it is safe to access the * parent directly. */ - struct kernfs_node *parent; const char *name; + struct kernfs_node __rcu *__parent; struct rb_node rb; @@ -416,6 +421,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv); void kernfs_destroy_root(struct kernfs_root *root); +unsigned int kernfs_root_flags(struct kernfs_node *kn); struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, @@ -514,6 +520,8 @@ kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, { return ERR_PTR(-ENOSYS); } static inline void kernfs_destroy_root(struct kernfs_root *root) { } +static inline unsigned int kernfs_root_flags(struct kernfs_node *kn) +{ return 0; } static inline struct kernfs_node * kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index e28d5f0d20ed0..c9752eb607ec9 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -844,7 +844,7 @@ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent if (kernfs_type(kn) != KERNFS_DIR) return -ENOTDIR; - if (kn->parent != new_parent) + if (rcu_access_pointer(kn->__parent) != new_parent) return -EIO; /* diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 68d58753c75c3..ddaaeddf1afa8 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -633,9 +633,22 @@ int cgroup_task_count(const struct cgroup *cgrp) return count; } +static struct cgroup *kn_priv(struct kernfs_node *kn) +{ + struct kernfs_node *parent; + /* + * The parent can not be replaced due to KERNFS_ROOT_INVARIANT_PARENT. + * Therefore it is always safe to dereference this pointer outside of a + * RCU section. + */ + parent = rcu_dereference_check(kn->__parent, + kernfs_root_flags(kn) & KERNFS_ROOT_INVARIANT_PARENT); + return parent->priv; +} + struct cgroup_subsys_state *of_css(struct kernfs_open_file *of) { - struct cgroup *cgrp = of->kn->parent->priv; + struct cgroup *cgrp = kn_priv(of->kn); struct cftype *cft = of_cft(of); /* @@ -1612,7 +1625,7 @@ void cgroup_kn_unlock(struct kernfs_node *kn) if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else - cgrp = kn->parent->priv; + cgrp = kn_priv(kn); cgroup_unlock(); @@ -1644,7 +1657,7 @@ struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline) if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else - cgrp = kn->parent->priv; + cgrp = kn_priv(kn); /* * We're gonna grab cgroup_mutex which nests outside kernfs @@ -2118,7 +2131,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) root->kf_root = kernfs_create_root(kf_sops, KERNFS_ROOT_CREATE_DEACTIVATED | KERNFS_ROOT_SUPPORT_EXPORTOP | - KERNFS_ROOT_SUPPORT_USER_XATTR, + KERNFS_ROOT_SUPPORT_USER_XATTR | + KERNFS_ROOT_INVARIANT_PARENT, root_cgrp); if (IS_ERR(root->kf_root)) { ret = PTR_ERR(root->kf_root); @@ -4144,7 +4158,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup_file_ctx *ctx = of->priv; - struct cgroup *cgrp = of->kn->parent->priv; + struct cgroup *cgrp = kn_priv(of->kn); struct cftype *cft = of_cft(of); struct cgroup_subsys_state *css; int ret; diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index 8bd1ebd7d6afd..813143b4985dc 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -223,7 +223,7 @@ static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node, if (bpf_cmp_likely(filepart_length, <=, MAX_PATH)) { payload += filepart_length; } - cgroup_node = BPF_CORE_READ(cgroup_node, parent); + cgroup_node = BPF_CORE_READ(cgroup_node, __parent); } return payload; } -- 2.39.5

