From db53c73a8b5db120cb741d7d932cdf831a576e8f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 4 Nov 2019 15:54:29 -0800 Subject: netprio: use css ID instead of cgroup ID netprio uses cgroup ID to index the priority mapping table. This is currently okay as cgroup IDs are allocated using idr and packed. However, cgroup IDs will be changed to use full 64bit range and won't be packed making this impractical. netprio doesn't care what type of IDs it uses as long as they can identify the controller instances and are packed. Let's switch to css IDs instead of cgroup IDs. Signed-off-by: Tejun Heo Acked-by: Neil Horman Reviewed-by: Greg Kroah-Hartman Cc: "David S. Miller" Cc: Namhyung Kim --- net/core/netprio_cgroup.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net/core') diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 256b7954b720..8881dd943dd0 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -93,7 +93,7 @@ static int extend_netdev_table(struct net_device *dev, u32 target_idx) static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev) { struct netprio_map *map = rcu_dereference_rtnl(dev->priomap); - int id = css->cgroup->id; + int id = css->id; if (map && id < map->priomap_len) return map->priomap[id]; @@ -113,7 +113,7 @@ static int netprio_set_prio(struct cgroup_subsys_state *css, struct net_device *dev, u32 prio) { struct netprio_map *map; - int id = css->cgroup->id; + int id = css->id; int ret; /* avoid extending priomap for zero writes */ @@ -177,7 +177,7 @@ static void cgrp_css_free(struct cgroup_subsys_state *css) static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft) { - return css->cgroup->id; + return css->id; } static int read_priomap(struct seq_file *sf, void *v) @@ -237,7 +237,7 @@ static void net_prio_attach(struct cgroup_taskset *tset) struct cgroup_subsys_state *css; cgroup_taskset_for_each(p, css, tset) { - void *v = (void *)(unsigned long)css->cgroup->id; + void *v = (void *)(unsigned long)css->id; task_lock(p); iterate_fd(p->files, 0, update_netprio, v); -- cgit v1.2.3-59-g8ed1b From 67c0496e87d193b8356d2af49ab95e8a1b954b3c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 4 Nov 2019 15:54:30 -0800 Subject: kernfs: convert kernfs_node->id from union kernfs_node_id to u64 kernfs_node->id is currently a union kernfs_node_id which represents either a 32bit (ino, gen) pair or u64 value. I can't see much value in the usage of the union - all that's needed is a 64bit ID which the current code is already limited to. Using a union makes the code unnecessarily complicated and prevents using 64bit ino without adding practical benefits. This patch drops union kernfs_node_id and makes kernfs_node->id a u64. ino is stored in the lower 32bits and gen upper. Accessors - kernfs[_id]_ino() and kernfs[_id]_gen() - are added to retrieve the ino and gen. This simplifies ID handling less cumbersome and will allow using 64bit inos on supported archs. This patch doesn't make any functional changes. Signed-off-by: Tejun Heo Reviewed-by: Greg Kroah-Hartman Cc: Namhyung Kim Cc: Jens Axboe Cc: Alexei Starovoitov --- fs/kernfs/dir.c | 10 +++--- fs/kernfs/file.c | 4 +-- fs/kernfs/inode.c | 4 +-- fs/kernfs/mount.c | 7 ++--- include/linux/cgroup.h | 17 +++++----- include/linux/kernfs.h | 45 ++++++++++++++++----------- include/trace/events/writeback.h | 4 +-- kernel/bpf/helpers.c | 2 +- kernel/bpf/local_storage.c | 2 +- kernel/cgroup/cgroup.c | 3 +- kernel/trace/blktrace.c | 67 +++++++++++++++++++--------------------- net/core/filter.c | 4 +-- 12 files changed, 85 insertions(+), 84 deletions(-) (limited to 'net/core') diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index beabb585a7d8..c67afb591e5b 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -532,7 +532,7 @@ void kernfs_put(struct kernfs_node *kn) kmem_cache_free(kernfs_iattrs_cache, kn->iattr); } spin_lock(&kernfs_idr_lock); - idr_remove(&root->ino_idr, kn->id.ino); + idr_remove(&root->ino_idr, kernfs_ino(kn)); spin_unlock(&kernfs_idr_lock); kmem_cache_free(kernfs_node_cache, kn); @@ -639,8 +639,8 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, idr_preload_end(); if (ret < 0) goto err_out2; - kn->id.ino = ret; - kn->id.generation = gen; + + kn->id = (u64)gen << 32 | ret; atomic_set(&kn->count, 1); atomic_set(&kn->active, KN_DEACTIVATED_BIAS); @@ -671,7 +671,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, return kn; err_out3: - idr_remove(&root->ino_idr, kn->id.ino); + idr_remove(&root->ino_idr, kernfs_ino(kn)); err_out2: kmem_cache_free(kernfs_node_cache, kn); err_out1: @@ -1656,7 +1656,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) const char *name = pos->name; unsigned int type = dt_type(pos); int len = strlen(name); - ino_t ino = pos->id.ino; + ino_t ino = kernfs_ino(pos); ctx->pos = pos->hash; file->private_data = pos; diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index e8c792b49616..34366db3620d 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -892,7 +892,7 @@ repeat: * have the matching @file available. Look up the inodes * and generate the events manually. */ - inode = ilookup(info->sb, kn->id.ino); + inode = ilookup(info->sb, kernfs_ino(kn)); if (!inode) continue; @@ -901,7 +901,7 @@ repeat: if (parent) { struct inode *p_inode; - p_inode = ilookup(info->sb, parent->id.ino); + p_inode = ilookup(info->sb, kernfs_ino(parent)); if (p_inode) { fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD, inode, FSNOTIFY_EVENT_INODE, &name, 0); diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index f3eaa8869f42..eac277c63d42 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -201,7 +201,7 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode) inode->i_private = kn; inode->i_mapping->a_ops = &kernfs_aops; inode->i_op = &kernfs_iops; - inode->i_generation = kn->id.generation; + inode->i_generation = kernfs_gen(kn); set_default_inode_attr(inode, kn->mode); kernfs_refresh_inode(kn, inode); @@ -247,7 +247,7 @@ struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn) { struct inode *inode; - inode = iget_locked(sb, kn->id.ino); + inode = iget_locked(sb, kernfs_ino(kn)); if (inode && (inode->i_state & I_NEW)) kernfs_init_inode(kn, inode); diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 067b7c380056..f05d5d6f926d 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -57,15 +57,14 @@ const struct super_operations kernfs_sops = { * Similar to kernfs_fh_get_inode, this one gets kernfs node from inode * number and generation */ -struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, - const union kernfs_node_id *id) +struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, u64 id) { struct kernfs_node *kn; - kn = kernfs_find_and_get_node_by_ino(root, id->ino); + kn = kernfs_find_and_get_node_by_ino(root, kernfs_id_ino(id)); if (!kn) return NULL; - if (kn->id.generation != id->generation) { + if (kernfs_gen(kn) != kernfs_id_gen(id)) { kernfs_put(kn); return NULL; } diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index f6b048902d6c..815fff49d555 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -616,7 +616,7 @@ static inline bool cgroup_is_populated(struct cgroup *cgrp) /* returns ino associated with a cgroup */ static inline ino_t cgroup_ino(struct cgroup *cgrp) { - return cgrp->kn->id.ino; + return kernfs_ino(cgrp->kn); } /* cft/css accessors for cftype->write() operation */ @@ -687,13 +687,12 @@ static inline void cgroup_kthread_ready(void) current->no_cgroup_migration = 0; } -static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) +static inline u64 cgroup_get_kernfs_id(struct cgroup *cgrp) { - return &cgrp->kn->id; + return cgrp->kn->id; } -void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, - char *buf, size_t buflen); +void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen); #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; @@ -718,9 +717,9 @@ static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_init_kthreadd(void) {} static inline void cgroup_kthread_ready(void) {} -static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) +static