diff options
Diffstat (limited to 'kernel')
64 files changed, 1320 insertions, 382 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index daad787fb795..f2cc0d118a0b 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -115,6 +115,8 @@ obj-$(CONFIG_TORTURE_TEST) += torture.o obj-$(CONFIG_HAS_IOMEM) += iomem.o obj-$(CONFIG_RSEQ) += rseq.o +obj-$(CONFIG_SYSCTL_KUNIT_TEST) += sysctl-test.o + obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o KASAN_SANITIZE_stackleak.o := n KCOV_INSTRUMENT_stackleak.o := n @@ -128,7 +130,7 @@ $(obj)/config_data.gz: $(KCONFIG_CONFIG) FORCE $(obj)/kheaders.o: $(obj)/kheaders_data.tar.xz quiet_cmd_genikh = CHK $(obj)/kheaders_data.tar.xz - cmd_genikh = $(BASH) $(srctree)/kernel/gen_kheaders.sh $@ + cmd_genikh = $(CONFIG_SHELL) $(srctree)/kernel/gen_kheaders.sh $@ $(obj)/kheaders_data.tar.xz: FORCE $(call cmd,genikh) diff --git a/kernel/audit.c b/kernel/audit.c index fcfbb3476ccd..05ae208ad442 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -879,7 +879,7 @@ main_queue: return 0; } -int audit_send_list(void *_dest) +int audit_send_list_thread(void *_dest) { struct audit_netlink_list *dest = _dest; struct sk_buff *skb; @@ -923,19 +923,30 @@ out_kfree_skb: return NULL; } +static void audit_free_reply(struct audit_reply *reply) +{ + if (!reply) + return; + + if (reply->skb) + kfree_skb(reply->skb); + if (reply->net) + put_net(reply->net); + kfree(reply); +} + static int audit_send_reply_thread(void *arg) { struct audit_reply *reply = (struct audit_reply *)arg; - struct sock *sk = audit_get_sk(reply->net); audit_ctl_lock(); audit_ctl_unlock(); /* Ignore failure. It'll only happen if the sender goes away, because our timeout is set to infinite. */ - netlink_unicast(sk, reply->skb, reply->portid, 0); - put_net(reply->net); - kfree(reply); + netlink_unicast(audit_get_sk(reply->net), reply->skb, reply->portid, 0); + reply->skb = NULL; + audit_free_reply(reply); return 0; } @@ -949,35 +960,32 @@ static int audit_send_reply_thread(void *arg) * @payload: payload data * @size: payload size * - * Allocates an skb, builds the netlink message, and sends it to the port id. - * No failure notifications. + * Allocates a skb, builds the netlink message, and sends it to the port id. */ static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done, int multi, const void *payload, int size) { - struct net *net = sock_net(NETLINK_CB(request_skb).sk); - struct sk_buff *skb; struct task_struct *tsk; - struct audit_reply *reply = kmalloc(sizeof(struct audit_reply), - GFP_KERNEL); + struct audit_reply *reply; + reply = kzalloc(sizeof(*reply), GFP_KERNEL); if (!reply) return; - skb = audit_make_reply(seq, type, done, multi, payload, size); - if (!skb) - goto out; - - reply->net = get_net(net); + reply->skb = audit_make_reply(seq, type, done, multi, payload, size); + if (!reply->skb) + goto err; + reply->net = get_net(sock_net(NETLINK_CB(request_skb).sk)); reply->portid = NETLINK_CB(request_skb).portid; - reply->skb = skb; tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply"); - if (!IS_ERR(tsk)) - return; - kfree_skb(skb); -out: - kfree(reply); + if (IS_ERR(tsk)) + goto err; + + return; + +err: + audit_free_reply(reply); } /* diff --git a/kernel/audit.h b/kernel/audit.h index 6fb7160412d4..ddc22878433d 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -229,7 +229,7 @@ struct audit_netlink_list { struct sk_buff_head q; }; -int audit_send_list(void *_dest); +int audit_send_list_thread(void *_dest); extern int selinux_audit_rule_update(void); diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 4508d5e0cf69..8a8fd732ff6d 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -302,8 +302,6 @@ static void audit_update_watch(struct audit_parent *parent, if (oentry->rule.exe) audit_remove_mark(oentry->rule.exe); - audit_watch_log_rule_change(r, owatch, "updated_rules"); - call_rcu(&oentry->rcu, audit_free_rule_rcu); } diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 026e34da4ace..a10e2997aa6c 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1161,11 +1161,8 @@ int audit_rule_change(int type, int seq, void *data, size_t datasz) */ int audit_list_rules_send(struct sk_buff *request_skb, int seq) { - u32 portid = NETLINK_CB(request_skb).portid; - struct net *net = sock_net(NETLINK_CB(request_skb).sk); struct task_struct *tsk; struct audit_netlink_list *dest; - int err = 0; /* We can't just spew out the rules here because we might fill * the available socket buffer space and deadlock waiting for @@ -1173,25 +1170,26 @@ int audit_list_rules_send(struct sk_buff *request_skb, int seq) * happen if we're actually running in the context of auditctl * trying to _send_ the stuff */ - dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL); + dest = kmalloc(sizeof(*dest), GFP_KERNEL); if (!dest) return -ENOMEM; - dest->net = get_net(net); - dest->portid = portid; + dest->net = get_net(sock_net(NETLINK_CB(request_skb).sk)); + dest->portid = NETLINK_CB(request_skb).portid; skb_queue_head_init(&dest->q); mutex_lock(&audit_filter_mutex); audit_list_rules(seq, &dest->q); mutex_unlock(&audit_filter_mutex); - tsk = kthread_run(audit_send_list, dest, "audit_send_list"); + tsk = kthread_run(audit_send_list_thread, dest, "audit_send_list"); if (IS_ERR(tsk)) { skb_queue_purge(&dest->q); + put_net(dest->net); kfree(dest); - err = PTR_ERR(tsk); + return PTR_ERR(tsk); } - return err; + return 0; } int audit_comparator(u32 left, u32 op, u32 right) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 869e2e1860e8..b701af27a779 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -966,16 +966,23 @@ static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp, static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) { - if (unlikely(max_optlen > PAGE_SIZE) || max_optlen < 0) + if (unlikely(max_optlen < 0)) return -EINVAL; + if (unlikely(max_optlen > PAGE_SIZE)) { + /* We don't expose optvals that are greater than PAGE_SIZE + * to the BPF program. + */ + max_optlen = PAGE_SIZE; + } + ctx->optval = kzalloc(max_optlen, GFP_USER); if (!ctx->optval) return -ENOMEM; ctx->optval_end = ctx->optval + max_optlen; - return 0; + return max_optlen; } static void sockopt_free_buf(struct bpf_sockopt_kern *ctx) @@ -1009,13 +1016,13 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, */ max_optlen = max_t(int, 16, *optlen); - ret = sockopt_alloc_buf(&ctx, max_optlen); - if (ret) - return ret; + max_optlen = sockopt_alloc_buf(&ctx, max_optlen); + if (max_optlen < 0) + return max_optlen; ctx.optlen = *optlen; - if (copy_from_user(ctx.optval, optval, *optlen) != 0) { + if (copy_from_user(ctx.optval, optval, min(*optlen, max_optlen)) != 0) { ret = -EFAULT; goto out; } @@ -1043,8 +1050,14 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, /* export any potential modifications */ *level = ctx.level; *optname = ctx.optname; - *optlen = ctx.optlen; - *kernel_optval = ctx.optval; + + /* optlen == 0 from BPF indicates that we should + * use original userspace data. + */ + if (ctx.optlen != 0) { + *optlen = ctx.optlen; + *kernel_optval = ctx.optval; + } } out: @@ -1076,12 +1089,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT)) return retval; - ret = sockopt_alloc_buf(&ctx, max_optlen); - if (ret) - return ret; - ctx.optlen = max_optlen; + max_optlen = sockopt_alloc_buf(&ctx, max_optlen); + if (max_optlen < 0) + return max_optlen; + if (!retval) { /* If kernel getsockopt finished successfully, * copy whatever was returned to the user back @@ -1095,10 +1108,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; } - if (ctx.optlen > max_optlen) - ctx.optlen = max_optlen; - - if (copy_from_user(ctx.optval, optval, ctx.optlen) != 0) { + if (copy_from_user(ctx.optval, optval, + min(ctx.optlen, max_optlen)) != 0) { ret = -EFAULT; goto out; } @@ -1127,10 +1138,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; } - if (copy_to_user(optval, ctx.optval, ctx.optlen) || - put_user(ctx.optlen, optlen)) { - ret = -EFAULT; - goto out; + if (ctx.optlen != 0) { + if (copy_to_user(optval, ctx.optval, ctx.optlen) || + put_user(ctx.optlen, optlen)) { + ret = -EFAULT; + goto out; + } } ret = ctx.retval; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index b4b6b77f309c..6684696fa457 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -88,12 +88,13 @@ struct bpf_dtab { static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); -static struct hlist_head *dev_map_create_hash(unsigned int entries) +static struct hlist_head *dev_map_create_hash(unsigned int entries, + int numa_node) { int i; struct hlist_head *hash; - hash = kmalloc_array(entries, sizeof(*hash), GFP_KERNEL); + hash = bpf_map_area_alloc(entries * sizeof(*hash), numa_node); if (hash != NULL) for (i = 0; i < entries; i++) INIT_HLIST_HEAD(&hash[i]); @@ -151,7 +152,8 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) INIT_LIST_HEAD(per_cpu_ptr(dtab->flush_list, cpu)); if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { - dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets); + dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, + dtab->map.numa_node); if (!dtab->dev_index_head) goto free_percpu; @@ -249,7 +251,7 @@ static void dev_map_free(struct bpf_map *map) } } - kfree(dtab->dev_index_head); + bpf_map_area_free(dtab->dev_index_head); } else { for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 22066a62c8c9..728ffec52cf3 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -664,26 +664,23 @@ static void htab_elem_free_rcu(struct rcu_head *head) struct htab_elem *l = container_of(head, struct htab_elem, rcu); struct bpf_htab *htab = l->htab; - /* must increment bpf_prog_active to avoid kprobe+bpf triggering while - * we're calling kfree, otherwise deadlock is possible if kprobes - * are placed somewhere inside of slub - */ - preempt_disable(); - __this_cpu_inc(bpf_prog_active); htab_elem_free(htab, l); - __this_cpu_dec(bpf_prog_active); - preempt_enable(); } -static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) { struct bpf_map *map = &htab->map; + void *ptr; if (map->ops->map_fd_put_ptr) { - void *ptr = fd_htab_map_get_ptr(map, l); - + ptr = fd_htab_map_get_ptr(map, l); map->ops->map_fd_put_ptr(ptr); } +} + +static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +{ + htab_put_fd_value(htab, l); if (htab_is_prealloc(htab)) { __pcpu_freelist_push(&htab->freelist, &l->fnode); @@ -735,6 +732,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, */ pl_new = this_cpu_ptr(htab->extra_elems); l_new = *pl_new; + htab_put_fd_value(htab, old_elem); *pl_new = old_elem; } else { struct pcpu_freelist_node *l; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 218c09ff6a27..375d93eb71c7 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -205,10 +205,12 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) else prev_key = key; + rcu_read_lock(); if (map->ops->map_get_next_key(map, prev_key, key)) { map_iter(m)->done = true; - return NULL; + key = NULL; } + rcu_read_unlock(); return key; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 946cfdd3b2cc..bf03d04a9e2f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1118,7 +1118,8 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || + !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -2028,10 +2029,10 @@ static int bpf_prog_detach(const union bpf_attr *attr) ptype = BPF_PROG_TYPE_CGROUP_DEVICE; break; case BPF_SK_MSG_VERDICT: - return sock_map_get_from_fd(attr, NULL); + return sock_map_prog_detach(attr, BPF_PROG_TYPE_SK_MSG); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - return sock_map_get_from_fd(attr, NULL); + return sock_map_prog_detach(attr, BPF_PROG_TYPE_SK_SKB); case BPF_LIRC_MODE2: return lirc_prog_detach(attr); case BPF_FLOW_DISSECTOR: @@ -2247,7 +2248,8 @@ static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog, return NULL; } -static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) +static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog, + const struct cred *f_cred) { const struct bpf_map *map; struct bpf_insn *insns; @@ -2270,7 +2272,7 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) insns[i].code == (BPF_JMP | BPF_CALL_ARGS)) { if (insns[i].code == (BPF_JMP | BPF_CALL_ARGS)) insns[i].code = BPF_JMP | BPF_CALL; - if (!bpf_dump_raw_ok()) + if (!bpf_dump_raw_ok(f_cred)) insns[i].imm = 0; continue; } @@ -2322,7 +2324,8 @@ static int set_info_rec_size(struct bpf_prog_info *info) return 0; } -static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, +static int bpf_prog_get_info_by_fd(struct file *file, + struct bpf_prog *prog, const union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -2391,11 +2394,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, struct bpf_insn *insns_sanitized; bool fault; - if (prog->blinded && !bpf_dump_raw_ok()) { + if (prog->blinded && !bpf_dump_raw_ok(file->f_cred)) { info.xlated_prog_insns = 0; goto done; } - insns_sanitized = bpf_insn_prepare_dump(prog); + insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred); if (!insns_sanitized) return -ENOMEM; uinsns = u64_to_user_ptr(info.xlated_prog_insns); @@ -2429,7 +2432,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } if (info.jited_prog_len && ulen) { - if (bpf_dump_raw_ok()) { + if (bpf_dump_raw_ok(file->f_cred)) { uinsns = u64_to_user_ptr(info.jited_prog_insns); ulen = min_t(u32, info.jited_prog_len, ulen); @@ -2464,7 +2467,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, ulen = info.nr_jited_ksyms; info.nr_jited_ksyms = prog->aux->func_cnt ? : 1; if (ulen) { - if (bpf_dump_raw_ok()) { + if (bpf_dump_raw_ok(file->f_cred)) { unsigned long ksym_addr; u64 __user *user_ksyms; u32 i; @@ -2495,7 +2498,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, ulen = info.nr_jited_func_lens; info.nr_jited_func_lens = prog->aux->func_cnt ? : 1; if (ulen) { - if (bpf_dump_raw_ok()) { + if (bpf_dump_raw_ok(file->f_cred)) { u32 __user *user_lens; u32 func_len, i; @@ -2552,7 +2555,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, else info.nr_jited_line_info = 0; if (info.nr_jited_line_info && ulen) { - if (bpf_dump_raw_ok()) { + if (bpf_dump_raw_ok(file->f_cred)) { __u64 __user *user_linfo; u32 i; @@ -2598,7 +2601,8 @@ done: return 0; } -static int bpf_map_get_info_by_fd(struct bpf_map *map, +static int bpf_map_get_info_by_fd(struct file *file, + struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -2640,7 +2644,8 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, return 0; } -static int bpf_btf_get_info_by_fd(struct btf *btf, +static int bpf_btf_get_info_by_fd(struct file *file, + struct btf *btf, const union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -2672,13 +2677,13 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return -EBADFD; if (f.file->f_op == &bpf_prog_fops) - err = bpf_prog_get_info_by_fd(f.file->private_data, attr, + err = bpf_prog_get_info_by_fd(f.file, f.file->private_data, attr, uattr); else if (f.file->f_op == &bpf_map_fops) - err = bpf_map_get_info_by_fd(f.file->private_data, attr, + err = bpf_map_get_info_by_fd(f.file, f.file->private_data, attr, uattr); else if (f.file->f_op == &btf_fops) - err = bpf_btf_get_info_by_fd(f.file->private_data, attr, uattr); + err = bpf_btf_get_info_by_fd(f.file, f.file->private_data, attr, uattr); else err = -EINVAL; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 7c9e97553a00..35faf082a709 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6379,18 +6379,8 @@ void cgroup_sk_alloc_disable(void) void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { - if (cgroup_sk_alloc_disabled) - return; - - /* Socket clone path */ - if (skcd->val) { - /* - * We might be cloning a socket which is left in an empty - * cgroup and the cgroup might have already been rmdir'd. - * Don't use cgroup_get_live(). - */ - cgroup_get(sock_cgroup_ptr(skcd)); - cgroup_bpf_get(sock_cgroup_ptr(skcd)); + if (cgroup_sk_alloc_disabled) { + skcd->no_refcnt = 1; return; } @@ -6415,10 +6405,27 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd) rcu_read_unlock(); } +void cgroup_sk_clone(struct sock_cgroup_data *skcd) +{ + if (skcd->val) { + if (skcd->no_refcnt) + return; + /* + * We might be cloning a socket which is left in an empty + * cgroup and the cgroup might have already been rmdir'd. + * Don't use cgroup_get_live(). + */ + cgroup_get(sock_cgroup_ptr(skcd)); + cgroup_bpf_get(sock_cgroup_ptr(skcd)); + } +} + void cgroup_sk_free(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); + if (skcd->no_refcnt) + return; cgroup_bpf_put(cgrp); cgroup_put(cgrp); } diff --git a/kernel/cpu.c b/kernel/cpu.c index d7890c1285bf..7527825ac7da 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -3,6 +3,7 @@ * * This code is licenced under the GPL. */ +#include <linux/sched/mm.h> #include <linux/proc_fs.h> #include <linux/smp.h> #include <linux/init.h> @@ -564,6 +565,21 @@ static int bringup_cpu(unsigned int cpu) return bringup_wait_for_ap(cpu); } +static int finish_cpu(unsigned int cpu) +{ + struct task_struct *idle = idle_thread_get(cpu); + struct mm_struct *mm = idle->active_mm; + + /* + * idle_task_exit() will have switched to &init_mm, now + * clean up any remaining active_mm state. + */ + if (mm != &init_mm) + idle->active_mm = &init_mm; + mmdrop(mm); + return 0; +} + /* * Hotplug state machine related functions */ @@ -1434,7 +1450,7 @@ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = bringup_cpu, - .teardown.single = NULL, + .teardown.single = finish_cpu, .cant_stop = true, }, /* Final state before CPU kills itself */ diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c index cbca6879ab7d..44a259338e33 100644 --- a/kernel/cpu_pm.c +++ b/kernel/cpu_pm.c @@ -80,7 +80,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier); */ int cpu_pm_enter(void) { - int nr_calls; + int nr_calls = 0; int ret = 0; ret = cpu_pm_notify(CPU_PM_ENTER, -1, &nr_calls); @@ -131,7 +131,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_exit); */ int cpu_cluster_pm_enter(void) { - int nr_calls; + int nr_calls = 0; int ret = 0; ret = cpu_pm_notify(CPU_CLUSTER_PM_ENTER, -1, &nr_calls); diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index f76d6f77dd5e..2222f3225e53 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -501,6 +501,7 @@ static int kgdb_reenter_check(struct kgdb_state *ks) if (exception_level > 1) { dump_stack(); + kgdb_io_module_registered = false; panic("Recursive entry to debugger"); } @@ -545,6 +546,7 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs, arch_kgdb_ops.disable_hw_break(regs); acquirelock: + rcu_read_lock(); /* * Interrupts will be restored by the 'trap return' code, except when * single stepping. @@ -601,6 +603,7 @@ return_normal: atomic_dec(&slaves_in_kgdb); dbg_touch_watchdogs(); local_irq_restore(flags); + rcu_read_unlock(); return 0; } cpu_relax(); @@ -619,6 +622,7 @@ return_normal: raw_spin_unlock(&dbg_master_lock); dbg_touch_watchdogs(); local_irq_restore(flags); + rcu_read_unlock(); goto acquirelock; } @@ -634,6 +638,8 @@ return_normal: if (kgdb_skipexception(ks->ex_vector, ks->linux_regs)) goto kgdb_restore; + atomic_inc(&ignore_console_lock_warning); + /* Call the I/O driver's pre_exception routine */ if (dbg_io_ops->pre_exception) dbg_io_ops->pre_exception(); @@ -706,6 +712,8 @@ cpu_master_loop: if (dbg_io_ops->post_exception) dbg_io_ops->post_exception(); + atomic_dec(&ignore_console_lock_warning); + if (!kgdb_single_step) { raw_spin_unlock(&dbg_slave_lock); /* Wait till all the CPUs have quit from the debugger. */ @@ -738,6 +746,7 @@ kgdb_restore: raw_spin_unlock(&dbg_master_lock); dbg_touch_watchdogs(); local_irq_restore(flags); + rcu_read_unlock(); return kgdb_info[cpu].ret_state; } diff --git a/kernel/events/core.c b/kernel/events/core.c index aaaf50b25cc9..47646050efa0 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1253,7 +1253,7 @@ static void put_ctx(struct perf_event_context *ctx) * function. * * Lock order: - * cred_guard_mutex + * exec_update_mutex * task_struct::perf_event_mutex * perf_event_context::mutex * perf_event::child_mutex; @@ -2171,6 +2171,7 @@ __perf_remove_from_context(struct perf_event *event, if (!ctx->nr_events && ctx->is_active) { ctx->is_active = 0; + ctx->rotate_necessary = 0; if (ctx->task) { WARN_ON_ONCE(cpuctx->task_ctx != ctx); cpuctx->task_ctx = NULL; @@ -3047,12 +3048,6 @@ static void ctx_sched_out(struct perf_event_context *ctx, if (!ctx->nr_active || !(is_active & EVENT_ALL)) return; - /* - * If we had been multiplexing, no rotations are necessary, now no events - * are active. - */ - ctx->rotate_necessary = 0; - perf_pmu_disable(ctx->pmu); if (is_active & EVENT_PINNED) { list_for_each_entry_safe(event, tmp, &ctx->pinned_active, active_list) @@ -3062,6 +3057,13 @@ static void ctx_sched_out(struct perf_event_context *ctx, if (is_active & EVENT_FLEXIBLE) { list_for_each_entry_safe(event, tmp, &ctx->flexible_active, active_list) group_sched_out(event, cpuctx, ctx); + + /* + * Since we cleared EVENT_FLEXIBLE, also clear + * rotate_necessary, is will be reset by + * ctx_flexible_sched_in() when needed. + */ + ctx->rotate_necessary = 0; } perf_pmu_enable(ctx->pmu); } @@ -3800,6 +3802,12 @@ ctx_event_to_rotate(struct perf_event_context *ctx) typeof(*event), group_node); } + /* + * Unconditionally clear rotate_necessary; if ctx_flexible_sched_in() + * finds there are unschedulable events, it will set it again. + */ + ctx->rotate_necessary = 0; + return event; } @@ -10994,14 +11002,14 @@ SYSCALL_DEFINE5(perf_event_open, } if (task) { - err = mutex_lock_interruptible(&task->signal->cred_guard_mutex); + err = mutex_lock_interruptible(&task->signal->exec_update_mutex); if (err) goto err_task; /* * Reuse ptrace permission checks for now. * - * We must hold cred_guard_mutex across this and any potential + * We must hold exec_update_mutex across this and any potential * perf_install_in_context() call for this new event to * serialize against exec() altering our credentials (and the * perf_event_exit_task() that could imply). @@ -11290,7 +11298,7 @@ SYSCALL_DEFINE5(perf_event_open, mutex_unlock(&ctx->mutex); if (task) { - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); put_task_struct(task); } @@ -11326,7 +11334,7 @@ err_alloc: free_event(event); err_cred: if (task) - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); err_task: if (task) put_task_struct(task); @@ -11631,7 +11639,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) /* * When a child task exits, feed back event values to parent events. * - * Can be called with cred_guard_mutex held when called from + * Can be called with exec_update_mutex held when called from * install_exec_creds(). */ void perf_event_exit_task(struct task_struct *child) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 291680ba8504..a793bd23fe56 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -211,7 +211,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, try_to_free_swap(old_page); page_vma_mapped_walk_done(&pvmw); - if (vma->vm_flags & VM_LOCKED) + if ((vma->vm_flags & VM_LOCKED) && !PageCompound(old_page)) munlock_vma_page(old_page); put_page(old_page); @@ -2205,7 +2205,7 @@ static void handle_swbp(struct pt_regs *regs) if (!uprobe) { if (is_swbp > 0) { /* No matching uprobe; signal SIGTRAP. */ - send_sig(SIGTRAP, current, 0); + force_sig(SIGTRAP); } else { /* * Either we raced with uprobe_unregister() or we can't diff --git a/kernel/exit.c b/kernel/exit.c index 22dfaac9e48c..fa46977b9c07 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -713,8 +713,12 @@ void __noreturn do_exit(long code) struct task_struct *tsk = current; int group_dead; - profile_task_exit(tsk); - kcov_task_exit(tsk); + /* + * We can get here from a kernel oops, sometimes with preemption off. + * Start by checking for critical errors. + * Then fix up important state like USER_DS and preemption. + * Then do everything else. + */ WARN_ON(blk_needs_flush_plug(tsk)); @@ -732,6 +736,16 @@ void __noreturn do_exit(long code) */ set_fs(USER_DS); + if (unlikely(in_atomic())) { + pr_info("note: %s[%d] exited with preempt_count %d\n", + current->comm, task_pid_nr(current), + preempt_count()); + preempt_count_set(PREEMPT_ENABLED); + } + + profile_task_exit(tsk); + kcov_task_exit(tsk); + ptrace_event(PTRACE_EVENT_EXIT, code); validate_creds_for_do_exit(tsk); @@ -749,13 +763,6 @@ void __noreturn do_exit(long code) exit_signals(tsk); /* sets PF_EXITING */ - if (unlikely(in_atomic())) { - pr_info("note: %s[%d] exited with preempt_count %d\n", - current->comm, task_pid_nr(current), - preempt_count()); - preempt_count_set(PREEMPT_ENABLED); - } - /* sync mm's RSS info before statistics gathering */ if (tsk->mm) sync_mm_rss(tsk->mm); diff --git a/kernel/fork.c b/kernel/fork.c index 9180f4416dba..594272569a80 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1221,7 +1221,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) struct mm_struct *mm; int err; - err = mutex_lock_killable(&task->signal->cred_guard_mutex); + err = mutex_lock_killable(&task->signal->exec_update_mutex); if (err) return ERR_PTR(err); @@ -1231,7 +1231,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) mmput(mm); mm = ERR_PTR(-EACCES); } - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); return mm; } @@ -1586,6 +1586,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); + mutex_init(&sig->exec_update_mutex); return 0; } diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index ec37563674d6..60c7be5ff5c8 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -19,7 +19,9 @@ #include <linux/vmalloc.h> #include "gcov.h" -#if (__GNUC__ >= 7) +#if (__GNUC__ >= 10) +#define GCOV_COUNTERS 8 +#elif (__GNUC__ >= 7) #define GCOV_COUNTERS 9 #elif (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1) #define GCOV_COUNTERS 10 diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 5a0fc0b0403a..c1510f0ab3ea 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -1,4 +1,4 @@ -#!