diff options
Diffstat (limited to 'kernel')
97 files changed, 1837 insertions, 806 deletions
diff --git a/kernel/acct.c b/kernel/acct.c index 81f9831a7859..6d98aed403ba 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -331,6 +331,8 @@ static comp_t encode_comp_t(unsigned long value) exp++; } + if (exp > (((comp_t) ~0U) >> MANTSIZE)) + return (comp_t) ~0U; /* * Clean it up and polish it off. */ diff --git a/kernel/async.c b/kernel/async.c index a893d6170944..e59bd2240cb8 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -115,7 +115,7 @@ static void async_run_entry_fn(struct work_struct *work) struct async_entry *entry = container_of(work, struct async_entry, work); unsigned long flags; - ktime_t uninitialized_var(calltime), delta, rettime; + ktime_t calltime, delta, rettime; /* 1) run (and print duration) */ if (initcall_debug && system_state < SYSTEM_RUNNING) { @@ -191,9 +191,6 @@ static async_cookie_t __async_schedule(async_func_t func, void *data, struct asy atomic_inc(&entry_count); spin_unlock_irqrestore(&async_lock, flags); - /* mark that this task has queued an async job, used by module init */ - current->flags |= PF_USED_ASYNC; - /* schedule for execution */ queue_work(system_unbound_wq, &entry->work); @@ -286,7 +283,7 @@ EXPORT_SYMBOL_GPL(async_synchronize_full_domain); */ void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *domain) { - ktime_t uninitialized_var(starttime), delta, endtime; + ktime_t starttime, delta, endtime; if (initcall_debug && system_state < SYSTEM_RUNNING) { pr_debug("async_waiting @ %i\n", task_pid_nr(current)); diff --git a/kernel/audit.c b/kernel/audit.c index 45741c3c48a4..471d3ad910aa 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -549,20 +549,22 @@ static void kauditd_printk_skb(struct sk_buff *skb) /** * kauditd_rehold_skb - Handle a audit record send failure in the hold queue * @skb: audit record + * @error: error code (unused) * * Description: * This should only be used by the kauditd_thread when it fails to flush the * hold queue. */ -static void kauditd_rehold_skb(struct sk_buff *skb) +static void kauditd_rehold_skb(struct sk_buff *skb, __always_unused int error) { - /* put the record back in the queue at the same place */ - skb_queue_head(&audit_hold_queue, skb); + /* put the record back in the queue */ + skb_queue_tail(&audit_hold_queue, skb); } /** * kauditd_hold_skb - Queue an audit record, waiting for auditd * @skb: audit record + * @error: error code * * Description: * Queue the audit record, waiting for an instance of auditd. When this @@ -572,19 +574,31 @@ static void kauditd_rehold_skb(struct sk_buff *skb) * and queue it, if we have room. If we want to hold on to the record, but we * don't have room, record a record lost message. */ -static void kauditd_hold_skb(struct sk_buff *skb) +static void kauditd_hold_skb(struct sk_buff *skb, int error) { /* at this point it is uncertain if we will ever send this to auditd so * try to send the message via printk before we go any further */ kauditd_printk_skb(skb); /* can we just silently drop the message? */ - if (!audit_default) { - kfree_skb(skb); - return; + if (!audit_default) + goto drop; + + /* the hold queue is only for when the daemon goes away completely, + * not -EAGAIN failures; if we are in a -EAGAIN state requeue the + * record on the retry queue unless it's full, in which case drop it + */ + if (error == -EAGAIN) { + if (!audit_backlog_limit || + skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { + skb_queue_tail(&audit_retry_queue, skb); + return; + } + audit_log_lost("kauditd retry queue overflow"); + goto drop; } - /* if we have room, queue the message */ + /* if we have room in the hold queue, queue the message */ if (!audit_backlog_limit || skb_queue_len(&audit_hold_queue) < audit_backlog_limit) { skb_queue_tail(&audit_hold_queue, skb); @@ -593,24 +607,32 @@ static void kauditd_hold_skb(struct sk_buff *skb) /* we have no other options - drop the message */ audit_log_lost("kauditd hold queue overflow"); +drop: kfree_skb(skb); } /** * kauditd_retry_skb - Queue an audit record, attempt to send again to auditd * @skb: audit record + * @error: error code (unused) * * Description: * Not as serious as kauditd_hold_skb() as we still have a connected auditd, * but for some reason we are having problems sending it audit records so * queue the given record and attempt to resend. */ -static void kauditd_retry_skb(struct sk_buff *skb) +static void kauditd_retry_skb(struct sk_buff *skb, __always_unused int error) { - /* NOTE: because records should only live in the retry queue for a - * short period of time, before either being sent or moved to the hold - * queue, we don't currently enforce a limit on this queue */ - skb_queue_tail(&audit_retry_queue, skb); + if (!audit_backlog_limit || + skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { + skb_queue_tail(&audit_retry_queue, skb); + return; + } + + /* we have to drop the record, send it via printk as a last effort */ + kauditd_printk_skb(skb); + audit_log_lost("kauditd retry queue overflow"); + kfree_skb(skb); } /** @@ -648,7 +670,7 @@ static void auditd_reset(const struct auditd_connection *ac) /* flush the retry queue to the hold queue, but don't touch the main * queue since we need to process that normally for multicast */ while ((skb = skb_dequeue(&audit_retry_queue))) - kauditd_hold_skb(skb); + kauditd_hold_skb(skb, -ECONNREFUSED); } /** @@ -722,16 +744,18 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, struct sk_buff_head *queue, unsigned int retry_limit, void (*skb_hook)(struct sk_buff *skb), - void (*err_hook)(struct sk_buff *skb)) + void (*err_hook)(struct sk_buff *skb, int error)) { int rc = 0; - struct sk_buff *skb; - static unsigned int failed = 0; + struct sk_buff *skb = NULL; + struct sk_buff *skb_tail; + unsigned int failed = 0; /* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */ - while ((skb = skb_dequeue(queue))) { + skb_tail = skb_peek_tail(queue); + while ((skb != skb_tail) && (skb = skb_dequeue(queue))) { /* call the skb_hook for each skb we touch */ if (skb_hook) (*skb_hook)(skb); @@ -739,36 +763,34 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, /* can we send to anyone via unicast? */ if (!sk) { if (err_hook) - (*err_hook)(skb); + (*err_hook)(skb, -ECONNREFUSED); continue; } +retry: /* grab an extra skb reference in case of error */ skb_get(skb); rc = netlink_unicast(sk, skb, portid, 0); if (rc < 0) { - /* fatal failure for our queue flush attempt? */ + /* send failed - try a few times unless fatal error */ if (++failed >= retry_limit || rc == -ECONNREFUSED || rc == -EPERM) { - /* yes - error processing for the queue */ sk = NULL; if (err_hook) - (*err_hook)(skb); - if (!skb_hook) - goto out; - /* keep processing with the skb_hook */ + (*err_hook)(skb, rc); + if (rc == -EAGAIN) + rc = 0; + /* continue to drain the queue */ continue; } else - /* no - requeue to preserve ordering */ - skb_queue_head(queue, skb); + goto retry; } else { - /* it worked - drop the extra reference and continue */ + /* skb sent - drop the extra reference and continue */ consume_skb(skb); failed = 0; } } -out: return (rc >= 0 ? 0 : rc); } @@ -1530,6 +1552,20 @@ static void audit_receive(struct sk_buff *skb) nlh = nlmsg_next(nlh, &len); } audit_ctl_unlock(); + + /* can't block with the ctrl lock, so penalize the sender now */ + if (audit_backlog_limit && + (skb_queue_len(&audit_queue) > audit_backlog_limit)) { + DECLARE_WAITQUEUE(wait, current); + + /* wake kauditd to try and flush the queue */ + wake_up_interruptible(&kauditd_wait); + + add_wait_queue_exclusive(&audit_backlog_wait, &wait); + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(audit_backlog_wait_time); + remove_wait_queue(&audit_backlog_wait, &wait); + } } /* Run custom bind function on netlink socket group connect or bind requests. */ @@ -1557,7 +1593,8 @@ static int __net_init audit_net_init(struct net *net) audit_panic("cannot initialize netlink socket in namespace"); return -ENOMEM; } - aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; + /* limit the timeout in case auditd is blocked/stopped */ + aunet->sk->sk_sndtimeo = HZ / 10; return 0; } @@ -1759,7 +1796,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, { struct audit_buffer *ab; struct timespec64 t; - unsigned int uninitialized_var(serial); + unsigned int serial; if (audit_initialized != AUDIT_INITIALIZED) return NULL; @@ -1773,7 +1810,9 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, * task_tgid_vnr() since auditd_pid is set in audit_receive_msg() * using a PID anchored in the caller's namespace * 2. generator holding the audit_cmd_mutex - we don't want to block - * while holding the mutex */ + * while holding the mutex, although we do penalize the sender + * later in audit_receive() when it is safe to block + */ if (!(auditd_test_task(current) || audit_ctl_owner_current())) { long stime = audit_backlog_wait_time; diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index fba78047fb37..57404292c6d1 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -111,6 +111,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, true); if (ret < 0) { + audit_mark->path = NULL; fsnotify_put_mark(&audit_mark->mark); audit_mark = ERR_PTR(ret); } diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 50952d6d8120..ff33536ae1ad 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -557,11 +557,18 @@ int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark) unsigned long ino; dev_t dev; - exe_file = get_task_exe_file(tsk); + /* only do exe filtering if we are recording @current events/records */ + if (tsk != current) + return 0; + + if (!current->mm) + return 0; + exe_file = get_mm_exe_file(current->mm); if (!exe_file) return 0; ino = file_inode(exe_file)->i_ino; dev = file_inode(exe_file)->i_sb->s_dev; fput(exe_file); + return audit_mark_compare(mark, ino, dev); } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 1513873e23bd..e4de5b9d5d3f 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1923,6 +1923,8 @@ void __audit_inode_child(struct inode *parent, } } + cond_resched(); + /* is there a matching child entry? */ list_for_each_entry(n, &context->names_list, list) { /* can only match entries that have a name */ diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c index 9b5eeff72fd3..39a0e768adc3 100644 --- a/kernel/bpf/bpf_lru_list.c +++ b/kernel/bpf/bpf_lru_list.c @@ -44,7 +44,12 @@ static struct list_head *local_pending_list(struct bpf_lru_locallist *loc_l) /* bpf_lru_node helpers */ static bool bpf_lru_node_is_ref(const struct bpf_lru_node *node) { - return node->ref; + return READ_ONCE(node->ref); +} + +static void bpf_lru_node_clear_ref(struct bpf_lru_node *node) +{ + WRITE_ONCE(node->ref, 0); } static void bpf_lru_list_count_inc(struct bpf_lru_list *l, @@ -92,7 +97,7 @@ static void __bpf_lru_node_move_in(struct bpf_lru_list *l, bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_move(&node->list, &l->lists[tgt_type]); } @@ -113,7 +118,7 @@ static void __bpf_lru_node_move(struct bpf_lru_list *l, bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; } - node->ref = 0; + bpf_lru_node_clear_ref(node); /* If the moving node is the next_inactive_rotation candidate, * move the next_inactive_rotation pointer also. @@ -356,7 +361,7 @@ static void __local_list_add_pending(struct bpf_lru *lru, *(u32 *)((void *)node + lru->hash_offset) = hash; node->cpu = cpu; node->type = BPF_LRU_LOCAL_LIST_T_PENDING; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, local_pending_list(loc_l)); } @@ -422,7 +427,7 @@ static struct bpf_lru_node *bpf_percpu_lru_pop_free(struct bpf_lru *lru, if (!list_empty(free_list)) { node = list_first_entry(free_list, struct bpf_lru_node, list); *(u32 *)((void *)node + lru->hash_offset) = hash; - node->ref = 0; + bpf_lru_node_clear_ref(node); __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE); } @@ -525,7 +530,7 @@ static void bpf_common_lru_push_free(struct bpf_lru *lru, } node->type = BPF_LRU_LOCAL_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_move(&node->list, local_free_list(loc_l)); raw_spin_unlock_irqrestore(&loc_l->lock, flags); @@ -571,7 +576,7 @@ static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf, node = (struct bpf_lru_node *)(buf + node_offset); node->type = BPF_LRU_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); buf += elem_size; } @@ -597,7 +602,7 @@ again: node = (struct bpf_lru_node *)(buf + node_offset); node->cpu = cpu; node->type = BPF_LRU_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); i++; buf += elem_size; diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index 7d4f89b7cb84..08da78b59f0b 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -66,11 +66,8 @@ struct bpf_lru { static inline void bpf_lru_node_set_ref(struct bpf_lru_node *node) { - /* ref is an approximation on access frequency. It does not - * have to be very accurate. Hence, no protection is used. - */ - if (!node->ref) - node->ref = 1; + if (!READ_ONCE(node->ref)) + WRITE_ONCE(node->ref, 1); } int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 471cc5c117a5..62e05b6283c0 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1660,7 +1660,7 @@ static int btf_struct_resolve(struct btf_verifier_env *env, if (v->next_member) { const struct btf_type *last_member_type; const struct btf_member *last_member; - u16 last_member_type_id; + u32 last_member_type_id; last_member = btf_type_member(v->t) + v->next_member - 1; last_member_type_id = last_member->type; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 4e5b5ae05406..285101772c75 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -32,6 +32,7 @@ #include <linux/kallsyms.h> #include <linux/rcupdate.h> #include <linux/perf_event.h> +#include <linux/nospec.h> #include <asm/barrier.h> #include <asm/unaligned.h> @@ -66,11 +67,13 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns { u8 *ptr = NULL; - if (k >= SKF_NET_OFF) + if (k >= SKF_NET_OFF) { ptr = skb_network_header(skb) + k - SKF_NET_OFF; - else if (k >= SKF_LL_OFF) + } else if (k >= SKF_LL_OFF) { + if (unlikely(!skb_mac_header_was_set(skb))) + return NULL; ptr = skb_mac_header(skb) + k - SKF_LL_OFF; - + } if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; @@ -600,7 +603,7 @@ static int __init bpf_jit_charge_init(void) { /* Only used as heuristic here to derive limit. */ bpf_jit_limit_max = bpf_jit_alloc_exec_limit(); - bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2, + bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 1, PAGE_SIZE), LONG_MAX); return 0; } @@ -1371,9 +1374,7 @@ out: * reuse preexisting logic from Spectre v1 mitigation that * happens to produce the required code on x86 for v4 as well. */ -#ifdef CONFIG_X86 barrier_nospec(); -#endif CONT; #define LDST(SIZEOP, SIZE) \ STX_MEM_##SIZEOP: \ diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 1a8b208f6c55..fcd3a15add41 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -194,6 +194,9 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key) struct lpm_trie_node *node, *found = NULL; struct bpf_lpm_trie_key *key = _key; + if (key->prefixlen > trie->max_prefixlen) + return NULL; + /* Start walking the trie from the root node ... */ for (node = rcu_dereference(trie->root); node;) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 353a8d672302..02e5bdb82a9a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -48,7 +48,8 @@ static DEFINE_SPINLOCK(prog_idr_lock); static DEFINE_IDR(map_idr); static DEFINE_SPINLOCK(map_idr_lock); -int sysctl_unprivileged_bpf_disabled __read_mostly; +int sysctl_unprivileged_bpf_disabled __read_mostly = + IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; static const struct bpf_map_ops * const bpf_map_types[] = { #define BPF_PROG_TYPE(_id, _ops) @@ -2324,7 +2325,9 @@ static int bpf_task_fd_query(const union bpf_attr *attr, if (attr->task_fd_query.flags != 0) return -EINVAL; + rcu_read_lock(); task = get_pid_task(find_vpid(pid), PIDTYPE_PID); + rcu_read_unlock(); if (!task) return -ENOENT; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 30ac8ee8294c..a48de55f5630 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1012,7 +1012,9 @@ static int check_stack_write(struct bpf_verifier_env *env, bool sanitize = reg && is_spillable_regtype(reg->type); for (i = 0; i < size; i++) { - if (state->stack[spi].slot_type[i] == STACK_INVALID) { + u8 type = state->stack[spi].slot_type[i]; + + if (type != STACK_MISC && type != STACK_ZERO) { sanitize = true; break; } @@ -3496,6 +3498,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, coerce_reg_to_size(dst_reg, 4); } + __update_reg_bounds(dst_reg); __reg_deduce_bounds(dst_reg); __reg_bound_offset(dst_reg); return 0; @@ -5933,7 +5936,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH, insn->dst_reg, shift); - insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg, + insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1ULL << size * 8) - 1); } } diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index 75568fcf2180..4168e7d97e87 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -34,6 +34,25 @@ extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; } \ } while (0) +struct cgroup_pidlist; + +struct cgroup_file_ctx { + struct cgroup_namespace *ns; + + struct { + void *trigger; + } psi; + + struct { + bool started; + struct css_task_iter iter; + } procs; + + struct { + struct cgroup_pidlist *pidlist; + } procs1; +}; + /* * A cgroup can be associated with multiple css_sets as different tasks may * belong to different cgroups on different hierarchies. In the other @@ -129,7 +148,6 @@ extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; extern struct cgroup_subsys *cgroup_subsys[]; extern struct list_head cgroup_roots; -extern struct file_system_type cgroup_fs_type; /* iterate across the hierarchies */ #define for_each_root(root) \ diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 5456611874eb..55a61deb3d04 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -13,6 +13,7 @@ #include <linux/delayacct.h> #include <linux/pid_namespace.h> #include <linux/cgroupstats.h> +#include <linux/cpu.h> #include <trace/events/cgroup.h> @@ -55,6 +56,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) int retval = 0; mutex_lock(&cgroup_mutex); + get_online_cpus(); percpu_down_write(&cgroup_threadgroup_rwsem); for_each_root(root) { struct cgroup *from_cgrp; @@ -71,6 +73,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) break; } percpu_up_write(&cgroup_threadgroup_rwsem); + put_online_cpus(); mutex_unlock(&cgroup_mutex); return retval; @@ -392,10 +395,9 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, } css_task_iter_end(&it); length = n; - /* now sort & (if procs) strip out duplicates */ + /* now sort & strip out duplicates (tgids or recycled thread PIDs) */ sort(array, length, sizeof(pid_t), cmppid, NULL); - if (type == CGROUP_FILE_PROCS) - length = pidlist_uniq(array, length); + length = pidlist_uniq(array, length); l = cgroup_pidlist_find_create(cgrp, type); if (!l) { @@ -426,6 +428,7 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) * next pid to display, if any */ struct kernfs_open_file *of = s->private; + struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_pidlist *l; enum cgroup_filetype type = seq_cft(s)->private; @@ -435,25 +438,24 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) mutex_lock(&cgrp->pidlist_mutex); /* - * !NULL @of->priv indicates that this isn't the first start() - * after open. If the matching pidlist is around, we can use that. - * Look for it. Note that @of->priv can't be used directly. It - * could already have been destroyed. + * !NULL @ctx->procs1.pidlist indicates that this isn't the first + * start() after open. If the matching pidlist is around, we can use + * that. Look for it. Note that @ctx->procs1.pidlist can't be used + * directly. It could already have been destroyed. */ - if (of->priv) - of->priv = cgroup_pidlist_find(cgrp, type); + if (ctx->procs1.pidlist) + ctx->procs1.pidlist = cgroup_pidlist_find(cgrp, type); /* * Either this is the first start() after open or the matching * pidlist has been destroyed inbetween. Create a new one. */ - if (!of->priv) { - ret = pidlist_array_load(cgrp, type, - (struct cgroup_pidlist **)&of->priv); + if (!ctx->procs1.pidlist) { + ret = pidlist_array_load(cgrp, type, &ctx->procs1.pidlist); if (ret) return ERR_PTR(ret); } - l = of->priv; + l = ctx->procs1.pidlist; if (pid) { int end = l->length; @@ -481,7 +483,8 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) static void cgroup_pidlist_stop(struct seq_file *s, void *v) { struct kernfs_open_file *of = s->private; - struct cgroup_pidlist *l = of->priv; + struct cgroup_file_ctx *ctx = of->priv; + struct cgroup_pidlist *l = ctx->procs1.pidlist; if (l) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, @@ -492,7 +495,8 @@ static void cgroup_pidlist_stop(struct seq_file *s, void *v) static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; - struct cgroup_pidlist *l = of->priv; + struct cgroup_file_ctx *ctx = of->priv; + struct cgroup_pidlist *l = ctx->procs1.pidlist; pid_t *p = v; pid_t *end = l->list + l->length; /* @@ -535,10 +539,11 @@ static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of, goto out_unlock; /* - * Even if we're attaching all tasks in the thread group, we only - * need to check permissions on one of them. + * Even if we're attaching all tasks in the thread group, we only need + * to check permissions on one of them. Check permissions using the + * credentials from file open to protect against inherited fd attacks. */ - cred = current_cred(); + cred = of->file->f_cred; tcred = get_task_cred(task); if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && !uid_eq(cred->euid, tcred->uid) && @@ -577,6 +582,14 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); + /* + * Release agent gets called with all capabilities, + * require capabilities to set release agent. + */ + if ((of->file->f_cred->user_ns != &init_user_ns) || + !capable(CAP_SYS_ADMIN)) + return -EPERM; + cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; @@ -1048,6 +1061,7 @@ static int cgroup1_remount(struct kernfs_root *kf_root, int *flags, char *data) { int ret = 0; struct cgroup_root *root = cgroup_root_from_kf(kf_root); + struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; struct cgroup_sb_opts opts; u16 added_mask, removed_mask; @@ -1061,6 +1075,12 @@ static int cgroup1_remount(struct kernfs_root *kf_root, int *flags, char *data) if (opts.subsys_mask != root->subsys_mask || opts.release_agent) pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n", task_tgid_nr(current), current->comm); + /* See cgroup1_mount release_agent handling */ + if (opts.release_agent && + ((ns->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN))) { + ret = -EINVAL; + goto out_unlock; + } added_mask = opts.subsys_mask & ~root->subsys_mask; removed_mask = root->subsys_mask & ~opts.subsys_mask; @@ -1224,6 +1244,15 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags, ret = -EPERM; goto out_unlock; } + /* + * Release agent gets called with all capabilities, + * require capabilities to set release agent. + */ + if (opts.release_agent && + ((ns->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN))) { + ret = -EINVAL; + goto out_unlock; + } root = kzalloc(sizeof(*root), GFP_KERNEL); if (!root) { diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 63eff85f251f..6322b56529e9 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -55,6 +55,7 @@ #include <linux/nsproxy.h> #include <linux/file.h> #include <linux/sched/cputime.h> +#include <linux/cpu.h> #include <net/sock.h> #define CREATE_TRACE_POINTS @@ -677,7 +678,8 @@ struct css_set init_css_set = { .task_iters = LIST_HEAD_INIT(init_css_set.task_iters), .threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets), .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), - .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node), + .mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node), + .mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node), .