inline union u64 cgroup_get_kernfs_id(struct cgroup *cgrp) { - return NULL; + return 0; } static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) @@ -739,8 +738,8 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, return true; } -static inline void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, - char *buf, size_t buflen) {} +static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) +{} #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUPS diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index f797ccc650e7..b2fc5c8ef6d9 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -104,21 +104,6 @@ struct kernfs_elem_attr { struct kernfs_node *notify_next; /* for kernfs_notify() */ }; -/* represent a kernfs node */ -union kernfs_node_id { - struct { - /* - * blktrace will export this struct as a simplified 'struct - * fid' (which is a big data struction), so userspace can use - * it to find kernfs node. The layout must match the first two - * fields of 'struct fid' exactly. - */ - u32 ino; - u32 generation; - }; - u64 id; -}; - /* * kernfs_node - the building block of kernfs hierarchy. Each and every * kernfs node is represented by single kernfs_node. Most fields are @@ -155,7 +140,12 @@ struct kernfs_node { void *priv; - union kernfs_node_id id; + /* + * 64bit unique ID. Lower 32bits carry the inode number and lower + * generation. + */ + u64 id; + unsigned short flags; umode_t mode; struct kernfs_iattrs *iattr; @@ -292,6 +282,26 @@ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) return kn->flags & KERNFS_TYPE_MASK; } +static inline ino_t kernfs_id_ino(u64 id) +{ + return (u32)id; +} + +static inline u32 kernfs_id_gen(u64 id) +{ + return id >> 32; +} + +static inline ino_t kernfs_ino(struct kernfs_node *kn) +{ + return kernfs_id_ino(kn->id); +} + +static inline ino_t kernfs_gen(struct kernfs_node *kn) +{ + return kernfs_id_gen(kn->id); +} + /** * kernfs_enable_ns - enable namespace under a directory * @kn: directory of interest, should be empty @@ -383,8 +393,7 @@ void kernfs_kill_sb(struct super_block *sb); void kernfs_init(void); -struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, - const union kernfs_node_id *id); +struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, u64 id); #else /* CONFIG_KERNFS */ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 95e50677476b..b4f0ffe1817e 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -152,7 +152,7 @@ DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode, static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { - return wb->memcg_css->cgroup->kn->id.ino; + return cgroup_ino(wb->memcg_css->cgroup); } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) @@ -260,7 +260,7 @@ TRACE_EVENT(track_foreign_dirty, __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); - __entry->page_cgroup_ino = page->mem_cgroup->css.cgroup->kn->id.ino; + __entry->page_cgroup_ino = cgroup_ino(page->mem_cgroup->css.cgroup); ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu", diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 5e28718928ca..912e761cd17a 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -317,7 +317,7 @@ BPF_CALL_0(bpf_get_current_cgroup_id) { struct cgroup *cgrp = task_dfl_cgroup(current); - return cgrp->kn->id.id; + return cgrp->kn->id; } const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index addd6fdceec8..5d867f6d7204 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -569,7 +569,7 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, return; storage->key.attach_type = type; - storage->key.cgroup_inode_id = cgroup->kn->id.id; + storage->key.cgroup_inode_id = cgroup->kn->id; map = storage->map; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index cf32c0c7a45d..c6bd1a5a1977 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5786,8 +5786,7 @@ static int __init cgroup_wq_init(void) } core_initcall(cgroup_wq_init); -void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, - char *buf, size_t buflen) +void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) { struct