/bin/bash +#!/bin/sh # SPDX-License-Identifier: GPL-2.0 # This script generates an archive consisting of kernel headers @@ -21,30 +21,38 @@ arch/$SRCARCH/include/ # Uncomment it for debugging. # if [ ! -f /tmp/iter ]; then iter=1; echo 1 > /tmp/iter; # else iter=$(($(cat /tmp/iter) + 1)); echo $iter > /tmp/iter; fi -# find $src_file_list -name "*.h" | xargs ls -l > /tmp/src-ls-$iter -# find $obj_file_list -name "*.h" | xargs ls -l > /tmp/obj-ls-$iter +# find $all_dirs -name "*.h" | xargs ls -l > /tmp/ls-$iter + +all_dirs= +if [ "$building_out_of_srctree" ]; then + for d in $dir_list; do + all_dirs="$all_dirs $srctree/$d" + done +fi +all_dirs="$all_dirs $dir_list" # include/generated/compile.h is ignored because it is touched even when none -# of the source files changed. This causes pointless regeneration, so let us -# ignore them for md5 calculation. -pushd $srctree > /dev/null -src_files_md5="$(find $dir_list -name "*.h" | - grep -v "include/generated/compile.h" | - grep -v "include/generated/autoconf.h" | - xargs ls -l | md5sum | cut -d ' ' -f1)" -popd > /dev/null -obj_files_md5="$(find $dir_list -name "*.h" | - grep -v "include/generated/compile.h" | - grep -v "include/generated/autoconf.h" | +# of the source files changed. +# +# When Kconfig regenerates include/generated/autoconf.h, its timestamp is +# updated, but the contents might be still the same. When any CONFIG option is +# changed, Kconfig touches the corresponding timestamp file include/config/*.h. +# Hence, the md5sum detects the configuration change anyway. We do not need to +# check include/generated/autoconf.h explicitly. +# +# Ignore them for md5 calculation to avoid pointless regeneration. +headers_md5="$(find $all_dirs -name "*.h" | + grep -v "include/generated/compile.h" | + grep -v "include/generated/autoconf.h" | xargs ls -l | md5sum | cut -d ' ' -f1)" + # Any changes to this script will also cause a rebuild of the archive. this_file_md5="$(ls -l $sfile | md5sum | cut -d ' ' -f1)" if [ -f $tarfile ]; then tarfile_md5="$(md5sum $tarfile | cut -d ' ' -f1)"; fi if [ -f kernel/kheaders.md5 ] && - [ "$(cat kernel/kheaders.md5|head -1)" == "$src_files_md5" ] && - [ "$(cat kernel/kheaders.md5|head -2|tail -1)" == "$obj_files_md5" ] && - [ "$(cat kernel/kheaders.md5|head -3|tail -1)" == "$this_file_md5" ] && - [ "$(cat kernel/kheaders.md5|tail -1)" == "$tarfile_md5" ]; then + [ "$(head -n 1 kernel/kheaders.md5)" = "$headers_md5" ] && + [ "$(head -n 2 kernel/kheaders.md5 | tail -n 1)" = "$this_file_md5" ] && + [ "$(tail -n 1 kernel/kheaders.md5)" = "$tarfile_md5" ]; then exit fi @@ -55,14 +63,17 @@ fi rm -rf $cpio_dir mkdir $cpio_dir -pushd $srctree > /dev/null -for f in $dir_list; - do find "$f" -name "*.h"; -done | cpio --quiet -pd $cpio_dir -popd > /dev/null +if [ "$building_out_of_srctree" ]; then + ( + cd $srctree + for f in $dir_list + do find "$f" -name "*.h"; + done | cpio --quiet -pd $cpio_dir + ) +fi -# The second CPIO can complain if files already exist which can -# happen with out of tree builds. Just silence CPIO for now. +# The second CPIO can complain if files already exist which can happen with out +# of tree builds having stale headers in srctree. Just silence CPIO for now. for f in $dir_list; do find "$f" -name "*.h"; done | cpio --quiet -pd $cpio_dir >/dev/null 2>&1 @@ -77,10 +88,9 @@ find $cpio_dir -type f -print0 | find $cpio_dir -printf "./%P\n" | LC_ALL=C sort | \ tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \ --owner=0 --group=0 --numeric-owner --no-recursion \ - -Jcf $tarfile -C $cpio_dir/ -T - > /dev/null + -I $XZ -cf $tarfile -C $cpio_dir/ -T - > /dev/null -echo "$src_files_md5" > kernel/kheaders.md5 -echo "$obj_files_md5" >> kernel/kheaders.md5 +echo $headers_md5 > kernel/kheaders.md5 echo "$this_file_md5" >> kernel/kheaders.md5 echo "$(md5sum $tarfile | cut -d ' ' -f1)" >> kernel/kheaders.md5 diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index b304c17d53a3..3b1d0a4725a4 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -194,9 +194,9 @@ void irq_set_thread_affinity(struct irq_desc *desc) set_bit(IRQTF_AFFINITY, &action->thread_flags); } +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK static void irq_validate_effective_affinity(struct irq_data *data) { -#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK const struct cpumask *m = irq_data_get_effective_affinity_mask(data); struct irq_chip *chip = irq_data_get_irq_chip(data); @@ -204,9 +204,19 @@ static void irq_validate_effective_affinity(struct irq_data *data) return; pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n", chip->name, data->irq); -#endif } +static inline void irq_init_effective_affinity(struct irq_data *data, + const struct cpumask *mask) +{ + cpumask_copy(irq_data_get_effective_affinity_mask(data), mask); +} +#else +static inline void irq_validate_effective_affinity(struct irq_data *data) { } +static inline void irq_init_effective_affinity(struct irq_data *data, + const struct cpumask *mask) { } +#endif + int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -265,6 +275,30 @@ static int irq_try_set_affinity(struct irq_data *data, return ret; } +static bool irq_set_affinity_deactivated(struct irq_data *data, + const struct cpumask *mask, bool force) +{ + struct irq_desc *desc = irq_data_to_desc(data); + + /* + * Handle irq chips which can handle affinity only in activated + * state correctly + * + * If the interrupt is not yet activated, just store the affinity + * mask and do not call the chip driver at all. On activation the + * driver has to make sure anyway that the interrupt is in a + * useable state so startup works. + */ + if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) || + irqd_is_activated(data) || !irqd_affinity_on_activate(data)) + return false; + + cpumask_copy(desc->irq_common_data.affinity, mask); + irq_init_effective_affinity(data, mask); + irqd_set(data, IRQD_AFFINITY_SET); + return true; +} + int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -275,6 +309,9 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, if (!chip || !chip->irq_set_affinity) return -EINVAL; + if (irq_set_affinity_deactivated(data, mask, force)) + return 0; + if (irq_can_move_pcntxt(data) && !irqd_is_setaffinity_pending(data)) { ret = irq_try_set_affinity(data, mask, force); } else { diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index 30cc217b8631..651a4ad6d711 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -380,6 +380,13 @@ int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk, unsigned int cpu, bit; struct cpumap *cm; + /* + * Not required in theory, but matrix_find_best_cpu() uses + * for_each_cpu() which ignores the cpumask on UP . + */ + if (cpumask_empty(msk)) + return -EINVAL; + cpu = matrix_find_best_cpu(m, msk); if (cpu == UINT_MAX) return -ENOSPC; diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c index 8f557fa1f4fe..c6c7e187ae74 100644 --- a/kernel/irq/pm.c +++ b/kernel/irq/pm.c @@ -185,14 +185,18 @@ void rearm_wake_irq(unsigned int irq) unsigned long flags; struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); - if (!desc || !(desc->istate & IRQS_SUSPENDED) || - !irqd_is_wakeup_set(&desc->irq_data)) + if (!desc) return; + if (!(desc->istate & IRQS_SUSPENDED) || + !irqd_is_wakeup_set(&desc->irq_data)) + goto unlock; + desc->istate &= ~IRQS_SUSPENDED; irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED); __enable_irq(desc); +unlock: irq_put_desc_busunlock(desc, flags); } diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 136ce049c4ad..61f9d781f70a 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -645,19 +645,20 @@ static inline int kallsyms_for_perf(void) * Otherwise, require CAP_SYSLOG (assuming kptr_restrict isn't set to * block even that). */ -int kallsyms_show_value(void) +bool kallsyms_show_value(const struct cred *cred) { switch (kptr_restrict) { case 0: if (kallsyms_for_perf()) - return 1; + return true; /* fallthrough */ case 1: - if (has_capability_noaudit(current, CAP_SYSLOG)) - return 1; + if (security_capable(cred, &init_user_ns, CAP_SYSLOG, + CAP_OPT_NOAUDIT) == 0) + return true; /* fallthrough */ default: - return 0; + return false; } } @@ -674,7 +675,11 @@ static int kallsyms_open(struct inode *inode, struct file *file) return -ENOMEM; reset_iter(iter, 0); - iter->show_value = kallsyms_show_value(); + /* + * Instead of checking this on every s_show() call, cache + * the result here at open time. + */ + iter->show_value = kallsyms_show_value(file->f_cred); return 0; } diff --git a/kernel/kcmp.c b/kernel/kcmp.c index a0e3d7a0e8b8..b3ff9288c6cc 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -173,8 +173,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, /* * One should have enough rights to inspect task details. */ - ret = kcmp_lock(&task1->signal->cred_guard_mutex, - &task2->signal->cred_guard_mutex); + ret = kcmp_lock(&task1->signal->exec_update_mutex, + &task2->signal->exec_update_mutex); if (ret) goto err; if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) || @@ -229,8 +229,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, } err_unlock: - kcmp_unlock(&task1->signal->cred_guard_mutex, - &task2->signal->cred_guard_mutex); + kcmp_unlock(&task1->signal->exec_update_mutex, + &task2->signal->exec_update_mutex); err: put_task_struct(task1); put_task_struct(task2); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 2625c241ac00..283c8b01ce78 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -326,7 +326,8 @@ struct kprobe *get_kprobe(void *addr) struct kprobe *p; head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)]; - hlist_for_each_entry_rcu(p, head, hlist) { + hlist_for_each_entry_rcu(p, head, hlist, + lockdep_is_held(&kprobe_mutex)) { if (p->addr == addr) return p; } @@ -586,11 +587,12 @@ static void kprobe_optimizer(struct work_struct *work) mutex_unlock(&module_mutex); mutex_unlock(&text_mutex); cpus_read_unlock(); - mutex_unlock(&kprobe_mutex); /* Step 5: Kick optimizer again if needed */ if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) kick_kprobe_optimizer(); + + mutex_unlock(&kprobe_mutex); } /* Wait for completing optimization and unoptimization */ @@ -1074,9 +1076,20 @@ static int disarm_kprobe_ftrace(struct kprobe *p) ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled); } #else /* !CONFIG_KPROBES_ON_FTRACE */ -#define prepare_kprobe(p) arch_prepare_kprobe(p) -#define arm_kprobe_ftrace(p) (-ENODEV) -#define disarm_kprobe_ftrace(p) (-ENODEV) +static inline int prepare_kprobe(struct kprobe *p) +{ + return arch_prepare_kprobe(p); +} + +static inline int arm_kprobe_ftrace(struct kprobe *p) +{ + return -ENODEV; +} + +static inline int disarm_kprobe_ftrace(struct kprobe *p) +{ + return -ENODEV; +} #endif /* Arm a kprobe with text_mutex */ @@ -1236,6 +1249,26 @@ __releases(hlist_lock) } NOKPROBE_SYMBOL(kretprobe_table_unlock); +struct kprobe kprobe_busy = { + .addr = (void *) get_kprobe, +}; + +void kprobe_busy_begin(void) +{ + struct kprobe_ctlblk *kcb; + + preempt_disable(); + __this_cpu_write(current_kprobe, &kprobe_busy); + kcb = get_kprobe_ctlblk(); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; +} + +void kprobe_busy_end(void) +{ + __this_cpu_write(current_kprobe, NULL); + preempt_enable(); +} + /* * This function is called from finish_task_switch when task tk becomes dead, * so that we can recycle any function-return probe instances associated @@ -1253,6 +1286,8 @@ void kprobe_flush_task(struct task_struct *tk) /* Early boot. kretprobe_table_locks not yet initialized. */ return; + kprobe_busy_begin(); + INIT_HLIST_HEAD(&empty_rp); hash = hash_ptr(tk, KPROBE_HASH_BITS); head = &kretprobe_inst_table[hash]; @@ -1266,6 +1301,8 @@ void kprobe_flush_task(struct task_struct *tk) hlist_del(&ri->hlist); kfree(ri); } + + kprobe_busy_end(); } NOKPROBE_SYMBOL(kprobe_flush_task); @@ -2062,6 +2099,9 @@ static void kill_kprobe(struct kprobe *p) { struct kprobe *kp; + if (WARN_ON_ONCE(kprobe_gone(p))) + return; + p->flags |= KPROBE_FLAG_GONE; if (kprobe_aggrprobe(p)) { /* @@ -2078,6 +2118,14 @@ static void kill_kprobe(struct kprobe *p) * the original probed function (which will be freed soon) any more. */ arch_remove_kprobe(p); + + /* + * The module is going away. We should disarm the kprobe which + * is using ftrace, because ftrace framework is still available at + * MODULE_STATE_GOING notification. + */ + if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed) + disarm_kprobe_ftrace(p); } /* Disable one kprobe */ @@ -2237,7 +2285,10 @@ static int kprobes_module_callback(struct notifier_block *nb, mutex_lock(&kprobe_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry_rcu(p, head, hlist) + hlist_for_each_entry_rcu(p, head, hlist) { + if (kprobe_gone(p)) + continue; + if (within_module_init((unsigned long)p->addr, mod) || (checkcore && within_module_core((unsigned