From b9c44b91476b67327a521568a854babecc4070ab Mon Sep 17 00:00:00 2001 From: Yabin Cui Date: Wed, 15 May 2024 12:36:07 -0700 Subject: perf/core: Save raw sample data conditionally based on sample type Currently, space for raw sample data is always allocated within sample records for both BPF output and tracepoint events. This leads to unused space in sample records when raw sample data is not requested. This patch enforces checking sample type of an event in perf_sample_save_raw_data(). So raw sample data will only be saved if explicitly requested, reducing overhead when it is not needed. Fixes: 0a9081cf0a11 ("perf/core: Add perf_sample_save_raw_data() helper") Signed-off-by: Yabin Cui Signed-off-by: Ingo Molnar Reviewed-by: Ian Rogers Acked-by: Namhyung Kim Link: https://lore.kernel.org/r/20240515193610.2350456-2-yabinc@google.com --- kernel/trace/bpf_trace.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index fdab7ecd8dfa..162bacf8aa5d 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -619,7 +619,8 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = { static __always_inline u64 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, - u64 flags, struct perf_sample_data *sd) + u64 flags, struct perf_raw_record *raw, + struct perf_sample_data *sd) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); @@ -644,6 +645,8 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, if (unlikely(event->oncpu != cpu)) return -EOPNOTSUPP; + perf_sample_save_raw_data(sd, event, raw); + return perf_event_output(event, sd, regs); } @@ -687,9 +690,8 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, } perf_sample_data_init(sd, 0, 0); - perf_sample_save_raw_data(sd, &raw); - err = __bpf_perf_event_output(regs, map, flags, sd); + err = __bpf_perf_event_output(regs, map, flags, &raw, sd); out: this_cpu_dec(bpf_trace_nest_level); preempt_enable(); @@ -748,9 +750,8 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, perf_fetch_caller_regs(regs); perf_sample_data_init(sd, 0, 0); - perf_sample_save_raw_data(sd, &raw); - ret = __bpf_perf_event_output(regs, map, flags, sd); + ret = __bpf_perf_event_output(regs, map, flags, &raw, sd); out: this_cpu_dec(bpf_event_output_nest_level); preempt_enable(); -- cgit v1.2.3 From 7863dcc72d0f4b13a641065670426435448b3d80 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 22 Nov 2024 14:24:58 +0100 Subject: pid: allow pid_max to be set per pid namespace The pid_max sysctl is a global value. For a long time the default value has been 65535 and during the pidfd dicussions Linus proposed to bump pid_max by default (cf. [1]). Based on this discussion systemd started bumping pid_max to 2^22. So all new systems now run with a very high pid_max limit with some distros having also backported that change. The decision to bump pid_max is obviously correct. It just doesn't make a lot of sense nowadays to enforce such a low pid number. There's sufficient tooling to make selecting specific processes without typing really large pid numbers available. In any case, there are workloads that have expections about how large pid numbers they accept. Either for historical reasons or architectural reasons. One concreate example is the 32-bit version of Android's bionic libc which requires pid numbers less than 65536. There are workloads where it is run in a 32-bit container on a 64-bit kernel. If the host has a pid_max value greater than 65535 the libc will abort thread creation because of size assumptions of pthread_mutex_t. That's a fairly specific use-case however, in general specific workloads that are moved into containers running on a host with a new kernel and a new systemd can run into issues with large pid_max values. Obviously making assumptions about the size of the allocated pid is suboptimal but we have userspace that does it. Of course, giving containers the ability to restrict the number of processes in their respective pid namespace indepent of the global limit through pid_max is something desirable in itself and comes in handy in general. Independent of motivating use-cases the existence of pid namespaces makes this also a good semantical extension and there have been prior proposals pushing in a similar direction. The trick here is to minimize the risk of regressions which I think is doable. The fact that pid namespaces are hierarchical will help us here. What we mostly care about is that when the host sets a low pid_max limit, say (crazy number) 100 that no descendant pid namespace can allocate a higher pid number in its namespace. Since pid allocation is hierarchial this can be ensured by checking each pid allocation against the pid namespace's pid_max limit. This means if the allocation in the descendant pid namespace succeeds, the ancestor pid namespace can reject it. If the ancestor pid namespace has a higher limit than the descendant pid namespace the descendant pid namespace will reject the pid allocation. The ancestor pid namespace will obviously not care about this. All in all this means pid_max continues to enforce a system wide limit on the number of processes but allows pid namespaces sufficient leeway in handling workloads with assumptions about pid values and allows containers to restrict the number of processes in a pid namespace through the pid_max interface. [1]: https://lore.kernel.org/linux-api/CAHk-=wiZ40LVjnXSi9iHLE_-ZBsWFGCgdmNiYZUXn1-V5YBg2g@mail.gmail.com - rebased from 5.14-rc1 - a few fixes (missing ns_free_inum on error path, missing initialization, etc) - permission check changes in pid_table_root_permissions - unsigned int pid_max -> int pid_max (keep pid_max type as it was) - add READ_ONCE in alloc_pid() as suggested by Christian - rebased from 6.7 and take into account: * sysctl: treewide: drop unused argument ctl_table_root::set_ownership(table) * sysctl: treewide: constify ctl_table_header::ctl_table_arg * pidfd: add pidfs * tracing: Move saved_cmdline code into trace_sched_switch.c Signed-off-by: Alexander Mikhalitsyn Link: https://lore.kernel.org/r/20241122132459.135120-2-aleksandr.mikhalitsyn@canonical.com Signed-off-by: Christian Brauner --- include/linux/pid.h | 3 - include/linux/pid_namespace.h | 10 ++- kernel/pid.c | 125 +++++++++++++++++++++++++++++++++++--- kernel/pid_namespace.c | 43 +++++++++---- kernel/sysctl.c | 9 --- kernel/trace/pid_list.c | 2 +- kernel/trace/trace.h | 2 - kernel/trace/trace_sched_switch.c | 2 +- 8 files changed, 161 insertions(+), 35 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/pid.h b/include/linux/pid.h index a3aad9b4074c..c800cbee584b 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -106,9 +106,6 @@ extern void exchange_tids(struct task_struct *task, struct task_struct *old); extern void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type); -extern int pid_max; -extern int pid_max_min, pid_max_max; - /* * look up a PID in the hash table. Must be called with the tasklist_lock * or rcu_read_lock() held. diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index f9f9931e02d6..7c67a5811199 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -30,6 +30,7 @@ struct pid_namespace { struct task_struct *child_reaper; struct kmem_cache *pid_cachep; unsigned int level; + int pid_max; struct pid_namespace *parent; #ifdef CONFIG_BSD_PROCESS_ACCT struct fs_pin *bacct; @@ -38,9 +39,14 @@ struct pid_namespace { struct ucounts *ucounts; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; -#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) + struct work_struct work; +#ifdef CONFIG_SYSCTL + struct ctl_table_set set; + struct ctl_table_header *sysctls; +#if defined(CONFIG_MEMFD_CREATE) int memfd_noexec_scope; #endif +#endif } __randomize_layout; extern struct pid_namespace init_pid_ns; @@ -117,6 +123,8 @@ static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); void pidhash_init(void); void pid_idr_init(void); +int register_pidns_sysctls(struct pid_namespace *pidns); +void unregister_pidns_sysctls(struct pid_namespace *pidns); static inline bool task_is_in_init_pid_ns(struct task_struct *tsk) { diff --git a/kernel/pid.c b/kernel/pid.c index 115448e89c3e..ce3e94e26a0f 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -60,10 +60,8 @@ struct pid init_struct_pid = { }, } }; -int pid_max = PID_MAX_DEFAULT; - -int pid_max_min = RESERVED_PIDS + 1; -int pid_max_max = PID_MAX_LIMIT; +static int pid_max_min = RESERVED_PIDS + 1; +static int pid_max_max = PID_MAX_LIMIT; /* * Pseudo filesystems start inode numbering after one. We use Reserved * PIDs as a natural offset. @@ -87,6 +85,7 @@ struct pid_namespace init_pid_ns = { #ifdef CONFIG_PID_NS .ns.ops = &pidns_operations, #endif + .pid_max = PID_MAX_DEFAULT, #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) .memfd_noexec_scope = MEMFD_NOEXEC_SCOPE_EXEC, #endif @@ -193,6 +192,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, for (i = ns->level; i >= 0; i--) { int tid = 0; + int pid_max = READ_ONCE(tmp->pid_max); if (set_tid_size) { tid = set_tid[ns->level - i]; @@ -644,17 +644,118 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) return fd; } +#ifdef CONFIG_SYSCTL +static struct ctl_table_set *pid_table_root_lookup(struct ctl_table_root *root) +{ + return &task_active_pid_ns(current)->set; +} + +static int set_is_seen(struct ctl_table_set *set) +{ + return &task_active_pid_ns(current)->set == set; +} + +static int pid_table_root_permissions(struct ctl_table_header *head, + const struct ctl_table *table) +{ + struct pid_namespace *pidns = + container_of(head->set, struct pid_namespace, set); + int mode = table->mode; + + if (ns_capable(pidns->user_ns, CAP_SYS_ADMIN) || + uid_eq(current_euid(), make_kuid(pidns->user_ns, 0))) + mode = (mode & S_IRWXU) >> 6; + else if (in_egroup_p(make_kgid(pidns->user_ns, 0))) + mode = (mode & S_IRWXG) >> 3; + else + mode = mode & S_IROTH; + return (mode << 6) | (mode << 3) | mode; +} + +static void pid_table_root_set_ownership(struct ctl_table_header *head, + kuid_t *uid, kgid_t *gid) +{ + struct pid_namespace *pidns = + container_of(head->set, struct pid_namespace, set); + kuid_t ns_root_uid; + kgid_t ns_root_gid; + + ns_root_uid = make_kuid(pidns->user_ns, 0); + if (uid_valid(ns_root_uid)) + *uid = ns_root_uid; + + ns_root_gid = make_kgid(pidns->user_ns, 0); + if (gid_valid(ns_root_gid)) + *gid = ns_root_gid; +} + +static struct ctl_table_root pid_table_root = { + .lookup = pid_table_root_lookup, + .permissions = pid_table_root_permissions, + .set_ownership = pid_table_root_set_ownership, +}; + +static struct ctl_table pid_table[] = { + { + .procname = "pid_max", + .data = &init_pid_ns.pid_max, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &pid_max_min, + .extra2 = &pid_max_max, + }, +}; +#endif + +int register_pidns_sysctls(struct pid_namespace *pidns) +{ +#ifdef CONFIG_SYSCTL + struct ctl_table *tbl; + + setup_sysctl_set(&pidns->set, &pid_table_root, set_is_seen); + + tbl = kmemdup(pid_table, sizeof(pid_table), GFP_KERNEL); + if (!tbl) + return -ENOMEM; + tbl->data = &pidns->pid_max; + pidns->pid_max = min(pid_max_max, max_t(int, pidns->pid_max, + PIDS_PER_CPU_DEFAULT * num_possible_cpus())); + + pidns->sysctls = __register_sysctl_table(&pidns->set, "kernel", tbl, + ARRAY_SIZE(pid_table)); + if (!pidns->sysctls) { + kfree(tbl); + retire_sysctl_set(&pidns->set); + return -ENOMEM; + } +#endif + return 0; +} + +void unregister_pidns_sysctls(struct pid_namespace *pidns) +{ +#ifdef CONFIG_SYSCTL + const struct ctl_table *tbl; + + tbl = pidns->sysctls->ctl_table_arg; + unregister_sysctl_table(pidns->sysctls); + retire_sysctl_set(&pidns->set); + kfree(tbl); +#endif +} + void __init pid_idr_init(void) { /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING); /* bump default and minimum pid_max based on number of cpus */ - pid_max = min(pid_max_max, max_t(int, pid_max, - PIDS_PER_CPU_DEFAULT * num_possible_cpus())); + init_pid_ns.pid_max = min(pid_max_max, max_t(int, init_pid_ns.pid_max, + PIDS_PER_CPU_DEFAULT * num_possible_cpus())); pid_max_min = max_t(int, pid_max_min, PIDS_PER_CPU_MIN * num_possible_cpus()); - pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min); + pr_info("pid_max: default: %u minimum: %u\n", init_pid_ns.pid_max, pid_max_min); idr_init(&init_pid_ns.idr); @@ -665,6 +766,16 @@ void __init pid_idr_init(void) NULL); } +static __init int pid_namespace_sysctl_init(void) +{ +#ifdef CONFIG_SYSCTL + /* "kernel" directory will have already been initialized. */ + BUG_ON(register_pidns_sysctls(&init_pid_ns)); +#endif + return 0; +} +subsys_initcall(pid_namespace_sysctl_init); + static struct file *__pidfd_fget(struct task_struct *task, int fd) { struct file *file; diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index d70ab49d5b4a..f1ffa032fc32 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -70,6 +70,8 @@ static void dec_pid_namespaces(struct ucounts *ucounts) dec_ucount(ucounts, UCOUNT_PID_NAMESPACES); } +static void destroy_pid_namespace_work(struct work_struct *work); + static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns, struct pid_namespace *parent_pid_ns) { @@ -105,17 +107,27 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns goto out_free_idr; ns->ns.ops = &pidns_operations; + ns->pid_max = parent_pid_ns->pid_max; + err = register_pidns_sysctls(ns); + if (err) + goto out_free_inum; + refcount_set(&ns->ns.count, 1); ns->level = level; ns->parent = get_pid_ns(parent_pid_ns); ns->user_ns = get_user_ns(user_ns); ns->ucounts = ucounts; ns->pid_allocated = PIDNS_ADDING; + INIT_WORK(&ns->work, destroy_pid_namespace_work); + #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) ns->memfd_noexec_scope = pidns_memfd_noexec_scope(parent_pid_ns); #endif + return ns; +out_free_inum: + ns_free_inum(&ns->ns); out_free_idr: idr_destroy(&ns->idr); kmem_cache_free(pid_ns_cachep, ns); @@ -137,12 +149,28 @@ static void delayed_free_pidns(struct rcu_head *p) static void destroy_pid_namespace(struct pid_namespace *ns) { + unregister_pidns_sysctls(ns); + ns_free_inum(&ns->ns); idr_destroy(&ns->idr); call_rcu(&ns->rcu, delayed_free_pidns); } +static void destroy_pid_namespace_work(struct work_struct *work) +{ + struct pid_namespace *ns = + container_of(work, struct pid_namespace, work); + + do { + struct pid_namespace *parent; + + parent = ns->parent; + destroy_pid_namespace(ns); + ns = parent; + } while (ns != &init_pid_ns && refcount_dec_and_test(&ns->ns.count)); +} + struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *old_ns) { @@ -155,15 +183,8 @@ struct pid_namespace *copy_pid_ns(unsigned long flags, void put_pid_ns(struct pid_namespace *ns) { - struct pid_namespace *parent; - - while (ns != &init_pid_ns) { - parent = ns->parent; - if (!refcount_dec_and_test(&ns->ns.count)) - break; - destroy_pid_namespace(ns); - ns = parent; - } + if (ns && ns != &init_pid_ns && refcount_dec_and_test(&ns->ns.count)) + schedule_work(&ns->work); } EXPORT_SYMBOL_GPL(put_pid_ns); @@ -274,6 +295,7 @@ static int pid_ns_ctl_handler(const struct ctl_table *table, int write, next = idr_get_cursor(&pid_ns->idr) - 1; tmp.data = &next; + tmp.extra2 = &pid_ns->pid_max; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (!ret && write) idr_set_cursor(&pid_ns->idr, next + 1); @@ -281,7 +303,6 @@ static int pid_ns_ctl_handler(const struct ctl_table *table, int write, return ret; } -extern int pid_max; static struct ctl_table pid_ns_ctl_table[] = { { .procname = "ns_last_pid", @@ -289,7 +310,7 @@ static struct ctl_table pid_ns_ctl_table[] = { .mode = 0666, /* permissions are checked in the handler */ .proc_handler = pid_ns_ctl_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &pid_max, + .extra2 = &init_pid_ns.pid_max, }, }; #endif /* CONFIG_CHECKPOINT_RESTORE */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 5c9202cb8f59..7ae7a4136855 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1803,15 +1803,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif - { - .procname = "pid_max", - .data = &pid_max, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &pid_max_min, - .extra2 = &pid_max_max, - }, { .procname = "panic_on_oops", .data = &panic_on_oops, diff --git a/kernel/trace/pid_list.c b/kernel/trace/pid_list.c index 4966e6bbdf6f..c62b9b3cfb3d 100644 --- a/kernel/trace/pid_list.c +++ b/kernel/trace/pid_list.c @@ -414,7 +414,7 @@ struct trace_pid_list *trace_pid_list_alloc(void) int i; /* According to linux/thread.h, pids can be no bigger that 30 bits */ - WARN_ON_ONCE(pid_max > (1 << 30)); + WARN_ON_ONCE(init_pid_ns.pid_max > (1 << 30)); pid_list = kzalloc(sizeof(*pid_list), GFP_KERNEL); if (!pid_list) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 266740b4e121..91def760f364 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -718,8 +718,6 @@ extern unsigned long tracing_thresh; /* PID filtering */ -extern int pid_max; - bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid); bool trace_ignore_this_task(struct trace_pid_list *filtered_pids, diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 573b5d8e8a28..cb49f7279dc8 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -442,7 +442,7 @@ int trace_alloc_tgid_map(void) if (tgid_map) return 0; - tgid_map_max = pid_max; + tgid_map_max = init_pid_ns.pid_max; map = kvcalloc(tgid_map_max + 1, sizeof(*tgid_map), GFP_KERNEL); if (!map) -- cgit v1.2.3 From b28573ebfabeca24757e121566bd143a68097030 