kernfs_node *kn; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 2d6e93ab0478..a986d2e74ca2 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -64,8 +64,7 @@ static void blk_unregister_tracepoints(void); * Send out a notify message. */ static void trace_note(struct blk_trace *bt, pid_t pid, int action, - const void *data, size_t len, - union kernfs_node_id *cgid) + const void *data, size_t len, u64 cgid) { struct blk_io_trace *t; struct ring_buffer_event *event = NULL; @@ -73,7 +72,7 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action, int pc = 0; int cpu = smp_processor_id(); bool blk_tracer = blk_tracer_enabled; - ssize_t cgid_len = cgid ? sizeof(*cgid) : 0; + ssize_t cgid_len = cgid ? sizeof(cgid) : 0; if (blk_tracer) { buffer = blk_tr->trace_buffer.buffer; @@ -100,8 +99,8 @@ record_it: t->pid = pid; t->cpu = cpu; t->pdu_len = len + cgid_len; - if (cgid) - memcpy((void *)t + sizeof(*t), cgid, cgid_len); + if (cgid_len) + memcpy((void *)t + sizeof(*t), &cgid, cgid_len); memcpy((void *) t + sizeof(*t) + cgid_len, data, len); if (blk_tracer) @@ -122,7 +121,7 @@ static void trace_note_tsk(struct task_struct *tsk) spin_lock_irqsave(&running_trace_lock, flags); list_for_each_entry(bt, &running_trace_list, running_list) { trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, - sizeof(tsk->comm), NULL); + sizeof(tsk->comm), 0); } spin_unlock_irqrestore(&running_trace_lock, flags); } @@ -139,7 +138,7 @@ static void trace_note_time(struct blk_trace *bt) words[1] = now.tv_nsec; local_irq_save(flags); - trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), NULL); + trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), 0); local_irq_restore(flags); } @@ -172,9 +171,9 @@ void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg, blkcg = NULL; #ifdef CONFIG_BLK_CGROUP trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, - blkcg ? cgroup_get_kernfs_id(blkcg->css.cgroup) : NULL); + blkcg ? cgroup_get_kernfs_id(blkcg->css.cgroup) : 0); #else - trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, NULL); + trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, 0); #endif local_irq_restore(flags); } @@ -212,7 +211,7 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ), */ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, int op, int op_flags, u32 what, int error, int pdu_len, - void *pdu_data, union kernfs_node_id *cgid) + void *pdu_data, u64 cgid) { struct task_struct *tsk = current; struct ring_buffer_event *event = NULL; @@ -223,7 +222,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, pid_t pid; int cpu, pc = 0; bool blk_tracer = blk_tracer_enabled; - ssize_t cgid_len = cgid ? sizeof(*cgid) : 0; + ssize_t cgid_len = cgid ? sizeof(cgid) : 0; if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer)) return; @@ -294,7 +293,7 @@ record_it: t->pdu_len = pdu_len + cgid_len; if (cgid_len) - memcpy((void *)t + sizeof(*t), cgid, cgid_len); + memcpy((void *)t + sizeof(*t), &cgid, cgid_len); if (pdu_len) memcpy((void *)t + sizeof(*t) + cgid_len, pdu_data, pdu_len); @@ -751,31 +750,29 @@ void blk_trace_shutdown(struct request_queue *q) } #ifdef CONFIG_BLK_CGROUP -static union kernfs_node_id * -blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) +static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { struct blk_trace *bt = q->blk_trace; if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) - return NULL; + return 0; if (!bio->bi_blkg) - return NULL; + return 0; return cgroup_get_kernfs_id(bio_blkcg(bio)->css.cgroup); } #else -static union kernfs_node_id * -blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) +u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { - return NULL; + return 0; } #endif -static union kernfs_node_id * +static u64 blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) { if (!rq->bio) - return NULL; + return 0; /* Use the first bio */ return blk_trace_bio_get_cgid(q, rq->bio); } @@ -797,8 +794,7 @@ blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) * **/ static void blk_add_trace_rq(struct request *rq, int error, - unsigned int nr_bytes, u32 what, - union kernfs_node_id *cgid) + unsigned int nr_bytes, u32 what, u64 cgid) { struct blk_trace *bt = rq->q->blk_trace; @@ -913,7 +909,7 @@ static void blk_add_trace_getrq(void *ignore, if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, - NULL, NULL); + NULL, 0); } } @@ -929,7 +925,7 @@ static void blk_add_trace_sleeprq(void *ignore, if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, - 0, 0, NULL, NULL); + 0, 0, NULL, 0); } } @@ -938,7 +934,7 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q) struct blk_trace *bt = q->blk_trace; if (bt) - __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, NULL); + __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, @@ -955,7 +951,7 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q, else what = BLK_TA_UNPLUG_TIMER; - __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, NULL); + __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0); } } @@ -1172,19 +1168,17 @@ const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent) static inline const void *pdu_start(const struct trace_entry *ent, bool has_cg) { - return (void *)(te_blk_io_trace(ent) + 1) + - (has_cg ? sizeof(union kernfs_node_id) : 0); + return (void *)(te_blk_io_trace(ent) + 1) + (has_cg ? sizeof(u64) : 0); } -static inline const void *cgid_start(const struct trace_entry *ent) +static inline u64 t_cgid(const struct trace_entry *ent) { - return (void *)(te_blk_io_trace(ent) + 1); + return *(u64 *)(te_blk_io_trace(ent) + 1); } static inline int pdu_real_len(const struct trace_entry *ent, bool has_cg) { - return te_blk_io_trace(ent)->pdu_len - - (has_cg ? sizeof(union kernfs_node_id) : 0); + return te_blk_io_trace(ent)->pdu_len - (has_cg ? sizeof(u64) : 0); } static inline u32 t_action(const struct trace_entry *ent) @@ -1257,7 +1251,7 @@ static void blk_log_action(struct trace_iterator *iter, const char *act, fill_rwbs(rwbs, t); if (has_cg) { - const union kernfs_node_id *id = cgid_start(iter->ent); + u64 id = t_cgid(iter->ent); if (blk_tracer_flags.val & TRACE_BLK_OPT_CGNAME) { char blkcg_name_buf[NAME_MAX + 1] = "<...>"; @@ -1269,9 +1263,10 @@ static void blk_log_action(struct trace_iterator *iter, const char *act, blkcg_name_buf, act, rwbs); } else trace_seq_printf(&iter->seq, - "%3d,%-3d %x,%-x %2s %3s ", + "%3d,%-3d %lx,%-x %2s %3s ", MAJOR(t->device), MINOR(t->device), - id->ino, id->generation, act, rwbs); + kernfs_id_ino(id), kernfs_id_gen(id), + act, rwbs); } else trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ", MAJOR(t->device), MINOR(t->device), act, rwbs); diff --git a/net/core/filter.c b/net/core/filter.c index ed6563622ce3..b360a7beb6fc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4089,7 +4089,7 @@ BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - return cgrp->kn->id.id; + return cgrp->kn->id; } static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { @@ -4114,7 +4114,7 @@ BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, if (!ancestor) return 0; - return ancestor->kn->id.id; + return ancestor->kn->id; } static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { -- cgit v1.2.3-59-g8ed1b From 743210386c0354a2f8ef3d697353c7d8477fa81d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 4 Nov 2019 15:54:30 -0800 Subject: cgroup: use cgrp->kn->id as the cgroup ID cgroup ID is currently allocated using a dedicated per-hierarchy idr and used internally and exposed through tracepoints and bpf. This is confusing because there are tracepoints and other interfaces which use the cgroupfs ino as IDs. The preceding changes made kn->id exposed as ino as 64bit ino on supported archs or ino+gen (low 32bits as ino, high gen). There's no reason for cgroup to use different IDs. The kernfs IDs are unique and userland can easily discover them and map them back to paths using standard file operations. This patch replaces cgroup IDs with kernfs IDs. * cgroup_id() is added and all cgroup ID users are