long)p->addr, mod))) { @@ -2254,6 +2305,7 @@ static int kprobes_module_callback(struct notifier_block *nb, */ kill_kprobe(p); } + } } mutex_unlock(&kprobe_mutex); return NOTIFY_DONE; @@ -2268,6 +2320,28 @@ static struct notifier_block kprobe_module_nb = { extern unsigned long __start_kprobe_blacklist[]; extern unsigned long __stop_kprobe_blacklist[]; +void kprobe_free_init_mem(void) +{ + void *start = (void *)(&__init_begin); + void *end = (void *)(&__init_end); + struct hlist_head *head; + struct kprobe *p; + int i; + + mutex_lock(&kprobe_mutex); + + /* Kill all kprobes on initmem */ + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry(p, head, hlist) { + if (start <= (void *)p->addr && (void *)p->addr < end) + kill_kprobe(p); + } + } + + mutex_unlock(&kprobe_mutex); +} + static int __init init_kprobes(void) { int i, err = 0; @@ -2336,7 +2410,7 @@ static void report_probe(struct seq_file *pi, struct kprobe *p, else kprobe_type = "k"; - if (!kallsyms_show_value()) + if (!kallsyms_show_value(pi->file->f_cred)) addr = NULL; if (sym) @@ -2437,7 +2511,7 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v) * If /proc/kallsyms is not showing kernel address, we won't * show them here either. */ - if (!kallsyms_show_value()) + if (!kallsyms_show_value(m->file->f_cred)) seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL, (void *)ent->start_addr); else diff --git a/kernel/kthread.c b/kernel/kthread.c index b262f47046ca..bfbfa481be3a 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -199,8 +199,15 @@ static void __kthread_parkme(struct kthread *self) if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags)) break; + /* + * Thread is going to call schedule(), do not preempt it, + * or the caller of kthread_park() may spend more time in + * wait_task_inactive(). + */ + preempt_disable(); complete(&self->parked); - schedule(); + schedule_preempt_disabled(); + preempt_enable(); } __set_current_state(TASK_RUNNING); } @@ -245,8 +252,14 @@ static int kthread(void *_create) /* OK, tell user we're spawned, wait for stop or wakeup */ __set_current_state(TASK_UNINTERRUPTIBLE); create->result = current; + /* + * Thread is going to call schedule(), do not preempt it, + * or the creator may spend more time in wait_task_inactive(). + */ + preempt_disable(); complete(done); - schedule(); + schedule_preempt_disabled(); + preempt_enable(); ret = -EINTR; if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) { diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 9ab1a965c3b9..bca0f7f71cde 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2302,18 +2302,6 @@ static int check_irq_usage(struct task_struct *curr, struct held_lock *prev, return 0; } -static void inc_chains(void) -{ - if (current->hardirq_context) - nr_hardirq_chains++; - else { - if (current->softirq_context) - nr_softirq_chains++; - else - nr_process_chains++; - } -} - #else static inline int check_irq_usage(struct task_struct *curr, @@ -2321,13 +2309,27 @@ static inline int check_irq_usage(struct task_struct *curr, { return 1; } +#endif /* CONFIG_TRACE_IRQFLAGS */ -static inline void inc_chains(void) +static void inc_chains(int irq_context) { - nr_process_chains++; + if (irq_context & LOCK_CHAIN_HARDIRQ_CONTEXT) + nr_hardirq_chains++; + else if (irq_context & LOCK_CHAIN_SOFTIRQ_CONTEXT) + nr_softirq_chains++; + else + nr_process_chains++; } -#endif /* CONFIG_TRACE_IRQFLAGS */ +static void dec_chains(int irq_context) +{ + if (irq_context & LOCK_CHAIN_HARDIRQ_CONTEXT) + nr_hardirq_chains--; + else if (irq_context & LOCK_CHAIN_SOFTIRQ_CONTEXT) + nr_softirq_chains--; + else + nr_process_chains--; +} static void print_deadlock_scenario(struct held_lock *nxt, struct held_lock *prv) @@ -2847,7 +2849,7 @@ static inline int add_chain_cache(struct task_struct *curr, hlist_add_head_rcu(&chain->entry, hash_head); debug_atomic_inc(chain_lookup_misses); - inc_chains(); + inc_chains(chain->irq_context); return 1; } @@ -3600,7 +3602,8 @@ lock_used: static inline unsigned int task_irq_context(struct task_struct *task) { - return 2 * !!task->hardirq_context + !!task->softirq_context; + return LOCK_CHAIN_HARDIRQ_CONTEXT * !!task->hardirq_context + + LOCK_CHAIN_SOFTIRQ_CONTEXT * !!task->softirq_context; } static int separate_irq_context(struct task_struct *curr, @@ -4805,6 +4808,8 @@ recalc: return; /* Overwrite the chain key for concurrent RCU readers. */ WRITE_ONCE(chain->chain_key, chain_key); + dec_chains(chain->irq_context); + /* * Note: calling hlist_del_rcu() from inside a * hlist_for_each_entry_rcu() loop is safe. @@ -4826,6 +4831,7 @@ recalc: } *new_chain = *chain; hlist_add_head_rcu(&new_chain->entry, chainhashentry(chain_key)); + inc_chains(new_chain->irq_context); #endif } diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index 18d85aebbb57..a525368b8cf6 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -106,6 +106,12 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ = #define STACK_TRACE_HASH_SIZE 16384 #endif +/* + * Bit definitions for lock_chain.irq_context + */ +#define LOCK_CHAIN_SOFTIRQ_CONTEXT (1 << 0) +#define LOCK_CHAIN_HARDIRQ_CONTEXT (1 << 1) + #define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) #define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index 9bb6d2497b04..581f81818138 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -400,7 +400,7 @@ static void seq_lock_time(struct seq_file *m, struct lock_time *lt) seq_time(m, lt->min); seq_time(m, lt->max); seq_time(m, lt->total); - seq_time(m, lt->nr ? div_s64(lt->total, lt->nr) : 0); + seq_time(m, lt->nr ? div64_u64(lt->total, lt->nr) : 0); } static void seq_stats(struct seq_file *m, struct lock_stat_data *data) diff --git a/kernel/module.c b/kernel/module.c index a2a47f4a33a7..819c5d3b4c29 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1507,8 +1507,7 @@ static inline bool sect_empty(const Elf_Shdr *sect) } struct module_sect_attr { - struct module_attribute mattr; - char *name; + struct bin_attribute battr; unsigned long address; }; @@ -1518,13 +1517,34 @@ struct module_sect_attrs { struct module_sect_attr attrs[0]; }; -static ssize_t module_sect_show(struct module_attribute *mattr, - struct module_kobject *mk, char *buf) +#define MODULE_SECT_READ_SIZE (3 /* "0x", "\n" */ + (BITS_PER_LONG / 4)) +static ssize_t module_sect_read(struct file *file, struct kobject *kobj, + struct bin_attribute *battr, + char *buf, loff_t pos, size_t count) { struct module_sect_attr *sattr = - container_of(mattr, struct module_sect_attr, mattr); - return sprintf(buf, "0x%px\n", kptr_restrict < 2 ? - (void *)sattr->address : NULL); + container_of(battr, struct module_sect_attr, battr); + char bounce[MODULE_SECT_READ_SIZE + 1]; + size_t wrote; + + if (pos != 0) + return -EINVAL; + + /* + * Since we're a binary read handler, we must account for the + * trailing NUL byte that sprintf will write: if "buf" is + * too small to hold the NUL, or the NUL is exactly the last + * byte, the read will look like it got truncated by one byte. + * Since there is no way to ask sprintf nicely to not write + * the NUL, we have to use a bounce buffer. + */ + wrote = scnprintf(bounce, sizeof(bounce), "0x%px\n", + kallsyms_show_value(file->f_cred) + ? (void *)sattr->address : NULL); + count = min(count, wrote); + memcpy(buf, bounce, count); + + return count; } static void free_sect_attrs(struct module_sect_attrs *sect_attrs) @@ -1532,7 +1552,7 @@ static void free_sect_attrs(struct module_sect_attrs *sect_attrs) unsigned int section; for (section = 0; section < sect_attrs->nsections; section++) - kfree(sect_attrs->attrs[section].name); + kfree(sect_attrs->attrs[section].battr.attr.name); kfree(sect_attrs); } @@ -1541,42 +1561,41 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info) unsigned int nloaded = 0, i, size[2]; struct module_sect_attrs *sect_attrs; struct module_sect_attr *sattr; - struct attribute **gattr; + struct bin_attribute **gattr; /* Count loaded sections and allocate structures */ for (i = 0; i < info->hdr->e_shnum; i++) if (!sect_empty(&info->sechdrs[i])) nloaded++; size[0] = ALIGN(struct_size(sect_attrs, attrs, nloaded), - sizeof(sect_attrs->grp.attrs[0])); - size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.attrs[0]); + sizeof(sect_attrs->grp.bin_attrs[0])); + size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.bin_attrs[0]); sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL); if (sect_attrs == NULL) return; /* Setup section attributes. */ sect_attrs->grp.name = "sections"; - sect_attrs->grp.attrs = (void *)sect_attrs + size[0]; + sect_attrs->grp.bin_attrs = (void *)sect_attrs + size[0]; sect_attrs->nsections = 0; sattr = §_attrs->attrs[0]; - gattr = §_attrs->grp.attrs[0]; + gattr = §_attrs->grp.bin_attrs[0]; for (i = 0; i < info->hdr->e_shnum; i++) { Elf_Shdr *sec = &info->sechdrs[i]; if (sect_empty(sec)) continue; + sysfs_bin_attr_init(&sattr->battr); sattr->address = sec->sh_addr; - sattr->name = kstrdup(info->secstrings + sec->sh_name, - GFP_KERNEL); - if (sattr->name == NULL) + sattr->battr.attr.name = + kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL); + if (sattr->battr.attr.name == NULL) goto out; sect_attrs->nsections++; - sysfs_attr_init(&sattr->mattr.attr); - sattr->mattr.show = module_sect_show; - sattr->mattr.store = NULL; - sattr->mattr.attr.name = sattr->name; - sattr->mattr.attr.mode = S_IRUSR; - *(gattr++) = &(sattr++)->mattr.attr; + sattr->battr.read = module_sect_read; + sattr->battr.size = MODULE_SECT_READ_SIZE; + sattr->battr.attr.mode = 0400; + *(gattr++) = &(sattr++)->battr; } *gattr = NULL; @@ -1666,7 +1685,7 @@ static void add_notes_attrs(struct module *mod, const struct load_info *info) continue; if (info->sechdrs[i].sh_type == SHT_NOTE) { sysfs_bin_attr_init(nattr); - nattr->attr.name = mod->sect_attrs->attrs[loaded].name; + nattr->attr.name = mod->sect_attrs->attrs[loaded].battr.attr.name; nattr->attr.mode = S_IRUGO; nattr->size = info->sechdrs[i].sh_size; nattr->private = (void *) info->sechdrs[i].sh_addr; @@ -4391,7 +4410,7 @@ static int modules_open(struct inode *inode, struct file *file) if (!err) { struct seq_file *m = file->private_data; - m->private = kallsyms_show_value() ? NULL : (void *)8ul; + m->private = kallsyms_show_value(file->f_cred) ? NULL : (void *)8ul; } return err; diff --git a/kernel/notifier.c b/kernel/notifier.c index 157d7c29f720..f6d5ffe4e72e 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -23,7 +23,10 @@ static int notifier_chain_register(struct notifier_block **nl, struct notifier_block *n) { while ((*nl) != NULL) { - WARN_ONCE(((*nl) == n), "double register detected"); + if (unlikely((*nl) == n)) { + WARN(1, "double register detected"); + return 0; + } if (n->priority > (*nl)->priority) break; nl = &((*nl)->next); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 971197f5d8ee..5569ef6bc183 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2193,6 +2193,9 @@ static int __init console_setup(char *str) char *s, *options, *brl_options = NULL; int idx; + if (str[0] == 0) + return 1; + if (_braille_console_setup(&str, &brl_options)) return 1; diff --git a/kernel/relay.c b/kernel/relay.c index 4b760ec16342..d3940becf2fc 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -197,6 +197,7 @@ free_buf: static void relay_destroy_channel(struct kref *kref) { struct rchan *chan = container_of(kref, struct rchan, kref); + free_percpu(chan->buf); kfree(chan); } diff --git a/kernel/resource.c b/kernel/resource.c index 76036a41143b..841737bbda9e 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1126,6 +1126,7 @@ struct resource * __request_region(struct resource *parent, { DECLARE_WAITQUEUE(wait, current); struct resource *res = alloc_resource(GFP_KERNEL); + struct resource *orig_parent = parent; if (!res) return NULL; @@ -1176,6 +1177,10 @@ struct resource * __request_region(struct resource *parent, break; } write_unlock(&resource_lock); + + if (res && orig_parent == &iomem_resource) + revoke_devmem(res); + return res; } EXPORT_SYMBOL(__request_region); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e99d326fa569..79ce22de4409 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -794,6 +794,26 @@ unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE; /* All clamps are required to be less or equal than these values */ static struct uclamp_se uclamp_default[UCLAMP_CNT]; +/* + * This static key is used to reduce the uclamp overhead in the fast path. It + * primarily disables the call to uclamp_rq_{inc, dec}() in + * enqueue/dequeue_task(). + * + * This allows users to continue to enable uclamp in their kernel config with + * minimum uclamp overhead in the fast path. + * + * As soon as userspace modifies any of the uclamp knobs, the static key is + * enabled, since we have an actual users that make use of uclamp + * functionality. + * + * The knobs that would enable this static key are: + * + * * A task modifying its uclamp value with sched_setattr(). + * * An admin modifying the sysctl_sched_uclamp_{min, max} via procfs. + * * An admin modifying the cgroup cpu.uclamp.