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 29 Nov 2024 09:59:33 +0100 Subject: bpf: Remove bpf_probe_write_user() warning message The warning message for bpf_probe_write_user() was introduced in 96ae52279594 ("bpf: Add bpf_probe_write_user BPF helper to be called in tracers"), with the following in the commit message: Given this feature is meant for experiments, and it has a risk of crashing the system, and running programs, we print a warning on when a proglet that attempts to use this helper is installed, along with the pid and process name. After 8 years since 96ae52279594, bpf_probe_write_user() has found successful applications beyond experiments [1, 2], with no other good alternatives. Despite its intended purpose for "experiments", that doesn't stop Hyrum's law, and there are likely many more users depending on this helper: "[..] it does not matter what you promise [..] all observable behaviors of your system will be depended on by somebody." The ominous "helper that may corrupt user memory!" has offered no real benefit, and has been found to lead to confusion where the system administrator is loading programs with valid use cases. As such, remove the warning message. Link: https://lore.kernel.org/lkml/20240404190146.1898103-1-elver@google.com/ [1] Link: https://lore.kernel.org/r/lkml/CAAn3qOUMD81-vxLLfep0H6rRd74ho2VaekdL4HjKq+Y1t9KdXQ@mail.gmail.com/ [2] Link: https://lore.kernel.org/all/CAEf4Bzb4D_=zuJrg3PawMOW3KqF8JvJm9SwF81_XHR2+u5hkUg@mail.gmail.com/ Signed-off-by: Marco Elver Acked-by: Jiri Olsa Acked-by: Daniel Borkmann Link: https://lore.kernel.org/r/20241129090040.2690691-1-elver@google.com Signed-off-by: Alexei Starovoitov --- kernel/trace/bpf_trace.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 949a3870946c..14c27228f7d3 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -362,9 +362,6 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void) if (!capable(CAP_SYS_ADMIN)) return NULL; - pr_warn_ratelimited("%s[%d] is installing a program with bpf_probe_write_user helper that may corrupt user memory!", - current->comm, task_pid_nr(current)); - return &bpf_probe_write_user_proto; } -- cgit v1.2.3 From 3bfb49d73fc281f06c0d976db898debebc8223e3 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 29 Nov 2024 09:59:34 +0100 Subject: bpf: Refactor bpf_tracing_func_proto() and remove bpf_get_probe_write_proto() With bpf_get_probe_write_proto() no longer printing a message, we can avoid it being a special case with its own permission check. Refactor bpf_tracing_func_proto() similar to bpf_base_func_proto() to have a section conditional on bpf_token_capable(CAP_SYS_ADMIN), where the proto for bpf_probe_write_user() is returned. Finally, remove the unnecessary bpf_get_probe_write_proto(). This simplifies the code, and adding additional CAP_SYS_ADMIN-only helpers in future avoids duplicating the same CAP_SYS_ADMIN check. Suggested-by: Andrii Nakryiko Signed-off-by: Marco Elver Acked-by: Jiri Olsa Acked-by: Daniel Borkmann Link: https://lore.kernel.org/r/20241129090040.2690691-2-elver@google.com Signed-off-by: Alexei Starovoitov --- kernel/trace/bpf_trace.c | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 14c27228f7d3..c6946ae19066 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -357,14 +357,6 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = { .arg3_type = ARG_CONST_SIZE, }; -static const struct bpf_func_proto *bpf_get_probe_write_proto(void) -{ - if (!capable(CAP_SYS_ADMIN)) - return NULL; - - return &bpf_probe_write_user_proto; -} - #define MAX_TRACE_PRINTK_VARARGS 3 #define BPF_TRACE_PRINTK_SIZE 1024 @@ -1441,6 +1433,8 @@ late_initcall(bpf_key_sig_kfuncs_init); static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { + const struct bpf_func_proto *func_proto; + switch (func_id) { case BPF_FUNC_map_lookup_elem: return &bpf_map_lookup_elem_proto; @@ -1482,9 +1476,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_read_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; - case BPF_FUNC_probe_write_user: - return security_locked_down(LOCKDOWN_BPF_WRITE_USER) < 0 ? - NULL : bpf_get_probe_write_proto(); case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: @@ -1563,7 +1554,22 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); default: - return bpf_base_func_proto(func_id, prog); + break; + } + + func_proto = bpf_base_func_proto(func_id, prog); + if (func_proto) + return func_proto; + + if (!bpf_token_capable(prog->aux->token, CAP_SYS_ADMIN)) + return NULL; + + switch (func_id) { + case BPF_FUNC_probe_write_user: + return security_locked_down(LOCKDOWN_BPF_WRITE_USER) < 0 ? + NULL : &bpf_probe_write_user_proto; + default: + return NULL; } } -- cgit v1.2.3 From ef1b808e3b7c98612feceedf985c2fbbeb28f956 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 10 Dec 2024 17:32:13 +0100 Subject: bpf: Fix UAF via mismatching bpf_prog/attachment RCU flavors Uprobes always use bpf_prog_run_array_uprobe() under tasks-trace-RCU protection. But it is possible to attach a non-sleepable BPF program to a uprobe, and non-sleepable BPF programs are freed via normal RCU (see __bpf_prog_put_noref()). This leads to UAF of the bpf_prog because a normal RCU grace period does not imply a tasks-trace-RCU grace period. Fix it by explicitly waiting for a tasks-trace-RCU grace period after removing the attachment of a bpf_prog to a perf_event. Fixes: 8c7dcb84e3b7 ("bpf: implement sleepable uprobes by chaining gps") Suggested-by: Andrii Nakryiko Suggested-by: Alexei Starovoitov Signed-off-by: Jann Horn Signed-off-by: Andrii Nakryiko Cc: stable@vger.kernel.org Link: https://lore.kernel.org/bpf/20241210-bpf-fix-actual-uprobe-uaf-v1-1-19439849dd44@google.com --- kernel/trace/bpf_trace.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 949a3870946c..a403b05a7091 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2258,6 +2258,13 @@ void perf_event_detach_bpf_prog(struct perf_event *event) bpf_prog_array_free_sleepable(old_array); } + /* + * It could be that the bpf_prog is not sleepable (and will be freed + * via normal RCU), but is called from a point that supports sleepable + * programs and uses tasks-trace-RCU. + */ + synchronize_rcu_tasks_trace(); + bpf_prog_put(event->prog); event->prog = NULL; -- cgit v1.2.3 From 978c4486cca5c7b9253d3ab98a88c8e769cb9bbd Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 8 Dec 2024 15:25:07 +0100 Subject: bpf,perf: Fix invalid prog_array access in perf_event_detach_bpf_prog Syzbot reported [1] crash that happens for following tracing scenario: - create tracepoint perf event with attr.inherit=1, attach it to the process and set bpf program to it - attached process forks -> chid creates inherited event the new child event shares the parent's bpf program and tp_event (hence prog_array) which is global for tracepoint - exit both process and its child -> release both events - first perf_event_detach_bpf_prog call will release tp_event->prog_array and second perf_event_detach_bpf_prog will crash, because tp_event->prog_array is NULL The fix makes sure the perf_event_detach_bpf_prog checks prog_array is valid before it tries to remove the bpf program from it. [1] https://lore.kernel.org/bpf/Z1MR6dCIKajNS6nU@krava/T/#m91dbf0688221ec7a7fc95e896a7ef9ff93b0b8ad Fixes: 0ee288e69d03 ("bpf,perf: Fix perf_event_detach_bpf_prog error handling") Reported-by: syzbot+2e0d2840414ce817aaac@syzkaller.appspotmail.com Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20241208142507.1207698-1-jolsa@kernel.org --- kernel/trace/bpf_trace.