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), /* @@ -1151,7 +1153,8 @@ static struct css_set *find_css_set(struct css_set *old_cset, INIT_LIST_HEAD(&cset->threaded_csets); INIT_HLIST_NODE(&cset->hlist); INIT_LIST_HEAD(&cset->cgrp_links); - INIT_LIST_HEAD(&cset->mg_preload_node); + INIT_LIST_HEAD(&cset->mg_src_preload_node); + INIT_LIST_HEAD(&cset->mg_dst_preload_node); INIT_LIST_HEAD(&cset->mg_node); /* Copy the set of subsystem state objects generated in @@ -1649,7 +1652,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) { struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; - int ssid, i, ret; + int ssid, ret; u16 dfl_disable_ss_mask = 0; lockdep_assert_held(&cgroup_mutex); @@ -1693,7 +1696,8 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; struct cgroup_subsys_state *css = cgroup_css(scgrp, ss); - struct css_set *cset; + struct css_set *cset, *cset_pos; + struct css_task_iter *it; WARN_ON(!css || cgroup_css(dcgrp, ss)); @@ -1711,9 +1715,22 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) css->cgroup = dcgrp; spin_lock_irq(&css_set_lock); - hash_for_each(css_set_table, i, cset, hlist) + WARN_ON(!list_empty(&dcgrp->e_csets[ss->id])); + list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id], + e_cset_node[ss->id]) { list_move_tail(&cset->e_cset_node[ss->id], &dcgrp->e_csets[ss->id]); + /* + * all css_sets of scgrp together in same order to dcgrp, + * patch in-flight iterators to preserve correct iteration. + * since the iterator is always advanced right away and + * finished when it->cset_pos meets it->cset_head, so only + * update it->cset_head is enough here. + */ + list_for_each_entry(it, &cset->task_iters, iters_node) + if (it->cset_head == &scgrp->e_csets[ss->id]) + it->cset_head = &dcgrp->e_csets[ss->id]; + } spin_unlock_irq(&css_set_lock); /* default hierarchy doesn't enable controllers by default */ @@ -2208,6 +2225,45 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) EXPORT_SYMBOL_GPL(task_cgroup_path); /** + * cgroup_attach_lock - Lock for ->attach() + * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem + * + * cgroup migration sometimes needs to stabilize threadgroups against forks and + * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach() + * implementations (e.g. cpuset), also need to disable CPU hotplug. + * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can + * lead to deadlocks. + * + * Bringing up a CPU may involve creating and destroying tasks which requires + * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside + * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while + * write-locking threadgroup_rwsem, the locking order is reversed and we end up + * waiting for an on-going CPU hotplug operation which in turn is waiting for + * the threadgroup_rwsem to be released to create new tasks. For more details: + * + * http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu + * + * Resolve the situation by always acquiring cpus_read_lock() before optionally + * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that + * CPU hotplug is disabled on entry. + */ +static void cgroup_attach_lock(void) +{ + get_online_cpus(); + percpu_down_write(&cgroup_threadgroup_rwsem); +} + +/** + * cgroup_attach_unlock - Undo cgroup_attach_lock() + * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem + */ +static void cgroup_attach_unlock(void) +{ + percpu_up_write(&cgroup_threadgroup_rwsem); + put_online_cpus(); +} + +/** * cgroup_migrate_add_task - add a migration target task to a migration context * @task: target task * @mgctx: target migration context @@ -2455,21 +2511,27 @@ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp) */ void cgroup_migrate_finish(struct cgroup_mgctx *mgctx) { - LIST_HEAD(preloaded); struct css_set *cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); - list_splice_tail_init(&mgctx->preloaded_src_csets, &preloaded); - list_splice_tail_init(&mgctx->preloaded_dst_csets, &preloaded); + list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets, + mg_src_preload_node) { + cset->mg_src_cgrp = NULL; + cset->mg_dst_cgrp = NULL; + cset->mg_dst_cset = NULL; + list_del_init(&cset->mg_src_preload_node); + put_css_set_locked(cset); + } - list_for_each_entry_safe(cset, tmp_cset, &preloaded, mg_preload_node) { + list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets, + mg_dst_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; - list_del_init(&cset->mg_preload_node); + list_del_init(&cset->mg_dst_preload_node); put_css_set_locked(cset); } @@ -2511,7 +2573,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset, src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); - if (!list_empty(&src_cset->mg_preload_node)) + if (!list_empty(&src_cset->mg_src_preload_node)) return; WARN_ON(src_cset->mg_src_cgrp); @@ -2522,7 +2584,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset, src_cset->mg_src_cgrp = src_cgrp; src_cset->mg_dst_cgrp = dst_cgrp; get_css_set(src_cset); - list_add_tail(&src_cset->mg_preload_node, &mgctx->preloaded_src_csets); + list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets); } /** @@ -2547,7 +2609,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) /* look up the dst cset for each src cset and link it to src */ list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets, - mg_preload_node) { + mg_src_preload_node) { struct css_set *dst_cset; struct cgroup_subsys *ss; int ssid; @@ -2566,7 +2628,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) if (src_cset == dst_cset) { src_cset->mg_src_cgrp = NULL; src_cset->mg_dst_cgrp = NULL; - list_del_init(&src_cset->mg_preload_node); + list_del_init(&src_cset->mg_src_preload_node); put_css_set(src_cset); put_css_set(dst_cset); continue; @@ -2574,8 +2636,8 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) src_cset->mg_dst_cset = dst_cset; - if (list_empty(&dst_cset->mg_preload_node)) - list_add_tail(&dst_cset->mg_preload_node, + if (list_empty(&dst_cset->mg_dst_preload_node)) + list_add_tail(&dst_cset->mg_dst_preload_node, &mgctx->preloaded_dst_csets); else put_css_set(dst_cset); @@ -2686,7 +2748,7 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup) if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return ERR_PTR(-EINVAL); - percpu_down_write(&cgroup_threadgroup_rwsem); + cgroup_attach_lock(); rcu_read_lock(); if (pid) { @@ -2717,7 +2779,7 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup) goto out_unlock_rcu; out_unlock_threadgroup: - percpu_up_write(&cgroup_threadgroup_rwsem); + cgroup_attach_unlock(); out_unlock_rcu: rcu_read_unlock(); return tsk; @@ -2732,7 +2794,7 @@ void cgroup_procs_write_finish(struct task_struct *task) /* release reference from cgroup_procs_write_start() */ put_task_struct(task); - percpu_up_write(&cgroup_threadgroup_rwsem); + cgroup_attach_unlock(); for_each_subsys(ss, ssid) if (ss->post_attach) ss->post_attach(); @@ -2791,7 +2853,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) lockdep_assert_held(&cgroup_mutex); - percpu_down_write(&cgroup_threadgroup_rwsem); + cgroup_attach_lock(); /* look up all csses currently attached to @cgrp's subtree */ spin_lock_irq(&css_set_lock); @@ -2809,7 +2871,8 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) goto out_finish; spin_lock_irq(&css_set_lock); - list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_preload_node) { + list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, + mg_src_preload_node) { struct task_struct *task, *ntask; /* all tasks in src_csets need to be migrated */ @@ -2821,7 +2884,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) ret = cgroup_migrate_execute(&mgctx); out_finish: cgroup_migrate_finish(&mgctx); - percpu_up_write(&cgroup_threadgroup_rwsem); + cgroup_attach_unlock(); return ret; } @@ -3451,24 +3514,43 @@ static int cpu_stat_show(struct seq_file *seq, void *v) static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of->kn->priv; + struct cgroup_file_ctx *ctx; + int ret; - if (cft->open) - return cft->open(of); - return 0; + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->ns = current->nsproxy->cgroup_ns; + get_cgroup_ns(ctx->ns); + of->priv = ctx; + + if (!cft->open) + return 0; + + ret = cft->open(of); + if (ret) { + put_cgroup_ns(ctx->ns); + kfree(ctx); + } + return ret; } static void cgroup_file_release(struct kernfs_open_file *of) { struct cftype *cft = of->kn->priv; + struct cgroup_file_ctx *ctx = of->priv; if (cft->release) cft->release(of); + put_cgroup_ns(ctx->ns); + kfree(ctx); } static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; + struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = of->kn->parent->priv; struct cftype *cft = of->kn->priv; struct cgroup_subsys_state *css; @@ -3482,7 +3564,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, */ if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) && !(cft->flags & CFTYPE_NS_DELEGATABLE) && - ns != &init_cgroup_ns && ns->root_cset->dfl_cgrp == cgrp) + ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp) return -EPERM; if (cft->write) @@ -4376,21 +4458,21 @@ void css_task_iter_end(struct css_task_iter *it) static void cgroup_procs_release(struct kernfs_open_file *of) { - if (of->priv) { - css_task_iter_end(of->priv); - kfree(of->priv); - } + struct cgroup_file_ctx *ctx = of->priv; + + if (ctx->procs.started) + css_task_iter_end(&ctx->procs.iter); } static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; - struct css_task_iter *it = of->priv; + struct cgroup_file_ctx *ctx = of->priv; if (pos) (*pos)++; - return css_task_iter_next(it); + return css_task_iter_next(&ctx->procs.iter); } static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, @@ -4398,21 +4480,18 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, { struct kernfs_open_file *of = s->private; struct cgroup *cgrp = seq_css(s)->cgroup; - struct css_task_iter *it = of->priv; + struct cgroup_file_ctx *ctx = of->priv; + struct css_task_iter *it = &ctx->procs.iter; /* * When a seq_file is seeked, it's always traversed sequentially * from position 0, so we can simply keep iterating on !0 *pos. */ - if (!it) { + if (!ctx->procs.started) { if (WARN_ON_ONCE((*pos))) return ERR_PTR(-EINVAL); - - it = kzalloc(sizeof(*it), GFP_KERNEL); - if (!it) - return ERR_PTR(-ENOMEM); - of->priv = it; css_task_iter_start(&cgrp->self, iter_flags, it); + ctx->procs.started = true; } else if (!(*pos)) { css_task_iter_end(it); css_task_iter_start(&cgrp->self, iter_flags, it); @@ -4447,9 +4526,9 @@ static int cgroup_procs_show(struct seq_file *s, void *v) static int cgroup_procs_write_permission(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, - struct super_block *sb) + struct super_block *sb, + struct cgroup_namespace *ns) { - struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; struct cgroup *com_cgrp = src_cgrp; struct inode *inode; int ret; @@ -4485,8 +4564,10 @@ static int cgroup_procs_write_permission(struct cgroup *src_cgrp, static ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { + struct cgroup_file_ctx *ctx = of->priv; struct cgroup *src_cgrp, *dst_cgrp; struct task_struct *task; + const struct cred *saved_cred; ssize_t ret; dst_cgrp = cgroup_kn_lock_live(of->kn, false); @@ -4503,8 +4584,16 @@ static ssize_t cgroup_procs_write(struct kernfs_open_file *of, src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); spin_unlock_irq(&css_set_lock); + /* + * Process and thread migrations follow same delegation rule. Check + * permissions using the credentials from file open to protect against + * inherited fd attacks. + */ + saved_cred = override_creds(of->file->f_cred); ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, - of->file->f_path.dentry->d_sb); + of->file->f_path.dentry->d_sb, + ctx->ns); + revert_creds(saved_cred); if (ret) goto out_finish; @@ -4526,8 +4615,10 @@ static void *cgroup_threads_start(struct seq_file *s, loff_t *pos) static ssize_t cgroup_threads_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { + struct cgroup_file_ctx *ctx = of->priv; struct cgroup *src_cgrp, *dst_cgrp; struct task_struct *task; + const struct cred *saved_cred; ssize_t ret; buf = strstrip(buf); @@ -4546,9 +4637,16 @@ static ssize_t cgroup_threads_write(struct kernfs_open_file *of, src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); spin_unlock_irq(&css_set_lock); - /* thread migrations follow the cgroup.procs delegation rule */ + /* + * Process and thread migrations follow same delegation rule. Check + * permissions using the credentials from file open to protect against + * inherited fd attacks. + */ + saved_cred = override_creds(of->file->f_cred); ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, - of->file->f_path.dentry->d_sb); + of->file->f_path.dentry->d_sb, + ctx->ns); + revert_creds(saved_cred); if (ret) goto out_finish; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index ff956ccbb6df..3067d3e5a51d 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -830,8 +830,8 @@ static void rebuild_sched_domains_locked(void) cpumask_var_t *doms; int ndoms; + lockdep_assert_cpus_held(); lockdep_assert_held(&cpuset_mutex); - get_online_cpus(); /* * We have raced with CPU hotplug. Don't do anything to avoid @@ -839,15 +839,13 @@ static void rebuild_sched_domains_locked(void) * Anyways, hotplug work item will rebuild sched domains. */ if (!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask)) - goto out; + return; /* Generate domain masks and attrs */ ndoms = generate_sched_domains(&doms, &attr); /* Have scheduler rebuild the domains */ partition_sched_domains(ndoms, doms, attr); -out: - put_online_cpus(); } #else /* !CONFIG_SMP */ static void rebuild_sched_domains_locked(void) @@ -857,9 +855,11 @@ static void rebuild_sched_domains_locked(void) void rebuild_sched_domains(void) { + get_online_cpus(); mutex_lock(&cpuset_mutex); rebuild_sched_domains_locked(); mutex_unlock(&cpuset_mutex); + put_online_cpus(); } /** @@ -1504,7 +1504,9 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset) cs = css_cs(css); mutex_lock(&cpuset_mutex); - css_cs(css)->attach_in_progress--; + cs->attach_in_progress--; + if (!cs->attach_in_progress) + wake_up(&cpuset_attach_wq); mutex_unlock(&cpuset_mutex); } @@ -1528,6 +1530,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) cgroup_taskset_first(tset, &css); cs = css_cs(css); + lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ mutex_lock(&cpuset_mutex); /* prepare for attach */ @@ -1611,6 +1614,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, cpuset_filetype_t type = cft->private; int retval = 0; + get_online_cpus(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) { retval = -ENODEV; @@ -1648,6 +1652,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, } out_unlock: mutex_unlock(&cpuset_mutex); + put_online_cpus(); return retval; } @@ -1658,6 +1663,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, cpuset_filetype_t type = cft->private; int retval = -ENODEV; + get_online_cpus(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; @@ -1672,6 +1678,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, } out_unlock: mutex_unlock(&cpuset_mutex); + put_online_cpus(); return retval; } @@ -1710,6 +1717,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, kernfs_break_active_protection(of->kn); flush_work(&cpuset_hotplug_work); + get_online_cpus(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; @@ -1735,6 +1743,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, free_trial_cpuset(trialcs); out_unlock: mutex_unlock(&cpuset_mutex); + put_online_cpus(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); flush_workqueue(cpuset_migrate_mm_wq); @@ -1979,6 +1988,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) if (!parent) return 0; + get_online_cpus(); mutex_lock(&cpuset_mutex); set_bit(CS_ONLINE, &cs->flags); @@ -2029,6 +2039,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) spin_unlock_irq(&callback_lock); out_unlock: mutex_unlock(&cpuset_mutex); + put_online_cpus(); return 0; } @@ -2042,6 +2053,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); + get_online_cpus(); mutex_lock(&cpuset_mutex); if (is_sched_load_balance(cs)) @@ -2051,6 +2063,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) clear_bit(CS_ONLINE, &cs->flags); mutex_unlock(&cpuset_mutex); + put_online_cpus(); } static void cpuset_css_free(struct cgroup_subsys_state *css) @@ -2397,8 +2410,11 @@ static struct notifier_block cpuset_track_online_nodes_nb = { */ void __init cpuset_init_smp(void) { - cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask); - top_cpuset.mems_allowed = node_states[N_MEMORY]; + /* + * cpus_allowd/mems_allowed set to v2 values in the initial + * cpuset_bind() call will be reset to v1 values in another + * cpuset_bind() call when v1 cpuset is mounted. + */ top_cpuset.old_mems_allowed = top_cpuset.mems_allowed; cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c index b05f1dd58a62..313e66b8c662 100644 --- a/kernel/cgroup/namespace.c +++ b/kernel/cgroup/namespace.c @@ -148,9 +148,3 @@ const struct proc_ns_operations cgroupns_operations = { .install = cgroupns_install, .owner = cgroupns_owner, }; - -static __init int cgroup_namespaces_init(void) -{ - return 0; -} -subsys_initcall(cgroup_namespaces_init); diff --git a/kernel/compat.c b/kernel/compat.c index e4548a9e9c52..5f320b0db8d0 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -307,7 +307,7 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len, if (len & (sizeof(compat_ulong_t)-1)) return -EINVAL; - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; ret = sched_getaffinity(pid, mask); diff --git a/kernel/cpu.c b/kernel/cpu.c index d6fd362afc81..34c09c3d37bc 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -32,6 +32,7 @@ #include <linux/slab.h> #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> +#include <linux/random.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS @@ -1404,6 +1405,11 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, + [CPUHP_RANDOM_PREPARE] = { + .name = "random:prepare", + .startup.single = random_prepare_cpu, + .teardown.single = NULL, + }, [CPUHP_WORKQUEUE_PREP] = { .name = "workqueue:prepare", .startup.single = workqueue_prepare_cpu, @@ -1412,7 +1418,7 @@ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_HRTIMERS_PREPARE] = { .name = "hrtimers:prepare", .startup.single = hrtimers_prepare_cpu, - .teardown.single = hrtimers_dead_cpu, + .teardown.single = NULL, }, [CPUHP_SMPCFD_PREPARE] = { .name = "smpcfd:prepare", @@ -1479,6 +1485,12 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = NULL, .teardown.single = smpcfd_dying_cpu, }, + [CPUHP_AP_HRTIMERS_DYING] = { + .name = "hrtimers:dying", + .startup.single = NULL, + .teardown.single = hrtimers_cpu_dying, + }, + /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { @@ -1520,6 +1532,11 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = workqueue_online_cpu, .teardown.single = workqueue_offline_cpu, }, + [CPUHP_AP_RANDOM_ONLINE] = { + .name = "random:online", + .startup.single = random_online_cpu, + .teardown.single = NULL, + }, [CPUHP_AP_RCUTREE_ONLINE] = { .name = "RCU/tree:online", .startup.single = rcutree_online_cpu, diff --git a/kernel/cred.c b/kernel/cred.c index a9f0f8b21d8c..8c58f0f63af2 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -101,17 +101,17 @@ static void put_cred_rcu(struct rcu_head *rcu) #ifdef CONFIG_DEBUG_CREDENTIALS if (cred->magic != CRED_MAGIC_DEAD || - atomic_read(&cred->usage) != 0 || + atomic_long_read(&cred->usage) != 0 || read_cred_subscribers(cred) != 0) panic("CRED: put_cred_rcu() sees %p with" - " mag %x, put %p, usage %d, subscr %d\n", + " mag %x, put %p, usage %ld, subscr %d\n", cred, cred->magic, cred->put_addr, - atomic_read(&cred->usage), + atomic_long_read(&cred->usage), read_cred_subscribers(cred)); #else - if (atomic_read(&cred->usage) != 0) - panic("CRED: put_cred_rcu() sees %p with usage %d\n", - cred, atomic_read(&cred->usage)); + if (atomic_long_read(&cred->usage) != 0) + panic("CRED: put_cred_rcu() sees %p with usage %ld\n", + cred, atomic_long_read(&cred->usage)); #endif security_cred_free(cred); @@ -134,11 +134,11 @@ static void put_cred_rcu(struct rcu_head *rcu) */ void __put_cred(struct cred *cred) { - kdebug("__put_cred(%p{%d,%d})", cred, - atomic_read(&cred->usage), + kdebug("__put_cred(%p{%ld,%d})", cred, + atomic_long_read(&cred->usage), read_cred_subscribers(cred)); - BUG_ON(atomic_read(&cred->usage) != 0); + BUG_ON(atomic_long_read(&cred->usage) != 0); #ifdef CONFIG_DEBUG_CREDENTIALS BUG_ON(read_cred_subscribers(cred) != 0); cred->magic = CRED_MAGIC_DEAD; @@ -161,8 +161,8 @@ void exit_creds(struct task_struct *tsk) { struct cred *cred; - kdebug("exit_creds(%u,%p,%p,{%d,%d})", tsk->pid, tsk->real_cred, tsk->cred, - atomic_read(&tsk->cred->usage), + kdebug("exit_creds(%u,%p,%p,{%ld,%d})", tsk->pid, tsk->real_cred, tsk->cred, + atomic_long_read(&tsk->cred->usage), read_cred_subscribers(tsk->cred)); cred = (struct cred *) tsk->real_cred; @@ -197,7 +197,7 @@ const struct cred *get_task_cred(struct task_struct *task) do { cred = __task_cred((task)); BUG_ON(!cred); - } while (!atomic_inc_not_zero(&((struct cred *)cred)->usage)); + } while (!atomic_long_inc_not_zero(&((struct cred *)cred)->usage)); rcu_read_unlock(); return cred; @@ -215,7 +215,7 @@ struct cred *cred_alloc_blank(void) if (!new) return NULL; - atomic_set(&new->usage, 1); + atomic_long_set(&new->usage, 1); #ifdef CONFIG_DEBUG_CREDENTIALS new->magic = CRED_MAGIC; #endif @@ -262,7 +262,7 @@ struct cred *prepare_creds(void) memcpy(new, old, sizeof(struct cred)); new->non_rcu = 0; - atomic_set(&new->usage, 1); + atomic_long_set(&new->usage, 1); set_cred_subscribers(new, 0); get_group_info(new->group_info); get_uid(new->user); @@ -338,8 +338,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) p->real_cred = get_cred(p->cred); get_cred(p->cred); alter_cred_subscribers(p->cred, 2); - kdebug("share_creds(%p{%d,%d})", - p->cred, atomic_read(&p->cred->usage), + kdebug("share_creds(%p{%ld,%d})", + p->cred, atomic_long_read(&p->cred->usage), read_cred_subscribers(p->cred)); atomic_inc(&p->cred->user->processes); return 0; @@ -429,8 +429,8 @@ int commit_creds(struct cred *new) struct task_struct *task = current; const struct cred *old = task->real_cred; - kdebug("commit_creds(%p{%d,%d})", new, - atomic_read(&new->usage), + kdebug("commit_creds(%p{%ld,%d})", new, + atomic_long_read(&new->usage), read_cred_subscribers(new)); BUG_ON(task->cred != old); @@ -439,7 +439,7 @@ int commit_creds(struct cred *new) validate_creds(old); validate_creds(new); #endif - BUG_ON(atomic_read(&new->usage) < 1); + BUG_ON(atomic_long_read(&new->usage) < 1); get_cred(new); /* we will require a ref for the subj creds too */ @@ -512,14 +512,14 @@ EXPORT_SYMBOL(commit_creds); */ void abort_creds(struct cred *new) { - kdebug("abort_creds(%p{%d,%d})", new, - atomic_read(&new->usage), + kdebug("abort_creds(%p{%ld,%d})", new, + atomic_long_read(&new->usage), read_cred_subscribers(new)); #ifdef CONFIG_DEBUG_CREDENTIALS BUG_ON(read_cred_subscribers(new) != 0); #endif - BUG_ON(atomic_read(&new->usage) < 1); + BUG_ON(atomic_long_read(&new->usage) < 1); put_cred(new); } EXPORT_SYMBOL(abort_creds); @@ -535,8 +535,8 @@ const struct cred *override_creds(const struct cred *new) { const struct cred *old = current->cred; - kdebug("override_creds(%p{%d,%d})", new, - atomic_read(&new->usage), + kdebug("override_creds(%p{%ld,%d})", new, + atomic_long_read(&new->usage), read_cred_subscribers(new)); validate_creds(old); @@ -558,8 +558,8 @@ const struct cred *override_creds(const struct cred *new) rcu_assign_pointer(current->cred, new); alter_cred_subscribers(old, -1); - kdebug("override_creds() = %p{%d,%d}", old, - atomic_read(&old->usage), + kdebug("override_creds() = %p{%ld,%d}", old, + atomic_long_read(&old->usage), read_cred_subscribers(old)); return old; } @@ -576,8 +576,8 @@ void revert_creds(const struct cred *old) { const struct cred *override = current->cred; - kdebug("revert_creds(%p{%d,%d})", old, - atomic_read(&old->usage), + kdebug("revert_creds(%p{%ld,%d})", old, + atomic_long_read(&old->usage), read_cred_subscribers(old)); validate_creds(old); @@ -637,7 +637,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) *new = *old; new->non_rcu = 0; - atomic_set(&new->usage, 1); + atomic_long_set(&new->usage, 1); set_cred_subscribers(new, 0); get_uid(new->user); get_user_ns(new->user_ns); @@ -760,8 +760,8 @@ static void dump_invalid_creds(const struct cred *cred, const char *label, cred == tsk->cred ? "[eff]" : ""); printk(KERN_ERR "CRED: ->magic=%x, put_addr=%p\n", cred->magic, cred->put_addr); - printk(KERN_ERR "CRED: ->usage=%d, subscr=%d\n", - atomic_read(&cred->usage), + printk(KERN_ERR "CRED: ->usage=%ld, subscr=%d\n", + atomic_long_read(&cred->usage), read_cred_subscribers(cred)); printk(KERN_ERR "CRED: ->*uid = { %d,%d,%d,%d }\n", from_kuid_munged(&init_user_ns, cred->uid), @@ -833,9 +833,9 @@ EXPORT_SYMBOL(__validate_process_creds); */ void validate_creds_for_do_exit(struct task_struct *tsk) { - kdebug("validate_creds_for_do_exit(%p,%p{%d,%d})", + kdebug("validate_creds_for_do_exit(%p,%p{%ld,%d})", tsk->real_cred, tsk->cred, - atomic_read(&tsk->cred->usage), + atomic_long_read(&tsk->cred->usage), read_cred_subscribers(tsk->cred)); __validate_process_creds(tsk, __FILE__, __LINE__); diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index