converted to use it. * kernfs_node creation is moved to earlier during cgroup init so that cgroup_id() is available during init. * While at it, s/cgroup/cgrp/ in psi helpers for consistency. * Fallback ID value is changed to 1 to be consistent with root cgroup ID. Signed-off-by: Tejun Heo Reviewed-by: Greg Kroah-Hartman Cc: Namhyung Kim --- include/linux/cgroup-defs.h | 17 ++-------- include/linux/cgroup.h | 17 ++++------ include/trace/events/cgroup.h | 6 ++-- kernel/bpf/helpers.c | 2 +- kernel/bpf/local_storage.c | 2 +- kernel/cgroup/cgroup.c | 76 ++++++++++++++----------------------------- kernel/trace/blktrace.c | 4 +-- net/core/filter.c | 4 +-- 8 files changed, 43 insertions(+), 85 deletions(-) (limited to 'net/core') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4904b1ebd1ff..63097cb243cb 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -354,16 +354,6 @@ struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ - /* - * idr allocated in-hierarchy ID. - * - * ID 0 is not used, the ID of the root cgroup is always 1, and a - * new cgroup will be assigned with a smallest available ID. - * - * Allocating/Removing ID must be protected by cgroup_mutex. - */ - int id; - /* * The depth this cgroup is at. The root is at depth zero and each * step down the hierarchy increments the level. This along with @@ -488,7 +478,7 @@ struct cgroup { struct cgroup_freezer_state freezer; /* ids of the ancestors at each level including self */ - int ancestor_ids[]; + u64 ancestor_ids[]; }; /* @@ -509,7 +499,7 @@ struct cgroup_root { struct cgroup cgrp; /* for cgrp->ancestor_ids[0] */ - int cgrp_ancestor_id_storage; + u64 cgrp_ancestor_id_storage; /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ atomic_t nr_cgrps; @@ -520,9 +510,6 @@ struct cgroup_root { /* Hierarchy-specific flags */ unsigned int flags; - /* IDs for cgroups in this hierarchy */ - struct idr cgroup_idr; - /* The path to use for release notifications. */ char release_agent_path[PATH_MAX]; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 815fff49d555..d7ddebd0cdec 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -304,6 +304,11 @@ void css_task_iter_end(struct css_task_iter *it); * Inline functions. */ +static inline u64 cgroup_id(struct cgroup *cgrp) +{ + return cgrp->kn->id; +} + /** * css_get - obtain a reference on the specified css * @css: target css @@ -565,7 +570,7 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp, { if (cgrp->root != ancestor->root || cgrp->level < ancestor->level) return false; - return cgrp->ancestor_ids[ancestor->level] == ancestor->id; + return cgrp->ancestor_ids[ancestor->level] == cgroup_id(ancestor); } /** @@ -687,17 +692,13 @@ static inline void cgroup_kthread_ready(void) current->no_cgroup_migration = 0; } -static inline u64 cgroup_get_kernfs_id(struct cgroup *cgrp) -{ - return cgrp->kn->id; -} - void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen); #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; struct cgroup; +static inline u64 cgroup_id(struct cgroup *cgrp) { return 1; } static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} static inline int cgroup_attach_task_all(struct task_struct *from, @@ -717,10 +718,6 @@ static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_init_kthreadd(void) {} static inline void cgroup_kthread_ready(void) {} -static inline union u64 cgroup_get_kernfs_id(struct cgroup *cgrp) -{ - return 0; -} static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { diff --git a/include/trace/events/cgroup.h b/include/trace/events/cgroup.h index a566cc521476..7f42a3de59e6 100644 --- a/include/trace/events/cgroup.h +++ b/include/trace/events/cgroup.h @@ -66,7 +66,7 @@ DECLARE_EVENT_CLASS(cgroup, TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; - __entry->id = cgrp->id; + __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path, path); ), @@ -135,7 +135,7 @@ DECLARE_EVENT_CLASS(cgroup_migrate, TP_fast_assign( __entry->dst_root = dst_cgrp->root->hierarchy_id; - __entry->dst_id = dst_cgrp->id; + __entry->dst_id = cgroup_id(dst_cgrp); __entry->dst_level = dst_cgrp->level; __assign_str(dst_path, path); __entry->pid = task->pid; @@ -179,7 +179,7 @@ DECLARE_EVENT_CLASS(cgroup_event, TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; - __entry->id = cgrp->id; + __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path, path); __entry->val = val; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 912e761cd17a..cada974c9f4e 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -317,7 +317,7 @@ BPF_CALL_0(bpf_get_current_cgroup_id) { struct cgroup *cgrp = task_dfl_cgroup(current); - return cgrp->kn->id; + return cgroup_id(cgrp); } const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 5d867f6d7204..2ba750725cb2 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -569,7 +569,7 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, return; storage->key.attach_type = type; - storage->key.cgroup_inode_id = cgroup->kn->id; + storage->key.cgroup_inode_id = cgroup_id(cgroup); map = storage->map; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index b5dcbee5aa6c..c12dcf7dc432 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1308,10 +1308,7 @@ static void cgroup_exit_root_id(struct cgroup_root *root) void cgroup_free_root(struct cgroup_root *root) { - if (root) { - idr_destroy(&root->cgroup_idr); - kfree(root); - } + kfree(root); } static void cgroup_destroy_root(struct cgroup_root *root) @@ -1917,7 +1914,6 @@ void init_cgroup_root(struct cgroup_fs_context *ctx) atomic_set(&root->nr_cgrps, 1); cgrp->root = root; init_cgroup_housekeeping(cgrp); - idr_init(&root->cgroup_idr); root->flags = ctx->flags; if (ctx->release_agent) @@ -1938,12 +1934,6 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) lockdep_assert_held(&cgroup_mutex); - ret = cgroup_idr_alloc(&root->cgroup_idr, root_cgrp, 1, 2, GFP_KERNEL); - if (ret < 0) - goto out; - root_cgrp->id = ret; - root_cgrp->ancestor_ids[0] = ret; - ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) @@ -1976,6 +1966,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) goto exit_root_id; } root_cgrp->kn = root->kf_root->kn; + WARN_ON_ONCE(cgroup_id(root_cgrp) != 1); + root_cgrp->ancestor_ids[0] = cgroup_id(root_cgrp); ret = css_populate_dir(&root_cgrp->self); if (ret) @@ -3552,22 +3544,22 @@ static int cpu_stat_show(struct seq_file *seq, void *v) #ifdef CONFIG_PSI static int cgroup_io_pressure_show(struct seq_file *seq, void *v) { - struct cgroup *cgroup = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup->id == 1 ? &psi_system : &cgroup->psi; + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_IO); } static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) { - struct cgroup *cgroup = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup->id == 1 ? &psi_system : &cgroup->psi; + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_MEM); } static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { - struct cgroup *cgroup = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup->id == 1 ? &psi_system : &cgroup->psi; + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_CPU); } @@ -4987,9 +4979,6 @@ static void css_release_work_fn(struct work_struct *work) tcgrp->nr_dying_descendants--; spin_unlock_irq(&css_set_lock); - cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id); - cgrp->id = -1; - /* * There are two control paths which try to determine * cgroup from dentry without going through kernfs - @@ -5154,10 +5143,12 @@ err_free_css: * it isn't associated with its kernfs_node and doesn't have the control * mask applied. */ -static struct cgroup *cgroup_create(struct cgroup *parent) +static struct cgroup *cgroup_create(struct cgroup *parent, const char *name, + umode_t mode) { struct cgroup_root *root = parent->root; struct cgroup *cgrp, *tcgrp; + struct kernfs_node *kn; int level = parent->level + 1; int ret; @@ -5177,15 +5168,13 @@ static struct cgroup *cgroup_create(struct cgroup *parent) goto out_cancel_ref; } - /* - * Temporarily set the pointer to NULL, so idr_find() won't return - * a