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index a403b05a7091..1b8db5aee9d3 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2250,6 +2250,9 @@ void perf_event_detach_bpf_prog(struct perf_event *event) goto unlock; old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); + if (!old_array) + goto put; + ret = bpf_prog_array_copy(old_array, event->prog, NULL, 0, &new_array); if (ret < 0) { bpf_prog_array_delete_safe(old_array, event->prog); @@ -2258,6 +2261,7 @@ void perf_event_detach_bpf_prog(struct perf_event *event) bpf_prog_array_free_sleepable(old_array); } +put: /* * It could be that the bpf_prog is not sleepable (and will be freed * via normal RCU), but is called from a point that supports sleepable -- cgit v1.2.3 From 7d0d673627e20cfa3b21a829a896ce03b58a4f1c Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 10 Dec 2024 20:08:14 +0100 Subject: bpf: Fix theoretical prog_array UAF in __uprobe_perf_func() Currently, the pointer stored in call->prog_array is loaded in __uprobe_perf_func(), with no RCU annotation and no immediately visible RCU protection, so it looks as if the loaded pointer can immediately be dangling. Later, bpf_prog_run_array_uprobe() starts a RCU-trace read-side critical section, but this is too late. It then uses rcu_dereference_check(), but this use of rcu_dereference_check() does not actually dereference anything. Fix it by aligning the semantics to bpf_prog_run_array(): Let the caller provide rcu_read_lock_trace() protection and then load call->prog_array with rcu_dereference_check(). This issue seems to be theoretical: I don't know of any way to reach this code without having handle_swbp() further up the stack, which is already holding a rcu_read_lock_trace() lock, so where we take rcu_read_lock_trace() in __uprobe_perf_func()/bpf_prog_run_array_uprobe() doesn't actually have any effect. Fixes: 8c7dcb84e3b7 ("bpf: implement sleepable uprobes by chaining gps") Suggested-by: Andrii Nakryiko Signed-off-by: Jann Horn Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20241210-bpf-fix-uprobe-uaf-v4-1-5fc8959b2b74@google.com --- include/linux/bpf.h | 13 +++++-------- kernel/trace/trace_uprobe.c | 6 +++++- 2 files changed, 10 insertions(+), 9 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index fe392d074973..805040813f5d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2194,26 +2194,25 @@ bpf_prog_run_array(const struct bpf_prog_array *array, * rcu-protected dynamically sized maps. */ static __always_inline u32 -bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu, +bpf_prog_run_array_uprobe(const struct bpf_prog_array *array, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; - const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; might_fault(); + RCU_LOCKDEP_WARN(!rcu_read_lock_trace_held(), "no rcu lock held"); + + if (unlikely(!array)) + return ret; - rcu_read_lock_trace(); migrate_disable(); run_ctx.is_uprobe = true; - array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held()); - if (unlikely(!array)) - goto out; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { @@ -2228,9 +2227,7 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu, rcu_read_unlock(); } bpf_reset_run_ctx(old_run_ctx); -out: migrate_enable(); - rcu_read_unlock_trace(); return ret; } diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index fed382b7881b..4875e7f5de3d 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1402,9 +1402,13 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, #ifdef CONFIG_BPF_EVENTS if (bpf_prog_array_valid(call)) { + const struct bpf_prog_array *array; u32 ret; - ret = bpf_prog_run_array_uprobe(call->prog_array, regs, bpf_prog_run); + rcu_read_lock_trace(); + array = rcu_dereference_check(call->prog_array, rcu_read_lock_trace_held()); + ret = bpf_prog_run_array_uprobe(array, regs, bpf_prog_run); + rcu_read_unlock_trace(); if (!ret) return; } -- cgit v1.2.3 From cc252bb592638e0f7aea40d580186c36d89526b8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 11 Dec 2024 13:53:35 -0500 Subject: fgraph: Still initialize idle shadow stacks when starting A bug was discovered where the idle shadow stacks were not initialized for offline CPUs when starting function graph tracer, and when they came online they were not traced due to the missing shadow stack. To fix this, the idle task shadow stack initialization was moved to using the CPU hotplug callbacks. But it removed the initialization when the function graph was enabled. The problem here is that the hotplug callbacks are called when the CPUs come online, but the idle shadow stack initialization only happens if function graph is currently active. This caused the online CPUs to not get their shadow stack initialized. The idle shadow stack initialization still needs to be done when the function graph is registered, as they will not be allocated if function graph is not registered. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20241211135335.094ba282@batman.local.home Fixes: 2c02f7375e65 ("fgraph: Use CPU hotplug mechanism to initialize idle shadow stacks") Reported-by: Linus Walleij Tested-by: Linus Walleij Closes: https://lore.kernel.org/all/CACRpkdaTBrHwRbbrphVy-=SeDz6MSsXhTKypOtLrTQ+DgGAOcQ@mail.gmail.com/ Signed-off-by: Steven Rostedt (Google) --- kernel/trace/fgraph.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 0bf78517b5d4..ddedcb50917f 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -1215,7 +1215,7 @@ void fgraph_update_pid_func(void) static int start_graph_tracing(void) { unsigned long **ret_stack_list; - int ret; + int ret, cpu; ret_stack_list = kcalloc(FTRACE_RETSTACK_ALLOC_SIZE, sizeof(*ret_stack_list), GFP_KERNEL); @@ -1223,6 +1223,12 @@ static int start_graph_tracing(void) if (!ret_stack_list) return -ENOMEM; + /* The cpu_boot init_task->ret_stack will never be freed */ + for_each_online_cpu(cpu) { + if (!idle_task(cpu)->ret_stack) + ftrace_graph_init_idle_task(idle_task(cpu), cpu); + } + do { ret = alloc_retstack_tasklist(ret_stack_list); } while (ret == -EAGAIN); -- cgit v1.2.3 From 166438a432d76c68d3f0da60667248f3c2303d6c Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 16 Dec 2024 16:46:33 -0500 Subject: ftrace: Do not find "true_parent" if HAVE_DYNAMIC_FTRACE_WITH_ARGS is not set When function tracing and function graph tracing are both enabled (in different instances) the "parent" of some of the function tracing events is "return_to_handler" which is the trampoline used by function graph tracing. To fix this, ftrace_get_true_parent_ip() was introduced that returns the "true" parent ip instead of the trampoline. To do this, the ftrace_regs_get_stack_pointer() is used, which uses kernel_stack_pointer(). The problem is that microblaze does not implement kerenl_stack_pointer() so when function graph tracing is enabled, the build fails. But microblaze also does not enabled HAVE_DYNAMIC_FTRACE_WITH_ARGS. That option has to be enabled by the architecture to reliably get the values from the fregs parameter passed in. When that config is not set, the architecture can also pass in NULL, which is not tested for in that function and could cause the kernel to crash. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Mark Rutland Cc: Al Viro Cc: Michal Simek Cc: Jeff Xie Link: https://lore.kernel.org/20241216164633.6df18e87@gandalf.local.home Fixes: 60b1f578b578 ("ftrace: Get the true parent ip for function tracer") Reported-by: Al Viro Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_functions.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 74c353164ca1..d358c9935164 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -176,7 +176,8 @@ static void function_trace_start(struct trace_array *tr) tracing_reset_online_cpus(&tr->array_buffer); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER +/* fregs are guaranteed not to be NULL if HAVE_DYNAMIC_FTRACE_WITH_ARGS is set */ +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) static __always_inline unsigned long function_get_true_parent_ip(unsigned long parent_ip, struct ftrace_regs *fregs) { -- cgit v1.2.3 From a6629626c584200daf495cc9a740048b455addcd Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 16 Dec 2024 21:41:19 -0500 Subject: tracing: Fix test_event_printk() to process entire print argument The test_event_printk() analyzes print formats of trace events looking for cases where it may dereference a pointer that is not in the ring buffer which can possibly be a bug when the trace event is read from the ring buffer and the content of that pointer no longer exists. The function needs to accurately go from one print format argument to the next. It handles quotes and parenthesis that may be included in an argument. When it finds the start of the next argument, it uses a simple "c = strstr(fmt + i, ',')" to find the end of that argument! In order to include "%s" dereferencing, it needs to process the entire content of the print format argument and not just the content of the first ',' it finds. As there may be content like: ({ const char *saved_ptr = trace_seq_buffer_ptr(p); static const char *access_str[] = { "---", "--x", "w--", "w-x", "-u-", "-ux", "wu-", "wux" }; union kvm_mmu_page_role role; role.word = REC->role; trace_seq_printf(p, "sp gen %u gfn %llx l%u %u-byte q%u%s %s%s" " %snxe %sad root %u %s%c", REC->mmu_valid_gen, REC->gfn, role.level, role.has_4_byte_gpte ? 4 : 8, role.quadrant, role.direct ? " direct" : "", access_str[role.access], role.invalid ? " invalid" : "", role.efer_nx ? "" : "!", role.ad_disabled ? "!" : "", REC->root_count, REC->unsync ? "unsync" : "sync", 0); saved_ptr; }) Which is an example of a full argument of an existing event. As the code already handles finding the next print format argument, process the argument at the end of it and not the start of it. This way it has both the start of the argument as well as the end of it. Add a helper function "process_pointer()" that will do the processing during the loop as well as at the end. It also makes the code cleaner and easier to read. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Al Viro Cc: Linus Torvalds Link: https://lore.kernel.org/20241217024720.362271189@goodmis.org Fixes: 5013f454a352c ("tracing: Add check of trace event print fmts for dereferencing pointers") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 82 +++++++++++++++++++++++++++++---------------- 1 file changed, 53 insertions(+), 29 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 77e68efbd43e..14e160a5b905 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -265,8 +265,7 @@ static bool test_field(const char *fmt, struct trace_event_call *call) len = p - fmt; for (; field->type; field++) { - if (strncmp(field->name, fmt, len) || - field->name[len]) + if (strncmp(field->name, fmt, len) || field->name[len]) continue; array_descriptor = strchr(field->type, '['); /* This is an array and is OK to dereference. */ @@ -275,6 +274,32 @@ static bool test_field(const char *fmt, struct trace_event_call *call) return false; } +/* Return true if the argument pointer is safe */ +static bool process_pointer(const char *fmt, int len, struct trace_event_call *call) +{ + const char *r, *e, *a; + + e = fmt + len; + + /* Find the REC-> in the argument */ + r = strstr(fmt, "REC->"); + if (r && r < e) { + /* + * Addresses of events on the buffer, or an array on the buffer is + * OK to dereference. There's ways to fool this, but + * this is to catch common mistakes, not malicious code. + */ + a = strchr(fmt, '&'); + if ((a && (a < r)) || test_field(r, call)) + return true; + } else if ((r = strstr(fmt, "__get_dynamic_array(")) && r < e) { + return true; + } else if ((r = strstr(fmt, "__get_sockaddr(")) && r < e) { + return true; + } + return false; +} + /* * Examine the print fmt of the event looking for unsafe dereference * pointers using %p* that could be recorded in the trace event and @@ -285,12 +310,12 @@ static void test_event_printk(struct trace_event_call *call) { u64 dereference_flags = 0; bool first = true; - const char *fmt, *c, *r, *a; + const char *fmt; int parens = 0; char in_quote = 0; int start_arg = 0; int arg = 0; - int i; + int i, e; fmt = call->print_fmt; @@ -403,42 +428,41 @@ static void test_event_printk(struct trace_event_call *call) case ',': if (in_quote || parens) continue; + e = i; i++; while (isspace(fmt[i])) i++; - start_arg = i; - if (!(dereference_flags & (1ULL << arg))) - goto next_arg; - /* Find the REC-> in the argument */ - c = strchr(fmt + i, ','); - r = strstr(fmt + i, "REC->"); - if (r && (!c || r < c)) { - /* - * Addresses of events on the buffer, - * or an array on the buffer is - * OK to dereference. - * There's ways to fool this, but - * this is to catch common mistakes, - * not malicious code. - */ - a = strchr(fmt + i, '&'); - if ((a && (a < r)) || test_field(r, call)) + /* + * If start_arg is zero, then this is the start of the + * first argument. The processing of the argument happens + * when the end of the argument is found, as it needs to + * handle paranthesis and such. + */ + if (!start_arg) { + start_arg = i; + /* Balance out the i++ in the for loop */ + i--; + continue; + } + + if (dereference_flags & (1ULL << arg)) { + if (process_pointer(fmt + start_arg, e - start_arg, call)) dereference_flags &= ~(1ULL << arg); - } else if ((r = strstr(fmt + i, "__get_dynamic_array(")) && - (!c || r < c)) { - dereference_flags &= ~(1ULL << arg); - } else if ((r = strstr(fmt + i, "__get_sockaddr(")) && - (!c || r < c)) { - dereference_flags &= ~(1ULL << arg); } - next_arg: - i--; + start_arg = i; arg++; + /* Balance out the i++ in the for loop */ + i--; } } + if (dereference_flags & (1ULL << arg)) { + if (process_pointer(fmt + start_arg, i - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } + /* * If you triggered the below warning, the trace event reported * uses an unsafe dereference pointer %p*. As the data stored -- cgit v1.2.3 From 917110481f6bc1c96b1e54b62bb114137fbc6d17 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 16 Dec 2024 21:41:20 -0500 Subject: tracing: Add missing helper functions in event pointer dereference check The process_pointer() helper function looks to see if various trace event macros are used. These macros are for storing data in the event. This makes it safe to dereference as the dereference will then point into the event on the ring buffer where the content of the data stays with the event itself. A few helper functions were missing. Those were: __get_rel_dynamic_array() __get_dynamic_array_len() __get_rel_dynamic_array_len() __get_rel_sockaddr() Also add a helper function find_print_string() to not need to use a middle man variable to test if the string exists. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Al Viro Cc: Linus Torvalds Link: https://lore.kernel.org/20241217024720.521836792@goodmis.org Fixes: 5013f454a352c ("tracing: Add check of trace event print fmts for dereferencing pointers") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 14e160a5b905..df75c06bb23f 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -274,6 +274,15 @@ static bool test_field(const char *fmt, struct trace_event_call *call) return false; } +/* Look for a string within an argument */ +static bool find_print_string(const char *arg, const char *str, const char *end) +{ + const char *r; + + r = strstr(arg, str); + return r && r < end; +} + /* Return true if the argument pointer is safe */ static bool process_pointer(const char *fmt, int len, struct trace_event_call *call) { @@ -292,9 +301,17 @@ static bool process_pointer(const char *fmt, int len, struct trace_event_call *c a = strchr(fmt, '&'); if ((a && (a < r)) || test_field(r, call)) return true; - } else if ((r = strstr(fmt, "__get_dynamic_array(")) && r < e) { + } else if (find_print_string(fmt, "__get_dynamic_array(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_dynamic_array(", e)) { + return true; + } else if (find_print_string(fmt, "__get_dynamic_array_len(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_dynamic_array_len(", e)) { + return true; + } else if (find_print_string(fmt, "__get_sockaddr(", e)) { return true; - } else if ((r = strstr(fmt, "__get_sockaddr(")) && r < e) { + } else if (find_print_string(fmt, "__get_rel_sockaddr(", e)) { return true; } return false; -- cgit v1.2.3 From 65a25d9f7ac02e0cf361356e834d1c71d36acca9 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 16 Dec 2024 21:41:21 -0500 Subject: tracing: Add "%s" check in test_event_printk() The test_event_printk() code makes sure that when a trace event is registered, any dereferenced pointers in from the event's TP_printk() are pointing to content in the ring buffer. But currently it does not handle "%s", as there's cases where the string pointer saved in the ring buffer points to a static string in the kernel that will never be freed. As that is a valid case, the pointer needs to be checked at runtime. Currently the runtime check is done via trace_check_vprintf(), but to not have to replicate everything in vsnprintf() it does some logic with the va_list that may not be reliable across architectures. In order to get rid of that logic, more work in the test_event_printk() needs to be done. Some of the strings can be validated at this time when it is obvious the string is valid because the string will be saved in the ring buffer content. Do all the validation of strings in the ring buffer at boot in test_event_printk(), and make sure that the field of the strings that point into the kernel are accessible. This will allow adding checks at runtime that will validate the fields themselves and not rely on paring the TP_printk() format at runtime. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Al Viro Cc: Linus Torvalds Link: https://lore.kernel.org/20241217024720.685917008@goodmis.org Fixes: 5013f454a352c ("tracing: Add check of trace event print fmts for dereferencing pointers") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 104 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 89 insertions(+), 15 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index df75c06bb23f..521ad2fd1fe7 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -244,19 +244,16 @@ int trace_event_get_offsets(struct trace_event_call *call) return tail->offset + tail->size; } -/* - * Check if the referenced field is an array and return true, - * as arrays are OK to dereference. - */ -static bool test_field(const char *fmt, struct trace_event_call *call) + +static struct trace_event_fields *find_event_field(const char *fmt, + struct trace_event_call *call) { struct trace_event_fields *field = call->class->fields_array; - const char *array_descriptor; const char *p = fmt; int len; if (!