dc6bf35e7884..7f78657dfa00 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -400,6 +400,13 @@ int kdb_set(int argc, const char **argv) return KDB_ARGCOUNT; /* + * Censor sensitive variables + */ + if (strcmp(argv[1], "PROMPT") == 0 && + !kdb_check_flags(KDB_ENABLE_MEM_READ, kdb_cmd_enabled, false)) + return KDB_NOPERM; + + /* * Check for internal variables */ if (strcmp(argv[1], "KDBDEBUG") == 0) { @@ -1299,14 +1306,9 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs, *(cmd_hist[cmd_head]) = '\0'; do_full_getstr: -#if defined(CONFIG_SMP) + /* PROMPT can only be set if we have MEM_READ permission. */ snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT"), raw_smp_processor_id()); -#else - snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT")); -#endif - if (defcmd_in_progress) - strncat(kdb_prompt_str, "[defcmd]", CMD_BUFLEN); /* * Fetch command from keyboard diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c index 597d40893862..4c7ffd094a57 100644 --- a/kernel/dma/coherent.c +++ b/kernel/dma/coherent.c @@ -369,8 +369,10 @@ static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev) static void rmem_dma_device_release(struct reserved_mem *rmem, struct device *dev) { - if (dev) + if (dev) { dev->dma_mem = NULL; + dev->dma_mem = NULL; + } } static const struct reserved_mem_ops rmem_dma_ops = { diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 1c82b0d25498..c345a6e2f7b7 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -469,7 +469,7 @@ void debug_dma_dump_mappings(struct device *dev) * At any time debug_dma_assert_idle() can be called to trigger a * warning if any cachelines in the given page are in the active set. */ -static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT); +static RADIX_TREE(dma_active_cacheline, GFP_ATOMIC); static DEFINE_SPINLOCK(radix_lock); #define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1) #define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT) @@ -963,7 +963,7 @@ static int device_dma_allocations(struct device *dev, struct dma_debug_entry **o static int dma_debug_device_change(struct notifier_block *nb, unsigned long action, void *data) { struct device *dev = data; - struct dma_debug_entry *uninitialized_var(entry); + struct dma_debug_entry *entry; int count; if (dma_debug_disabled()) @@ -1056,7 +1056,7 @@ static __init int dma_debug_cmdline(char *str) global_disable = true; } - return 0; + return 1; } static __init int dma_debug_entries_cmdline(char *str) @@ -1065,7 +1065,7 @@ static __init int dma_debug_entries_cmdline(char *str) return -EINVAL; if (!get_option(&str, &nr_prealloc_entries)) nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES; - return 0; + return 1; } __setup("dma_debug=", dma_debug_cmdline); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 6f7d4e977c5c..b1e2ce2f9c2d 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -587,10 +587,15 @@ found: */ for (i = 0; i < nslots; i++) io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT); - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && - (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) + /* + * When dir == DMA_FROM_DEVICE we could omit the copy from the orig + * to the tlb buffer, if we knew for sure the device will + * overwirte the entire current content. But we don't. Thus + * unconditional bounce may prevent leaking swiotlb content (i.e. + * kernel memory) to user-space. + */ + if (orig_addr) swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE); - return tlb_addr; } diff --git a/kernel/events/core.c b/kernel/events/core.c index e6e11b598438..1f215aa8f30d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -798,7 +798,7 @@ static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list); */ static void perf_cgroup_switch(struct task_struct *task, int mode) { - struct perf_cpu_context *cpuctx; + struct perf_cpu_context *cpuctx, *tmp; struct list_head *list; unsigned long flags; @@ -809,7 +809,7 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) local_irq_save(flags); list = this_cpu_ptr(&cgrp_cpuctx_list); - list_for_each_entry(cpuctx, list, cgrp_cpuctx_entry) { + list_for_each_entry_safe(cpuctx, tmp, list, cgrp_cpuctx_entry) { WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0); perf_ctx_lock(cpuctx, cpuctx->task_ctx); @@ -1133,6 +1133,11 @@ static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx) return 0; } +static int perf_mux_hrtimer_restart_ipi(void *arg) +{ + return perf_mux_hrtimer_restart(arg); +} + void perf_pmu_disable(struct pmu *pmu) { int *count = this_cpu_ptr(pmu->pmu_disable_count); @@ -1705,28 +1710,34 @@ static inline void perf_event__state_init(struct perf_event *event) PERF_EVENT_STATE_INACTIVE; } -static void __perf_event_read_size(struct perf_event *event, int nr_siblings) +static int __perf_event_read_size(u64 read_format, int nr_siblings) { int entry = sizeof(u64); /* value */ int size = 0; int nr = 1; - if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) size += sizeof(u64); - if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) size += sizeof(u64); - if (event->attr.read_format & PERF_FORMAT_ID) + if (read_format & PERF_FORMAT_ID) + entry += sizeof(u64); + + if (read_format & PERF_FORMAT_LOST) entry += sizeof(u64); - if (event->attr.read_format & PERF_FORMAT_GROUP) { + if (read_format & PERF_FORMAT_GROUP) { nr += nr_siblings; size += sizeof(u64); } - size += entry * nr; - event->read_size = size; + /* + * Since perf_event_validate_size() limits this to 16k and inhibits + * adding more siblings, this will never overflow. + */ + return size + nr * entry; } static void __perf_event_header_size(struct perf_event *event, u64 sample_type) @@ -1767,8 +1778,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type) */ static void perf_event__header_size(struct perf_event *event) { - __perf_event_read_size(event, - event->group_leader->nr_siblings); + event->read_size = + __perf_event_read_size(event->attr.read_format, + event->group_leader->nr_siblings); __perf_event_header_size(event, event->attr.sample_type); } @@ -1799,23 +1811,44 @@ static void perf_event__id_header_size(struct perf_event *event) event->id_header_size = size; } +/* + * Check that adding an event to the group does not result in anybody + * overflowing the 64k event limit imposed by the output buffer. + * + * Specifically, check that the read_size for the event does not exceed 16k, + * read_size being the one term that grows with groups size. Since read_size + * depends on per-event read_format, also (re)check the existing events. + * + * This leaves 48k for the constant size fields and things like callchains, + * branch stacks and register sets. + */ static bool perf_event_validate_size(struct perf_event *event) { - /* - * The values computed here will be over-written when we actually - * attach the event. - */ - __perf_event_read_size(event, event->group_leader->nr_siblings + 1); - __perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ); - perf_event__id_header_size(event); + struct perf_event *sibling, *group_leader = event->group_leader; + + if (__perf_event_read_size(event->attr.read_format, + group_leader->nr_siblings + 1) > 16*1024) + return false; + + if (__perf_event_read_size(group_leader->attr.read_format, + group_leader->nr_siblings + 1) > 16*1024) + return false; /* - * Sum the lot; should not exceed the 64k limit we have on records. - * Conservative limit to allow for callchains and other variable fields. + * When creating a new group leader, group_leader->ctx is initialized + * after the size has been validated, but we cannot safely use + * for_each_sibling_event() until group_leader->ctx is set. A new group + * leader cannot have any siblings yet, so we can safely skip checking + * the non-existent siblings. */ - if (event->read_size + event->header_size + - event->id_header_size + sizeof(struct perf_event_header) >= 16*1024) - return false; + if (event == group_leader) + return true; + + for_each_sibling_event(sibling, group_leader) { + if (__perf_event_read_size(sibling->attr.read_format, + group_leader->nr_siblings + 1) > 16*1024) + return false; + } return true; } @@ -1843,6 +1876,7 @@ static void perf_group_attach(struct perf_event *event) list_add_tail(&event->sibling_list, &group_leader->sibling_list); group_leader->nr_siblings++; + group_leader->group_generation++; perf_event__header_size(group_leader); @@ -1913,6 +1947,7 @@ static void perf_group_detach(struct perf_event *event) if (event->group_leader != event) { list_del_init(&event->sibling_list); event->group_leader->nr_siblings--; + event->group_leader->group_generation++; goto out; } @@ -4750,7 +4785,7 @@ static int __perf_read_group_add(struct perf_event *leader, u64 read_format, u64 *values) { struct perf_event_context *ctx = leader->ctx; - struct perf_event *sub; + struct perf_event *sub, *parent; unsigned long flags; int n = 1; /* skip @nr */ int ret; @@ -4760,6 +4795,33 @@ static int __perf_read_group_add(struct perf_event *leader, return ret; raw_spin_lock_irqsave(&ctx->lock, flags); + /* + * Verify the grouping between the parent and child (inherited) + * events is still in tact. + * + * Specifically: + * - leader->ctx->lock pins leader->sibling_list + * - parent->child_mutex pins parent->child_list + * - parent->ctx->mutex pins parent->sibling_list + * + * Because parent->ctx != leader->ctx (and child_list nests inside + * ctx->mutex), group destruction is not atomic between children, also + * see perf_event_release_kernel(). Additionally, parent can grow the + * group. + * + * Therefore it is possible to have parent and child groups in a + * different configuration and summing over such a beast makes no sense + * what so ever. + * + * Reject this. + */ + parent = leader->parent; + if (parent && + (parent->group_generation != leader->group_generation || + parent->nr_siblings != leader->nr_siblings)) { + ret = -ECHILD; + goto unlock; + } /* * Since we co-schedule groups, {enabled,running} times of siblings @@ -4782,15 +4844,20 @@ static int __perf_read_group_add(struct perf_event *leader, values[n++] += perf_event_count(leader); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(leader); + if (read_format & PERF_FORMAT_LOST) + values[n++] = atomic64_read(&leader->lost_samples); for_each_sibling_event(sub, leader) { values[n++] += perf_event_count(sub); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(sub); + if (read_format & PERF_FORMAT_LOST) + values[n++] = atomic64_read(&sub->lost_samples); } +unlock: raw_spin_unlock_irqrestore(&ctx->lock, flags); - return 0; + return ret; } static int perf_read_group(struct perf_event *event, @@ -4809,10 +4876,6 @@ static int perf_read_group(struct perf_event *event, values[0] = 1 + leader->nr_siblings; - /* - * By locking the child_mutex of the leader we effectively - * lock the child list of all siblings.. XXX explain how. - */ mutex_lock(&leader->child_mutex); ret = __perf_read_group_add(leader, read_format, values); @@ -4843,7 +4906,7 @@ static int perf_read_one(struct perf_event *event, u64 read_format, char __user *buf) { u64 enabled, running; - u64 values[4]; + u64 values[5]; int n = 0; values[n++] = __perf_event_read_value(event, &enabled, &running); @@ -4853,6 +4916,8 @@ static int perf_read_one(struct perf_event *event, values[n++] = running; if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(event); + if (read_format & PERF_FORMAT_LOST) + values[n++] = atomic64_read(&event->lost_samples); if (copy_to_user(buf, values, n * sizeof(u64))) return -EFAULT; @@ -5719,10 +5784,10 @@ again: if (!atomic_inc_not_zero(&event->rb->mmap_count)) { /* - * Raced against perf_mmap_close() through - * perf_event_set_output(). Try again, hope for better - * luck. + * Raced against perf_mmap_close(); remove the + * event and try again. */ + ring_buffer_attach(event, NULL); mutex_unlock(&event->mmap_mutex); goto again; } @@ -6162,7 +6227,7 @@ static void perf_output_read_one(struct perf_output_handle *handle, u64 enabled, u64 running) { u64 read_format = event->attr.read_format; - u64 values[4]; + u64 values[5]; int n = 0; values[n++] = perf_event_count(event); @@ -6176,6 +6241,8 @@ static void perf_output_read_one(struct perf_output_handle *handle, } if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(event); + if (read_format & PERF_FORMAT_LOST) + values[n++] = atomic64_read(&event->lost_samples); __output_copy(handle, values, n * sizeof(u64)); } @@ -6186,7 +6253,7 @@ static void perf_output_read_group(struct perf_output_handle *handle, { struct perf_event *leader = event->group_leader, *sub; u64 read_format = event->attr.read_format; - u64 values[5]; + u64 values[6]; int n = 0; values[n++] = 1 + leader->nr_siblings; @@ -6204,6 +6271,8 @@ static void perf_output_read_group(struct perf_output_handle *handle, values[n++] = perf_event_count(leader); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(leader); + if (read_format & PERF_FORMAT_LOST) + values[n++] = atomic64_read(&leader->lost_samples); __output_copy(handle, values, n * sizeof(u64)); @@ -6217,6 +6286,8 @@ static void perf_output_read_group(struct perf_output_handle *handle, values[n++] = perf_event_count(sub); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(sub); + if (read_format & PERF_FORMAT_LOST) + values[n++] = atomic64_read(&sub->lost_samples); __output_copy(handle, values, n * sizeof(u64)); } @@ -7843,8 +7914,8 @@ __perf_event_account_interrupt(struct perf_event *event, int throttle) hwc->interrupts = 1; } else { hwc->interrupts++; - if (unlikely(throttle - && hwc->interrupts >= max_samples_per_tick)) { + if (unlikely(throttle && + hwc->interrupts > max_samples_per_tick)) { __this_cpu_inc(perf_throttled_count); tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS); hwc->interrupts = MAX_INTERRUPTS; @@ -9137,8 +9208,11 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, } /* ready to consume more filters */ + kfree(filename); + filename = NULL; state = IF_STATE_ACTION; filter = NULL; + kernel = 0; } } @@ -9641,8 +9715,7 @@ perf_event_mux_interval_ms_store(struct device *dev, cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer); - cpu_function_call(cpu, - (remote_function_f)perf_mux_hrtimer_restart, cpuctx); + cpu_function_call(cpu, perf_mux_hrtimer_restart_ipi, cpuctx); } cpus_read_unlock(); mutex_unlock(&mux_interval_mutex); @@ -9679,13 +9752,15 @@ static int pmu_dev_alloc(struct pmu *pmu) pmu->dev->groups = pmu->attr_groups; device_initialize(pmu->dev); - ret = dev_set_name(pmu->dev, "%s", pmu->name); - if (ret) - goto free_dev; dev_set_drvdata(pmu->dev, pmu); pmu->dev->bus = &pmu_bus; pmu->dev->release = pmu_dev_release; + + ret = dev_set_name(pmu->dev, "%s", pmu->name); + if (ret) + goto free_dev; + ret = device_add(pmu->dev); if (ret) goto free_dev; @@ -10393,14 +10468,25 @@ err_size: goto out; } +static void mutex_lock_double(struct mutex *a, struct mutex *b) +{ + if (b < a) + swap(a, b); + + mutex_lock(a); + mutex_lock_nested(b, SINGLE_DEPTH_NESTING); +} + static int perf_event_set_output(struct perf_event *event, struct perf_event *output_event) { struct ring_buffer *rb = NULL; int ret = -EINVAL; - if (!output_event) + if (!output_event) { + mutex_lock(&event->mmap_mutex); goto set; + } /* don't allow circular references */ if (event == output_event) @@ -10415,7 +10501,7 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event) /* * If its not a per-cpu rb, it must be the same task. */ - if (output_event->cpu == -1 && output_event->ctx != event->ctx) + if (output_event->cpu == -1 && output_event->hw.target != event->hw.target) goto out; /* @@ -10438,8 +10524,15 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event) event->pmu != output_event->pmu) goto out; + /* + * Hold both mmap_mutex to serialize against perf_mmap_close(). Since + * output_event is already on rb->event_list, and the list iteration + * restarts after every removal, it is guaranteed this new event is + * observed *OR* if output_event is already removed, it's guaranteed we + * observe !rb->mmap_count. + */ + mutex_lock_double(&event->mmap_mutex, &output_event->mmap_mutex); set: - mutex_lock(&event->mmap_mutex); /* Can't redirect output if we've got an active mmap() */ if (atomic_read(&event->mmap_count)) goto unlock; @@ -10449,6 +10542,12 @@ set: rb = ring_buffer_get(output_event); if (!rb) goto unlock; + + /* did we race against perf_mmap_close() */ + if (!atomic_read(&rb->mmap_count)) { + ring_buffer_put(rb); + goto unlock; + } } ring_buffer_attach(event, rb); @@ -10456,20 +10555,13 @@ set: ret = 0; unlock: mutex_unlock(&event->mmap_mutex); + if (output_event) + mutex_unlock(&output_event->mmap_mutex); out: return ret; } -static void mutex_lock_double(struct mutex *a, struct mutex *b) -{ - if (b < a) - swap(a, b); - - mutex_lock(a); - mutex_lock_nested(b, SINGLE_DEPTH_NESTING); -} - static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id) { bool nmi_safe = false; @@ -10553,7 +10645,7 @@ SYSCALL_DEFINE5(perf_event_open, struct perf_event *group_leader = NULL, *output_event = NULL; struct perf_event *event, *sibling; struct perf_event_attr attr; - struct perf_event_context *ctx, *uninitialized_var(gctx); + struct perf_event_context *ctx, *gctx; struct file *event_file = NULL; struct fd group = {NULL, 0}; struct task_struct *task = NULL; @@ -10755,6 +10847,9 @@ SYSCALL_DEFINE5(perf_event_open, * Do not allow to attach to a group in a different task * or CPU context. If we're moving SW events, we'll fix * this up later, so allow that. + * + * Racy, not holding group_leader->ctx->mutex, see comment with + * perf_event_ctx_lock(). */ if (!move_group && group_leader->ctx != ctx) goto err_context; @@ -10804,6 +10899,7 @@ SYSCALL_DEFINE5(perf_event_open, } else { perf_event_ctx_unlock(group_leader, gctx); move_group = 0; + goto not_move_group; } } @@ -10820,7 +10916,17 @@ SYSCALL_DEFINE5(perf_event_open, } } else { mutex_lock(&ctx->mutex); + + /* + * Now that we hold ctx->lock, (re)validate group_leader->ctx == ctx, + * see the group_leader && !move_group test earlier. + */ + if (group_leader && group_leader->ctx != ctx) { + err = -EINVAL; + goto err_locked; + } } +not_move_group: if (ctx->task == TASK_TOMBSTONE) { err = -ESRCH; @@ -11563,6 +11669,8 @@ static int inherit_group(struct perf_event *parent_event, if (IS_ERR(child_ctr)) return PTR_ERR(child_ctr); } + if (leader) + leader->group_generation = parent_event->group_generation; return 0; } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 12f351b253bb..ddcbd03eccbb 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -165,8 +165,10 @@ __perf_output_begin(struct perf_output_handle *handle, goto out; if (unlikely(rb->paused)) { - if (rb->nr_pages) + if (rb->nr_pages) { local_inc(&rb->lost); + atomic64_inc(&event->lost_samples); + } goto out; } @@ -249,6 +251,7 @@ __perf_output_begin(struct perf_output_handle *handle, fail: local_inc(&rb->lost); + atomic64_inc(&event->lost_samples); perf_output_put_handle(handle); out: rcu_read_unlock(); @@ -639,6 +642,12 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, } } + /* + * kcalloc_node() is unable to allocate buffer if the size is larger + * than: PAGE_SIZE << MAX_ORDER; directly bail out in this case. + */ + if (get_order((unsigned long)nr_pages * sizeof(void *)) > MAX_ORDER) + return -ENOMEM; rb->aux_pages = kcalloc_node(nr_pages, sizeof(void *), GFP_KERNEL, node); if (!rb->aux_pages) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 24342bca11f2..72ae05d65066 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1887,7 +1887,7 @@ static void handle_swbp(struct pt_regs *regs) { struct uprobe *uprobe; unsigned long bp_vaddr; - int uninitialized_var(is_swbp); + int is_swbp; bp_vaddr = uprobe_get_swbp_addr(regs); if (bp_vaddr == get_trampoline_vaddr()) diff --git a/kernel/exit.c b/kernel/exit.c index 908e7a33e1fc..0d1cca15e66f 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -62,12 +62,59 @@ #include <linux/random.h> #include <linux/rcuwait.h> #include <linux/compat.h> +#include <linux/sysfs.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/pgtable.h> #include <asm/mmu_context.h> +/* + * The default value should be high enough to not crash a system that randomly + * crashes its kernel from time to time, but low enough to at least not permit + * overflowing 32-bit refcounts or the ldsem writer count. + */ +static unsigned int oops_limit = 10000; + +#ifdef CONFIG_SYSCTL +static struct ctl_table kern_exit_table[] = { + { + .procname = "oops_limit", + .data = &oops_limit, + .maxlen = sizeof(oops_limit), + .mode = 0644, + .proc_handler = proc_douintvec, + }, + { } +}; + +static __init int kernel_exit_sysctls_init(void) +{ + register_sysctl_init("kernel", kern_exit_table); + return 0; +} +late_initcall(kernel_exit_sysctls_init); +#endif + +static atomic_t oops_count = ATOMIC_INIT(0); + +#ifdef CONFIG_SYSFS +static ssize_t oops_count_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + return sysfs_emit(page, "%d\n", atomic_read(&oops_count)); +} + +static struct kobj_attribute oops_count_attr = __ATTR_RO(oops_count); + +static __init int kernel_exit_sysfs_init(void) +{ + sysfs_add_file_to_group(kernel_kobj, &oops_count_attr.attr, NULL); + return 0; +} +late_initcall(kernel_exit_sysfs_init); +#endif + static void __unhash_process(struct task_struct *p, bool group_dead) { nr_threads--; @@ -93,7 +140,7 @@ static void __exit_signal(struct task_struct *tsk) struct signal_struct *sig = tsk->signal; bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; - struct tty_struct *uninitialized_var(tty); + struct tty_struct *tty; u64 utime, stime; sighand = rcu_dereference_check(tsk->sighand, @@ -922,6 +969,31 @@ void __noreturn do_exit(long code) } EXPORT_SYMBOL_GPL(do_exit); +void __noreturn make_task_dead(int signr) +{ + /* + * Take the task off the cpu after something catastrophic has + * happened. + */ + unsigned int limit; + + /* + * Every time the system oopses, if the oops happens while a reference + * to an object was held, the reference leaks. + * If the oops doesn't also leak memory, repeated oopsing can cause + * reference counters to wrap around (if they're not using refcount_t). + * This means that repeated oopsing can make unexploitable-looking bugs + * exploitable through repeated oopsing. + * To make sure this can't happen, place an upper bound on how often the + * kernel may oops without panic(). + */ + limit = READ_ONCE(oops_limit); + if (atomic_inc_return(&oops_count) >= limit && limit) + panic("Oopsed too often (kernel.oops_limit is %d)", limit); + + do_exit(signr); +} + void complete_and_exit(struct completion *comp, long code) { if (comp) diff --git a/kernel/extable.c b/kernel/extable.c index 6a5b61ebc66c..b3ca75d6bf92 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -46,7 +46,8 @@ u32 __initdata __visible main_extable_sort_needed = 1; /* Sort the kernel's built-in exception table */ void __init sort_main_extable(void) { - if (main_extable_sort_needed && __stop___ex_table > __start___ex_table) { + if (main_extable_sort_needed && + &__stop___ex_table > &__start___ex_table) { pr_notice("Sorting __ex_table...