1 month, 1 week

1
0
0 0

[PATCH AUTOSEL 6.14 551/642] bridge: mdb: Allow replace of a host-joined group

by Sasha Levin

From: Petr Machata <petrm(a)nvidia.com> [ Upstream commit d9e9f6d7b7d0c520bb87f19d2cbc57aeeb2091d5 ] Attempts to replace an MDB group membership of the host itself are currently bounced: # ip link add name br up type bridge vlan_filtering 1 # bridge mdb replace dev br port br grp 239.0.0.1 vid 2 # bridge mdb replace dev br port br grp 239.0.0.1 vid 2 Error: bridge: Group is already joined by host. A similar operation done on a member port would succeed. Ignore the check for replacement of host group memberships as well. The bit of code that this enables is br_multicast_host_join(), which, for already-joined groups only refreshes the MC group expiration timer, which is desirable; and a userspace notification, also desirable. Change a selftest that exercises this code path from expecting a rejection to expecting a pass. The rest of MDB selftests pass without modification. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Ido Schimmel <idosch(a)nvidia.com> Acked-by: Nikolay Aleksandrov <razor(a)blackwall.org> Link: https://patch.msgid.link/e5c5188b9787ae806609e7ca3aa2a0a501b9b5c4.173868564… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- net/bridge/br_mdb.c | 2 +- tools/testing/selftests/net/forwarding/bridge_mdb.sh | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 1a52a0bca086d..7e1ad229e1330 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -1040,7 +1040,7 @@ static int br_mdb_add_group(const struct br_mdb_config *cfg, /* host join */ if (!port) { - if (mp->host_joined) { + if (mp->host_joined && !(cfg->nlflags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "Group is already joined by host"); return -EEXIST; } diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index d9d587454d207..8c1597ebc2d38 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -149,7 +149,7 @@ cfg_test_host_common() check_err $? "Failed to add $name host entry" bridge mdb replace dev br0 port br0 grp $grp $state vid 10 &> /dev/null - check_fail $? "Managed to replace $name host entry" + check_err $? "Failed to replace $name host entry" bridge mdb del dev br0 port br0 grp $grp $state vid 10 bridge mdb get dev br0 grp $grp vid 10 &> /dev/null -- 2.39.5

1 month, 1 week

1
0
0 0

[PATCH AUTOSEL 6.14 533/642] netdevsim: allow normal queue reset while down

by Sasha Levin

From: Jakub Kicinski <kuba(a)kernel.org> [ Upstream commit 285b3f78eabd951e59e98f01f86abaaa6c76cd44 ] Resetting queues while the device is down should be legal. Allow it, test it. Ideally we'd test this with a real device supporting devmem but I don't have access to such devices. Reviewed-by: Mina Almasry <almasrymina(a)google.com> Link: https://patch.msgid.link/20250206225638.1387810-5-kuba@kernel.org Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/net/netdevsim/netdev.c | 10 ++++------ tools/testing/selftests/net/nl_netdev.py | 18 +++++++++++++++++- 2 files changed, 21 insertions(+), 7 deletions(-) diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index e4c0d77849b82..a41dc79e9c2e0 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -664,8 +664,11 @@ nsim_queue_mem_alloc(struct net_device *dev, void *per_queue_mem, int idx) if (ns->rq_reset_mode > 3) return -EINVAL; - if (ns->rq_reset_mode == 1) + if (ns->rq_reset_mode == 1) { + if (!netif_running(ns->netdev)) + return -ENETDOWN; return nsim_create_page_pool(&qmem->pp, &ns->rq[idx]->napi); + } qmem->rq = nsim_queue_alloc(); if (!qmem->rq) @@ -773,11 +776,6 @@ nsim_qreset_write(struct file *file, const char __user *data, return -EINVAL; rtnl_lock(); - if (!netif_running(ns->netdev)) { - ret = -ENETDOWN; - goto exit_unlock; - } - if (queue >= ns->netdev->real_num_rx_queues) { ret = -EINVAL; goto exit_unlock; diff --git a/tools/testing/selftests/net/nl_netdev.py b/tools/testing/selftests/net/nl_netdev.py index 93e8cb671c3d9..beaee5e4e2aab 100755 --- a/tools/testing/selftests/net/nl_netdev.py +++ b/tools/testing/selftests/net/nl_netdev.py @@ -35,6 +35,21 @@ def napi_list_check(nf) -> None: comment=f"queue count after reset queue {q} mode {i}") +def nsim_rxq_reset_down(nf) -> None: + """ + Test that the queue API supports resetting a queue + while the interface is down. We should convert this + test to testing real HW once more devices support + queue API. + """ + with NetdevSimDev(queue_count=4) as nsimdev: + nsim = nsimdev.nsims[0] + + ip(f"link set dev {nsim.ifname} down") + for i in [0, 2, 3]: + nsim.dfs_write("queue_reset", f"1 {i}") + + def page_pool_check(nf) -> None: with NetdevSimDev() as nsimdev: nsim = nsimdev.nsims[0] @@ -106,7 +121,8 @@ def page_pool_check(nf) -> None: def main() -> None: nf = NetdevFamily() - ksft_run([empty_check, lo_check, page_pool_check, napi_list_check], + ksft_run([empty_check, lo_check, page_pool_check, napi_list_check, + nsim_rxq_reset_down], args=(nf, )) ksft_exit() -- 2.39.5