{min, max} + */ +DEFINE_STATIC_KEY_FALSE(sched_uclamp_used); + /* Integer rounded range for each bucket */ #define UCLAMP_BUCKET_DELTA DIV_ROUND_CLOSEST(SCHED_CAPACITY_SCALE, UCLAMP_BUCKETS) @@ -990,10 +1010,38 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p, lockdep_assert_held(&rq->lock); + /* + * If sched_uclamp_used was enabled after task @p was enqueued, + * we could end up with unbalanced call to uclamp_rq_dec_id(). + * + * In this case the uc_se->active flag should be false since no uclamp + * accounting was performed at enqueue time and we can just return + * here. + * + * Need to be careful of the following enqeueue/dequeue ordering + * problem too + * + * enqueue(taskA) + * // sched_uclamp_used gets enabled + * enqueue(taskB) + * dequeue(taskA) + * // Must not decrement bukcet->tasks here + * dequeue(taskB) + * + * where we could end up with stale data in uc_se and + * bucket[uc_se->bucket_id]. + * + * The following check here eliminates the possibility of such race. + */ + if (unlikely(!uc_se->active)) + return; + bucket = &uc_rq->bucket[uc_se->bucket_id]; + SCHED_WARN_ON(!bucket->tasks); if (likely(bucket->tasks)) bucket->tasks--; + uc_se->active = false; /* @@ -1021,6 +1069,15 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) { enum uclamp_id clamp_id; + /* + * Avoid any overhead until uclamp is actually used by the userspace. + * + * The condition is constructed such that a NOP is generated when + * sched_uclamp_used is disabled. + */ + if (!static_branch_unlikely(&sched_uclamp_used)) + return; + if (unlikely(!p->sched_class->uclamp_enabled)) return; @@ -1036,6 +1093,15 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) { enum uclamp_id clamp_id; + /* + * Avoid any overhead until uclamp is actually used by the userspace. + * + * The condition is constructed such that a NOP is generated when + * sched_uclamp_used is disabled. + */ + if (!static_branch_unlikely(&sched_uclamp_used)) + return; + if (unlikely(!p->sched_class->uclamp_enabled)) return; @@ -1145,8 +1211,10 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, update_root_tg = true; } - if (update_root_tg) + if (update_root_tg) { + static_branch_enable(&sched_uclamp_used); uclamp_update_root_tg(); + } /* * We update all RUNNABLE tasks only when task groups are in use. @@ -1181,6 +1249,15 @@ static int uclamp_validate(struct task_struct *p, if (upper_bound > SCHED_CAPACITY_SCALE) return -EINVAL; + /* + * We have valid uclamp attributes; make sure uclamp is enabled. + * + * We need to do that here, because enabling static branches is a + * blocking operation which obviously cannot be done while holding + * scheduler locks. + */ + static_branch_enable(&sched_uclamp_used); + return 0; } @@ -1238,6 +1315,20 @@ static void uclamp_fork(struct task_struct *p) } } +static void __init init_uclamp_rq(struct rq *rq) +{ + enum uclamp_id clamp_id; + struct uclamp_rq *uc_rq = rq->uclamp; + + for_each_clamp_id(clamp_id) { + uc_rq[clamp_id] = (struct uclamp_rq) { + .value = uclamp_none(clamp_id) + }; + } + + rq->uclamp_flags = 0; +} + static void __init init_uclamp(void) { struct uclamp_se uc_max = {}; @@ -1246,11 +1337,8 @@ static void __init init_uclamp(void) mutex_init(&uclamp_mutex); - for_each_possible_cpu(cpu) { - memset(&cpu_rq(cpu)->uclamp, 0, - sizeof(struct uclamp_rq)*UCLAMP_CNT); - cpu_rq(cpu)->uclamp_flags = 0; - } + for_each_possible_cpu(cpu) + init_uclamp_rq(cpu_rq(cpu)); for_each_clamp_id(clamp_id) { uclamp_se_set(&init_task.uclamp_req[clamp_id], @@ -1649,7 +1737,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, goto out; } - if (cpumask_equal(p->cpus_ptr, new_mask)) + if (cpumask_equal(&p->cpus_mask, new_mask)) goto out; dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask); @@ -2889,6 +2977,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) * Silence PROVE_RCU. */ raw_spin_lock_irqsave(&p->pi_lock, flags); + rseq_migrate(p); /* * We're setting the CPU for the first time, we don't migrate, * so use __set_task_cpu(). @@ -2953,6 +3042,7 @@ void wake_up_new_task(struct task_struct *p) * as we're not fully set-up yet. */ p->recent_used_cpu = task_cpu(p); + rseq_migrate(p); __set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); #endif rq = __task_rq_lock(p, &rf); @@ -4109,7 +4199,8 @@ static inline void sched_submit_work(struct task_struct *tsk) * it wants to wake up a task to maintain concurrency. * As this function is called inside the schedule() context, * we disable preemption to avoid it calling schedule() again - * in the possible wakeup of a kworker. + * in the possible wakeup of a kworker and because wq_worker_sleeping() + * requires it. */ if (tsk->flags & PF_WQ_WORKER) { preempt_disable(); @@ -4447,7 +4538,8 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) */ if (dl_prio(prio)) { if (!dl_prio(p->normal_prio) || - (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) { + (pi_task && dl_prio(pi_task->prio) && + dl_entity_preempt(&pi_task->dl, &p->dl))) { p->dl.dl_boosted = 1; queue_flag |= ENQUEUE_REPLENISH; } else @@ -6177,13 +6269,14 @@ void idle_task_exit(void) struct mm_struct *mm = current->active_mm; BUG_ON(cpu_online(smp_processor_id())); + BUG_ON(current != this_rq()->idle); if (mm != &init_mm) { switch_mm(mm, &init_mm, current); - current->active_mm = &init_mm; finish_arch_post_lock_switch(); } - mmdrop(mm); + + /* finish_cpu(), as ran on the BP, will clean up the active_mm state */ } /* @@ -7279,6 +7372,8 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf, if (req.ret) return req.ret; + static_branch_enable(&sched_uclamp_used); + mutex_lock(&uclamp_mutex); rcu_read_lock(); @@ -7373,6 +7468,8 @@ static DEFINE_MUTEX(cfs_constraints_mutex); const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */ static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */ +/* More than 203 days if BW_SHIFT equals 20. */ +static const u64 max_cfs_runtime = MAX_BW * NSEC_PER_USEC; static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime); @@ -7401,6 +7498,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) return -EINVAL; /* + * Bound quota to defend quota against overflow during bandwidth shift. + */ + if (quota != RUNTIME_INF && quota > max_cfs_runtime) + return -EINVAL; + + /* * Prevent race between setting of cfs_rq->runtime_enabled and * unthrottle_offline_cfs_rqs(). */ diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index b6f56e7c8dd1..4cb80e6042c4 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -210,7 +210,7 @@ unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs, unsigned long dl_util, util, irq; struct rq *rq = cpu_rq(cpu); - if (!IS_BUILTIN(CONFIG_UCLAMP_TASK) && + if (!uclamp_is_used() && type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) { return max; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 08bdee0480b3..4cb00538a207 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2693,6 +2693,7 @@ 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; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index f7e4579e746c..c4b702fe1d73 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -258,7 +258,7 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd) set_table_entry(&table[2], "busy_factor", &sd->busy_factor, sizeof(int), 0644, proc_dointvec_minmax); set_table_entry(&table[3], "imbalance_pct", &sd->imbalance_pct, sizeof(int), 0644, proc_dointvec_minmax); set_table_entry(&table[4], "cache_nice_tries", &sd->cache_nice_tries, sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[5], "flags", &sd->flags, sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[5], "flags", &sd->flags, sizeof(int), 0444, proc_dointvec_minmax); set_table_entry(&table[6], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax); set_table_entry(&table[7], "name", sd->name, CORENAME_MAX_SIZE, 0444, proc_dostring); /* &table[8] is terminator */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 8a0e6bdba50d..b02a83ff4068 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3824,7 +3824,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) return; } - rq->misfit_task_load = task_h_load(p); + /* + * Make sure that misfit_task_load will not be null even if + * task_h_load() returns 0. + */ + rq->misfit_task_load = max_t(unsigned long, task_h_load(p), 1); } #else /* CONFIG_SMP */ @@ -4379,16 +4383,16 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) } /* returns 0 on failure to allocate runtime */ -static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) +static int __assign_cfs_rq_runtime(struct cfs_bandwidth *cfs_b, + struct cfs_rq *cfs_rq, u64 target_runtime) { - struct task_group *tg = cfs_rq->tg; - struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); - u64 amount = 0, min_amount; + u64 min_amount, amount = 0; + + lockdep_assert_held(&cfs_b->lock); /* note: this is a positive sum as runtime_remaining <= 0 */ - min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining; + min_amount = target_runtime - cfs_rq->runtime_remaining; - raw_spin_lock(&cfs_b->lock); if (cfs_b->quota == RUNTIME_INF) amount = min_amount; else { @@ -4400,13 +4404,25 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) cfs_b->idle = 0; } } - raw_spin_unlock(&cfs_b->lock); cfs_rq->runtime_remaining += amount; return cfs_rq->runtime_remaining > 0; } +/* returns 0 on failure to allocate runtime */ +static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + int ret; + + raw_spin_lock(&cfs_b->lock); + ret = __assign_cfs_rq_runtime(cfs_b, cfs_rq, sched_cfs_bandwidth_slice()); + raw_spin_unlock(&cfs_b->lock); + + return ret; +} + static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) { /* dock delta_exec before expiring quota (as it could span periods) */ @@ -4495,13 +4511,33 @@ static int tg_throttle_down(struct task_group *tg, void *data) return 0; } -static void throttle_cfs_rq(struct cfs_rq *cfs_rq) +static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) { struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; long task_delta, idle_task_delta, dequeue = 1; - bool empty; + + raw_spin_lock(&cfs_b->lock); + /* This will start the period timer if necessary */ + if (__assign_cfs_rq_runtime(cfs_b, cfs_rq, 1)) { + /* + * We have raced with bandwidth becoming available, and if we + * actually throttled the timer might not unthrottle us for an + * entire period. We additionally needed to make sure that any + * subsequent check_cfs_rq_runtime calls agree not to throttle + * us, as we may commit to do cfs put_prev+pick_next, so we ask + * for 1ns of runtime rather than just check cfs_b. + */ + dequeue = 0; + } else { + list_add_tail_rcu(&cfs_rq->throttled_list, + &cfs_b->throttled_cfs_rq); + } + raw_spin_unlock(&cfs_b->lock); + + if (!dequeue) + return false; /* Throttle no longer required. */ se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))]; @@ -4530,29 +4566,13 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) if (!se) sub_nr_running(rq, task_delta); - cfs_rq->throttled = 1; - cfs_rq->throttled_clock = rq_clock(rq); - raw_spin_lock(&cfs_b->lock); - empty = list_empty(&cfs_b->throttled_cfs_rq); - - /* - * Add to the _head_ of the list, so that an already-started - * distribute_cfs_runtime will not see us. If disribute_cfs_runtime is - * not running add to the tail so that later runqueues don't get starved. - */ - if (cfs_b->distribute_running) - list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); - else - list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); - /* - * If we're the first throttled task, make sure the bandwidth - * timer is running. + * Note: distribution will already see us throttled via the + * throttled-list. rq->lock protects completion. */ - if (empty) - start_cfs_bandwidth(cfs_b); - - raw_spin_unlock(&cfs_b->lock); + cfs_rq->throttled = 1; + cfs_rq->throttled_clock = rq_clock(rq); + return true; } void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) @@ -4911,8 +4931,7 @@ static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) if (cfs_rq_throttled(cfs_rq)) return true; - throttle_cfs_rq(cfs_rq); - return true; + return throttle_cfs_rq(cfs_rq); } static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) @@ -4942,6 +4961,8 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) if (!overrun) break; + idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); + if (++count > 3) { u64 new, old = ktime_to_ns(cfs_b->period); @@ -4971,8 +4992,6 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) /* reset count so we don't come right back in here */ count = 0; } - - idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); } if (idle) cfs_b->period_active = 0; @@ -7407,7 +7426,15 @@ static int detach_tasks(struct lb_env *env) if (!can_migrate_task(p, env)) goto next; - load = task_h_load(p); + /* + * Depending of the number of CPUs and tasks and the + * cgroup hierarchy, task_h_load() can return a null + * value. Make sure that env->imbalance decreases + * otherwise detach_tasks() will stop only after + * detaching up to loop_max tasks. + */ + load = max_t(unsigned long, task_h_load(p), 1); + if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed) goto next; @@ -9373,7 +9400,12 @@ static void kick_ilb(unsigned int flags) { int ilb_cpu; - nohz.next_balance++; + /* + * Increase nohz.next_balance only when if full ilb is triggered but + * not if we only update stats. + */ + if (flags & NOHZ_BALANCE_KICK) + nohz.next_balance = jiffies+1; ilb_cpu = find_new_ilb(); @@ -9691,6 +9723,14 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags, } } + /* + * next_balance will be updated only when there is a need. + * When the CPU is attached to null domain for ex, it will not be + * updated. + */ + if (likely(update_next_balance)) + nohz.next_balance = next_balance; + /* Newly idle CPU doesn't need an update */ if (idle != CPU_NEWLY_IDLE) { update_blocked_averages(this_cpu); @@ -9711,14 +9751,6 @@ abort: if (has_blocked_load) WRITE_ONCE(nohz.has_blocked, 1); - /* - * next_balance will be updated only when there is a need. - * When the CPU is attached to null domain for ex, it will not be - * updated. - */ - if (likely(update_next_balance)) - nohz.next_balance = next_balance; - return ret; } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 7bf917e4d63a..5b04bba4500d 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -9,6 +9,8 @@ int sched_rr_timeslice = RR_TIMESLICE; int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; +/* More than 4 hours if BW_SHIFT equals 20. */ +static const u64 max_rt_runtime = MAX_BW; static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun); @@ -2513,6 +2515,12 @@ static int tg_set_rt_bandwidth(struct task_group *tg, if (rt_period == 0) return -EINVAL; + /* + * Bound quota to defend quota against overflow during bandwidth shift. + */ + if (rt_runtime != RUNTIME_INF && rt_runtime > max_rt_runtime) + return -EINVAL; + mutex_lock(&rt_constraints_mutex); read_lock(&tasklist_lock); err = __rt_schedulable(tg, rt_period, rt_runtime); @@ -2634,7 +2642,9 @@ static int sched_rt_global_validate(void) return -EINVAL; if ((sysctl_sched_rt_runtime != RUNTIME_INF) && - (sysctl_sched_rt_runtime > sysctl_sched_rt_period)) + ((sysctl_sched_rt_runtime > sysctl_sched_rt_period) || + ((u64)sysctl_sched_rt_runtime * + NSEC_PER_USEC > max_rt_runtime))) return -EINVAL; return 0; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c7e7481968bf..9f2a9e34a78d 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -841,6 +841,8 @@ struct uclamp_rq { unsigned int value; struct uclamp_bucket bucket[UCLAMP_BUCKETS]; }; + +DECLARE_STATIC_KEY_FALSE(sched_uclamp_used); #endif /* CONFIG_UCLAMP_TASK */ /* @@ -1889,6 +1891,8 @@ extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq); #define BW_SHIFT 20 #define BW_UNIT (1 << BW_SHIFT) #define RATIO_SHIFT 8 +#define MAX_BW_BITS (64 - BW_SHIFT) +#define MAX_BW ((1ULL << MAX_BW_BITS) - 1) unsigned long to_ratio(u64 period, u64 runtime); extern void init_entity_runnable_average(struct sched_entity *se); @@ -2317,12 +2321,35 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #ifdef CONFIG_UCLAMP_TASK unsigned int uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id); +/** + * uclamp_util_with - clamp @util with @rq and @p effective uclamp values. + * @rq: The rq to clamp against. Must not be NULL. + * @util: The util value to clamp. + * @p: The task to clamp against. Can be NULL if you want to clamp + * against @rq only. + * + * Clamps the passed @util to the max(@rq, @p) effective uclamp values. + * + * If sched_uclamp_used static key is disabled, then just return the util + * without any clamping since uclamp aggregation at the rq level in the fast + * path is disabled, rendering this operation a NOP. + * + * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It + * will return the correct effective uclamp value of the task even if the + * static key is disabled. + */ static __always_inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util, struct task_struct *p) { - unsigned int min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value); - unsigned int max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value); + unsigned int min_util; + unsigned int max_util; + + if (!static_branch_likely(&sched_uclamp_used)) + return util; + + min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value); + max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value); if (p) { min_util = max(min_util, uclamp_eff_value(p, UCLAMP_MIN)); @@ -2344,6 +2371,19 @@ static inline unsigned int uclamp_util(struct rq *rq, unsigned int util) { return uclamp_util_with(rq, util, NULL); } + +/* + * When uclamp is compiled in, the aggregation at rq level is 'turned off' + * by default in the fast path and only gets turned on once userspace performs + * an operation that requires it. + * + * Returns true if userspace opted-in to use uclamp and aggregation at rq level + * hence is active. + */ +static inline bool uclamp_is_used(void) +{ + return static_branch_likely(&sched_uclamp_used); +} #else /* CONFIG_UCLAMP_TASK */ static inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util, struct task_struct *p) @@ -2354,6 +2394,11 @@ static inline unsigned int uclamp_util(struct rq *rq, unsigned int util) { return util; } + +static inline bool uclamp_is_used(void) +{ + return false; +} #endif /* CONFIG_UCLAMP_TASK */ #ifdef arch_scale_freq_capacity diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 1fa1e13a5944..ffaa97a8d405 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1333,7 +1333,7 @@ sd_init(struct sched_domain_topology_level *tl, sd_flags = (*tl->sd_flags)(); if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS, "wrong sd_flags in topology description\n")) - sd_flags &= ~TOPOLOGY_SD_FLAGS; + sd_flags &= TOPOLOGY_SD_FLAGS; /* Apply detected topology flags */ sd_flags |= dflags; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 2c697ce7be21..e0fd97235653 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -42,6 +42,14 @@ #include <linux/uaccess.h> #include <linux/anon_inodes.h> +/* + * When SECCOMP_IOCTL_NOTIF_ID_VALID was first introduced, it had the + * wrong direction flag in the ioctl number. This is the broken one, + * which the kernel needs to keep supporting until all userspaces stop + * using the wrong command number. + */ +#define SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR SECCOMP_IOR(2, __u64) + enum notify_state { SECCOMP_NOTIFY_INIT, SECCOMP_NOTIFY_SENT, @@ -1168,6 +1176,7 @@ static long seccomp_notify_ioctl(struct file *file, unsigned int cmd, return seccomp_notify_recv(filter, buf); case SECCOMP_IOCTL_NOTIF_SEND: return seccomp_notify_send(filter, buf); + case SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR: case SECCOMP_IOCTL_NOTIF_ID_VALID: return seccomp_notify_id_valid(filter, buf); default: diff --git a/kernel/sys.c b/kernel/sys.c index a611d1d58c7d..3459a5ce0da0 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1279,11 +1279,13 @@ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) { - struct oldold_utsname tmp = {}; + struct oldold_utsname tmp; if (!name) return -EFAULT; + memset(&tmp, 0, sizeof(tmp)); + down_read(&uts_sem); memcpy(&tmp.sysname, &utsname()->sysname, __OLD_UTS_LEN); memcpy(&tmp.nodename, &utsname()->nodename, __OLD_UTS_LEN); diff --git a/kernel/sysctl-test.c b/kernel/sysctl-test.c new file mode 100644 index 000000000000..2a63241a8453 --- /dev/null +++ b/kernel/sysctl-test.c @@ -0,0 +1,392 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit test of proc sysctl. + */ + +#include <kunit/test.h> +#include <linux/sysctl.h> + +#define KUNIT_PROC_READ 0 +#define KUNIT_PROC_WRITE 1 + +static int i_zero; +static int i_one_hundred = 100; + +/* + * Test that proc_dointvec will not try to use a NULL .data field even when the + * length is non-zero. + */ +static void sysctl_test_api_dointvec_null_tbl_data(struct kunit *test) +{ + struct ctl_table null_data_table = { + .procname = "foo", + /* + * Here we are testing that proc_dointvec behaves correctly when + * we give it a NULL .data field. Normally this would point to a + * piece of memory where the value would be stored. + */ + .data = NULL, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + /* + * proc_dointvec expects a buffer in user space, so we allocate one. We + * also need to cast it to __user so sparse doesn't get mad. + */ + void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), + GFP_USER); + size_t len; + loff_t pos; + + /* + * We don't care what the starting length is since proc_dointvec should + * not try to read because .data is NULL. + */ + len = 1234; + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&null_data_table, + KUNIT_PROC_READ, buffer, &len, + &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); + + /* + * See above. + */ + len = 1234; + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&null_data_table, + KUNIT_PROC_WRITE, buffer, &len, + &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); +} + +/* + * Similar to the previous test, we create a struct ctrl_table that has a .data + * field that proc_dointvec cannot do anything with; however, this time it is + * because we tell proc_dointvec that the size is 0. + */ +static void sysctl_test_api_dointvec_table_maxlen_unset(struct kunit *test) +{ + int data = 0; + struct ctl_table data_maxlen_unset_table = { + .procname = "foo", + .data = &data, + /* + * So .data is no longer NULL, but we tell proc_dointvec its + * length is 0, so it still shouldn't try to use it. + */ + .maxlen = 0, + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), + GFP_USER); + size_t len; + loff_t pos; + + /* + * As before, we don't care what buffer length is because proc_dointvec + * cannot do anything because its internal .data buffer has zero length. + */ + len = 1234; + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&data_maxlen_unset_table, + KUNIT_PROC_READ, buffer, &len, + &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); + + /* + * See previous comment. + */ + len = 1234; + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&data_maxlen_unset_table, + KUNIT_PROC_WRITE, buffer, &len, + &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); +} + +/* + * Here we provide a valid struct ctl_table, but we try to read and write from + * it using a buffer of zero length, so it should still fail in a similar way as + * before. + */ +static void sysctl_test_api_dointvec_table_len_is_zero(struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), + GFP_USER); + /* + * However, now our read/write buffer has zero length. + */ + size_t len = 0; + loff_t pos; + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ, buffer, + &len, &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_WRITE, buffer, + &len, &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); +} + +/* + * Test that proc_dointvec refuses to read when the file position is non-zero. + */ +static void sysctl_test_api_dointvec_table_read_but_position_set( + struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), + GFP_USER); + /* + * We don't care about our buffer length because we start off with a + * non-zero file position. + */ + size_t len = 1234; + /* + * proc_dointvec should refuse to read into the buffer since the file + * pos is non-zero. + */ + loff_t pos = 1; + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ, buffer, + &len, &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); +} + +/* + * Test that we can read a two digit number in a sufficiently size buffer. + * Nothing fancy. + */ +static void sysctl_test_dointvec_read_happy_single_positive(struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + size_t len = 4; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + /* Store 13 in the data field. */ + *((int *)table.data) = 13; + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ, + user_buffer, &len, &pos)); + KUNIT_ASSERT_EQ(test, (size_t)3, len); + buffer[len] = '\0'; + /* And we read 13 back out. */ + KUNIT_EXPECT_STREQ(test, "13\n", buffer); +} + +/* + * Same as previous test, just now with negative numbers. + */ +static void sysctl_test_dointvec_read_happy_single_negative(struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + size_t len = 5; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + *((int *)table.data) = -16; + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ, + user_buffer, &len, &pos)); + KUNIT_ASSERT_EQ(test, (size_t)4, len); + buffer[len] = '\0'; + KUNIT_EXPECT_STREQ(test, "-16\n", (char *)buffer); +} + +/* + * Test that a simple positive write works. + */ +static void sysctl_test_dointvec_write_happy_single_positive(struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + char input[] = "9"; + size_t len = sizeof(input) - 1; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + + memcpy(buffer, input, len); + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_WRITE, + user_buffer, &len, &pos)); + KUNIT_EXPECT_EQ(test, sizeof(input) - 1, len); + KUNIT_EXPECT_EQ(test, sizeof(input) - 1, (size_t)pos); + KUNIT_EXPECT_EQ(test, 9, *((int *)table.data)); +} + +/* + * Same as previous test, but now with negative numbers. + */ +static void sysctl_test_dointvec_write_happy_single_negative(struct kunit *test) +{ + int data = 0; + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + char input[] = "-9"; + size_t len = sizeof(input) - 1; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + + memcpy(buffer, input, len); + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_WRITE, + user_buffer, &len, &pos)); + KUNIT_EXPECT_EQ(test, sizeof(input) - 1, len); + KUNIT_EXPECT_EQ(test, sizeof(input) - 1, (size_t)pos); + KUNIT_EXPECT_EQ(test, -9, *((int *)table.data)); +} + +/* + * Test that writing a value smaller than the minimum possible value is not + * allowed. + */ +static void sysctl_test_api_dointvec_write_single_less_int_min( + struct kunit *test) +{ + int data = 0; + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + size_t max_len = 32, len = max_len; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, max_len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + unsigned long abs_of_less_than_min = (unsigned long)INT_MAX + - (INT_MAX + INT_MIN) + 1; + + /* + * We use this rigmarole to create a string that contains a value one + * less than the minimum accepted value. + */ + KUNIT_ASSERT_LT(test, + (size_t)snprintf(buffer, max_len, "-%lu", + abs_of_less_than_min), + max_len); + + KUNIT_EXPECT_EQ(test, -EINVAL, proc_dointvec(&table, KUNIT_PROC_WRITE, + user_buffer, &len, &pos)); + KUNIT_EXPECT_EQ(test, max_len, len); + KUNIT_EXPECT_EQ(test, 0, *((int *)table.data)); +} + +/* + * Test that writing the maximum possible value works. + */ +static void sysctl_test_api_dointvec_write_single_greater_int_max( + struct kunit *test) +{ + int data = 0; + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + size_t max_len = 32, len = max_len; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, max_len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + unsigned long greater_than_max = (unsigned long)INT_MAX + 1; + + KUNIT_ASSERT_GT(test, greater_than_max, (unsigned long)INT_MAX); + KUNIT_ASSERT_LT(test, (size_t)snprintf(buffer, max_len, "%lu", + greater_than_max), + max_len); + KUNIT_EXPECT_EQ(test, -EINVAL, proc_dointvec(&table, KUNIT_PROC_WRITE, + user_buffer, &len, &pos)); + KUNIT_ASSERT_EQ(test, max_len, len); + KUNIT_EXPECT_EQ(test, 0, *((int *)table.data)); +} + +static struct kunit_case sysctl_test_cases[] = { + KUNIT_CASE(sysctl_test_api_dointvec_null_tbl_data), + KUNIT_CASE(sysctl_test_api_dointvec_table_maxlen_unset), + KUNIT_CASE(sysctl_test_api_dointvec_table_len_is_zero), + KUNIT_CASE(sysctl_test_api_dointvec_table_read_but_position_set), + KUNIT_CASE(sysctl_test_dointvec_read_happy_single_positive), + KUNIT_CASE(sysctl_test_dointvec_read_happy_single_negative), + KUNIT_CASE(sysctl_test_dointvec_write_happy_single_positive), + KUNIT_CASE(sysctl_test_dointvec_write_happy_single_negative), + KUNIT_CASE(sysctl_test_api_dointvec_write_single_less_int_min), + KUNIT_CASE(sysctl_test_api_dointvec_write_single_greater_int_max), + {} +}; + +static struct kunit_suite sysctl_test_suite = { + .name = "sysctl_test", + .test_cases = sysctl_test_cases, +}; + +kunit_test_suite(sysctl_test_suite); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index ca69290bee2a..4fc2af4367a7 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1005,9 +1005,8 @@ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; - rem *= mult; - do_div(rem, div); + rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; } diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 4820823515e9..a3ae244b1bcd 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -43,6 +43,7 @@ #include <linux/sched/debug.h> #include <linux/slab.h> #include <linux/compat.h> +#include <linux/random.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -522,8 +523,8 @@ static int calc_wheel_index(unsigned long expires, unsigned long clk) * Force expire obscene large timeouts to expire at the * capacity limit of the wheel. */ - if (expires >= WHEEL_TIMEOUT_CUTOFF) - expires = WHEEL_TIMEOUT_MAX; + if (delta >= WHEEL_TIMEOUT_CUTOFF) + expires = clk + WHEEL_TIMEOUT_MAX; idx = calc_index(expires, LVL_DEPTH - 1); } @@ -585,7 +586,15 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) * Set the next expiry time and kick the CPU so it can reevaluate the * wheel: */ - base->next_expiry = timer->expires; + if (time_before(timer->expires, base->clk)) { + /* + * Prevent from forward_timer_base() moving the base->clk + * backward + */ + base->next_expiry = base->clk; + } else { + base->next_expiry = timer->expires; + } wake_up_nohz_cpu(base->cpu); } @@ -897,10 +906,13 @@ static inline void forward_timer_base(struct timer_base *base) * If the next expiry value is > jiffies, then we fast forward to * jiffies otherwise we forward to the next expiry value. */ - if (time_after(base->next_expiry, jnow)) + if (time_after(base->next_expiry, jnow)) { base->clk = jnow; - else + } else { + if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk))) + return; base->clk = base->next_expiry; + } #endif } @@ -1731,6 +1743,13 @@ void update_process_times(int user_tick) scheduler_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); + + /* The current CPU might make use of net randoms without receiving IRQs + * to renew them often enough. Let's update the net_rand_state from a + * non-constant value that's not affine to the number of calls to make + * sure it's updated when there's some activity (we don't care in idle). + */ + this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick); } /** diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index e7e483cdbea6..884333b9fc76 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -3,6 +3,9 @@ * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk> * */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/blktrace_api.h> @@ -495,6 +498,16 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, */ strreplace(buts->name, '/', '_'); + /* + * bdev can be NULL, as with scsi-generic, this is a helpful as + * we can be. + */ + if (q->blk_trace) { + pr_warn("Concurrent blktraces are not allowed on %s\n", + buts->name); + return -EBUSY; + } + bt = kzalloc(sizeof(*bt), GFP_KERNEL); if (!bt) return -ENOMEM; @@ -508,12 +521,32 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (!bt->msg_data) goto err; - ret = -ENOENT; - - dir = debugfs_lookup(buts->name, blk_debugfs_root); - if (!dir) +#ifdef CONFIG_BLK_DEBUG_FS + /* + * When tracing whole make_request drivers (multiqueue) block devices, + * reuse the existing debugfs directory created by the block layer on + * init. For request-based block devices, all partitions block devices, + * and scsi-generic block devices we create a temporary new debugfs + * directory that will be removed once the trace ends. + */ + if (queue_is_mq(q) && bdev && bdev == bdev->bd_contains) + dir = q->debugfs_dir; + else +#endif bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root); + /* + * As blktrace relies on debugfs for its interface the debugfs directory + * is required, contrary to the usual mantra of not checking for debugfs + * files or directories. + */ + if (IS_ERR_OR_NULL(dir)) { + pr_warn("debugfs_dir not present for %s so skipping\n", + buts->name); + ret = -ENOENT; + goto err; + } + bt->dev = dev; atomic_set(&bt->dropped, 0); INIT_LIST_HEAD(&bt->running_list); @@ -552,8 +585,6 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, ret = 0; err: - if (dir && !bt->dir) - dput(dir); if (ret) blk_trace_free(bt); return ret; @@ -999,8 +1030,10 @@ static void blk_add_trace_split(void *ignore, __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, - BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu), - &rpdu, blk_trace_bio_get_cgid(q, bio)); + BLK_TA_SPLIT, + blk_status_to_errno(bio->bi_status), + sizeof(rpdu), &rpdu, + blk_trace_bio_get_cgid(q, bio)); } rcu_read_unlock(); } @@ -1037,7 +1070,8 @@ static void blk_add_trace_bio_remap(void *ignore, r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, - bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status, + bio_op(bio), bio->bi_opf, BLK_TA_REMAP, + blk_status_to_errno(bio->bi_status), sizeof(r), &r, blk_trace_bio_get_cgid(q, bio)); rcu_read_unlock(); } @@ -1259,21 +1293,10 @@ static inline __u16 t_error(const struct trace_entry *ent) static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg) { - const __u64 *val = pdu_start(ent, has_cg); + const __be64 *val = pdu_start(ent, has_cg); return be64_to_cpu(*val); } -static void get_pdu_remap(const struct trace_entry *ent, - struct blk_io_trace_remap *r, bool has_cg) -{ - const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg); - __u64 sector_from = __r->sector_from; - - r->device_from = be32_to_cpu(__r->device_from); - r->device_to = be32_to_cpu(__r->device_to); - r->sector_from = be64_to_cpu(sector_from); -} - typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act, bool has_cg); @@ -1399,13 +1422,13 @@ static void blk_log_with_error(struct trace_seq *s, static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { - struct blk_io_trace_remap r = { .device_from = 0, }; + const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg); - get_pdu_remap(ent, &r, has_cg); trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n", t_sector(ent), t_sec(ent), - MAJOR(r.device_from), MINOR(r.device_from), - (unsigned long long)r.sector_from); + MAJOR(be32_to_cpu(__r->device_from)), + MINOR(be32_to_cpu(__r->device_from)), + be64_to_cpu(__r->sector_from)); } static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 15160d707da4..fbba31baef53 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5699,8 +5699,11 @@ static int referenced_filters(struct dyn_ftrace *rec) int cnt = 0; for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) { - if (ops_references_rec(ops, rec)) - cnt++; + if (ops_references_rec(ops, rec)) { + cnt++; + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) + rec->flags |= FTRACE_FL_REGS; + } } return cnt; @@ -5877,8 +5880,8 @@ void ftrace_module_enable(struct module *mod) if (ftrace_start_up) cnt += referenced_filters(rec); - /* This clears FTRACE_FL_DISABLED */ - rec->flags = cnt; + rec->flags &= ~FTRACE_FL_DISABLED; + rec->flags += cnt; if (ftrace_start_up && cnt) { int failed = __ftrace_replace_code(rec, 1); @@ -6379,16 +6382,14 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip, { int bit; - if ((op->flags & FTRACE_OPS_FL_RCU) && !rcu_is_watching()) - return; - bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX); if (bit < 0) return; preempt_disable_notrace(); - op->func(ip, parent_ip, op, regs); + if (!(op->flags & FTRACE_OPS_FL_RCU) || rcu_is_watching()) + op->func(ip, parent_ip, op, regs); preempt_enable_notrace(); trace_clear_recursion(bit); @@ -6459,12 +6460,12 @@ void ftrace_pid_follow_fork(struct trace_array *tr, bool enable) if (enable) { register_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork, tr); - register_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit, + register_trace_sched_process_free(ftrace_pid_follow_sched_process_exit, tr); } else { unregister_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork, tr); - unregister_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit, + unregister_trace_sched_process_free(ftrace_pid_follow_sched_process_exit, tr); } } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 4bf050fcfe3b..9a2581fe7ed5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2358,7 +2358,7 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer, if (unlikely(info->add_timestamp)) { bool abs = ring_buffer_time_stamp_abs(cpu_buffer->buffer); - event = rb_add_time_stamp(event, info->delta, abs); + event = rb_add_time_stamp(event, abs ? info->delta : delta, abs); length -= RB_LEN_TIME_EXTEND; delta = 0; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 721947b9962d..5b2a664812b1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3233,6 +3233,9 @@ int trace_array_printk(struct trace_array *tr, if (!