\n"); sort_extable(__start___ex_table, __stop___ex_table); } diff --git a/kernel/futex.c b/kernel/futex.c index 3c67da9b8408..ca2a2a894839 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1398,7 +1398,7 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval, static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval) { int err; - u32 uninitialized_var(curval); + u32 curval; if (unlikely(should_fail_futex(true))) return -EFAULT; @@ -1569,7 +1569,7 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q) */ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_state) { - u32 uninitialized_var(curval), newval; + u32 curval, newval; struct task_struct *new_owner; bool postunlock = false; DEFINE_WAKE_Q(wake_q); @@ -3083,7 +3083,7 @@ uaddr_faulted: */ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) { - u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current); + u32 curval, uval, vpid = task_pid_vnr(current); union futex_key key = FUTEX_KEY_INIT; struct futex_hash_bucket *hb; struct futex_q *top_waiter; @@ -3558,7 +3558,7 @@ err_unlock: static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, bool pi, bool pending_op) { - u32 uval, uninitialized_var(nval), mval; + u32 uval, nval, mval; int err; /* Futex address must be 32bit aligned */ @@ -3688,7 +3688,7 @@ static void exit_robust_list(struct task_struct *curr) struct robust_list_head __user *head = curr->robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; - unsigned int uninitialized_var(next_pi); + unsigned int next_pi; unsigned long futex_offset; int rc; @@ -3987,7 +3987,7 @@ static void compat_exit_robust_list(struct task_struct *curr) struct compat_robust_list_head __user *head = curr->compat_robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; - unsigned int uninitialized_var(next_pi); + unsigned int next_pi; compat_uptr_t uentry, next_uentry, upending; compat_long_t futex_offset; int rc; diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index 5b9e76117ded..1c2bd1f23536 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -33,6 +33,13 @@ #define GCOV_TAG_FUNCTION_LENGTH 3 +/* Since GCC 12.1 sizes are in BYTES and not in WORDS (4B). */ +#if (__GNUC__ >= 12) +#define GCOV_UNIT_SIZE 4 +#else +#define GCOV_UNIT_SIZE 1 +#endif + static struct gcov_info *gcov_info_head; /** @@ -78,6 +85,7 @@ struct gcov_fn_info { * @version: gcov version magic indicating the gcc version used for compilation * @next: list head for a singly-linked list * @stamp: uniquifying time stamp + * @checksum: unique object checksum * @filename: name of the associated gcov data file * @merge: merge functions (null for unused counter type) * @n_functions: number of instrumented functions @@ -90,6 +98,10 @@ struct gcov_info { unsigned int version; struct gcov_info *next; unsigned int stamp; + /* Since GCC 12.1 a checksum field is added. */ +#if (__GNUC__ >= 12) + unsigned int checksum; +#endif const char *filename; void (*merge[GCOV_COUNTERS])(gcov_type *, unsigned int); unsigned int n_functions; @@ -439,12 +451,18 @@ static size_t convert_to_gcda(char *buffer, struct gcov_info *info) pos += store_gcov_u32(buffer, pos, info->version); pos += store_gcov_u32(buffer, pos, info->stamp); +#if (__GNUC__ >= 12) + /* Use zero as checksum of the compilation unit. */ + pos += store_gcov_u32(buffer, pos, 0); +#endif + for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) { fi_ptr = info->functions[fi_idx]; /* Function record. */ pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION); - pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION_LENGTH); + pos += store_gcov_u32(buffer, pos, + GCOV_TAG_FUNCTION_LENGTH * GCOV_UNIT_SIZE); pos += store_gcov_u32(buffer, pos, fi_ptr->ident); pos += store_gcov_u32(buffer, pos, fi_ptr->lineno_checksum); pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum); @@ -458,7 +476,8 @@ static size_t convert_to_gcda(char *buffer, struct gcov_info *info) /* Counter record. */ pos += store_gcov_u32(buffer, pos, GCOV_TAG_FOR_COUNTER(ct_idx)); - pos += store_gcov_u32(buffer, pos, ci_ptr->num * 2); + pos += store_gcov_u32(buffer, pos, + ci_ptr->num * 2 * GCOV_UNIT_SIZE); for (cv_idx = 0; cv_idx < ci_ptr->num; cv_idx++) { pos += store_gcov_u64(buffer, pos, diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index e2999a070a99..4195e7ad1ff2 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -537,21 +537,34 @@ EXPORT_SYMBOL_GPL(irq_setup_alt_chip); void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk, unsigned int clr, unsigned int set) { - unsigned int i = gc->irq_base; + unsigned int i, virq; raw_spin_lock(&gc_lock); list_del(&gc->list); raw_spin_unlock(&gc_lock); - for (; msk; msk >>= 1, i++) { + for (i = 0; msk; msk >>= 1, i++) { if (!(msk & 0x01)) continue; + /* + * Interrupt domain based chips store the base hardware + * interrupt number in gc::irq_base. Otherwise gc::irq_base + * contains the base Linux interrupt number. + */ + if (gc->domain) { + virq = irq_find_mapping(gc->domain, gc->irq_base + i); + if (!virq) + continue; + } else { + virq = gc->irq_base + i; + } + /* Remove handler first. That will mask the irq line */ - irq_set_handler(i, NULL); - irq_set_chip(i, &no_irq_chip); - irq_set_chip_data(i, NULL); - irq_modify_status(i, clr, set); + irq_set_handler(virq, NULL); + irq_set_chip(virq, &no_irq_chip); + irq_set_chip_data(virq, NULL); + irq_modify_status(virq, clr, set); } } EXPORT_SYMBOL_GPL(irq_remove_generic_chip); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 38554bc35375..e2f7afcb1ae6 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -188,7 +188,7 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) retval = __handle_irq_event_percpu(desc, &flags); - add_interrupt_randomness(desc->irq_data.irq, flags); + add_interrupt_randomness(desc->irq_data.irq); if (!noirqdebug) note_interrupt(desc, retval); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 3f4618510d05..10eccbc84686 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -29,12 +29,14 @@ extern struct irqaction chained_action; * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed * IRQTF_AFFINITY - irq thread is requested to adjust affinity * IRQTF_FORCED_THREAD - irq action is force threaded + * IRQTF_READY - signals that irq thread is ready */ enum { IRQTF_RUNTHREAD, IRQTF_WARNED, IRQTF_AFFINITY, IRQTF_FORCED_THREAD, + IRQTF_READY, }; /* diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 26814a14013c..3633540b0f16 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -404,6 +404,7 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, lockdep_set_class(&desc->lock, &irq_desc_lock_class); mutex_init(&desc->request_mutex); init_rcu_head(&desc->rcu); + init_waitqueue_head(&desc->wait_for_threads); desc_set_defaults(irq, desc, node, affinity, owner); irqd_set(&desc->irq_data, flags); @@ -568,6 +569,7 @@ int __init early_irq_init(void) raw_spin_lock_init(&desc[i].lock); lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); mutex_init(&desc[i].request_mutex); + init_waitqueue_head(&desc[i].wait_for_threads); desc_set_defaults(i, &desc[i], node, NULL, NULL); } return arch_early_irq_init(); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 1e42fc2ad4d5..3ebe231a5eda 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -494,6 +494,9 @@ void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) return; hwirq = irq_data->hwirq; + + mutex_lock(&irq_domain_mutex); + irq_set_status_flags(irq, IRQ_NOREQUEST); /* remove chip and handler */ @@ -513,10 +516,12 @@ void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) /* Clear reverse map for this hwirq */ irq_domain_clear_mapping(domain, hwirq); + + mutex_unlock(&irq_domain_mutex); } -int irq_domain_associate(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq) +static int irq_domain_associate_locked(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq) { struct irq_data *irq_data = irq_get_irq_data(virq); int ret; @@ -529,7 +534,6 @@ int irq_domain_associate(struct irq_domain *domain, unsigned int virq, if (WARN(irq_data->domain, "error: virq%i is already associated", virq)) return -EINVAL; - mutex_lock(&irq_domain_mutex); irq_data->hwirq = hwirq; irq_data->domain = domain; if (domain->ops->map) { @@ -546,7 +550,6 @@ int irq_domain_associate(struct irq_domain *domain, unsigned int virq, } irq_data->domain = NULL; irq_data->hwirq = 0; - mutex_unlock(&irq_domain_mutex); return ret; } @@ -557,12 +560,23 @@ int irq_domain_associate(struct irq_domain *domain, unsigned int virq, domain->mapcount++; irq_domain_set_mapping(domain, hwirq, irq_data); - mutex_unlock(&irq_domain_mutex); irq_clear_status_flags(virq, IRQ_NOREQUEST); return 0; } + +int irq_domain_associate(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq) +{ + int ret; + + mutex_lock(&irq_domain_mutex); + ret = irq_domain_associate_locked(domain, virq, hwirq); + mutex_unlock(&irq_domain_mutex); + + return ret; +} EXPORT_SYMBOL_GPL(irq_domain_associate); void irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base, @@ -818,13 +832,8 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) } irq_data = irq_get_irq_data(virq); - if (!irq_data) { - if (irq_domain_is_hierarchy(domain)) - irq_domain_free_irqs(virq, 1); - else - irq_dispose_mapping(virq); + if (WARN_ON(!irq_data)) return 0; - } /* Store trigger type */ irqd_set_trigger_type(irq_data, type); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index c377dbb869f8..18f3cdbf41fd 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1064,6 +1064,31 @@ static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action) } /* + * Internal function to notify that a interrupt thread is ready. + */ +static void irq_thread_set_ready(struct irq_desc *desc, + struct irqaction *action) +{ + set_bit(IRQTF_READY, &action->thread_flags); + wake_up(&desc->wait_for_threads); +} + +/* + * Internal function to wake up a interrupt thread and wait until it is + * ready. + */ +static void wake_up_and_wait_for_irq_thread_ready(struct irq_desc *desc, + struct irqaction *action) +{ + if (!action || !action->thread) + return; + + wake_up_process(action->thread); + wait_event(desc->wait_for_threads, + test_bit(IRQTF_READY, &action->thread_flags)); +} + +/* * Interrupt handler thread */ static int irq_thread(void *data) @@ -1074,6 +1099,8 @@ static int irq_thread(void *data) irqreturn_t (*handler_fn)(struct irq_desc *desc, struct irqaction *action); + irq_thread_set_ready(desc, action); + if (force_irqthreads && test_bit(IRQTF_FORCED_THREAD, &action->thread_flags)) handler_fn = irq_forced_thread_fn; @@ -1462,8 +1489,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } if (!shared) { - init_waitqueue_head(&desc->wait_for_threads); - /* Setup the type (level, edge polarity) if configured: */ if (new->flags & IRQF_TRIGGER_MASK) { ret = __irq_set_trigger(desc, @@ -1553,14 +1578,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) irq_setup_timings(desc, new); - /* - * Strictly no need to wake it up, but hung_task complains - * when no hard interrupt wakes the thread up. - */ - if (new->thread) - wake_up_process(new->thread); - if (new->secondary) - wake_up_process(new->secondary->thread); + wake_up_and_wait_for_irq_thread_ready(desc, new); + wake_up_and_wait_for_irq_thread_ready(desc, new->secondary); register_irq_proc(irq, desc); new->dir = NULL; diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index 8e586858bcf4..d25edbb87119 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -466,16 +466,16 @@ unsigned int irq_matrix_reserved(struct irq_matrix *m) } /** - * irq_matrix_allocated - Get the number of allocated irqs on the local cpu + * irq_matrix_allocated - Get the number of allocated non-managed irqs on the local CPU * @m: Pointer to the matrix to search * - * This returns number of allocated irqs + * This returns number of allocated non-managed interrupts. */ unsigned int irq_matrix_allocated(struct irq_matrix *m) { struct cpumap *cm = this_cpu_ptr(m->maps); - return cm->allocated; + return cm->allocated - cm->managed_allocated; } #ifdef CONFIG_GENERIC_IRQ_DEBUGFS diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 6b3d7f7211dd..3666d434a8f5 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1020,6 +1020,7 @@ int crash_shrink_memory(unsigned long new_size) start = crashk_res.start; end = crashk_res.end; old_size = (end == 0) ? 0 : end - start + 1; + new_size = roundup(new_size, KEXEC_CRASH_MEM_ALIGN); if (new_size >= old_size) { ret = (new_size == old_size) ? 0 : -EINVAL; goto unlock; @@ -1031,9 +1032,7 @@ int crash_shrink_memory(unsigned long new_size) goto unlock; } - start = roundup(start, KEXEC_CRASH_MEM_ALIGN); - end = roundup(start + new_size, KEXEC_CRASH_MEM_ALIGN); - + end = start + new_size; crash_free_reserved_phys_range(end, crashk_res.end); if ((start == end) && (crashk_res.parent != NULL)) diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 89d41c0a10f1..416c1e0fdc91 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -111,40 +111,6 @@ int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf, #endif /* - * arch_kexec_apply_relocations_add - apply relocations of type RELA - * @pi: Purgatory to be relocated. - * @section: Section relocations applying to. - * @relsec: Section containing RELAs. - * @symtab: Corresponding symtab. - * - * Return: 0 on success, negative errno on error. - */ -int __weak -arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section, - const Elf_Shdr *relsec, const Elf_Shdr *symtab) -{ - pr_err("RELA relocation unsupported.\n"); - return -ENOEXEC; -} - -/* - * arch_kexec_apply_relocations - apply relocations of type REL - * @pi: Purgatory to be relocated. - * @section: Section relocations applying to. - * @relsec: Section containing RELs. - * @symtab: Corresponding symtab. - * - * Return: 0 on success, negative errno on error. - */ -int __weak -arch_kexec_apply_relocations(struct purgatory_info *pi, Elf_Shdr *section, - const Elf_Shdr *relsec, const Elf_Shdr *symtab) -{ - pr_err("REL relocation unsupported.\n"); - return -ENOEXEC; -} - -/* * Free up memory used by kernel, initrd, and command line. This is temporary * memory allocation which is not needed any more after these buffers have * been loaded into separate segments and have been copied elsewhere. @@ -827,10 +793,22 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi, } offset = ALIGN(offset, align); + + /* + * Check if the segment contains the entry point, if so, + * calculate the value of image->start based on it. + * If the compiler has produced more than one .text section + * (Eg: .text.hot), they are generally after the main .text + * section, and they shall not be used to calculate + * image->start. So do not re-calculate image->start if it + * is not set to the initial value, and warn the user so they + * have a chance to fix their purgatory's linker script. + */ if (sechdrs[i].sh_flags & SHF_EXECINSTR && pi->ehdr->e_entry >= sechdrs[i].sh_addr && pi->ehdr->e_entry < (sechdrs[i].sh_addr - + sechdrs[i].sh_size)) { + + sechdrs[i].sh_size) && + !WARN_ON(kbuf->image->start != pi->ehdr->e_entry)) { kbuf->image->start -= sechdrs[i].sh_addr; kbuf->image->start += kbuf->mem + offset; } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 993b84cc1db5..e1fb6453e8e9 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -418,8 +418,8 @@ static inline int kprobe_optready(struct kprobe *p) return 0; } -/* Return true(!0) if the kprobe is disarmed. Note: p must be on hash list */ -static inline int kprobe_disarmed(struct kprobe *p) +/* Return true if the kprobe is disarmed. Note: p must be on hash list */ +bool kprobe_disarmed(struct kprobe *p) { struct optimized_kprobe *op; @@ -626,7 +626,7 @@ void wait_for_kprobe_optimizer(void) mutex_unlock(&kprobe_mutex); } -static bool optprobe_queued_unopt(struct optimized_kprobe *op) +bool optprobe_queued_unopt(struct optimized_kprobe *op) { struct optimized_kprobe *_op; @@ -1566,7 +1566,9 @@ static int check_kprobe_address_safe(struct kprobe *p, preempt_disable(); /* Ensure it is not in reserved area nor out of text */ - if (!kernel_text_address((unsigned long) p->addr) || + if (!(core_kernel_text((unsigned long) p->addr) || + is_module_text_address((unsigned long) p->addr)) || + in_gate_area_no_mm((unsigned long) p->addr) || within_kprobe_blacklist((unsigned long) p->addr) || jump_label_text_reserved(p->addr, p->addr) || find_bug((unsigned long)p->addr)) { @@ -1708,11 +1710,12 @@ static struct kprobe *__disable_kprobe(struct kprobe *p) /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { /* - * If kprobes_all_disarmed is set, orig_p - * should have already been disarmed, so - * skip unneed disarming process. + * Don't be lazy here. Even if 'kprobes_all_disarmed' + * is false, 'orig_p' might not have been armed yet. + * Note arm_all_kprobes() __tries__ to arm all kprobes + * on the best effort basis. */ - if (!kprobes_all_disarmed) { + if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) { ret = disarm_kprobe(orig_p, true); if (ret) { p->flags &= ~KPROBE_FLAG_DISABLED; @@ -2169,8 +2172,11 @@ int enable_kprobe(struct kprobe *kp) if (!kprobes_all_disarmed && kprobe_disabled(p)) { p->flags &= ~KPROBE_FLAG_DISABLED; ret = arm_kprobe(p); - if (ret) + if (ret) { p->flags |= KPROBE_FLAG_DISABLED; + if (p != kp) + kp->flags |= KPROBE_FLAG_DISABLED; + } } out: mutex_unlock(&kprobe_mutex); diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index 5bc349805e03..20277ad6b7d2 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -563,9 +563,23 @@ void klp_reverse_transition(void) /* Called from copy_process() during fork */ void klp_copy_process(struct task_struct *child) { - child->patch_state = current->patch_state; - /* TIF_PATCH_PENDING gets copied in setup_thread_stack() */ + /* + * The parent process may have gone through a KLP transition since + * the thread flag was copied in setup_thread_stack earlier. Bring + * the task flag up to date with the parent here. + * + * The operation is serialized against all klp_*_transition() + * operations by the tasklist_lock. The only exception is + * klp_update_patch_state(current), but we cannot race with + * that because we are current. + */ + if (test_tsk_thread_flag(current, TIF_PATCH_PENDING)) + set_tsk_thread_flag(child, TIF_PATCH_PENDING); + else + clear_tsk_thread_flag(child, TIF_PATCH_PENDING); + + child->patch_state = current->patch_state; } /* diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 4dc79f57af82..46a6d1f7c351 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -1246,7 +1246,7 @@ static int noop_count(struct lock_list *entry, void *data) static unsigned long __lockdep_count_forward_deps(struct lock_list *this) { unsigned long count = 0; - struct lock_list *uninitialized_var(target_entry); + struct lock_list *target_entry; __bfs_forwards(this, (void *)&count, noop_count, &target_entry); @@ -1274,7 +1274,7 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class) static unsigned long __lockdep_count_backward_deps(struct lock_list *this) { unsigned long count = 0; - struct lock_list *uninitialized_var(target_entry); + struct lock_list *target_entry; __bfs_backwards(this, (void *)&count, noop_count, &target_entry); @@ -2662,7 +2662,7 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this, { int ret; struct lock_list root; - struct lock_list *uninitialized_var(target_entry); + struct lock_list *target_entry; root.parent = NULL; root.class = hlock_class(this); diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 65a3b7e55b9f..4fd05d9d5d6d 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -439,7 +439,6 @@ retry: } while (!time_after(jiffies, stress->timeout)); kfree(order); - kfree(stress); } struct reorder_lock { @@ -504,7 +503,6 @@ out: list_for_each_entry_safe(ll, ln, &locks, link) kfree(ll); kfree(order); - kfree(stress); } static void stress_one_work(struct work_struct *work) @@ -525,8 +523,6 @@ static void stress_one_work(struct work_struct *work) break; } } while (!time_after(jiffies, stress->timeout)); - - kfree(stress); } #define STRESS_INORDER BIT(0) @@ -537,15 +533,24 @@ static void stress_one_work(struct work_struct *work) static int stress(int nlocks, int nthreads, unsigned int flags) { struct ww_mutex *locks; - int n; + struct stress *stress_array; + int n, count; locks = kmalloc_array(nlocks, sizeof(*locks), GFP_KERNEL); if (!locks) return -ENOMEM; + stress_array = kmalloc_array(nthreads, sizeof(*stress_array), + GFP_KERNEL); + if (!stress_array) { + kfree(locks); + return -ENOMEM; + } + for (n = 0; n < nlocks; n++) ww_mutex_init(&locks[n], &ww_class); + count = 0; for (n = 0; nthreads; n++) { struct stress *stress; void (*fn)(struct work_struct *work); @@ -569,9 +574,7 @@ static int stress(int nlocks, int nthreads, unsigned int flags) if (!fn) continue; - stress = kmalloc(sizeof(*stress), GFP_KERNEL); - if (!stress) - break; + stress = &stress_array[count++]; INIT_WORK(&stress->work, fn); stress->locks = locks; @@ -586,6 +589,7 @@ static int stress(int nlocks, int nthreads, unsigned int flags) for (n = 0; n < nlocks; n++) ww_mutex_destroy(&locks[n]); + kfree(stress_array); kfree(locks); return 0; diff --git a/kernel/module.c b/kernel/module.c index 68637e661d75..2ec961945fa8 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2261,15 +2261,26 @@ static void free_module(struct module *mod) void *__symbol_get(const char *symbol) { struct module *owner; + enum mod_license license; const struct kernel_symbol *sym; preempt_disable(); - sym = find_symbol(symbol, &owner, NULL, NULL, true, true); - if (sym && strong_try_module_get(owner)) + sym = find_symbol(symbol, &owner, NULL, &license, true, true); + if (!sym) + goto fail; + if (license != GPL_ONLY) { + pr_warn("failing symbol_get of non-GPLONLY symbol %s.\n", + symbol); + goto fail; + } + if (strong_try_module_get(owner)) sym = NULL; preempt_enable(); return sym ? (void *)kernel_symbol_value(sym) : NULL; +fail: + preempt_enable(); + return NULL; } EXPORT_SYMBOL_GPL(__symbol_get); @@ -3478,7 +3489,8 @@ static bool finished_loading(const char *name) sched_annotate_sleep(); mutex_lock(&module_mutex); mod = find_module_all(name, strlen(name), true); - ret = !mod || mod->state == MODULE_STATE_LIVE; + ret = !mod || mod->state == MODULE_STATE_LIVE + || mod->state == MODULE_STATE_GOING; mutex_unlock(&module_mutex); return ret; @@ -3526,12 +3538,6 @@ static noinline int do_init_module(struct module *mod) } freeinit->module_init = mod->init_layout.base; - /* - * We want to find out whether @mod uses async during init. Clear - * PF_USED_ASYNC. async_schedule*() will set it. - */ - current->flags &= ~PF_USED_ASYNC; - do_mod_ctors(mod); /* Start the module */ if (mod->init != NULL) @@ -3557,22 +3563,13 @@ static noinline int do_init_module(struct module *mod) /* * We need to finish all async code before the module init sequence - * is done. This has potential to deadlock. For example, a newly - * detected block device can trigger request_module() of the - * default iosched from async probing task. Once userland helper - * reaches here, async_synchronize_full() will wait on the async - * task waiting on request_module() and deadlock. + * is done. This has potential to deadlock if synchronous module + * loading is requested from async (which is not allowed!). * - * This deadlock is avoided by perfomring async_synchronize_full() - * iff module init queued any async jobs. This isn't a full - * solution as it will deadlock the same if module loading from - * async jobs nests more than once; however, due to the various - * constraints, this hack seems to be the best option for now. - * Please refer to the following thread for details. - * - * http://thread.gmane.org/gmane.linux.kernel/1420814 + * See commit 0fdff3ec6d87 ("async, kmod: warn on synchronous + * request_module() from async workers") for more details. */ - if (!mod->async_probe_requested && (current->flags & PF_USED_ASYNC)) + if (!mod->async_probe_requested) async_synchronize_full(); ftrace_free_mem(mod, mod->init_layout.base, mod->init_layout.base + @@ -3647,20 +3644,35 @@ static int add_unformed_module(struct module *mod) mod->state = MODULE_STATE_UNFORMED; -again: mutex_lock(&module_mutex); old = find_module_all(mod->name, strlen(mod->name), true); if (old != NULL) { - if (old->state != MODULE_STATE_LIVE) { + if (old->state == MODULE_STATE_COMING + || old->state == MODULE_STATE_UNFORMED) { /* Wait in case it fails to load. */ mutex_unlock(&module_mutex); err = wait_event_interruptible(module_wq, finished_loading(mod->name)); if (err) goto out_unlocked; - goto again; + + /* The module might have gone in the meantime. */ + mutex_lock(&module_mutex); + old = find_module_all(mod->name, strlen(mod->name), + true); } - err = -EEXIST; + + /* + * We are here only when the same module was being loaded. Do + * not try to load it again right now. It prevents long delays + * caused by serialized module load failures. It might happen + * when more devices of the same type trigger load of + * a particular module. + */ + if (old && old->state == MODULE_STATE_LIVE) + err = -EEXIST; + else + err = -EBUSY; goto out; } mod_update_bounds(mod); diff --git a/kernel/padata.c b/kernel/padata.c index 7f2b6d369fd4..a9e14183e188 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -121,7 +121,7 @@ int padata_do_parallel(struct padata_instance *pinst, if (!cpumask_test_cpu(cb_cpu, pd->cpumask.cbcpu)) goto out; - err = -EBUSY; + err = -EBUSY; if ((pinst->flags & PADATA_RESET)) goto out; diff --git a/kernel/panic.c b/kernel/panic.c index 8138a676fb7d..982ecba286c0 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -29,6 +29,7 @@ #include <linux/bug.h> #include <linux/ratelimit.h> #include <linux/debugfs.h> +#include <linux/sysfs.h> #include <asm/sections.h> #define PANIC_TIMER_STEP 100 @@ -42,6 +43,7 @@ static int pause_on_oops_flag; static DEFINE_SPINLOCK(pause_on_oops_lock); bool crash_kexec_post_notifiers; int panic_on_warn __read_mostly; +static unsigned int warn_limit __read_mostly; int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); @@ -50,6 +52,45 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); +#ifdef CONFIG_SYSCTL +static struct ctl_table kern_panic_table[] = { + { + .procname = "warn_limit", + .data = &warn_limit, + .maxlen = sizeof(warn_limit), + .mode = 0644, + .proc_handler = proc_douintvec, + }, + { } +}; + +static __init int kernel_panic_sysctls_init(void) +{ + register_sysctl_init("kernel", kern_panic_table); + return 0; +} +late_initcall(kernel_panic_sysctls_init); +#endif + +static atomic_t warn_count = ATOMIC_INIT(0); + +#ifdef CONFIG_SYSFS +static ssize_t warn_count_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + return sysfs_emit(page, "%d\n", atomic_read(&warn_count)); +} + +static struct kobj_attribute warn_count_attr = __ATTR_RO(warn_count); + +static __init int kernel_panic_sysfs_init(void) +{ + sysfs_add_file_to_group(kernel_kobj, &warn_count_attr.attr, NULL); + return 0; +} +late_initcall(kernel_panic_sysfs_init); +#endif + static long no_blink(int state) { return 0; @@ -125,6 +166,19 @@ void nmi_panic(struct pt_regs *regs, const char *msg) } EXPORT_SYMBOL(nmi_panic); +void check_panic_on_warn(const char *origin) +{ + unsigned int limit; + + if (panic_on_warn) + panic("%s: panic_on_warn set ...