1 month, 1 week

1
0
0 0

[PATCH AUTOSEL 6.14 423/642] kunit: tool: Use qboot on QEMU x86_64

by Sasha Levin

From: Brendan Jackman <jackmanb(a)google.com> [ Upstream commit 08fafac4c9f289a9d9a22d838921e4b3eb22c664 ] As noted in [0], SeaBIOS (QEMU default) makes a mess of the terminal, qboot does not. It turns out this is actually useful with kunit.py, since the user is exposed to this issue if they set --raw_output=all. qboot is also faster than SeaBIOS, but it's is marginal for this usecase. [0] https://lore.kernel.org/all/CA+i-1C0wYb-gZ8Mwh3WSVpbk-LF-Uo+njVbASJPe1WXDUR… Both SeaBIOS and qboot are x86-specific. Link: https://lore.kernel.org/r/20250124-kunit-qboot-v1-1-815e4d4c6f7c@google.com Signed-off-by: Brendan Jackman <jackmanb(a)google.com> Reviewed-by: David Gow <davidgow(a)google.com> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/kunit/qemu_configs/x86_64.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/kunit/qemu_configs/x86_64.py b/tools/testing/kunit/qemu_configs/x86_64.py index dc79490768630..4a6bf4e048f5b 100644 --- a/tools/testing/kunit/qemu_configs/x86_64.py +++ b/tools/testing/kunit/qemu_configs/x86_64.py @@ -7,4 +7,6 @@ CONFIG_SERIAL_8250_CONSOLE=y''', qemu_arch='x86_64', kernel_path='arch/x86/boot/bzImage', kernel_command_line='console=ttyS0', - extra_qemu_params=[]) + # qboot is faster than SeaBIOS and doesn't mess up + # the terminal. + extra_qemu_params=['-bios', 'qboot.rom']) -- 2.39.5

1 month, 1 week

1
0
0 0

[PATCH AUTOSEL 6.14 300/642] selftests/net: have `gro.sh -t` return a correct exit code

by Sasha Levin

From: Kevin Krakauer <krakauer(a)google.com> [ Upstream commit 784e6abd99f24024a8998b5916795f0bec9d2fd9 ] Modify gro.sh to return a useful exit code when the -t flag is used. It formerly returned 0 no matter what. Tested: Ran `gro.sh -t large` and verified that test failures return 1. Signed-off-by: Kevin Krakauer <krakauer(a)google.com> Reviewed-by: Willem de Bruijn <willemb(a)google.com> Link: https://patch.msgid.link/20250226192725.621969-2-krakauer@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/net/gro.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh index 02c21ff4ca81f..aabd6e5480b8e 100755 --- a/tools/testing/selftests/net/gro.sh +++ b/tools/testing/selftests/net/gro.sh @@ -100,5 +100,6 @@ trap cleanup EXIT if [[ "${test}" == "all" ]]; then run_all_tests else - run_test "${proto}" "${test}" + exit_code=$(run_test "${proto}" "${test}") + exit $exit_code fi; -- 2.39.5

1 month, 1 week

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror May 2025