half-baked cgroup. - */ - cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_KERNEL); - if (cgrp->id < 0) { - ret = -ENOMEM; + /* create the directory */ + kn = kernfs_create_dir(parent->kn, name, mode, cgrp); + if (IS_ERR(kn)) { + ret = PTR_ERR(kn); goto out_stat_exit; } + cgrp->kn = kn; init_cgroup_housekeeping(cgrp); @@ -5195,7 +5184,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent) ret = psi_cgroup_alloc(cgrp); if (ret) - goto out_idr_free; + goto out_kernfs_remove; ret = cgroup_bpf_inherit(cgrp); if (ret) @@ -5219,7 +5208,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent) spin_lock_irq(&css_set_lock); for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { - cgrp->ancestor_ids[tcgrp->level] = tcgrp->id; + cgrp->ancestor_ids[tcgrp->level] = cgroup_id(tcgrp); if (tcgrp != cgrp) { tcgrp->nr_descendants++; @@ -5248,12 +5237,6 @@ static struct cgroup *cgroup_create(struct cgroup *parent) atomic_inc(&root->nr_cgrps); cgroup_get_live(parent); - /* - * @cgrp is now fully operational. If something fails after this - * point, it'll be released via the normal destruction path. - */ - cgroup_idr_replace(&root->cgroup_idr, cgrp, cgrp->id); - /* * On the default hierarchy, a child doesn't automatically inherit * subtree_control from the parent. Each is configured manually. @@ -5267,8 +5250,8 @@ static struct cgroup *cgroup_create(struct cgroup *parent) out_psi_free: psi_cgroup_free(cgrp); -out_idr_free: - cgroup_idr_remove(&root->cgroup_idr, cgrp->id); +out_kernfs_remove: + kernfs_remove(cgrp->kn); out_stat_exit: if (cgroup_on_dfl(parent)) cgroup_rstat_exit(cgrp); @@ -5305,7 +5288,6 @@ fail: int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) { struct cgroup *parent, *cgrp; - struct kernfs_node *kn; int ret; /* do not accept '\n' to prevent making /proc//cgroup unparsable */ @@ -5321,27 +5303,19 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) goto out_unlock; } - cgrp = cgroup_create(parent); + cgrp = cgroup_create(parent, name, mode); if (IS_ERR(cgrp)) { ret = PTR_ERR(cgrp); goto out_unlock; } - /* create the directory */ - kn = kernfs_create_dir(parent->kn, name, mode, cgrp); - if (IS_ERR(kn)) { - ret = PTR_ERR(kn); - goto out_destroy; - } - cgrp->kn = kn; - /* * This extra ref will be put in cgroup_free_fn() and guarantees * that @cgrp->kn is always accessible. */ - kernfs_get(kn); + kernfs_get(cgrp->kn); - ret = cgroup_kn_set_ugid(kn); + ret = cgroup_kn_set_ugid(cgrp->kn); if (ret) goto out_destroy; @@ -5356,7 +5330,7 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) TRACE_CGROUP_PATH(mkdir, cgrp); /* let's create and online css's */ - kernfs_activate(kn); + kernfs_activate(cgrp->kn); ret = 0; goto out_unlock; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index a7dac5b63f3f..475e29498bca 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -171,7 +171,7 @@ void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg, blkcg = NULL; #ifdef CONFIG_BLK_CGROUP trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, - blkcg ? cgroup_get_kernfs_id(blkcg->css.cgroup) : 0); + blkcg ? cgroup_id(blkcg->css.cgroup) : 1); #else trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, 0); #endif @@ -759,7 +759,7 @@ static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) if (!bio->bi_blkg) return 0; - return cgroup_get_kernfs_id(bio_blkcg(bio)->css.cgroup); + return cgroup_id(bio_blkcg(bio)->css.cgroup); } #else u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) diff --git a/net/core/filter.c b/net/core/filter.c index b360a7beb6fc..caef7c74cad5 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4089,7 +4089,7 @@ BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - return cgrp->kn->id; + return cgroup_id(cgrp); } static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { @@ -4114,7 +4114,7 @@ BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, if (!ancestor) return 0; - return ancestor->kn->id; + return cgroup_id(ancestor); } static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { -- cgit v1.2.3-59-g8ed1b