\n", origin); + + limit = READ_ONCE(warn_limit); + if (atomic_inc_return(&warn_count) >= limit && limit) + panic("%s: system warned too often (kernel.warn_limit is %d)", + origin, limit); +} + /** * panic - halt the system * @fmt: The text string to print @@ -142,6 +196,16 @@ void panic(const char *fmt, ...) int old_cpu, this_cpu; bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers; + if (panic_on_warn) { + /* + * This thread may hit another WARN() in the panic path. + * Resetting this prevents additional WARN() from panicking the + * system on this thread. Other threads are blocked by the + * panic_mutex in panic(). + */ + panic_on_warn = 0; + } + /* * Disable local interrupts. This will prevent panic_smp_self_stop * from deadlocking the first cpu that invokes the panic, since @@ -530,16 +594,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint, if (args) vprintk(args->fmt, args->args); - if (panic_on_warn) { - /* - * This thread may hit another WARN() in the panic path. - * Resetting this prevents additional WARN() from panicking the - * system on this thread. Other threads are blocked by the - * panic_mutex in panic(). - */ - panic_on_warn = 0; - panic("panic_on_warn set ...\n"); - } + check_panic_on_warn("kernel"); print_modules(); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 6670a44ec5d4..6737ae6ffbae 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -626,7 +626,7 @@ static void power_down(void) int error; if (hibernation_mode == HIBERNATION_SUSPEND) { - error = suspend_devices_and_enter(PM_SUSPEND_MEM); + error = suspend_devices_and_enter(mem_sleep_current); if (error) { hibernation_mode = hibernation_ops ? HIBERNATION_PLATFORM : @@ -1219,7 +1219,7 @@ static int __init resumedelay_setup(char *str) int rc = kstrtouint(str, 0, &resume_delay); if (rc) - return rc; + pr_warn("resumedelay: bad option string '%s'\n", str); return 1; } diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index f2635fc751d9..5abe4582df1b 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -2376,8 +2376,9 @@ static void *get_highmem_page_buffer(struct page *page, pbe->copy_page = tmp; } else { /* Copy of the page will be stored in normal memory */ - kaddr = safe_pages_list; - safe_pages_list = safe_pages_list->next; + kaddr = __get_safe_page(ca->gfp_mask); + if (!kaddr) + return ERR_PTR(-ENOMEM); pbe->copy_page = virt_to_page(kaddr); } pbe->next = highmem_pblist; @@ -2557,8 +2558,9 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca) return ERR_PTR(-ENOMEM); } pbe->orig_address = page_address(page); - pbe->address = safe_pages_list; - safe_pages_list = safe_pages_list->next; + pbe->address = __get_safe_page(ca->gfp_mask); + if (!pbe->address) + return ERR_PTR(-ENOMEM); pbe->next = restore_pblist; restore_pblist = pbe; return pbe->address; @@ -2589,8 +2591,6 @@ int snapshot_write_next(struct snapshot_handle *handle) if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages) return 0; - handle->sync_read = 1; - if (!handle->cur) { if (!buffer) /* This makes the buffer be freed by swsusp_free() */ @@ -2631,7 +2631,6 @@ int snapshot_write_next(struct snapshot_handle *handle) memory_bm_position_reset(&orig_bm); restore_pblist = NULL; handle->buffer = get_buffer(&orig_bm, &ca); - handle->sync_read = 0; if (IS_ERR(handle->buffer)) return PTR_ERR(handle->buffer); } @@ -2643,9 +2642,8 @@ int snapshot_write_next(struct snapshot_handle *handle) handle->buffer = get_buffer(&orig_bm, &ca); if (IS_ERR(handle->buffer)) return PTR_ERR(handle->buffer); - if (handle->buffer != buffer) - handle->sync_read = 0; } + handle->sync_read = (handle->buffer == buffer); handle->cur++; return PAGE_SIZE; } diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c index 6a897e8b2a88..3f6345d60256 100644 --- a/kernel/power/suspend_test.c +++ b/kernel/power/suspend_test.c @@ -158,22 +158,22 @@ static int __init setup_test_suspend(char *value) value++; suspend_type = strsep(&value, ","); if (!suspend_type) - return 0; + return 1; repeat = strsep(&value, ","); if (repeat) { if (kstrtou32(repeat, 0, &test_repeat_count_max)) - return 0; + return 1; } for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) if (!strcmp(pm_labels[i], suspend_type)) { test_state_label = pm_labels[i]; - return 0; + return 1; } printk(warn_bad_state, suspend_type); - return 0; + return 1; } __setup("test_suspend", setup_test_suspend); diff --git a/kernel/power/user.c b/kernel/power/user.c index 2d8b60a3c86b..6a11154b3d52 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -29,6 +29,7 @@ #include "power.h" +static bool need_wait; #define SNAPSHOT_MINOR 231 @@ -82,7 +83,7 @@ static int snapshot_open(struct inode *inode, struct file *filp) * Resuming. We may need to wait for the image device to * appear. */ - wait_for_device_probe(); + need_wait = true; data->swap = -1; data->mode = O_WRONLY; @@ -174,6 +175,11 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf, ssize_t res; loff_t pg_offp = *offp & ~PAGE_MASK; + if (need_wait) { + wait_for_device_probe(); + need_wait = false; + } + lock_system_sleep(); data = filp->private_data; @@ -209,6 +215,11 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, loff_t size; sector_t offset; + if (need_wait) { + wait_for_device_probe(); + need_wait = false; + } + if (_IOC_TYPE(cmd) != SNAPSHOT_IOC_MAGIC) return -ENOTTY; if (_IOC_NR(cmd) > SNAPSHOT_IOC_MAXNR) diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c index 4210152e56f0..aad7c8fcb22f 100644 --- a/kernel/power/wakelock.c +++ b/kernel/power/wakelock.c @@ -39,23 +39,19 @@ ssize_t pm_show_wakelocks(char *buf, bool show_active) { struct rb_node *node; struct wakelock *wl; - char *str = buf; - char *end = buf + PAGE_SIZE; + int len = 0; mutex_lock(&wakelocks_lock); for (node = rb_first(&wakelocks_tree); node; node = rb_next(node)) { wl = rb_entry(node, struct wakelock, node); if (wl->ws.active == show_active) - str += scnprintf(str, end - str, "%s ", wl->name); + len += sysfs_emit_at(buf, len, "%s ", wl->name); } - if (str > buf) - str--; - - str += scnprintf(str, end - str, "\n"); + len += sysfs_emit_at(buf, len, "\n"); mutex_unlock(&wakelocks_lock); - return (str - buf); + return len; } #if CONFIG_PM_WAKELOCKS_LIMIT > 0 diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 57742e193214..2ba16c426ba5 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -127,8 +127,10 @@ static int __control_devkmsg(char *str) static int __init control_devkmsg(char *str) { - if (__control_devkmsg(str) < 0) + if (__control_devkmsg(str) < 0) { + pr_warn("printk.devkmsg: bad option string '%s'\n", str); return 1; + } /* * Set sysctl string accordingly: @@ -147,7 +149,7 @@ static int __init control_devkmsg(char *str) */ devkmsg_log |= DEVKMSG_LOG_MASK_LOCK; - return 0; + return 1; } __setup("printk.devkmsg=", control_devkmsg); diff --git a/kernel/profile.c b/kernel/profile.c index efa58f63dc1b..7fc621404230 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -108,6 +108,13 @@ int __ref profile_init(void) /* only text is profiled */ prof_len = (_etext - _stext) >> prof_shift; + + if (!prof_len) { + pr_warn("profiling shift: %u too large\n", prof_shift); + prof_on = 0; + return -EINVAL; + } + buffer_bytes = prof_len*sizeof(atomic_t); if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL)) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index af74e843221b..bf8360e86f62 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -364,6 +364,26 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode) return !err; } +static int check_ptrace_options(unsigned long data) +{ + if (data & ~(unsigned long)PTRACE_O_MASK) + return -EINVAL; + + if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { + if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) || + !IS_ENABLED(CONFIG_SECCOMP)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (seccomp_mode(¤t->seccomp) != SECCOMP_MODE_DISABLED || + current->ptrace & PT_SUSPEND_SECCOMP) + return -EPERM; + } + return 0; +} + static int ptrace_attach(struct task_struct *task, long request, unsigned long addr, unsigned long flags) @@ -375,8 +395,16 @@ static int ptrace_attach(struct task_struct *task, long request, if (seize) { if (addr != 0) goto out; + /* + * This duplicates the check in check_ptrace_options() because + * ptrace_attach() and ptrace_setoptions() have historically + * used different error codes for unknown ptrace options. + */ if (flags & ~(unsigned long)PTRACE_O_MASK) goto out; + retval = check_ptrace_options(flags); + if (retval) + return retval; flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT); } else { flags = PT_PTRACED; @@ -649,22 +677,11 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds static int ptrace_setoptions(struct task_struct *child, unsigned long data) { unsigned flags; + int ret; - if (data & ~(unsigned long)PTRACE_O_MASK) - return -EINVAL; - - if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { - if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) || - !IS_ENABLED(CONFIG_SECCOMP)) - return -EINVAL; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - if (seccomp_mode(¤t->seccomp) != SECCOMP_MODE_DISABLED || - current->ptrace & PT_SUSPEND_SECCOMP) - return -EPERM; - } + ret = check_ptrace_options(data); + if (ret) + return ret; /* Avoid intermediate state when all opts are cleared */ flags = child->ptrace; @@ -1104,9 +1121,8 @@ int ptrace_request(struct task_struct *child, long request, return ptrace_resume(child, request, data); case PTRACE_KILL: - if (child->exit_state) /* already dead */ - return 0; - return ptrace_resume(child, request, SIGKILL); + send_sig_info(SIGKILL, SEND_SIG_NOINFO, child); + return 0; #ifdef CONFIG_HAVE_ARCH_TRACEHOOK case PTRACE_GETREGSET: diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 72770a551c24..fa6ae9ed2e1d 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -577,7 +577,9 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) mask = leaf_node_cpu_bit(rnp, cpu); if (!(rnp->expmask & mask)) continue; + preempt_disable(); // For smp_processor_id() in dump_cpu_task(). dump_cpu_task(cpu); + preempt_enable(); } } jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3; diff --git a/kernel/relay.c b/kernel/relay.c index 735cb208f023..e6f70f4c41a3 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -163,13 +163,13 @@ static struct rchan_buf *relay_create_buf(struct rchan *chan) { struct rchan_buf *buf; - if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t *)) + if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t)) return NULL; buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL); if (!buf) return NULL; - buf->padding = kmalloc_array(chan->n_subbufs, sizeof(size_t *), + buf->padding = kmalloc_array(chan->n_subbufs, sizeof(size_t), GFP_KERNEL); if (!buf->padding) goto free_buf; @@ -997,14 +997,14 @@ static void relay_file_read_consume(struct rchan_buf *buf, /* * relay_file_read_avail - boolean, are there unconsumed bytes available? */ -static int relay_file_read_avail(struct rchan_buf *buf, size_t read_pos) +static int relay_file_read_avail(struct rchan_buf *buf) { size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; size_t produced = buf->subbufs_produced; size_t consumed = buf->subbufs_consumed; - relay_file_read_consume(buf, read_pos, 0); + relay_file_read_consume(buf, 0, 0); consumed = buf->subbufs_consumed; @@ -1065,23 +1065,21 @@ static size_t relay_file_read_subbuf_avail(size_t read_pos, /** * relay_file_read_start_pos - find the first available byte to read - * @read_pos: file read position * @buf: relay channel buffer * - * If the @read_pos is in the middle of padding, return the + * If the read_pos is in the middle of padding, return the * position of the first actually available byte, otherwise * return the original value. */ -static size_t relay_file_read_start_pos(size_t read_pos, - struct rchan_buf *buf) +static size_t relay_file_read_start_pos(struct rchan_buf *buf) { size_t read_subbuf, padding, padding_start, padding_end; size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; size_t consumed = buf->subbufs_consumed % n_subbufs; + size_t read_pos = (consumed * subbuf_size + buf->bytes_consumed) + % (n_subbufs * subbuf_size); - if (!read_pos) - read_pos = consumed * subbuf_size + buf->bytes_consumed; read_subbuf = read_pos / subbuf_size; padding = buf->padding[read_subbuf]; padding_start = (read_subbuf + 1) * subbuf_size - padding; @@ -1137,10 +1135,10 @@ static ssize_t relay_file_read(struct file *filp, do { void *from; - if (!relay_file_read_avail(buf, *ppos)) + if (!relay_file_read_avail(buf)) break; - read_start = relay_file_read_start_pos(*ppos, buf); + read_start = relay_file_read_start_pos(buf); avail = relay_file_read_subbuf_avail(read_start, buf); if (!avail) break; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 32af895bd86b..8d5a9fa8a951 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -741,6 +741,9 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) void activate_task(struct rq *rq, struct task_struct *p, int flags) { + if (task_on_rq_migrating(p)) + flags |= ENQUEUE_MIGRATED; + if (task_contributes_to_load(p)) rq->nr_uninterruptible--; @@ -3316,8 +3319,7 @@ static noinline void __schedule_bug(struct task_struct *prev) print_ip_sym(preempt_disable_ip); pr_cont("\n"); } - if (panic_on_warn) - panic("scheduling while atomic\n"); + check_panic_on_warn("scheduling while atomic"); dump_stack(); add_taint(TAINT_WARN, LOCKDEP_STILL_OK); @@ -3869,20 +3871,21 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) if (!dl_prio(p->normal_prio) || (pi_task && dl_prio(pi_task->prio) && dl_entity_preempt(&pi_task->dl, &p->dl))) { - p->dl.dl_boosted = 1; + p->dl.pi_se = pi_task->dl.pi_se; queue_flag |= ENQUEUE_REPLENISH; - } else - p->dl.dl_boosted = 0; + } else { + p->dl.pi_se = &p->dl; + } p->sched_class = &dl_sched_class; } else if (rt_prio(prio)) { if (dl_prio(oldprio)) - p->dl.dl_boosted = 0; + p->dl.pi_se = &p->dl; if (oldprio < prio) queue_flag |= ENQUEUE_HEAD; p->sched_class = &rt_sched_class; } else { if (dl_prio(oldprio)) - p->dl.dl_boosted = 0; + p->dl.pi_se = &p->dl; if (rt_prio(oldprio)) p->rt.timeout = 0; p->sched_class = &fair_sched_class; @@ -4950,14 +4953,14 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, if (len & (sizeof(unsigned long)-1)) return -EINVAL; - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; ret = sched_getaffinity(pid, mask); if (ret == 0) { unsigned int retlen = min(len, cpumask_size()); - if (copy_to_user(user_mask_ptr, mask, retlen)) + if (copy_to_user(user_mask_ptr, cpumask_bits(mask), retlen)) ret = -EFAULT; else ret = retlen; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 54eb9457b21d..532682125ef6 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -146,10 +146,10 @@ void account_guest_time(struct task_struct *p, u64 cputime) /* Add guest time to cpustat. */ if (task_nice(p) > 0) { - cpustat[CPUTIME_NICE] += cputime; + task_group_account_field(p, CPUTIME_NICE, cputime); cpustat[CPUTIME_GUEST_NICE] += cputime; } else { - cpustat[CPUTIME_USER] += cputime; + task_group_account_field(p, CPUTIME_USER, cputime); cpustat[CPUTIME_GUEST] += cputime; } } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index beec5081a55a..29ed5d8d30d6 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -43,6 +43,28 @@ static inline int on_dl_rq(struct sched_dl_entity *dl_se) return !RB_EMPTY_NODE(&dl_se->rb_node); } +#ifdef CONFIG_RT_MUTEXES +static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se) +{ + return dl_se->pi_se; +} + +static inline bool is_dl_boosted(struct sched_dl_entity *dl_se) +{ + return pi_of(dl_se) != dl_se; +} +#else +static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se) +{ + return dl_se; +} + +static inline bool is_dl_boosted(struct sched_dl_entity *dl_se) +{ + return false; +} +#endif + #ifdef CONFIG_SMP static inline struct dl_bw *dl_bw_of(int i) { @@ -657,7 +679,7 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - WARN_ON(dl_se->dl_boosted); + WARN_ON(is_dl_boosted(dl_se)); WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline)); /* @@ -695,21 +717,20 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se) * could happen are, typically, a entity voluntarily trying to overcome its * runtime, or it just underestimated it during sched_setattr(). */ -static void replenish_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se) +static void replenish_dl_entity(struct sched_dl_entity *dl_se) { struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - BUG_ON(pi_se->dl_runtime <= 0); + BUG_ON(pi_of(dl_se)->dl_runtime <= 0); /* * This could be the case for a !-dl task that is boosted. * Just go with full inherited parameters. */ if (dl_se->dl_deadline == 0) { - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } if (dl_se->dl_yielded && dl_se->runtime > 0) @@ -722,8 +743,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * arbitrary large. */ while (dl_se->runtime <= 0) { - dl_se->deadline += pi_se->dl_period; - dl_se->runtime += pi_se->dl_runtime; + dl_se->deadline += pi_of(dl_se)->dl_period; + dl_se->runtime += pi_of(dl_se)->dl_runtime; } /* @@ -737,8 +758,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, */ if (dl_time_before(dl_se->deadline, rq_clock(rq))) { printk_deferred_once("sched: DL replenish lagged too much\n"); - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } if (dl_se->dl_yielded) @@ -771,8 +792,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * task with deadline equal to period this is the same of using * dl_period instead of dl_deadline in the equation above. */ -static bool dl_entity_overflow(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se, u64 t) +static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t) { u64 left, right; @@ -794,9 +814,9 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, * of anything below microseconds resolution is actually fiction * (but still we want to give the user that illusion >;). */ - left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); + left = (pi_of(dl_se)->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); right = ((dl_se->deadline - t) >> DL_SCALE) * - (pi_se->dl_runtime >> DL_SCALE); + (pi_of(dl_se)->dl_runtime >> DL_SCALE); return dl_time_before(right, left); } @@ -881,24 +901,23 @@ static inline bool dl_is_implicit(struct sched_dl_entity *dl_se) * Please refer to the comments update_dl_revised_wakeup() function to find * more about the Revised CBS rule. */ -static void update_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se) +static void update_dl_entity(struct sched_dl_entity *dl_se) { struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); if (dl_time_before(dl_se->deadline, rq_clock(rq)) || - dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { + dl_entity_overflow(dl_se, rq_clock(rq))) { if (unlikely(!dl_is_implicit(dl_se) && !dl_time_before(dl_se->deadline, rq_clock(rq)) && - !dl_se->dl_boosted)){ + !is_dl_boosted(dl_se))) { update_dl_revised_wakeup(dl_se, rq); return; } - dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; - dl_se->runtime = pi_se->dl_runtime; + dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline; + dl_se->runtime = pi_of(dl_se)->dl_runtime; } } @@ -997,7 +1016,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * The task might have been boosted by someone else and might be in the * boosting/deboosting path, its not throttled. */ - if (dl_se->dl_boosted) + if (is_dl_boosted(dl_se)) goto unlock; /* @@ -1025,7 +1044,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * but do not enqueue -- wait for our wakeup to do that. */ if (!task_on_rq_queued(p)) { - replenish_dl_entity(dl_se, dl_se); + replenish_dl_entity(dl_se); goto unlock; } @@ -1115,7 +1134,7 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se) if (dl_time_before(dl_se->deadline, rq_clock(rq)) && dl_time_before(rq_clock(rq), dl_next_period(dl_se))) { - if (unlikely(dl_se->dl_boosted || !start_dl_timer(p))) + if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p))) return; dl_se->dl_throttled = 1; if (dl_se->runtime > 0) @@ -1246,7 +1265,7 @@ throttle: dl_se->dl_overrun = 1; __dequeue_task_dl(rq, curr, 0); - if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr))) + if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr))) enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH); if (!is_leftmost(curr, &rq->dl)) @@ -1440,8 +1459,7 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se) } static void -enqueue_dl_entity(struct sched_dl_entity *dl_se, - struct sched_dl_entity *pi_se, int flags) +enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags) { BUG_ON(on_dl_rq(dl_se)); @@ -1452,9 +1470,9 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, */ if (flags & ENQUEUE_WAKEUP) { task_contending(dl_se, flags); - update_dl_entity(dl_se, pi_se); + update_dl_entity(dl_se); } else if (flags & ENQUEUE_REPLENISH) { - replenish_dl_entity(dl_se, pi_se); + replenish_dl_entity(dl_se); } else if ((flags & ENQUEUE_RESTORE) && dl_time_before(dl_se->deadline, rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) { @@ -1471,28 +1489,40 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se) static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) { - struct task_struct *pi_task = rt_mutex_get_top_task(p); - struct sched_dl_entity *pi_se = &p->dl; - - /* - * Use the scheduling parameters of the top pi-waiter task if: - * - we have a top pi-waiter which is a SCHED_DEADLINE task AND - * - our dl_boosted is set (i.e. the pi-waiter's (absolute) deadline is - * smaller than our deadline OR we are a !SCHED_DEADLINE task getting - * boosted due to a SCHED_DEADLINE pi-waiter). - * Otherwise we keep our runtime and deadline. - */ - if (pi_task && dl_prio(pi_task->normal_prio) && p->dl.dl_boosted) { - pi_se = &pi_task->dl; + if (is_dl_boosted(&p->dl)) { + /* + * Because of delays in the detection of the overrun of a + * thread's runtime, it might be the case that a thread + * goes to sleep in a rt mutex with negative runtime. As + * a consequence, the thread will be throttled. + * + * While waiting for the mutex, this thread can also be + * boosted via PI, resulting in a thread that is throttled + * and boosted at the same time. + * + * In this case, the boost overrides the throttle. + */ + if (p->dl.dl_throttled) { + /* + * The replenish timer needs to be canceled. No + * problem if it fires concurrently: boosted threads + * are ignored in dl_task_timer(). + */ + hrtimer_try_to_cancel(&p->dl.dl_timer); + p->dl.dl_throttled = 0; + } } else if (!dl_prio(p->normal_prio)) { /* - * Special case in which we have a !SCHED_DEADLINE task - * that is going to be deboosted, but exceeds its - * runtime while doing so. No point in replenishing - * it, as it's going to return back to its original - * scheduling class after this. + * Special case in which we have a !SCHED_DEADLINE task that is going + * to be deboosted, but exceeds its runtime while doing so. No point in + * replenishing it, as it's going to return back to its original + * scheduling class after this. If it has been throttled, we need to + * clear the flag, otherwise the task may wake up as throttled after + * being boosted again with no means to replenish the runtime and clear + * the throttle. */ - BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH); + p->dl.dl_throttled = 0; + BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH); return; } @@ -1529,7 +1559,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) return; } - enqueue_dl_entity(&p->dl, pi_se, flags); + enqueue_dl_entity(&p->dl, flags); if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); @@ -2691,11 +2721,14 @@ void __dl_clear_params(struct task_struct *p) dl_se->dl_bw = 0; dl_se->dl_density = 0; - dl_se->dl_boosted = 0; dl_se->dl_throttled = 0; dl_se->dl_yielded = 0; dl_se->dl_non_contending = 0; dl_se->dl_overrun = 0; + +#ifdef CONFIG_RT_MUTEXES + dl_se->pi_se = dl_se; +#endif } bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr) diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 9518606fa1e5..b1ef4f2e7edc 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -871,25 +871,15 @@ void print_numa_stats(struct seq_file *m, int node, unsigned long tsf, static void sched_show_numa(struct task_struct *p, struct seq_file *m) { #ifdef CONFIG_NUMA_BALANCING - struct mempolicy *pol; - if (p->mm) P(mm->numa_scan_seq); - task_lock(p); - pol = p->mempolicy; - if (pol && !