(global_trace.trace_flags & TRACE_ITER_PRINTK)) return 0; + if (!tr) + return -ENOENT; + va_start(ap, fmt); ret = trace_array_vprintk(tr, ip, fmt, ap); va_end(ap); @@ -3581,14 +3584,14 @@ unsigned long trace_total_entries(struct trace_array *tr) static void print_lat_help_header(struct seq_file *m) { - seq_puts(m, "# _------=> CPU# \n" - "# / _-----=> irqs-off \n" - "# | / _----=> need-resched \n" - "# || / _---=> hardirq/softirq \n" - "# ||| / _--=> preempt-depth \n" - "# |||| / delay \n" - "# cmd pid ||||| time | caller \n" - "# \\ / ||||| \\ | / \n"); + seq_puts(m, "# _------=> CPU# \n" + "# / _-----=> irqs-off \n" + "# | / _----=> need-resched \n" + "# || / _---=> hardirq/softirq \n" + "# ||| / _--=> preempt-depth \n" + "# |||| / delay \n" + "# cmd pid ||||| time | caller \n" + "# \\ / ||||| \\ | / \n"); } static void print_event_info(struct trace_buffer *buf, struct seq_file *m) @@ -3609,26 +3612,26 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m, print_event_info(buf, m); - seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? "TGID " : ""); - seq_printf(m, "# | | %s | | |\n", tgid ? " | " : ""); + seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? " TGID " : ""); + seq_printf(m, "# | | %s | | |\n", tgid ? " | " : ""); } static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m, unsigned int flags) { bool tgid = flags & TRACE_ITER_RECORD_TGID; - const char *space = " "; - int prec = tgid ? 10 : 2; + const char *space = " "; + int prec = tgid ? 12 : 2; print_event_info(buf, m); - seq_printf(m, "# %.*s _-----=> irqs-off\n", prec, space); - seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space); - seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space); - seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space); - seq_printf(m, "# %.*s||| / delay\n", prec, space); - seq_printf(m, "# TASK-PID %.*sCPU# |||| TIMESTAMP FUNCTION\n", prec, " TGID "); - seq_printf(m, "# | | %.*s | |||| | |\n", prec, " | "); + seq_printf(m, "# %.*s _-----=> irqs-off\n", prec, space); + seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space); + seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space); + seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space); + seq_printf(m, "# %.*s||| / delay\n", prec, space); + seq_printf(m, "# TASK-PID %.*s CPU# |||| TIMESTAMP FUNCTION\n", prec, " TGID "); + seq_printf(m, "# | | %.*s | |||| | |\n", prec, " | "); } void @@ -5686,7 +5689,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) } /* If trace pipe files are being read, we can't change the tracer */ - if (tr->current_trace->ref) { + if (tr->trace_ref) { ret = -EBUSY; goto out; } @@ -5902,7 +5905,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) nonseekable_open(inode, filp); - tr->current_trace->ref++; + tr->trace_ref++; out: mutex_unlock(&trace_types_lock); return ret; @@ -5921,7 +5924,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) mutex_lock(&trace_types_lock); - tr->current_trace->ref--; + tr->trace_ref--; if (iter->trace->pipe_close) iter->trace->pipe_close(iter); @@ -7230,7 +7233,7 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) filp->private_data = info; - tr->current_trace->ref++; + tr->trace_ref++; mutex_unlock(&trace_types_lock); @@ -7331,7 +7334,7 @@ static int tracing_buffers_release(struct inode *inode, struct file *file) mutex_lock(&trace_types_lock); - iter->tr->current_trace->ref--; + iter->tr->trace_ref--; __trace_array_put(iter->tr); @@ -8470,7 +8473,7 @@ static int __remove_instance(struct trace_array *tr) { int i; - if (tr->ref || (tr->current_trace && tr->current_trace->ref)) + if (tr->ref || (tr->current_trace && tr->trace_ref)) return -EBUSY; list_del(&tr->list); @@ -8502,17 +8505,26 @@ static int __remove_instance(struct trace_array *tr) return 0; } -int trace_array_destroy(struct trace_array *tr) +int trace_array_destroy(struct trace_array *this_tr) { + struct trace_array *tr; int ret; - if (!tr) + if (!this_tr) return -EINVAL; mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); - ret = __remove_instance(tr); + ret = -ENODEV; + + /* Making sure trace array exists before destroying it. */ + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr == this_tr) { + ret = __remove_instance(tr); + break; + } + } mutex_unlock(&trace_types_lock); mutex_unlock(&event_mutex); @@ -9134,7 +9146,7 @@ __init static int tracer_alloc_buffers(void) goto out_free_buffer_mask; /* Only allocate trace_printk buffers if a trace_printk exists */ - if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt) + if (&__stop___trace_bprintk_fmt != &__start___trace_bprintk_fmt) /* Must be called before global_trace.buffer is allocated */ trace_printk_init_buffers(); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index a3c29d5fcc61..4055158c1dd2 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -309,6 +309,7 @@ struct trace_array { struct trace_event_file *trace_marker_file; cpumask_var_t tracing_cpumask; /* only trace on set CPUs */ int ref; + int trace_ref; #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops *ops; struct trace_pid_list __rcu *function_pids; @@ -498,7 +499,6 @@ struct tracer { struct tracer *next; struct tracer_flags *flags; int enabled; - int ref; bool print_max; bool allow_instances; #ifdef CONFIG_TRACER_MAX_TRACE diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index fc8e97328e54..78c146efb862 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -174,7 +174,7 @@ FTRACE_ENTRY(kernel_stack, stack_entry, F_STRUCT( __field( int, size ) - __dynamic_array(unsigned long, caller ) + __array( unsigned long, caller, FTRACE_STACK_ENTRIES ) ), F_printk("\t=> %ps\n\t=> %ps\n\t=> %ps\n" diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 995061bb2dec..309b2b3c5349 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -527,12 +527,12 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable) if (enable) { register_trace_prio_sched_process_fork(event_filter_pid_sched_process_fork, tr, INT_MIN); - register_trace_prio_sched_process_exit(event_filter_pid_sched_process_exit, + register_trace_prio_sched_process_free(event_filter_pid_sched_process_exit, tr, INT_MAX); } else { unregister_trace_sched_process_fork(event_filter_pid_sched_process_fork, tr); - unregister_trace_sched_process_exit(event_filter_pid_sched_process_exit, + unregister_trace_sched_process_free(event_filter_pid_sched_process_exit, tr); } } @@ -793,6 +793,8 @@ int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) char *event = NULL, *sub = NULL, *match; int ret; + if (!tr) + return -ENOENT; /* * The buf format can be <subsystem>:<event-name> * *:<event-name> means any event by that name. diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 8107574e8af9..a616b314fb7a 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -4770,7 +4770,6 @@ 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]); ret = -ENOMEM; goto free; } diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index de840de87a18..e913d41a4194 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -216,11 +216,17 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file) static int trigger_process_regex(struct trace_event_file *file, char *buff) { - char *command, *next = buff; + char *command, *next; struct event_command *p; int ret = -EINVAL; + next = buff = skip_spaces(buff); command = strsep(&next, ": \t"); + if (next) { + next = skip_spaces(next); + if (!*next) + next = NULL; + } command = (command[0] != '!') ? command : command + 1; mutex_lock(&trigger_cmd_mutex); @@ -630,8 +636,14 @@ event_trigger_callback(struct event_command *cmd_ops, int ret; /* separate the trigger from the filter (t:n [if filter]) */ - if (param && isdigit(param[0])) + if (param && isdigit(param[0])) { trigger = strsep(¶m, " \t"); + if (param) { + param = skip_spaces(param); + if (!*param) + param = NULL; + } + } trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger); @@ -1368,6 +1380,11 @@ int event_enable_trigger_func(struct event_command *cmd_ops, trigger = strsep(¶m, " \t"); if (!trigger) return -EINVAL; + if (param) { + param = skip_spaces(param); + if (!*param) + param = NULL; + } system = strsep(&trigger, ":"); if (!trigger) diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index 862f4b0139fc..35512ed26d9f 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -270,6 +270,7 @@ static bool disable_migrate; static void move_to_next_cpu(void) { struct cpumask *current_mask = &save_cpumask; + struct trace_array *tr = hwlat_trace; int next_cpu; if (disable_migrate) @@ -283,7 +284,7 @@ static void move_to_next_cpu(void) goto disable; get_online_cpus(); - cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask); + cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask); next_cpu = cpumask_next(smp_processor_id(), current_mask); put_online_cpus(); @@ -360,7 +361,7 @@ static int start_kthread(struct trace_array *tr) /* Just pick the first CPU on first iteration */ current_mask = &save_cpumask; get_online_cpus(); - cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask); + cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask); put_online_cpus(); next_cpu = cpumask_first(current_mask); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index fba4b48451f6..26de9c654956 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1464,7 +1464,7 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, if (perf_type_tracepoint) tk = find_trace_kprobe(pevent, group); else - tk = event->tp_event->data; + tk = trace_kprobe_primary_from_call(event->tp_event); if (!tk) return -EINVAL; diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index d54ce252b05a..a0a45901dc02 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -482,7 +482,7 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) trace_find_cmdline(entry->pid, comm); - trace_seq_printf(s, "%8.8s-%-5d %3d", + trace_seq_printf(s, "%8.8s-%-7d %3d", comm, entry->pid, cpu); return trace_print_lat_fmt(s, entry); @@ -573,15 +573,15 @@ int trace_print_context(struct trace_iterator *iter) trace_find_cmdline(entry->pid, comm); - trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid); + trace_seq_printf(s, "%16s-%-7d ", comm, entry->pid); if (tr->trace_flags & TRACE_ITER_RECORD_TGID) { unsigned int tgid = trace_find_tgid(entry->pid); if (!tgid) - trace_seq_printf(s, "(-----) "); + trace_seq_printf(s, "(-------) "); else - trace_seq_printf(s, "(%5d) ", tgid); + trace_seq_printf(s, "(%7d) ", tgid); } trace_seq_printf(s, "[%03d] ", iter->cpu); @@ -624,7 +624,7 @@ int trace_print_lat_context(struct trace_iterator *iter) trace_find_cmdline(entry->pid, comm); trace_seq_printf( - s, "%16s %5d %3d %d %08x %08lx ", + s, "%16s %7d %3d %d %08x %08lx ", comm, entry->pid, iter->cpu, entry->flags, entry->preempt_count, iter->idx); } else { @@ -905,7 +905,7 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, S = task_index_to_char(field->prev_state); trace_find_cmdline(field->next_pid, comm); trace_seq_printf(&iter->seq, - " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", + " %7d:%3d:%c %s [%03d] %7d:%3d:%c %s\n", field->prev_pid, field->prev_prio, S, delim, diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c index 4d8e99fdbbbe..26b06b09c9f6 100644 --- a/kernel/trace/trace_preemptirq.c +++ b/kernel/trace/trace_preemptirq.c @@ -63,14 +63,14 @@ NOKPROBE_SYMBOL(trace_hardirqs_on_caller); __visible void trace_hardirqs_off_caller(unsigned long caller_addr) { + lockdep_hardirqs_off(CALLER_ADDR0); + if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, caller_addr); if (!in_nmi()) trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr); } - - lockdep_hardirqs_off(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_off_caller); NOKPROBE_SYMBOL(trace_hardirqs_off_caller); diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index ab8b6436d53f..f98d6d94cbbf 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -639,8 +639,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size, ret = -EINVAL; goto fail; } - if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM) || - parg->count) { + if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM || + code->op == FETCH_OP_DATA) || parg->count) { /* * IMM, DATA and COMM is pointing actual address, those * must be kept, and if parg->count != 0, this is an diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 2619bc5ed520..5294843de6ef 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1405,7 +1405,7 @@ int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, if (perf_type_tracepoint) tu = find_probe_event(pevent, group); else - tu = event->tp_event->data; + tu = trace_uprobe_primary_from_call(event->tp_event); if (!tu) return -EINVAL; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1a0c224af6fb..4aa268582a22 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -864,7 +864,8 @@ void wq_worker_running(struct task_struct *task) * @task: task going to sleep * * This function is called from schedule() when a busy worker is - * going to sleep. + * going to sleep. Preemption needs to be disabled to protect ->sleeping + * assignment. */ void wq_worker_sleeping(struct task_struct *task) { @@ -881,7 +882,8 @@ void wq_worker_sleeping(struct task_struct *task) pool = worker->pool; - if (WARN_ON_ONCE(worker->sleeping)) + /* Return if preempted before wq_worker_running() was reached */ + if (worker->sleeping) return; worker->sleeping = 1; |