(pol->flags & MPOL_F_MORON)) - pol = NULL; - mpol_get(pol); - task_unlock(p); - P(numa_pages_migrated); P(numa_preferred_nid); P(total_numa_faults); SEQ_printf(m, "current_node=%d, numa_group_id=%d\n", task_node(p), task_numa_group_id(p)); show_numa_stats(p, m); - mpol_put(pol); #endif } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 84e7efda98da..09f82c84474b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3854,6 +3854,29 @@ static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se) #endif } +static inline bool entity_is_long_sleeper(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq; + u64 sleep_time; + + if (se->exec_start == 0) + return false; + + cfs_rq = cfs_rq_of(se); + + sleep_time = rq_clock_task(rq_of(cfs_rq)); + + /* Happen while migrating because of clock task divergence */ + if (sleep_time <= se->exec_start) + return false; + + sleep_time -= se->exec_start; + if (sleep_time > ((1ULL << 63) / scale_load_down(NICE_0_LOAD))) + return true; + + return false; +} + static void place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) { @@ -3882,8 +3905,29 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) vruntime -= thresh; } - /* ensure we never gain time by being placed backwards. */ - se->vruntime = max_vruntime(se->vruntime, vruntime); + /* + * Pull vruntime of the entity being placed to the base level of + * cfs_rq, to prevent boosting it if placed backwards. + * However, min_vruntime can advance much faster than real time, with + * the extreme being when an entity with the minimal weight always runs + * on the cfs_rq. If the waking entity slept for a long time, its + * vruntime difference from min_vruntime may overflow s64 and their + * comparison may get inversed, so ignore the entity's original + * vruntime in that case. + * The maximal vruntime speedup is given by the ratio of normal to + * minimal weight: scale_load_down(NICE_0_LOAD) / MIN_SHARES. + * When placing a migrated waking entity, its exec_start has been set + * from a different rq. In order to take into account a possible + * divergence between new and prev rq's clocks task because of irq and + * stolen time, we take an additional margin. + * So, cutting off on the sleep time of + * 2^63 / scale_load_down(NICE_0_LOAD) ~ 104 days + * should be safe. + */ + if (entity_is_long_sleeper(se)) + se->vruntime = vruntime; + else + se->vruntime = max_vruntime(se->vruntime, vruntime); } static void check_enqueue_throttle(struct cfs_rq *cfs_rq); @@ -3978,6 +4022,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (flags & ENQUEUE_WAKEUP) place_entity(cfs_rq, se, 0); + /* Entity has migrated, no longer consider this task hot */ + if (flags & ENQUEUE_MIGRATED) + se->exec_start = 0; check_schedstat_required(); update_stats_enqueue(cfs_rq, se, flags); @@ -6544,9 +6591,6 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu) /* Tell new CPU we are migrated */ p->se.avg.last_update_time = 0; - /* We have migrated, no longer consider this task hot */ - p->se.exec_start = 0; - update_scan_period(p, new_cpu); } @@ -8677,7 +8721,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, .sd = sd, .dst_cpu = this_cpu, .dst_rq = this_rq, - .dst_grpmask = sched_group_span(sd->groups), + .dst_grpmask = group_balance_mask(sd->groups), .idle = idle, .loop_break = sched_nr_migrate_break, .cpus = cpus, diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 44a17366c8ec..4e3d149d64ad 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -53,17 +53,18 @@ __setup("hlt", cpu_idle_nopoll_setup); static noinline int __cpuidle cpu_idle_poll(void) { + trace_cpu_idle(0, smp_processor_id()); + stop_critical_timings(); rcu_idle_enter(); - trace_cpu_idle_rcuidle(0, smp_processor_id()); local_irq_enable(); - stop_critical_timings(); while (!tif_need_resched() && - (cpu_idle_force_poll || tick_check_broadcast_expired())) + (cpu_idle_force_poll || tick_check_broadcast_expired())) cpu_relax(); - start_critical_timings(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); + rcu_idle_exit(); + start_critical_timings(); + trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); return 1; } @@ -90,7 +91,9 @@ void __cpuidle default_idle_call(void) local_irq_enable(); } else { stop_critical_timings(); + rcu_idle_enter(); arch_cpu_idle(); + rcu_idle_exit(); start_critical_timings(); } } @@ -148,7 +151,6 @@ static void cpuidle_idle_call(void) if (cpuidle_not_available(drv, dev)) { tick_nohz_idle_stop_tick(); - rcu_idle_enter(); default_idle_call(); goto exit_idle; @@ -166,19 +168,15 @@ static void cpuidle_idle_call(void) if (idle_should_enter_s2idle() || dev->use_deepest_state) { if (idle_should_enter_s2idle()) { - rcu_idle_enter(); entered_state = cpuidle_enter_s2idle(drv, dev); if (entered_state > 0) { local_irq_enable(); goto exit_idle; } - - rcu_idle_exit(); } tick_nohz_idle_stop_tick(); - rcu_idle_enter(); next_state = cpuidle_find_deepest_state(drv, dev); call_cpuidle(drv, dev, next_state); @@ -195,8 +193,6 @@ static void cpuidle_idle_call(void) else tick_nohz_idle_retain_tick(); - rcu_idle_enter(); - entered_state = call_cpuidle(drv, dev, next_state); /* * Give the governor an opportunity to reflect on the outcome @@ -212,8 +208,6 @@ exit_idle: */ if (WARN_ON_ONCE(irqs_disabled())) local_irq_enable(); - - rcu_idle_exit(); } /* diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index b980cc96604f..394c66442cff 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -50,11 +50,8 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) rt_b->rt_period_timer.function = sched_rt_period_timer; } -static void start_rt_bandwidth(struct rt_bandwidth *rt_b) +static inline void do_start_rt_bandwidth(struct rt_bandwidth *rt_b) { - if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) - return; - raw_spin_lock(&rt_b->rt_runtime_lock); if (!rt_b->rt_period_active) { rt_b->rt_period_active = 1; @@ -72,6 +69,14 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) raw_spin_unlock(&rt_b->rt_runtime_lock); } +static void start_rt_bandwidth(struct rt_bandwidth *rt_b) +{ + if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) + return; + + do_start_rt_bandwidth(rt_b); +} + void init_rt_rq(struct rt_rq *rt_rq) { struct rt_prio_array *array; @@ -429,7 +434,7 @@ static inline void rt_queue_push_tasks(struct rq *rq) #endif /* CONFIG_SMP */ static void enqueue_top_rt_rq(struct rt_rq *rt_rq); -static void dequeue_top_rt_rq(struct rt_rq *rt_rq); +static void dequeue_top_rt_rq(struct rt_rq *rt_rq, unsigned int count); static inline int on_rt_rq(struct sched_rt_entity *rt_se) { @@ -511,7 +516,7 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) rt_se = rt_rq->tg->rt_se[cpu]; if (!rt_se) { - dequeue_top_rt_rq(rt_rq); + dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running); /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ cpufreq_update_util(rq_of_rt_rq(rt_rq), 0); } @@ -597,7 +602,7 @@ static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq) static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq) { - dequeue_top_rt_rq(rt_rq); + dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running); } static inline int rt_rq_throttled(struct rt_rq *rt_rq) @@ -980,19 +985,23 @@ static void update_curr_rt(struct rq *rq) for_each_sched_rt_entity(rt_se) { struct rt_rq *rt_rq = rt_rq_of_se(rt_se); + int exceeded; if (sched_rt_runtime(rt_rq) != RUNTIME_INF) { raw_spin_lock(&rt_rq->rt_runtime_lock); rt_rq->rt_time += delta_exec; - if (sched_rt_runtime_exceeded(rt_rq)) + exceeded = sched_rt_runtime_exceeded(rt_rq); + if (exceeded) resched_curr(rq); raw_spin_unlock(&rt_rq->rt_runtime_lock); + if (exceeded) + do_start_rt_bandwidth(sched_rt_bandwidth(rt_rq)); } } } static void -dequeue_top_rt_rq(struct rt_rq *rt_rq) +dequeue_top_rt_rq(struct rt_rq *rt_rq, unsigned int count) { struct rq *rq = rq_of_rt_rq(rt_rq); @@ -1003,7 +1012,7 @@ dequeue_top_rt_rq(struct rt_rq *rt_rq) BUG_ON(!rq->nr_running); - sub_nr_running(rq, rt_rq->rt_nr_running); + sub_nr_running(rq, count); rt_rq->rt_queued = 0; } @@ -1282,18 +1291,21 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flag static void dequeue_rt_stack(struct sched_rt_entity *rt_se, unsigned int flags) { struct sched_rt_entity *back = NULL; + unsigned int rt_nr_running; for_each_sched_rt_entity(rt_se) { rt_se->back = back; back = rt_se; } - dequeue_top_rt_rq(rt_rq_of_se(back)); + rt_nr_running = rt_rq_of_se(back)->rt_nr_running; for (rt_se = back; rt_se; rt_se = rt_se->back) { if (on_rt_rq(rt_se)) __dequeue_rt_entity(rt_se, flags); } + + dequeue_top_rt_rq(rt_rq_of_se(back), rt_nr_running); } static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) @@ -1510,6 +1522,8 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, BUG_ON(idx >= MAX_RT_PRIO); queue = array->queue + idx; + if (SCHED_WARN_ON(list_empty(queue))) + return NULL; next = list_entry(queue->next, struct sched_rt_entity, run_list); return next; @@ -1523,7 +1537,8 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) do { rt_se = pick_next_rt_entity(rq, rt_rq); - BUG_ON(!rt_se); + if (unlikely(!rt_se)) + return NULL; rt_rq = group_rt_rq(rt_se); } while (rt_rq); @@ -2655,8 +2670,12 @@ static int sched_rt_global_validate(void) static void sched_rt_do_global(void) { + unsigned long flags; + + raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); def_rt_bandwidth.rt_runtime = global_rt_runtime(); def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period()); + raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); } int sched_rt_handler(struct ctl_table *table, int write, diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index f58efa5cc647..02e85cd233d4 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1322,66 +1322,58 @@ static void init_numa_topology_type(void) } } + +#define NR_DISTANCE_VALUES (1 << DISTANCE_BITS) + void sched_init_numa(void) { - int next_distance, curr_distance = node_distance(0, 0); struct sched_domain_topology_level *tl; - int level = 0; - int i, j, k; - - sched_domains_numa_distance = kzalloc(sizeof(int) * (nr_node_ids + 1), GFP_KERNEL); - if (!sched_domains_numa_distance) - return; - - /* Includes NUMA identity node at level 0. */ - sched_domains_numa_distance[level++] = curr_distance; - sched_domains_numa_levels = level; + unsigned long *distance_map; + int nr_levels = 0; + int i, j; /* * O(nr_nodes^2) deduplicating selection sort -- in order to find the * unique distances in the node_distance() table. - * - * Assumes node_distance(0,j) includes all distances in - * node_distance(i,j) in order to avoid cubic time. */ - next_distance = curr_distance; + distance_map = bitmap_alloc(NR_DISTANCE_VALUES, GFP_KERNEL); + if (!distance_map) + return; + + bitmap_zero(distance_map, NR_DISTANCE_VALUES); for (i = 0; i < nr_node_ids; i++) { for (j = 0; j < nr_node_ids; j++) { - for (k = 0; k < nr_node_ids; k++) { - int distance = node_distance(i, k); - - if (distance > curr_distance && - (distance < next_distance || - next_distance == curr_distance)) - next_distance = distance; - - /* - * While not a strong assumption it would be nice to know - * about cases where if node A is connected to B, B is not - * equally connected to A. - */ - if (sched_debug() && node_distance(k, i) != distance) - sched_numa_warn("Node-distance not symmetric"); + int distance = node_distance(i, j); - if (sched_debug() && i && !find_numa_distance(distance)) - sched_numa_warn("Node-0 not representative"); + if (distance < LOCAL_DISTANCE || distance >= NR_DISTANCE_VALUES) { + sched_numa_warn("Invalid distance value range"); + return; } - if (next_distance != curr_distance) { - sched_domains_numa_distance[level++] = next_distance; - sched_domains_numa_levels = level; - curr_distance = next_distance; - } else break; + + bitmap_set(distance_map, distance, 1); } + } + /* + * We can now figure out how many unique distance values there are and + * allocate memory accordingly. + */ + nr_levels = bitmap_weight(distance_map, NR_DISTANCE_VALUES); - /* - * In case of sched_debug() we verify the above assumption. - */ - if (!sched_debug()) - break; + sched_domains_numa_distance = kcalloc(nr_levels, sizeof(int), GFP_KERNEL); + if (!sched_domains_numa_distance) { + bitmap_free(distance_map); + return; } + for (i = 0, j = 0; i < nr_levels; i++, j++) { + j = find_next_bit(distance_map, NR_DISTANCE_VALUES, j); + sched_domains_numa_distance[i] = j; + } + + bitmap_free(distance_map); + /* - * 'level' contains the number of unique distances + * 'nr_levels' contains the number of unique distances * * The sched_domains_numa_distance[] array includes the actual distance * numbers. @@ -1390,15 +1382,15 @@ void sched_init_numa(void) /* * Here, we should temporarily reset sched_domains_numa_levels to 0. * If it fails to allocate memory for array sched_domains_numa_masks[][], - * the array will contain less then 'level' members. This could be + * the array will contain less then 'nr_levels' members. This could be * dangerous when we use it to iterate array sched_domains_numa_masks[][] * in other functions. * - * We reset it to 'level' at the end of this function. + * We reset it to 'nr_levels' at the end of this function. */ sched_domains_numa_levels = 0; - sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL); + sched_domains_numa_masks = kzalloc(sizeof(void *) * nr_levels, GFP_KERNEL); if (!sched_domains_numa_masks) return; @@ -1406,7 +1398,7 @@ void sched_init_numa(void) * Now for each level, construct a mask per node which contains all * CPUs of nodes that are that many hops away from us. */ - for (i = 0; i < level; i++) { + for (i = 0; i < nr_levels; i++) { sched_domains_numa_masks[i] = kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); if (!sched_domains_numa_masks[i]) @@ -1414,12 +1406,17 @@ void sched_init_numa(void) for (j = 0; j < nr_node_ids; j++) { struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL); + int k; + if (!mask) return; sched_domains_numa_masks[i][j] = mask; for_each_node(k) { + if (sched_debug() && (node_distance(j, k) != node_distance(k, j))) + sched_numa_warn("Node-distance not symmetric"); + if (node_distance(j, k) > sched_domains_numa_distance[i]) continue; @@ -1431,7 +1428,7 @@ void sched_init_numa(void) /* Compute default topology size */ for (i = 0; sched_domain_topology[i].mask; i++); - tl = kzalloc((i + level + 1) * + tl = kzalloc((i + nr_levels + 1) * sizeof(struct sched_domain_topology_level), GFP_KERNEL); if (!tl) return; @@ -1454,7 +1451,7 @@ void sched_init_numa(void) /* * .. and append 'j' levels of NUMA goodness. */ - for (j = 1; j < level; i++, j++) { + for (j = 1; j < nr_levels; i++, j++) { tl[i] = (struct sched_domain_topology_level){ .mask = sd_numa_mask, .sd_flags = cpu_numa_flags, @@ -1466,8 +1463,8 @@ void sched_init_numa(void) sched_domain_topology = tl; - sched_domains_numa_levels = level; - sched_max_numa_distance = sched_domains_numa_distance[level - 1]; + sched_domains_numa_levels = nr_levels; + sched_max_numa_distance = sched_domains_numa_distance[nr_levels - 1]; init_numa_topology_type(); } diff --git a/kernel/seccomp.c b/kernel/seccomp.c index a9dd2325bdda..69b4e34e191b 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -28,6 +28,9 @@ #include <linux/syscalls.h> #include <linux/sysctl.h> +/* Not exposed in headers: strictly internal use only. */ +#define SECCOMP_MODE_DEAD (SECCOMP_MODE_FILTER + 1) + #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER #include <asm/syscall.h> #endif @@ -628,6 +631,7 @@ static void __secure_computing_strict(int this_syscall) #ifdef SECCOMP_DEBUG dump_stack(); #endif + current->seccomp.mode = SECCOMP_MODE_DEAD; seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL_THREAD, true); do_exit(SIGKILL); } @@ -742,6 +746,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, case SECCOMP_RET_KILL_THREAD: case SECCOMP_RET_KILL_PROCESS: default: + current->seccomp.mode = SECCOMP_MODE_DEAD; seccomp_log(this_syscall, SIGSYS, action, true); /* Dump core only if this is the last remaining thread. */ if (action == SECCOMP_RET_KILL_PROCESS || @@ -794,6 +799,11 @@ int __secure_computing(const struct seccomp_data *sd) return 0; case SECCOMP_MODE_FILTER: return __seccomp_filter(this_syscall, sd, false); + /* Surviving SECCOMP_RET_KILL_* must be proactively impossible. */ + case SECCOMP_MODE_DEAD: + WARN_ON_ONCE(1); + do_exit(SIGKILL); + return -1; default: BUG(); } diff --git a/kernel/signal.c b/kernel/signal.c index 4cc3f3ba13a9..c79b87ac1041 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1825,12 +1825,12 @@ bool do_notify_parent(struct task_struct *tsk, int sig) bool autoreap = false; u64 utime, stime; - BUG_ON(sig == -1); + WARN_ON_ONCE(sig == -1); - /* do_notify_parent_cldstop should have been called instead. */ - BUG_ON(task_is_stopped_or_traced(tsk)); + /* do_notify_parent_cldstop should have been called instead. */ + WARN_ON_ONCE(task_is_stopped_or_traced(tsk)); - BUG_ON(!tsk->ptrace && + WARN_ON_ONCE(!tsk->ptrace && (tsk->group_leader != tsk || !thread_group_empty(tsk))); if (sig != SIGCHLD) { diff --git a/kernel/smp.c b/kernel/smp.c index 00d208ef07c7..9fa2fe6c0c05 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -221,7 +221,7 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline) /* There shouldn't be any pending callbacks on an offline CPU. */ if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && - !warned && !llist_empty(head))) { + !warned && entry != NULL)) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); diff --git a/kernel/sys.c b/kernel/sys.c index d0663f8e6fb8..3548467f6459 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1530,6 +1530,8 @@ int do_prlimit(struct task_struct *tsk, unsigned int resource, if (resource >= RLIM_NLIMITS) return -EINVAL; + resource = array_index_nospec(resource, RLIM_NLIMITS); + if (new_rlim) { if (new_rlim->rlim_cur > new_rlim->rlim_max) return -EINVAL; diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index df556175be50..acd7e1221774 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -257,6 +257,7 @@ COND_SYSCALL_COMPAT(keyctl); /* mm/fadvise.c */ COND_SYSCALL(fadvise64_64); +COND_SYSCALL_COMPAT(fadvise64_64); /* mm/, CONFIG_MMU only */ COND_SYSCALL(swapon); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index a5d75bc38eea..4bb194f096ec 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -250,6 +250,36 @@ static int sysrq_sysctl_handler(struct ctl_table *table, int write, #endif +#ifdef CONFIG_BPF_SYSCALL + +void __weak unpriv_ebpf_notify(int new_state) +{ +} + +static int bpf_unpriv_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret, unpriv_enable = *(int *)table->data; + bool locked_state = unpriv_enable == 1; + struct ctl_table tmp = *table; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + tmp.data = &unpriv_enable; + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret) { + if (locked_state && unpriv_enable != 1) + return -EPERM; + *(int *)table->data = unpriv_enable; + } + + unpriv_ebpf_notify(unpriv_enable); + + return ret; +} +#endif + static struct ctl_table kern_table[]; static struct ctl_table vm_table[]; static struct ctl_table fs_table[]; @@ -1220,10 +1250,9 @@ static struct ctl_table kern_table[] = { .data = &sysctl_unprivileged_bpf_disabled, .maxlen = sizeof(sysctl_unprivileged_bpf_disabled), .mode = 0644, - /* only handle a transition from default "0" to "1" */ - .proc_handler = proc_dointvec_minmax, - .extra1 = &one, - .extra2 = &one, + .proc_handler = bpf_unpriv_handler, + .extra1 = &zero, + .extra2 = &two, }, #endif #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) @@ -2052,13 +2081,14 @@ int proc_dostring(struct ctl_table *table, int write, (char __user *)buffer, lenp, ppos); } -static size_t proc_skip_spaces(char **buf) +static void proc_skip_spaces(char **buf, size_t *size) { - size_t ret; - char *tmp = skip_spaces(*buf); - ret = tmp - *buf; - *buf = tmp; - return ret; + while (*size) { + if (!isspace(**buf)) + break; + (*size)--; + (*buf)++; + } } static void proc_skip_char(char **buf, size_t *size, const char v) @@ -2127,13 +2157,12 @@ static int proc_get_long(char **buf, size_t *size, unsigned long *val, bool *neg, const char *perm_tr, unsigned perm_tr_len, char *tr) { - int len; char *p, tmp[TMPBUFLEN]; + ssize_t len = *size; - if (!*size) + if (len <= 0) return -EINVAL; - len = *size; if (len > TMPBUFLEN - 1) len = TMPBUFLEN - 1; @@ -2296,7 +2325,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, bool neg; if (write) { - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (!left) break; @@ -2327,7 +2356,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, if (!write && !first && left && !err) err = proc_put_char(&buffer, &left, '\n'); if (write && !err && left) - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (write) { kfree(kbuf); if (first) @@ -2376,7 +2405,7 @@ static int do_proc_douintvec_w(unsigned int *tbl_data, if (IS_ERR(kbuf)) return -EINVAL; - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (!left) { err = -EINVAL; goto out_free; @@ -2396,7 +2425,7 @@ static int do_proc_douintvec_w(unsigned int *tbl_data, } if (!err && left) - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); out_free: kfree(kbuf); @@ -2817,7 +2846,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int if (write) { bool neg; - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (!left) break; @@ -2850,7 +2879,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int if (!write && !first && left && !err) err = proc_put_char(&buffer, &left, '\n'); if (write && !err) - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (write) { kfree(kbuf); if (first) diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 6a2ba39889bd..56af8a97cf2d 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -476,11 +476,35 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) } EXPORT_SYMBOL_GPL(alarm_forward); -u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throttle) { struct alarm_base *base = &alarm_bases[alarm->type]; + ktime_t now = base->gettime(); + + if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && throttle) { + /* + * Same issue as with posix_timer_fn(). Timers which are + * periodic but the signal is ignored can starve the system + * with a very small interval. The real fix which was + * promised in the context of posix_timer_fn() never + * materialized, but someone should really work on it. + * + * To prevent DOS fake @now to be 1 jiffie out which keeps + * the overrun accounting correct but creates an + * inconsistency vs. timer_gettime(2). + */ + ktime_t kj = NSEC_PER_SEC / HZ; + + if (interval < kj) + now = ktime_add(now, kj); + } + + return alarm_forward(alarm, now, interval); +} - return alarm_forward(alarm, base->gettime(), interval); +u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +{ + return __alarm_forward_now(alarm, interval, false); } EXPORT_SYMBOL_GPL(alarm_forward_now); @@ -554,9 +578,10 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, if (posix_timer_event(ptr, si_private) && ptr->it_interval) { /* * Handle ignored signals and rearm the timer. This will go - * away once we handle ignored signals proper. + * away once we handle ignored signals proper. Ensure that + * small intervals cannot starve the system. */ - ptr->it_overrun += alarm_forward_now(alarm, ptr->it_interval); + ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true); ++ptr->it_requeue_pending; ptr->it_active = 1; result = ALARMTIMER_RESTART; diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 32ee24f5142a..bf74f43e42af 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1838,6 +1838,7 @@ SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, if (!timespec64_valid(&tu)) return -EINVAL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC); @@ -1858,6 +1859,7 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp, if (!timespec64_valid(&tu)) return -EINVAL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC); @@ -1920,29 +1922,22 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, } } -int hrtimers_dead_cpu(unsigned int scpu) +int hrtimers_cpu_dying(unsigned int dying_cpu) { struct hrtimer_cpu_base *old_base, *new_base; - int i; + int i, ncpu = cpumask_first(cpu_active_mask); - BUG_ON(cpu_online(scpu)); - tick_cancel_sched_timer(scpu); + tick_cancel_sched_timer(dying_cpu); + + old_base = this_cpu_ptr(&hrtimer_bases); + new_base = &per_cpu(hrtimer_bases, ncpu); - /* - * this BH disable ensures that raise_softirq_irqoff() does - * not wakeup ksoftirqd (and acquire the pi-lock) while - * holding the cpu_base lock - */ - local_bh_disable(); - local_irq_disable(); - old_base = &per_cpu(hrtimer_bases, scpu); - new_base = this_cpu_ptr(&hrtimer_bases); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ - raw_spin_lock(&new_base->lock); - raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); + raw_spin_lock(&old_base->lock); + raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { migrate_hrtimer_list(&old_base->clock_base[i], @@ -1953,15 +1948,13 @@ int hrtimers_dead_cpu(unsigned int scpu) * The migration might have changed the first expiring softirq * timer on this CPU. Update it. */ - hrtimer_update_softirq_timer(new_base, false); + __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT); + /* Tell the other CPU to retrigger the next event */ + smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); - raw_spin_unlock(&old_base->lock); raw_spin_unlock(&new_base->lock); + raw_spin_unlock(&old_base->lock); - /* Check, if we got expired work to do */ - __hrtimer_peek_ahead_timers(); - local_irq_enable(); - local_bh_enable(); return 0; } diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index 2c6847d5d69b..362c159fb3f8 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -144,6 +144,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; return hrtimer_nanosleep(&t, flags & TIMER_ABSTIME ? @@ -230,6 +231,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; return hrtimer_nanosleep(&t, flags & TIMER_ABSTIME ? diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 48758108e055..8768ce2c4bf5 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -159,25 +159,30 @@ static struct k_itimer *posix_timer_by_id(timer_t id) static int posix_timer_add(struct k_itimer *timer) { struct signal_struct *sig = current->signal; - int first_free_id = sig->posix_timer_id; struct hlist_head *head; - int ret = -ENOENT; + unsigned int cnt, id; - do { + /* + * FIXME: Replace this by a per signal struct xarray once there is + * a plan to handle the resulting CRIU regression gracefully. + */ + for (cnt = 0; cnt <= INT_MAX; cnt++) { spin_lock(&hash_lock); - head = &posix_timers_hashtable[hash(sig, sig->posix_timer_id)]; - if (!__posix_timers_find(head, sig, sig->posix_timer_id)) { + id = sig->next_posix_timer_id; + + /* Write the next ID back. Clamp it to the positive space */ + sig->next_posix_timer_id = (id + 1) & INT_MAX; + + head = &posix_timers_hashtable[hash(sig, id)]; + if (!__posix_timers_find(head, sig, id)) { hlist_add_head_rcu(&timer->t_hash, head); - ret = sig->posix_timer_id; + spin_unlock(&hash_lock); + return id; } - if (++sig->posix_timer_id < 0) - sig->posix_timer_id = 0; - if ((sig->posix_timer_id == first_free_id) && (ret == -ENOENT)) - /* Loop over all possible ids completed */ - ret = -EAGAIN; spin_unlock(&hash_lock); - } while (ret == -ENOENT); - return ret; + } + /* POSIX return code when no timer ID could be allocated */ + return -EAGAIN; } static inline void unlock_timer(struct k_itimer *timr, unsigned long flags) @@ -1225,6 +1230,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; @@ -1252,6 +1258,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 48403fb653c2..a05b735b96ac 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -199,6 +199,11 @@ static bool check_tick_dependency(atomic_t *dep) return true; } + if (val & TICK_DEP_MASK_RCU) { + trace_tick_stop(0, TICK_DEP_MASK_RCU); + return true; + } + return false; } @@ -325,6 +330,7 @@ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) preempt_enable(); } } +EXPORT_SYMBOL_GPL(tick_nohz_dep_set_cpu); void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { @@ -332,6 +338,7 @@ void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) atomic_andnot(BIT(bit), &ts->tick_dep_mask); } +EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu); /* * Set a per-task tick dependency. Posix CPU timers need this in order to elapse @@ -399,7 +406,7 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask) tick_nohz_full_running = true; } -static int tick_nohz_cpu_down(unsigned int cpu) +bool tick_nohz_cpu_hotpluggable(unsigned int cpu) { /* * The boot CPU handles housekeeping duty (unbound timers, @@ -407,8 +414,13 @@ static int tick_nohz_cpu_down(unsigned int cpu) * CPUs. It must remain online when nohz full is enabled. */ if (tick_nohz_full_running && tick_do_timer_cpu == cpu) - return -EBUSY; - return 0; + return false; + return true; +} + +static int tick_nohz_cpu_down(unsigned int cpu) +{ + return tick_nohz_cpu_hotpluggable(cpu) ? 0 : -EBUSY; } void __init tick_nohz_init(void) @@ -1333,13 +1345,18 @@ void tick_setup_sched_timer(void) void tick_cancel_sched_timer(int cpu) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + ktime_t idle_sleeptime, iowait_sleeptime; # ifdef CONFIG_HIGH_RES_TIMERS if (ts->sched_timer.base) hrtimer_cancel(&ts->sched_timer); # endif + idle_sleeptime = ts->idle_sleeptime; + iowait_sleeptime = ts->iowait_sleeptime; memset(ts, 0, sizeof(*ts)); + ts->idle_sleeptime = idle_sleeptime; + ts->iowait_sleeptime = iowait_sleeptime; } #endif diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index c66fd11d94bc..087f71183c3f 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -22,6 +22,7 @@ #include <linux/clocksource.h> #include <linux/jiffies.h> #include <linux/time.h> +#include <linux/timex.h> #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> @@ -1235,8 +1236,7 @@ int do_settimeofday64(const struct timespec64 *ts) timekeeping_forward_now(tk); xt = tk_xtime(tk); - ts_delta.tv_sec = ts->tv_sec - xt.tv_sec; - ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec; + ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { ret = -EINVAL; @@ -2309,6 +2309,20 @@ static int timekeeping_validate_timex(const struct timex *txc) return 0; } +/** + * random_get_entropy_fallback - Returns the raw clock source value, + * used by random.c for platforms with no valid random_get_entropy(). + */ +unsigned long random_get_entropy_fallback(void) +{ + struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; + struct clocksource *clock = READ_ONCE(tkr->clock); + + if (unlikely(timekeeping_suspended || !clock)) + return 0; + return clock->read(clock); +} +EXPORT_SYMBOL_GPL(random_get_entropy_fallback); /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 75ea1a5be31a..113cbe1a20aa 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1594,7 +1594,8 @@ blk_trace_event_print_binary(struct trace_iterator *iter, int flags, static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter) { - if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) + if ((iter->ent->type != TRACE_BLK) || + !(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) return TRACE_TYPE_UNHANDLED; return print_one_line(iter, true); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 1cb13d6368f3..b794470bb42e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1274,7 +1274,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, #ifdef CONFIG_UPROBE_EVENTS if (flags & TRACE_EVENT_FL_UPROBE) err = bpf_get_uprobe_info(event, fd_type, buf, - probe_offset, + probe_offset, probe_addr, event->attr.type == PERF_TYPE_TRACEPOINT); #endif } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 998d141488a9..81f5c9c85d06 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1124,7 +1124,7 @@ struct ftrace_page { struct ftrace_page *next; struct dyn_ftrace *records; int index; - int size; + int order; }; #define ENTRY_SIZE sizeof(struct dyn_ftrace) @@ -1331,6 +1331,7 @@ static int ftrace_add_mod(struct trace_array *tr, if (!ftrace_mod) return -ENOMEM; + INIT_LIST_HEAD(&ftrace_mod->list); ftrace_mod->func = kstrdup(func, GFP_KERNEL); ftrace_mod->module = kstrdup(module, GFP_KERNEL); ftrace_mod->enable = enable; @@ -1580,7 +1581,8 @@ unsigned long ftrace_location_range(unsigned long start, unsigned long end) key.flags = end; /* overload flags, as it is unsigned long */ for (pg = ftrace_pages_start; pg; pg = pg->next) { - if (end < pg->records[0].ip || + if (pg->index == 0 || + end < pg->records[0].ip || start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE)) continue; rec = bsearch(&key, pg->records, pg->index, @@ -2748,6 +2750,16 @@ static int ftrace_startup(struct ftrace_ops *ops, int command) ftrace_startup_enable(command); + /* + * If ftrace is in an undefined state, we just remove ops from list + * to prevent the NULL pointer, instead of totally rolling it back and + * free trampoline, because those actions could cause further damage. + */ + if (unlikely(ftrace_disabled)) { + __unregister_ftrace_function(ops); + return -ENODEV; + } + ops->flags &= ~FTRACE_OPS_FL_ADDING; return 0; @@ -2903,6 +2915,8 @@ static void ftrace_shutdown_sysctl(void) static u64 ftrace_update_time; unsigned long ftrace_update_tot_cnt; +unsigned long ftrace_number_of_pages; +unsigned long ftrace_number_of_groups; static inline int ops_traces_mod(struct ftrace_ops *ops) { @@ -3023,12 +3037,15 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) /* if we can't allocate this size, try something smaller */ if (!order) return -ENOMEM; - order >>= 1; + order--; goto again; } + ftrace_number_of_pages += 1 << order; + ftrace_number_of_groups++; + cnt = (PAGE_SIZE << order) / ENTRY_SIZE; - pg->size = cnt; + pg->order = order; if (cnt > count) cnt = count; @@ -3036,12 +3053,27 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) return cnt; } +static void ftrace_free_pages(struct ftrace_page *pages) +{ + struct ftrace_page *pg = pages; + + while (pg) { + if (pg->records) { + free_pages((unsigned long)pg->records, pg->order); + ftrace_number_of_pages -= 1 << pg->order; + } + pages = pg->next; + kfree(pg); + pg = pages; + ftrace_number_of_groups--; + } +} + static struct ftrace_page * ftrace_allocate_pages(unsigned long num_to_init) { struct ftrace_page *start_pg; struct ftrace_page *pg; - int order; int cnt; if (!num_to_init) @@ -3075,14 +3107,7 @@ ftrace_allocate_pages(unsigned long num_to_init) return start_pg; free_pages: - pg = start_pg; - while (pg) { - order = get_count_order(pg->size / ENTRIES_PER_PAGE); - free_pages((unsigned long)pg->records, order); - start_pg = pg->next; - kfree(pg); - pg = start_pg; - } + ftrace_free_pages(start_pg); pr_info("ftrace: FAILED to allocate memory for functions\n"); return NULL; } @@ -5044,8 +5069,12 @@ int ftrace_regex_release(struct inode *inode, struct file *file) if (filter_hash) { orig_hash = &iter->ops->func_hash->filter_hash; - if (iter->tr && !list_empty(&iter->tr->mod_trace)) - iter->hash->flags |= FTRACE_HASH_FL_MOD; + if (iter->tr) { + if (list_empty(&iter->tr->mod_trace)) + iter->hash->flags &= ~FTRACE_HASH_FL_MOD; + else + iter->hash->flags |= FTRACE_HASH_FL_MOD; + } } else orig_hash = &iter->ops->func_hash->notrace_hash; @@ -5570,9 +5599,11 @@ static int ftrace_process_locs(struct module *mod, unsigned long *start, unsigned long *end) { + struct ftrace_page *pg_unuse = NULL; struct ftrace_page *start_pg; struct ftrace_page *pg; struct dyn_ftrace *rec; + unsigned long skipped = 0; unsigned long count; unsigned long *p; unsigned long addr; @@ -5618,6 +5649,7 @@ static int ftrace_process_locs(struct module *mod, p = start; pg = start_pg; while (p < end) { + unsigned long end_offset; addr = ftrace_call_adjust(*p++); /* * Some architecture linkers will pad between @@ -5625,10 +5657,13 @@ static int ftrace_process_locs(struct module *mod, * object files to satisfy alignments. * Skip any NULL pointers. */ - if (!addr) + if (!addr) { + skipped++; continue; + } - if (pg->index == pg->size) { + end_offset = (pg->index+1) * sizeof(pg->records[0]); + if (end_offset > PAGE_SIZE << pg->order) { /* We should have allocated enough */ if (WARN_ON(!pg->next)) break; @@ -5639,8 +5674,10 @@ static int ftrace_process_locs(struct module *mod, rec->ip = addr; } - /* We should have used all pages */ - WARN_ON(pg->next); + if (pg->next) { + pg_unuse = pg->next; + pg->next = NULL; + } /* Assign the last page to ftrace_pages */ ftrace_pages = pg; @@ -5662,6 +5699,11 @@ static int ftrace_process_locs(struct module *mod, out: mutex_unlock(&ftrace_lock); + /* We should have used all pages unless we skipped some */ + if (pg_unuse) { + WARN_ON(!skipped); + ftrace_free_pages(pg_unuse); + } return ret; } @@ -5768,7 +5810,6 @@ void ftrace_release_mod(struct module *mod) struct ftrace_page **last_pg; struct ftrace_page *tmp_page = NULL; struct ftrace_page *pg; - int order; mutex_lock(&ftrace_lock); @@ -5819,10 +5860,13 @@ void ftrace_release_mod(struct module *mod) /* Needs to be called outside of ftrace_lock */ clear_mod_from_hashes(pg); - order = get_count_order(pg->size / ENTRIES_PER_PAGE); - free_pages((unsigned long)pg->records, order); + if (pg->records) { + free_pages((unsigned long)pg->records, pg->order); + ftrace_number_of_pages -= 1 << pg->order; + } tmp_page = pg->next; kfree(pg); + ftrace_number_of_groups--; } } @@ -6128,7 +6172,6 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) struct ftrace_mod_map *mod_map = NULL; struct ftrace_init_func *func, *func_next; struct list_head clear_hash; - int order; INIT_LIST_HEAD(&clear_hash); @@ -6166,8 +6209,11 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) ftrace_update_tot_cnt--; if (!pg->index) { *last_pg = pg->next; - order = get_count_order(pg->size / ENTRIES_PER_PAGE); - free_pages((unsigned long)pg->records, order); + if (pg->records) { + free_pages((unsigned long)pg->records, pg->order); + ftrace_number_of_pages -= 1 << pg->order; + } + ftrace_number_of_groups--; kfree(pg); pg = container_of(last_pg, struct ftrace_page, next); if (!(*last_pg)) @@ -6215,7 +6261,7 @@ void __init ftrace_init(void) } pr_info("ftrace: allocating %ld entries in %ld pages\n", - count, count / ENTRIES_PER_PAGE + 1); + count, DIV_ROUND_UP(count, ENTRIES_PER_PAGE)); last_ftrace_enabled = ftrace_enabled = 1; @@ -6223,6 +6269,9 @@ void __init ftrace_init(void) __start_mcount_loc, __stop_mcount_loc); + pr_info("ftrace: allocated %ld pages with %ld groups\n", + ftrace_number_of_pages, ftrace_number_of_groups); + set_ftrace_early_filters(); return; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 987d3447bf2a..d2903d8834fe 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -493,6 +493,8 @@ struct ring_buffer_per_cpu { unsigned long read_bytes; u64 write_stamp; u64 read_stamp; + /* pages removed since last reset */ + unsigned long pages_removed; /* ring buffer pages to update, > 0 to add, < 0 to remove */ long nr_pages_to_update; struct list_head new_pages; /* new pages to add */ @@ -528,6 +530,7 @@ struct ring_buffer_iter { struct buffer_page *head_page; struct buffer_page *cache_reader_page; unsigned long cache_read; + unsigned long cache_pages_removed; u64 read_stamp; }; @@ -542,8 +545,9 @@ static void rb_wake_up_waiters(struct irq_work *work) struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work); wake_up_all(&rbwork->waiters); - if (rbwork->wakeup_full) { + if (rbwork->full_waiters_pending || rbwork->wakeup_full) { rbwork->wakeup_full = false; + rbwork->full_waiters_pending = false; wake_up_all(&rbwork->full_waiters); } } @@ -560,7 +564,7 @@ static void rb_wake_up_waiters(struct irq_work *work) */ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full) { - struct ring_buffer_per_cpu *uninitialized_var(cpu_buffer); + struct ring_buffer_per_cpu *cpu_buffer; DEFINE_WAIT(wait); struct rb_irq_work *work; int ret = 0; @@ -1325,11 +1329,13 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) struct list_head *head = cpu_buffer->pages; struct buffer_page *bpage, *tmp; - free_buffer_page(cpu_buffer->reader_page); + irq_work_sync(&cpu_buffer->irq_work.work); - rb_head_page_deactivate(cpu_buffer); + free_buffer_page(cpu_buffer->reader_page); if (head) { + rb_head_page_deactivate(cpu_buffer); + list_for_each_entry_safe(bpage, tmp, head, list) { list_del_init(&bpage->list); free_buffer_page(bpage); @@ -1338,6 +1344,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) free_buffer_page(bpage); } + free_page((unsigned long)cpu_buffer->free_page); + kfree(cpu_buffer); } @@ -1430,6 +1438,8 @@ ring_buffer_free(struct ring_buffer *buffer) cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node); + irq_work_sync(&buffer->irq_work.work); + for_each_buffer_cpu(buffer, cpu) rb_free_cpu_buffer(buffer->buffers[cpu]); @@ -1509,6 +1519,8 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) to_remove = rb_list_head(to_remove)->next; head_bit |= (unsigned long)to_remove & RB_PAGE_HEAD; } + /* Read iterators need to reset themselves when some pages removed */ + cpu_buffer->pages_removed += nr_removed; next_page = rb_list_head(to_remove)->next; @@ -1530,12 +1542,6 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) cpu_buffer->head_page = list_entry(next_page, struct buffer_page, list); - /* - * change read pointer to make sure any read iterators reset - * themselves - */ - cpu_buffer->read = 0; - /* pages are removed, resume tracing and then free the pages */ atomic_dec(&cpu_buffer->record_disabled); raw_spin_unlock_irq(&cpu_buffer->reader_lock); @@ -1749,6 +1755,8 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, err = -ENOMEM; goto out_err; } + + cond_resched(); } get_online_cpus(); @@ -2156,6 +2164,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* Mark the rest of the page with padding */ rb_event_set_padding(event); + /* Make sure the padding is visible before the write update */ + smp_wmb(); + /* Set the write back to the previous setting */ local_sub(length, &tail_page->write); return; @@ -2167,6 +2178,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* time delta must be non zero */ event->time_delta = 1; + /* Make sure the padding is visible before the tail_page->write update */ + smp_wmb(); + /* Set write to end of buffer */ length = (tail + length) - BUF_PAGE_SIZE; local_sub(length, &tail_page->write); @@ -2456,6 +2470,10 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) if (RB_WARN_ON(cpu_buffer, rb_is_reader_page(cpu_buffer->tail_page))) return; + /* + * No need for a memory barrier here, as the update + * of the tail_page did it for this page. + */ local_set(&cpu_buffer->commit_page->page->commit, rb_page_write(cpu_buffer->commit_page)); rb_inc_page(cpu_buffer, &cpu_buffer->commit_page); @@ -2469,6 +2487,8 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) while (rb_commit_index(cpu_buffer) != rb_page_write(cpu_buffer->commit_page)) { + /* Make sure the readers see the content of what is committed. */ + smp_wmb(); local_set(&cpu_buffer->commit_page->page->commit, rb_page_write(cpu_buffer->commit_page)); RB_WARN_ON(cpu_buffer, @@ -2871,6 +2891,12 @@ rb_reserve_next_event(struct ring_buffer *buffer, int nr_loops = 0; u64 diff; + /* ring buffer does cmpxchg, make sure it is safe in NMI context */ + if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) && + (unlikely(in_nmi()))) { + return NULL; + } + rb_start_commit(cpu_buffer); #ifdef CONFIG_RING_BUFFER_ALLOW_SWAP @@ -3565,6 +3591,7 @@ static void rb_iter_reset(struct ring_buffer_iter *iter) iter->cache_reader_page = iter->head_page; iter->cache_read = cpu_buffer->read; + iter->cache_pages_removed = cpu_buffer->pages_removed; if (iter->head) iter->read_stamp = cpu_buffer->read_stamp; @@ -3812,6 +3839,38 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) arch_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); + /* + * The writer has preempt disable, wait for it. But not forever + * Although, 1 second is pretty much "forever" + */ +#define USECS_WAIT 1000000 + for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) { + /* If the write is past the end of page, a writer is still updating it */ + if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE)) + break; + + udelay(1); + + /* Get the latest version of the reader write value */ + smp_rmb(); + } + + /* The writer is not moving forward? Something is wrong */ + if (RB_WARN_ON(cpu_buffer, nr_loops == USECS_WAIT)) + reader = NULL; + + /* + * Make sure we see any padding after the write update + * (see rb_reset_tail()). + * + * In addition, a writer may be writing on the reader page + * if the page has not been fully filled, so the read barrier + * is also needed to make sure we see the content of what is + * committed by the writer (see rb_set_commit_to_write()). + */ + smp_rmb(); + + return reader; } @@ -3973,12 +4032,13 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) buffer = cpu_buffer->buffer; /* - * Check if someone performed a consuming read to - * the buffer. A consuming read invalidates the iterator - * and we need to reset the iterator in this case. + * Check if someone performed a consuming read to the buffer + * or removed some pages from the buffer. In these cases, + * iterator was invalidated and we need to reset it. */ if (unlikely(iter->cache_read != cpu_buffer->read || - iter->cache_reader_page != cpu_buffer->reader_page)) + iter->cache_reader_page != cpu_buffer->reader_page || + iter->cache_pages_removed != cpu_buffer->pages_removed)) rb_iter_reset(iter); again: @@ -4359,28 +4419,34 @@ unsigned long ring_buffer_size(struct ring_buffer *buffer, int cpu) } EXPORT_SYMBOL_GPL(ring_buffer_size); +static void rb_clear_buffer_page(struct buffer_page *page) +{ + local_set(&page->write, 0); + local_set(&page->entries, 0); + rb_init_page(page->page); + page->read = 0; +} + static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) { + struct buffer_page *page; + rb_head_page_deactivate(cpu_buffer); cpu_buffer->head_page = list_entry(cpu_buffer->pages, struct buffer_page, list); - local_set(&cpu_buffer->head_page->write, 0); - local_set(&cpu_buffer->head_page->entries, 0); - local_set(&cpu_buffer->head_page->page->commit, 0); - - cpu_buffer->head_page->read = 0; + rb_clear_buffer_page(cpu_buffer->head_page); + list_for_each_entry(page, cpu_buffer->pages, list) { + rb_clear_buffer_page(page); + } cpu_buffer->tail_page = cpu_buffer->head_page; cpu_buffer->commit_page = cpu_buffer->head_page; INIT_LIST_HEAD(&cpu_buffer->reader_page->list); INIT_LIST_HEAD(&cpu_buffer->new_pages); - local_set(&cpu_buffer->reader_page->write, 0); - local_set(&cpu_buffer->reader_page->entries, 0); - local_set(&cpu_buffer->reader_page->page->commit, 0); - cpu_buffer->reader_page->read = 0; + rb_clear_buffer_page(cpu_buffer->reader_page); local_set(&cpu_buffer->entries_bytes, 0); local_set(&cpu_buffer->overrun, 0); @@ -4399,6 +4465,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->last_overrun = 0; rb_head_page_activate(cpu_buffer); + cpu_buffer->pages_removed = 0; } /** @@ -4651,11 +4718,16 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page); */ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data) { - struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + struct ring_buffer_per_cpu *cpu_buffer; struct buffer_data_page *bpage = data; struct page *page = virt_to_page(bpage); unsigned long flags; + if (!buffer || !buffer->buffers || !buffer->buffers[cpu]) + return; + + cpu_buffer = buffer->buffers[cpu]; + /* If the page is still in use someplace else, we can't reuse it */ if (page_ref_count(page) > 1) goto out; @@ -4770,7 +4842,15 @@ int ring_buffer_read_page(struct ring_buffer *buffer, unsigned int pos = 0; unsigned int size; - if (full) + /* + * If a full page is expected, this can still be returned + * if there's been a previous partial read and the + * rest of the page can be read and the commit page is off + * the reader page. + */ + if (full && + (!read || (len < (commit - read)) || + cpu_buffer->reader_page == cpu_buffer->commit_page)) goto out_unlock; if (len > (commit - read)) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8168403427a6..e6b2d443bab9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -232,6 +232,10 @@ __setup("trace_clock=", set_trace_boot_clock); static int __init set_tracepoint_printk(char *str) { + /* Ignore the "tp_printk_stop_on_boot" param */ + if (*str == '_') + return 0; + if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0)) tracepoint_printk = 1; return 1; @@ -1114,10 +1118,12 @@ static int __init set_buf_size(char *str) if (!str) return 0; buf_size = memparse(str, &str); - /* nr_entries can not be zero */ - if (buf_size == 0) - return 0; - trace_buf_size = buf_size; + /* + * nr_entries can not be zero and the startup + * tests require some buffer space. Therefore + * ensure we have at least 4096 bytes of buffer. + */ + trace_buf_size = max(4096UL, buf_size); return 1; } __setup("trace_buf_size=", set_buf_size); @@ -2203,8 +2209,11 @@ void trace_buffered_event_enable(void) for_each_tracing_cpu(cpu) { page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, 0); - if (!page) - goto failed; + /* This is just an optimization and can handle failures */ + if (!page) { + pr_err("Failed to allocate event buffer\n"); + break; + } event = page_address(page); memset(event, 0, sizeof(*event)); @@ -2218,10 +2227,6 @@ void trace_buffered_event_enable(void) WARN_ON_ONCE(1); preempt_enable(); } - - return; - failed: - trace_buffered_event_disable(); } static void enable_trace_buffered_event(void *data) @@ -2256,11 +2261,9 @@ void trace_buffered_event_disable(void) if (--trace_buffered_event_ref) return; - preempt_disable(); /* For each CPU, set the buffer as used. */ - smp_call_function_many(tracing_buffer_mask, - disable_trace_buffered_event, NULL, 1); - preempt_enable(); + on_each_cpu_mask(tracing_buffer_mask, disable_trace_buffered_event, + NULL, true); /* Wait for all current users to finish */ synchronize_sched(); @@ -2269,17 +2272,19 @@ void trace_buffered_event_disable(void) free_page((unsigned long)per_cpu(trace_buffered_event, cpu)); per_cpu(trace_buffered_event, cpu) = NULL; } + /* - * Make sure trace_buffered_event is NULL before clearing - * trace_buffered_event_cnt. + * Wait for all CPUs that potentially started checking if they can use + * their event buffer only after the previous synchronize_rcu() call and + * they still read a valid pointer from trace_buffered_event. It must be + * ensured they don't see cleared trace_buffered_event_cnt else they + * could wrongly decide to use the pointed-to buffer which is now freed. */ - smp_wmb(); + synchronize_rcu(); - preempt_disable(); - /* Do the work on each cpu */ - smp_call_function_many(tracing_buffer_mask, - enable_trace_buffered_event, NULL, 1); - preempt_enable(); + /* For each CPU, relinquish the buffer */ + on_each_cpu_mask(tracing_buffer_mask, enable_trace_buffered_event, NULL, + true); } static struct ring_buffer *temp_buffer; @@ -2325,7 +2330,7 @@ trace_event_buffer_lock_reserve(struct ring_buffer **current_rb, } EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve); -static DEFINE_SPINLOCK(tracepoint_iter_lock); +static DEFINE_RAW_SPINLOCK(tracepoint_iter_lock); static DEFINE_MUTEX(tracepoint_printk_mutex); static void output_printk(struct trace_event_buffer *fbuffer) @@ -2346,14 +2351,14 @@ static void output_printk(struct trace_event_buffer *fbuffer) event = &fbuffer->trace_file->event_call->event; - spin_lock_irqsave(&tracepoint_iter_lock, flags); + raw_spin_lock_irqsave(&tracepoint_iter_lock, flags); trace_seq_init(&iter->seq); iter->ent = fbuffer->entry; event_call->event.funcs->trace(iter, 0, event); trace_seq_putc(&iter->seq, 0); printk("%s", iter->seq.buffer); - spin_unlock_irqrestore(&tracepoint_iter_lock, flags); + raw_spin_unlock_irqrestore(&tracepoint_iter_lock, flags); } int tracepoint_printk_sysctl(struct ctl_table *table, int write, @@ -2812,7 +2817,7 @@ struct trace_buffer_struct { char buffer[4][TRACE_BUF_SIZE]; }; -static struct trace_buffer_struct *trace_percpu_buffer; +static struct trace_buffer_struct __percpu *trace_percpu_buffer; /* * Thise allows for lockless recording. If we're nested too deeply, then @@ -2822,7 +2827,7 @@ static char *get_trace_buf(void) { struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer); - if (!buffer || buffer->nesting >= 4) + if (!trace_percpu_buffer || buffer->nesting >= 4) return NULL; buffer->nesting++; @@ -2841,7 +2846,7 @@ static void put_trace_buf(void) static int alloc_percpu_trace_buffer(void) { - struct trace_buffer_struct *buffers; + struct trace_buffer_struct __percpu *buffers; buffers = alloc_percpu(struct trace_buffer_struct); if (WARN(!buffers, "Could not allocate percpu trace_printk buffer")) @@ -3271,8 +3276,15 @@ static void *s_start(struct seq_file *m, loff_t *pos) * will point to the same string as current_trace->name. */ mutex_lock(&trace_types_lock); - if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) + if (unlikely(tr->current_trace && iter->trace->name != tr->current_trace->name)) { + /* Close iter->trace before switching to the new current tracer */ + if (iter->trace->close) + iter->trace->close(iter); *iter->trace = *tr->current_trace; + /* Reopen the new current tracer */ + if (iter->trace->open) + iter->trace->open(iter); + } mutex_unlock(&trace_types_lock); #ifdef CONFIG_TRACER_MAX_TRACE @@ -3816,7 +3828,11 @@ static int s_show(struct seq_file *m, void *v) iter->leftover = ret; } else { - print_trace_line(iter); + ret = print_trace_line(iter); + if (ret == TRACE_TYPE_PARTIAL_LINE) { + iter->seq.full = 0; + trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n"); + } ret = trace_print_seq(m, &iter->seq); /* * If we overflow the seq_file buffer, then it will @@ -5246,8 +5262,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, return ret; #ifdef CONFIG_TRACER_MAX_TRACE - if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) || - !tr->current_trace->use_max_tr) + if (!tr->current_trace->use_max_tr) goto out; ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu); @@ -5362,12 +5377,18 @@ static void tracing_set_nop(struct trace_array *tr) tr->current_trace = &nop_trace; } +static bool tracer_options_updated; + static void add_tracer_options(struct trace_array *tr, struct tracer *t) { /* Only enable if the directory has been created already. */ if (!tr->dir) return; + /* Only create trace option files after update_tracer_options finish */ + if (!tracer_options_updated) + return; + create_trace_option_files(tr, t); } @@ -5791,7 +5812,20 @@ waitagain: ret = print_trace_line(iter); if (ret == TRACE_TYPE_PARTIAL_LINE) { - /* don't print partial lines */ + /* + * If one print_trace_line() fills entire trace_seq in one shot, + * trace_seq_to_user() will returns -EBUSY because save_len == 0, + * In this case, we need to consume it, otherwise, loop will peek + * this event next time, resulting in an infinite loop. + */ + if (save_len == 0) { + iter->seq.full = 0; + trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n"); + trace_consume(iter); + break; + } + + /* In other cases, don't print partial lines */ iter->seq.seq.len = save_len; break; } @@ -7082,14 +7116,23 @@ static ssize_t tracing_read_dyn_info(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - unsigned long *p = filp->private_data; - char buf[64]; /* Not too big for a shallow stack */ + ssize_t ret; + char *buf; int r; - r = scnprintf(buf, 63, "%ld", *p); - buf[r++] = '\n'; + /* 256 should be plenty to hold the amount needed */ + buf = kmalloc(256, GFP_KERNEL); + if (!buf) + return -ENOMEM; - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + r = scnprintf(buf, 256, "%ld pages:%ld groups: %ld\n", + ftrace_update_tot_cnt, + ftrace_number_of_pages, + ftrace_number_of_groups); + + ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + kfree(buf); + return ret; } static const struct file_operations tracing_dyn_info_fops = { @@ -7814,6 +7857,7 @@ static void __update_tracer_options(struct trace_array *tr) static void update_tracer_options(struct trace_array *tr) { mutex_lock(&trace_types_lock); + tracer_options_updated = true; __update_tracer_options(tr); mutex_unlock(&trace_types_lock); } @@ -8220,7 +8264,7 @@ static __init int tracer_init_tracefs(void) #ifdef CONFIG_DYNAMIC_FTRACE trace_create_file("dyn_ftrace_total_info", 0444, d_tracer, - &ftrace_update_tot_cnt, &tracing_dyn_info_fops); + NULL, &tracing_dyn_info_fops); #endif create_trace_instances(d_tracer); @@ -8648,6 +8692,8 @@ void __init early_trace_init(void) static_key_enable(&tracepoint_printk_key.key); } tracer_alloc_buffers(); + + init_events(); } void __init trace_init(void) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 74185fb040f3..f4d83b552a47 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -748,6 +748,8 @@ extern void trace_event_follow_fork(struct trace_array *tr, bool enable); #ifdef CONFIG_DYNAMIC_FTRACE extern unsigned long ftrace_update_tot_cnt; +extern unsigned long ftrace_number_of_pages; +extern unsigned long ftrace_number_of_groups; void ftrace_init_trace_array(struct trace_array *tr); #else static inline void ftrace_init_trace_array(struct trace_array *tr) { } @@ -1530,6 +1532,7 @@ extern void trace_event_enable_cmd_record(bool enable); extern void trace_event_enable_tgid_record(bool enable); extern int event_trace_init(void); +extern int init_events(void); extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern int event_trace_del_tracer(struct trace_array *tr); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 1ca64a9296d0..ed39d3ec202e 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -173,6 +173,7 @@ static int trace_define_generic_fields(void) __generic_field(int, CPU, FILTER_CPU); __generic_field(int, cpu, FILTER_CPU); + __generic_field(int, common_cpu, FILTER_CPU); __generic_field(char *, COMM, FILTER_COMM); __generic_field(char *, comm, FILTER_COMM); @@ -371,7 +372,6 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, { struct trace_event_call *call = file->event_call; struct trace_array *tr = file->tr; - unsigned long file_flags = file->flags; int ret = 0; int disable; @@ -395,6 +395,8 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, break; disable = file->flags & EVENT_FILE_FL_SOFT_DISABLED; clear_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags); + /* Disable use of trace_buffered_event */ + trace_buffered_event_disable(); } else disable = !(file->flags & EVENT_FILE_FL_SOFT_MODE); @@ -433,6 +435,8 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, if (atomic_inc_return(&file->sm_ref) > 1) break; set_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags); + /* Enable use of trace_buffered_event */ + trace_buffered_event_enable(); } if (!(file->flags & EVENT_FILE_FL_ENABLED)) { @@ -472,15 +476,6 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, break; } - /* Enable or disable use of trace_buffered_event */ - if ((file_flags & EVENT_FILE_FL_SOFT_DISABLED) != - (file->flags & EVENT_FILE_FL_SOFT_DISABLED)) { - if (file->flags & EVENT_FILE_FL_SOFT_DISABLED) - trace_buffered_event_enable(); - else - trace_buffered_event_disable(); - } - return ret; } @@ -2247,6 +2242,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len) update_event_printk(call, map[i]); } } + cond_resched(); } up_write(&trace_event_sem); } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 44d1340634f6..e004daf8cad5 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1764,6 +1764,9 @@ static const char *hist_field_name(struct hist_field *field, { const char *field_name = ""; + if (WARN_ON_ONCE(!field)) + return field_name; + if (level > 1) return field_name; @@ -2314,6 +2317,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, unsigned long fl = flags & ~HIST_FIELD_FL_LOG2; hist_field->fn = hist_field_log2; hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL); + if (!hist_field->operands[0]) + goto free; hist_field->size = hist_field->operands[0]->size; hist_field->type = kstrdup(hist_field->operands[0]->type, GFP_KERNEL); if (!hist_field->type) @@ -2456,8 +2461,11 @@ static int init_var_ref(struct hist_field *ref_field, return err; free: kfree(ref_field->system); + ref_field->system = NULL; kfree(ref_field->event_name); + ref_field->event_name = NULL; kfree(ref_field->name); + ref_field->name = NULL; goto out; } @@ -2635,9 +2643,9 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, /* * For backward compatibility, if field_name * was "cpu", then we treat this the same as - * common_cpu. + * common_cpu. This also works for "CPU". */ - if (strcmp(field_name, "cpu") == 0) { + if (field && field->filter_type == FILTER_CPU) { *flags |= HIST_FIELD_FL_CPU; } else { hist_err("Couldn't find field: ", field_name); @@ -4263,6 +4271,8 @@ static int parse_var_defs(struct hist_trigger_data *hist_data) s = kstrdup(field_str, GFP_KERNEL); if (!s) { + kfree(hist_data->attrs->var_defs.name[n_vars]); + hist_data->attrs->var_defs.name[n_vars] = NULL; ret = -ENOMEM; goto free; } @@ -4642,7 +4652,7 @@ static int create_tracing_map_fields(struct hist_trigger_data *hist_data) if (hist_field->flags & HIST_FIELD_FL_STACKTRACE) cmp_fn = tracing_map_cmp_none; - else if (!field) + else if (!field || hist_field->flags & HIST_FIELD_FL_CPU) cmp_fn = tracing_map_cmp_num(hist_field->size, hist_field->is_signed); else if (is_string_field(field)) @@ -5777,13 +5787,16 @@ static int event_hist_trigger_func(struct event_command *cmd_ops, if (get_named_trigger_data(trigger_data)) goto enable; - if (has_hist_vars(hist_data)) - save_hist_vars(hist_data); - ret = create_actions(hist_data, file); if (ret) goto out_unreg; + if (has_hist_vars(hist_data) || hist_data->n_var_refs) { + ret = save_hist_vars(hist_data); + if (ret) + goto out_unreg; + } + ret = tracing_map_init(hist_data->map); if (ret) goto out_unreg; @@ -5802,7 +5815,7 @@ enable: /* Just return zero, not the number of registered triggers */ ret = 0; out: - if (ret == 0) + if (ret == 0 && glob[0]) hist_err_clear(); return ret; diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 0c3b1551cfca..4b0bde304ad7 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -933,6 +933,16 @@ static void traceon_trigger(struct event_trigger_data *data, void *rec, struct ring_buffer_event *event) { + struct trace_event_file *file = data->private_data; + + if (file) { + if (tracer_tracing_is_on(file->tr)) + return; + + tracer_tracing_on(file->tr); + return; + } + if (tracing_is_on()) return; @@ -943,8 +953,15 @@ static void traceon_count_trigger(struct event_trigger_data *data, void *rec, struct ring_buffer_event *event) { - if (tracing_is_on()) - return; + struct trace_event_file *file = data->private_data; + + if (file) { + if (tracer_tracing_is_on(file->tr)) + return; + } else { + if (tracing_is_on()) + return; + } if (!data->count) return; @@ -952,13 +969,26 @@ traceon_count_trigger(struct event_trigger_data *data, void *rec, if (data->count != -1) (data->count)--; - tracing_on(); + if (file) + tracer_tracing_on(file->tr); + else + tracing_on(); } static void traceoff_trigger(struct event_trigger_data *data, void *rec, struct ring_buffer_event *event) { + struct trace_event_file *file = data->private_data; + + if (file) { + if (!tracer_tracing_is_on(file->tr)) + return; + + tracer_tracing_off(file->tr); + return; + } + if (!tracing_is_on()) return; @@ -969,8 +999,15 @@ static void traceoff_count_trigger(struct event_trigger_data *data, void *rec, struct ring_buffer_event *event) { - if (!tracing_is_on()) - return; + struct trace_event_file *file = data->private_data; + + if (file) { + if (!tracer_tracing_is_on(file->tr)) + return; + } else { + if (!tracing_is_on()) + return; + } if (!data->count) return; @@ -978,7 +1015,10 @@ traceoff_count_trigger(struct event_trigger_data *data, void *rec, if (data->count != -1) (data->count)--; - tracing_off(); + if (file) + tracer_tracing_off(file->tr); + else + tracing_off(); } static int @@ -1172,7 +1212,14 @@ static void stacktrace_trigger(struct event_trigger_data *data, void *rec, struct ring_buffer_event *event) { - trace_dump_stack(STACK_SKIP); + struct trace_event_file *file = data->private_data; + unsigned long flags; + + if (file) { + local_save_flags(flags); + __trace_stack(file->tr, flags, STACK_SKIP, preempt_count()); + } else + trace_dump_stack(STACK_SKIP); } static void diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 98ea6d28df15..0f36bb59970d 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -222,7 +222,8 @@ static void irqsoff_trace_open(struct trace_iterator *iter) { if (is_graph(iter->tr)) graph_trace_open(iter); - + else + iter->private = NULL; } static void irqsoff_trace_close(struct trace_iterator *iter) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 6e6cc64faa38..43fb832d26d2 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1320,11 +1320,12 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter, { struct print_entry *field; struct trace_seq *s = &iter->seq; + int max = iter->ent_size - offsetof(struct print_entry, buf); trace_assign_type(field, iter->ent); seq_print_ip_sym(s, field->ip, flags); - trace_seq_printf(s, ": %s", field->buf); + trace_seq_printf(s, ": %.*s", max, field->buf); return trace_handle_return(s); } @@ -1333,10 +1334,11 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags, struct trace_event *event) { struct print_entry *field; + int max = iter->ent_size - offsetof(struct print_entry, buf); trace_assign_type(field, iter->ent); - trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf); + trace_seq_printf(&iter->seq, "# %lx %.*s", field->ip, max, field->buf); return trace_handle_return(&iter->seq); } @@ -1395,7 +1397,7 @@ static struct trace_event *events[] __initdata = { NULL }; -__init static int init_events(void) +__init int init_events(void) { struct trace_event *event; int i, ret; @@ -1413,4 +1415,3 @@ __init static int init_events(void) return 0; } -early_initcall(init_events); diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index e99c3ce7aa65..d85ee1778b99 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -361,7 +361,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t, } } else ret = -EINVAL; - } else if (strcmp(arg, "comm") == 0) { + } else if (strcmp(arg, "comm") == 0 || strcmp(arg, "COMM") == 0) { if (strcmp(t->name, "string") != 0 && strcmp(t->name, "string_size") != 0) return -EINVAL; @@ -544,7 +544,7 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size, * The default type of $comm should be "string", and it can't be * dereferenced. */ - if (!t && strcmp(arg, "$comm") == 0) + if (!t && (strcmp(arg, "$comm") == 0 || strcmp(arg, "$COMM") == 0)) t = "string"; parg->type = find_fetch_type(t, ftbl); if (!parg->type) { diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 11f4dbd9526b..8041bd5e4262 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -287,6 +287,8 @@ static void wakeup_trace_open(struct trace_iterator *iter) { if (is_graph(iter->tr)) graph_trace_open(iter); + else + iter->private = NULL; } static void wakeup_trace_close(struct trace_iterator *iter) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 0da379b90249..0e3bdd69fa2d 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1159,7 +1159,7 @@ static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, const char **filename, u64 *probe_offset, - bool perf_type_tracepoint) + u64 *probe_addr, bool perf_type_tracepoint) { const char *pevent = trace_event_name(event->tp_event); const char *group = event->tp_event->class->system; @@ -1176,6 +1176,7 @@ int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, : BPF_FD_TYPE_UPROBE; *filename = tu->filename; *probe_offset = tu->offset; + *probe_addr = 0; return 0; } #endif /* CONFIG_PERF_EVENTS */ diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 10657b8dc2c2..83c2a0598c64 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -15,6 +15,7 @@ #include <linux/jhash.h> #include <linux/slab.h> #include <linux/sort.h> +#include <linux/kmemleak.h> #include "tracing_map.h" #include "trace.h" @@ -307,6 +308,7 @@ void tracing_map_array_free(struct tracing_map_array *a) for (i = 0; i < a->n_pages; i++) { if (!a->pages[i]) break; + kmemleak_free(a->pages[i]); free_page((unsigned long)a->pages[i]); } @@ -342,6 +344,7 @@ struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts, a->pages[i] = (void *)get_zeroed_page(GFP_KERNEL); if (!a->pages[i]) goto free; + kmemleak_alloc(a->pages[i], PAGE_SIZE, 1, GFP_KERNEL); } out: return a; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 370724b45391..8d7c6d3f1daa 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -46,11 +46,10 @@ void bacct_add_tsk(struct user_namespace *user_ns, /* Convert to seconds for btime */ do_div(delta, USEC_PER_SEC); stats->ac_btime = get_seconds() - delta; - if (thread_group_leader(tsk)) { + if (tsk->flags & PF_EXITING) stats->ac_exitcode = tsk->exit_code; - if (tsk->flags & PF_FORKNOEXEC) - stats->ac_flag |= AFORK; - } + if (thread_group_leader(tsk) && (tsk->flags & PF_FORKNOEXEC)) + stats->ac_flag |= AFORK; if (tsk->flags & PF_SUPERPRIV) stats->ac_flag |= ASU; if (tsk->flags & PF_DUMPCORE) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 6d60701dc636..44096c4f4d60 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -561,7 +561,7 @@ int lockup_detector_offline_cpu(unsigned int cpu) return 0; } -static void lockup_detector_reconfigure(void) +static void __lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_nmi_stop(); @@ -581,6 +581,13 @@ static void lockup_detector_reconfigure(void) __lockup_detector_cleanup(); } +void lockup_detector_reconfigure(void) +{ + mutex_lock(&watchdog_mutex); + __lockup_detector_reconfigure(); + mutex_unlock(&watchdog_mutex); +} + /* * Create the watchdog thread infrastructure and configure the detector(s). * @@ -601,13 +608,13 @@ static __init void lockup_detector_setup(void) return; mutex_lock(&watchdog_mutex); - lockup_detector_reconfigure(); + __lockup_detector_reconfigure(); softlockup_initialized = true; mutex_unlock(&watchdog_mutex); } #else /* CONFIG_SOFTLOCKUP_DETECTOR */ -static void lockup_detector_reconfigure(void) +static void __lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_nmi_stop(); @@ -615,9 +622,13 @@ static void lockup_detector_reconfigure(void) watchdog_nmi_start(); cpus_read_unlock(); } +void lockup_detector_reconfigure(void) +{ + __lockup_detector_reconfigure(); +} static inline void lockup_detector_setup(void) { - lockup_detector_reconfigure(); + __lockup_detector_reconfigure(); } #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ @@ -657,7 +668,7 @@ static void proc_watchdog_update(void) { /* Remove impossible cpus to keep sysctl output clean. */ cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); - lockup_detector_reconfigure(); + __lockup_detector_reconfigure(); } /* diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 71381168dede..f8e460b4a59d 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -114,14 +114,14 @@ static void watchdog_overflow_callback(struct perf_event *event, /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; + if (!watchdog_check_timestamp()) + return; + if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; } - if (!watchdog_check_timestamp()) - return; - /* check for a hardlockup * This is done by making sure our timer interrupt * is incrementing. The timer interrupt should have diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b1bb6cb5802e..017939097451 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -680,12 +680,17 @@ static void clear_work_data(struct work_struct *work) set_work_data(work, WORK_STRUCT_NO_POOL, 0); } +static inline struct pool_workqueue *work_struct_pwq(unsigned long data) +{ + return (struct pool_workqueue *)(data & WORK_STRUCT_WQ_DATA_MASK); +} + static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) - return (void *)(data & WORK_STRUCT_WQ_DATA_MASK); + return work_struct_pwq(data); else return NULL; } @@ -713,8 +718,7 @@ static struct worker_pool *get_work_pool(struct work_struct *work) assert_rcu_or_pool_mutex(); if (data & WORK_STRUCT_PWQ) - return ((struct pool_workqueue *) - (data & WORK_STRUCT_WQ_DATA_MASK))->pool; + return work_struct_pwq(data)->pool; pool_id = data >> WORK_OFFQ_POOL_SHIFT; if (pool_id == WORK_OFFQ_POOL_NONE) @@ -735,8 +739,7 @@ static int get_work_pool_id(struct work_struct *work) unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) - return ((struct pool_workqueue *) - (data & WORK_STRUCT_WQ_DATA_MASK))->pool->id; + return work_struct_pwq(data)->pool->id; return data >> WORK_OFFQ_POOL_SHIFT; } @@ -2917,10 +2920,8 @@ static bool __flush_work(struct work_struct *work, bool from_cancel) if (WARN_ON(!work->func)) return false; - if (!from_cancel) { - lock_map_acquire(&work->lockdep_map); - lock_map_release(&work->lockdep_map); - } + lock_map_acquire(&work->lockdep_map); + lock_map_release(&work->lockdep_map); if (start_flush_work(work, &barr, from_cancel)) { wait_for_completion(&barr.done); @@ -5086,9 +5087,13 @@ static int workqueue_apply_unbound_cpumask(void) list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_UNBOUND)) continue; + /* creating multiple pwqs breaks ordering guarantee */ - if (wq->flags & __WQ_ORDERED) - continue; + if (!list_empty(&wq->pwqs)) { + if (wq->flags & __WQ_ORDERED_EXPLICIT) + continue; + wq->flags &= ~__WQ_ORDERED; + } ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs); if (!ctx) { |