(len = str_has_prefix(fmt, "REC->"))) - return false; + return NULL; fmt += len; for (p = fmt; *p; p++) { if (!isalnum(*p) && *p != '_') @@ -267,11 +264,26 @@ static bool test_field(const char *fmt, struct trace_event_call *call) for (; field->type; field++) { if (strncmp(field->name, fmt, len) || field->name[len]) continue; - array_descriptor = strchr(field->type, '['); - /* This is an array and is OK to dereference. */ - return array_descriptor != NULL; + + return field; } - return false; + return NULL; +} + +/* + * Check if the referenced field is an array and return true, + * as arrays are OK to dereference. + */ +static bool test_field(const char *fmt, struct trace_event_call *call) +{ + struct trace_event_fields *field; + + field = find_event_field(fmt, call); + if (!field) + return false; + + /* This is an array and is OK to dereference. */ + return strchr(field->type, '[') != NULL; } /* Look for a string within an argument */ @@ -317,6 +329,53 @@ static bool process_pointer(const char *fmt, int len, struct trace_event_call *c return false; } +/* Return true if the string is safe */ +static bool process_string(const char *fmt, int len, struct trace_event_call *call) +{ + const char *r, *e, *s; + + e = fmt + len; + + /* + * There are several helper functions that return strings. + * If the argument contains a function, then assume its field is valid. + * It is considered that the argument has a function if it has: + * alphanumeric or '_' before a parenthesis. + */ + s = fmt; + do { + r = strstr(s, "("); + if (!r || r >= e) + break; + for (int i = 1; r - i >= s; i++) { + char ch = *(r - i); + if (isspace(ch)) + continue; + if (isalnum(ch) || ch == '_') + return true; + /* Anything else, this isn't a function */ + break; + } + /* A function could be wrapped in parethesis, try the next one */ + s = r + 1; + } while (s < e); + + /* + * If there's any strings in the argument consider this arg OK as it + * could be: REC->field ? "foo" : "bar" and we don't want to get into + * verifying that logic here. + */ + if (find_print_string(fmt, "\"", e)) + return true; + + /* Dereferenced strings are also valid like any other pointer */ + if (process_pointer(fmt, len, call)) + return true; + + /* Make sure the field is found, and consider it OK for now if it is */ + return find_event_field(fmt, call) != NULL; +} + /* * Examine the print fmt of the event looking for unsafe dereference * pointers using %p* that could be recorded in the trace event and @@ -326,6 +385,7 @@ static bool process_pointer(const char *fmt, int len, struct trace_event_call *c static void test_event_printk(struct trace_event_call *call) { u64 dereference_flags = 0; + u64 string_flags = 0; bool first = true; const char *fmt; int parens = 0; @@ -416,8 +476,16 @@ static void test_event_printk(struct trace_event_call *call) star = true; continue; } - if ((fmt[i + j] == 's') && star) - arg++; + if ((fmt[i + j] == 's')) { + if (star) + arg++; + if (WARN_ONCE(arg == 63, + "Too many args for event: %s", + trace_event_name(call))) + return; + dereference_flags |= 1ULL << arg; + string_flags |= 1ULL << arg; + } break; } break; @@ -464,7 +532,10 @@ static void test_event_printk(struct trace_event_call *call) } if (dereference_flags & (1ULL << arg)) { - if (process_pointer(fmt + start_arg, e - start_arg, call)) + if (string_flags & (1ULL << arg)) { + if (process_string(fmt + start_arg, e - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } else if (process_pointer(fmt + start_arg, e - start_arg, call)) dereference_flags &= ~(1ULL << arg); } @@ -476,7 +547,10 @@ static void test_event_printk(struct trace_event_call *call) } if (dereference_flags & (1ULL << arg)) { - if (process_pointer(fmt + start_arg, i - start_arg, call)) + if (string_flags & (1ULL << arg)) { + if (process_string(fmt + start_arg, i - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } else if (process_pointer(fmt + start_arg, i - start_arg, call)) dereference_flags &= ~(1ULL << arg); } -- cgit v1.2.3 From afd2627f727b89496d79a6b934a025fc916d4ded Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 16 Dec 2024 21:41:22 -0500 Subject: tracing: Check "%s" dereference via the field and not the TP_printk format The TP_printk() portion of a trace event is executed at the time a event is read from the trace. This can happen seconds, minutes, hours, days, months, years possibly later since the event was recorded. If the print format contains a dereference to a string via "%s", and that string was allocated, there's a chance that string could be freed before it is read by the trace file. To protect against such bugs, there are two functions that verify the event. The first one is test_event_printk(), which is called when the event is created. It reads the TP_printk() format as well as its arguments to make sure nothing may be dereferencing a pointer that was not copied into the ring buffer along with the event. If it is, it will trigger a WARN_ON(). For strings that use "%s", it is not so easy. The string may not reside in the ring buffer but may still be valid. Strings that are static and part of the kernel proper which will not be freed for the life of the running system, are safe to dereference. But to know if it is a pointer to a static string or to something on the heap can not be determined until the event is triggered. This brings us to the second function that tests for the bad dereferencing of strings, trace_check_vprintf(). It would walk through the printf format looking for "%s", and when it finds it, it would validate that the pointer is safe to read. If not, it would produces a WARN_ON() as well and write into the ring buffer "[UNSAFE-MEMORY]". The problem with this is how it used va_list to have vsnprintf() handle all the cases that it didn't need to check. Instead of re-implementing vsnprintf(), it would make a copy of the format up to the %s part, and call vsnprintf() with the current va_list ap variable, where the ap would then be ready to point at the string in question. For architectures that passed va_list by reference this was possible. For architectures that passed it by copy it was not. A test_can_verify() function was used to differentiate between the two, and if it wasn't possible, it would disable it. Even for architectures where this was feasible, it was a stretch to rely on such a method that is undocumented, and could cause issues later on with new optimizations of the compiler. Instead, the first function test_event_printk() was updated to look at "%s" as well. If the "%s" argument is a pointer outside the event in the ring buffer, it would find the field type of the event that is the problem and mark the structure with a new flag called "needs_test". The event itself will be marked by TRACE_EVENT_FL_TEST_STR to let it be known that this event has a field that needs to be verified before the event can be printed using the printf format. When the event fields are created from the field type structure, the fields would copy the field type's "needs_test" value. Finally, before being printed, a new function ignore_event() is called which will check if the event has the TEST_STR flag set (if not, it returns false). If the flag is set, it then iterates through the events fields looking for the ones that have the "needs_test" flag set. Then it uses the offset field from the field structure to find the pointer in the ring buffer event. It runs the tests to make sure that pointer is safe to print and if not, it triggers the WARN_ON() and also adds to the trace output that the event in question has an unsafe memory access. The ignore_event() makes the trace_check_vprintf() obsolete so it is removed. Link: https://lore.kernel.org/all/CAHk-=wh3uOnqnZPpR0PeLZZtyWbZLboZ7cHLCKRWsocvs9Y7hQ@mail.gmail.com/ Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Al Viro Cc: Linus Torvalds Link: https://lore.kernel.org/20241217024720.848621576@goodmis.org Fixes: 5013f454a352c ("tracing: Add check of trace event print fmts for dereferencing pointers") Signed-off-by: Steven Rostedt (Google) --- include/linux/trace_events.h | 6 +- kernel/trace/trace.c | 255 +++++++++---------------------------------- kernel/trace/trace.h | 6 +- kernel/trace/trace_events.c | 32 ++++-- kernel/trace/trace_output.c | 6 +- 5 files changed, 88 insertions(+), 217 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 2a5df5b62cfc..91b8ffbdfa8c 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -273,7 +273,8 @@ struct trace_event_fields { const char *name; const int size; const int align; - const int is_signed; + const unsigned int is_signed:1; + unsigned int needs_test:1; const int filter_type; const int len; }; @@ -324,6 +325,7 @@ enum { TRACE_EVENT_FL_EPROBE_BIT, TRACE_EVENT_FL_FPROBE_BIT, TRACE_EVENT_FL_CUSTOM_BIT, + TRACE_EVENT_FL_TEST_STR_BIT, }; /* @@ -340,6 +342,7 @@ enum { * CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint) * This is set when the custom event has not been attached * to a tracepoint yet, then it is cleared when it is. + * TEST_STR - The event has a "%s" that points to a string outside the event */ enum { TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), @@ -352,6 +355,7 @@ enum { TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT), TRACE_EVENT_FL_FPROBE = (1 << TRACE_EVENT_FL_FPROBE_BIT), TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT), + TRACE_EVENT_FL_TEST_STR = (1 << TRACE_EVENT_FL_TEST_STR_BIT), }; #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index be62f0ea1814..7cc18b9bce27 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3611,17 +3611,12 @@ char *trace_iter_expand_format(struct trace_iterator *iter) } /* Returns true if the string is safe to dereference from an event */ -static bool trace_safe_str(struct trace_iterator *iter, const char *str, - bool star, int len) +static bool trace_safe_str(struct trace_iterator *iter, const char *str) { unsigned long addr = (unsigned long)str; struct trace_event *trace_event; struct trace_event_call *event; - /* Ignore strings with no length */ - if (star && !len) - return true; - /* OK if part of the event data */ if ((addr >= (unsigned long)iter->ent) && (addr < (unsigned long)iter->ent + iter->ent_size)) @@ -3661,181 +3656,69 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str, return false; } -static DEFINE_STATIC_KEY_FALSE(trace_no_verify); - -static int test_can_verify_check(const char *fmt, ...) -{ - char buf[16]; - va_list ap; - int ret; - - /* - * The verifier is dependent on vsnprintf() modifies the va_list - * passed to it, where it is sent as a reference. Some architectures - * (like x86_32) passes it by value, which means that vsnprintf() - * does not modify the va_list passed to it, and the verifier - * would then need to be able to understand all the values that - * vsnprintf can use. If it is passed by value, then the verifier - * is disabled. - */ - va_start(ap, fmt); - vsnprintf(buf, 16, "%d", ap); - ret = va_arg(ap, int); - va_end(ap); - - return ret; -} - -static void test_can_verify(void) -{ - if (!test_can_verify_check("%d %d", 0, 1)) { - pr_info("trace event string verifier disabled\n"); - static_branch_inc(&trace_no_verify); - } -} - /** - * trace_check_vprintf - Check dereferenced strings while writing to the seq buffer + * ignore_event - Check dereferenced fields while writing to the seq buffer * @iter: The iterator that holds the seq buffer and the event being printed - * @fmt: The format used to print the event - * @ap: The va_list holding the data to print from @fmt. * - * This writes the data into the @iter->seq buffer using the data from - * @fmt and @ap. If the format has a %s, then the source of the string - * is examined to make sure it is safe to print, otherwise it will - * warn and print "[UNSAFE MEMORY]" in place of the dereferenced string - * pointer. + * At boot up, test_event_printk() will flag any event that dereferences + * a string with "%s" that does exist in the ring buffer. It may still + * be valid, as the string may point to a static string in the kernel + * rodata that never gets freed. But if the string pointer is pointing + * to something that was allocated, there's a chance that it can be freed + * by the time the user reads the trace. This would cause a bad memory + * access by the kernel and possibly crash the system. + * + * This function will check if the event has any fields flagged as needing + * to be checked at runtime and perform those checks. + * + * If it is found that a field is unsafe, it will write into the @iter->seq + * a message stating what was found to be unsafe. + * + * @return: true if the event is unsafe and should be ignored, + * false otherwise. */ -void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, - va_list ap) +bool ignore_event(struct trace_iterator *iter) { - long text_delta = 0; - long data_delta = 0; - const char *p = fmt; - const char *str; - bool good; - int i, j; + struct ftrace_event_field *field; + struct trace_event *trace_event; + struct trace_event_call *event; + struct list_head *head; + struct trace_seq *seq; + const void *ptr; - if (WARN_ON_ONCE(!fmt)) - return; + trace_event = ftrace_find_event(iter->ent->type); - if (static_branch_unlikely(&trace_no_verify)) - goto print; + seq = &iter->seq; - /* - * When the kernel is booted with the tp_printk command line - * parameter, trace events go directly through to printk(). - * It also is checked by this function, but it does not - * have an associated trace_array (tr) for it. - */ - if (iter->tr) { - text_delta = iter->tr->text_delta; - data_delta = iter->tr->data_delta; + if (!trace_event) { + trace_seq_printf(seq, "EVENT ID %d NOT FOUND?\n", iter->ent->type); + return true; } - /* Don't bother checking when doing a ftrace_dump() */ - if (iter->fmt == static_fmt_buf) - goto print; - - while (*p) { - bool star = false; - int len = 0; - - j = 0; - - /* - * We only care about %s and variants - * as well as %p[sS] if delta is non-zero - */ - for (i = 0; p[i]; i++) { - if (i + 1 >= iter->fmt_size) { - /* - * If we can't expand the copy buffer, - * just print it. - */ - if (!trace_iter_expand_format(iter)) - goto print; - } - - if (p[i] == '\\' && p[i+1]) { - i++; - continue; - } - if (p[i] == '%') { - /* Need to test cases like %08.*s */ - for (j = 1; p[i+j]; j++) { - if (isdigit(p[i+j]) || - p[i+j] == '.') - continue; - if (p[i+j] == '*') { - star = true; - continue; - } - break; - } - if (p[i+j] == 's') - break; - - if (text_delta && p[i+1] == 'p' && - ((p[i+2] == 's' || p[i+2] == 'S'))) - break; - - star = false; - } - j = 0; - } - /* If no %s found then just print normally */ - if (!p[i]) - break; - - /* Copy up to the %s, and print that */ - strncpy(iter->fmt, p, i); - iter->fmt[i] = '\0'; - trace_seq_vprintf(&iter->seq, iter->fmt, ap); + event = container_of(trace_event, struct trace_event_call, event); + if (!(event->flags & TRACE_EVENT_FL_TEST_STR)) + return false; - /* Add delta to %pS pointers */ - if (p[i+1] == 'p') { - unsigned long addr; - char fmt[4]; + head = trace_get_fields(event); + if (!head) { + trace_seq_printf(seq, "FIELDS FOR EVENT '%s' NOT FOUND?\n", + trace_event_name(event)); + return true; + } - fmt[0] = '%'; - fmt[1] = 'p'; - fmt[2] = p[i+2]; /* Either %ps or %pS */ - fmt[3] = '\0'; + /* Offsets are from the iter->ent that points to the raw event */ + ptr = iter->ent; - addr = va_arg(ap, unsigned long); - addr += text_delta; - trace_seq_printf(&iter->seq, fmt, (void *)addr); + list_for_each_entry(field, head, link) { + const char *str; + bool good; - p += i + 3; + if (!field->needs_test) continue; - } - /* - * If iter->seq is full, the above call no longer guarantees - * that ap is in sync with fmt processing, and further calls - * to va_arg() can return wrong positional arguments. - * - * Ensure that ap is no longer used in this case. - */ - if (iter->seq.full) { - p = ""; - break; - } - - if (star) - len = va_arg(ap, int); - - /* The ap now points to the string data of the %s */ - str = va_arg(ap, const char *); + str = *(const char **)(ptr + field->offset); - good = trace_safe_str(iter, str, star, len); - - /* Could be from the last boot */ - if (data_delta && !good) { - str += data_delta; - good = trace_safe_str(iter, str, star, len); - } + good = trace_safe_str(iter, str); /* * If you hit this warning, it is likely that the @@ -3846,44 +3729,14 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, * instead. See samples/trace_events/trace-events-sample.h * for reference. */ - if (WARN_ONCE(!good, "fmt: '%s' current_buffer: '%s'", - fmt, seq_buf_str(&iter->seq.seq))) { - int ret; - - /* Try to safely read the string */ - if (star) { - if (len + 1 > iter->fmt_size) - len = iter->fmt_size - 1; - if (len < 0) - len = 0; - ret = copy_from_kernel_nofault(iter->fmt, str, len); - iter->fmt[len] = 0; - star = false; - } else { - ret = strncpy_from_kernel_nofault(iter->fmt, str, - iter->fmt_size); - } - if (ret < 0) - trace_seq_printf(&iter->seq, "(0x%px)", str); - else - trace_seq_printf(&iter->seq, "(0x%px:%s)", - str, iter->fmt); - str = "[UNSAFE-MEMORY]"; - strcpy(iter->fmt, "%s"); - } else { - strncpy(iter->fmt, p + i, j + 1); - iter->fmt[j+1] = '\0'; + if (WARN_ONCE(!good, "event '%s' has unsafe pointer field '%s'", + trace_event_name(event), field->name)) { + trace_seq_printf(seq, "EVENT %s: HAS UNSAFE POINTER FIELD '%s'\n", + trace_event_name(event), field->name); + return true; } - if (star) - trace_seq_printf(&iter->seq, iter->fmt, len, str); - else - trace_seq_printf(&iter->seq, iter->fmt, str); - - p += i + j + 1; } - print: - if (*p) - trace_seq_vprintf(&iter->seq, p, ap); + return false; } const char *trace_event_format(struct trace_iterator *iter, const char *fmt) @@ -10777,8 +10630,6 @@ __init static int tracer_alloc_buffers(void) register_snapshot_cmd(); - test_can_verify(); - return 0; out_free_pipe_cpumask: diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 266740b4e121..9691b47b5f3d 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -667,9 +667,8 @@ void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, bool trace_is_tracepoint_string(const char *str); const char *trace_event_format(struct trace_iterator *iter, const char *fmt); -void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, - va_list ap) __printf(2, 0); char *trace_iter_expand_format(struct trace_iterator *iter); +bool ignore_event(struct trace_iterator *iter); int trace_empty(struct trace_iterator *iter); @@ -1413,7 +1412,8 @@ struct ftrace_event_field { int filter_type; int offset; int size; - int is_signed; + unsigned int is_signed:1; + unsigned int needs_test:1; int len; }; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 521ad2fd1fe7..1545cc8b49d0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -82,7 +82,7 @@ static int system_refcount_dec(struct event_subsystem *system) } static struct ftrace_event_field * -__find_event_field(struct list_head *head, char *name) +__find_event_field(struct list_head *head, const char *name) { struct ftrace_event_field *field; @@ -114,7 +114,8 @@ trace_find_event_field(struct trace_event_call *call, char *name) static int __trace_define_field(struct list_head *head, const char *type, const char *name, int offset, int size, - int is_signed, int filter_type, int len) + int is_signed, int filter_type, int len, + int need_test) { struct ftrace_event_field *field; @@ -133,6 +134,7 @@ static int __trace_define_field(struct list_head *head, const char *type, field->offset = offset; field->size = size; field->is_signed = is_signed; + field->needs_test = need_test; field->len = len; list_add(&field->link, head); @@ -151,13 +153,13 @@ int trace_define_field(struct trace_event_call *call, const char *type, head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type, 0); + is_signed, filter_type, 0, 0); } EXPORT_SYMBOL_GPL(trace_define_field); static int trace_define_field_ext(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, - int filter_type, int len) + int filter_type, int len, int need_test) { struct list_head *head; @@ -166,13 +168,13 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type, len); + is_signed, filter_type, len, need_test); } #define __generic_field(type, item, filter_type) \ ret = __trace_define_field(&ftrace_generic_fields, #type, \ #item, 0, 0, is_signed_type(type), \ - filter_type, 0); \ + filter_type, 0, 0); \ if (ret) \ return ret; @@ -181,7 +183,8 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ "common_" #item, \ offsetof(typeof(ent), item), \ sizeof(ent.item), \ - is_signed_type(type), FILTER_OTHER, 0); \ + is_signed_type(type), FILTER_OTHER, \ + 0, 0); \ if (ret) \ return ret; @@ -332,6 +335,7 @@ static bool process_pointer(const char *fmt, int len, struct trace_event_call *c /* Return true if the string is safe */ static bool process_string(const char *fmt, int len, struct trace_event_call *call) { + struct trace_event_fields *field; const char *r, *e, *s; e = fmt + len; @@ -372,8 +376,16 @@ static bool process_string(const char *fmt, int len, struct trace_event_call *ca if (process_pointer(fmt, len, call)) return true; - /* Make sure the field is found, and consider it OK for now if it is */ - return find_event_field(fmt, call) != NULL; + /* Make sure the field is found */ + field = find_event_field(fmt, call); + if (!field) + return false; + + /* Test this field's string before printing the event */ + call->flags |= TRACE_EVENT_FL_TEST_STR; + field->needs_test = 1; + + return true; } /* @@ -2586,7 +2598,7 @@ event_define_fields(struct trace_event_call *call) ret = trace_define_field_ext(call, field->type, field->name, offset, field->size, field->is_signed, field->filter_type, - field->len); + field->len, field->needs_test); if (WARN_ON_ONCE(ret)) { pr_err("error code is %d\n", ret); break; diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index da748b7cbc4d..03d56f711ad1 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -317,10 +317,14 @@ EXPORT_SYMBOL(trace_raw_output_prep); void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...) { + struct trace_seq *s = &iter->seq; va_list ap; + if (ignore_event(iter)) + return; + va_start(ap, fmt); - trace_check_vprintf(iter, trace_event_format(iter, fmt), ap); + trace_seq_vprintf(s, trace_event_format(iter, fmt), ap); va_end(ap); } EXPORT_SYMBOL(trace_event_printf); -- cgit v1.2.3 From c58a812c8e49ad688f94f4b050ad5c5b388fc5d2 Mon Sep 17 00:00:00 2001 From: Edward Adam Davis Date: Wed, 18 Dec 2024 21:36:55 +0800 Subject: ring-buffer: Fix overflow in __rb_map_vma An overflow occurred when performing the following calculation: nr_pages = ((nr_subbufs + 1) << subbuf_order) - pgoff; Add a check before the calculation to avoid this problem. syzbot reported this as a slab-out-of-bounds in __rb_map_vma: BUG: KASAN: slab-out-of-bounds in __rb_map_vma+0x9ab/0xae0 kernel/trace/ring_buffer.c:7058 Read of size 8 at addr ffff8880767dd2b8 by task syz-executor187/5836 CPU: 0 UID: 0 PID: 5836 Comm: syz-executor187 Not tainted 6.13.0-rc2-syzkaller-00159-gf932fb9b4074 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/25/2024 Call Trace: __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xc3/0x620 mm/kasan/report.c:489 kasan_report+0xd9/0x110 mm/kasan/report.c:602 __rb_map_vma+0x9ab/0xae0 kernel/trace/ring_buffer.c:7058 ring_buffer_map+0x56e/0x9b0 kernel/trace/ring_buffer.c:7138 tracing_buffers_mmap+0xa6/0x120 kernel/trace/trace.c:8482 call_mmap include/linux/fs.h:2183 [inline] mmap_file mm/internal.h:124 [inline] __mmap_new_file_vma mm/vma.c:2291 [inline] __mmap_new_vma mm/vma.c:2355 [inline] __mmap_region+0x1786/0x2670 mm/vma.c:2456 mmap_region+0x127/0x320 mm/mmap.c:1348 do_mmap+0xc00/0xfc0 mm/mmap.c:496 vm_mmap_pgoff+0x1ba/0x360 mm/util.c:580 ksys_mmap_pgoff+0x32c/0x5c0 mm/mmap.c:542 __do_sys_mmap arch/x86/kernel/sys_x86_64.c:89 [inline] __se_sys_mmap arch/x86/kernel/sys_x86_64.c:82 [inline] __x64_sys_mmap+0x125/0x190 arch/x86/kernel/sys_x86_64.c:82 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f The reproducer for this bug is: ------------------------8<------------------------- #include #include #include #include #include int main(int argc, char **argv) { int page_size = getpagesize(); int fd; void *meta; system("echo 1 > /sys/kernel/tracing/buffer_size_kb"); fd = open("/sys/kernel/tracing/per_cpu/cpu0/trace_pipe_raw", O_RDONLY); meta = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, page_size * 5); } ------------------------>8------------------------- Cc: stable@vger.kernel.org Fixes: 117c39200d9d7 ("ring-buffer: Introducing ring-buffer mapping functions") Link: https://lore.kernel.org/tencent_06924B6674ED771167C23CC336C097223609@qq.com Reported-by: syzbot+345e4443a21200874b18@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=345e4443a21200874b18 Signed-off-by: Edward Adam Davis Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 7e257e855dd1..60210fb5b211 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7019,7 +7019,11 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, lockdep_assert_held(&cpu_buffer->mapping_lock); nr_subbufs = cpu_buffer->nr_pages + 1; /* + reader-subbuf */ - nr_pages = ((nr_subbufs + 1) << subbuf_order) - pgoff; /* + meta-page */ + nr_pages = ((nr_subbufs + 1) << subbuf_order); /* + meta-page */ + if (nr_pages <= pgoff) + return -EINVAL; + + nr_pages -= pgoff; nr_vma_pages = vma_pages(vma); if (!nr_vma_pages || nr_vma_pages > nr_pages) -- cgit v1.2.3 From 8cd63406d08110c8098e1efda8aef7ddab4db348 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 18 Dec 2024 14:15:07 -0500 Subject: trace/ring-buffer: Do not use TP_printk() formatting for boot mapped buffers The TP_printk() of a TRACE_EVENT() is a generic printf format that any developer can create for their event. It may include pointers to strings and such. A boot mapped buffer may contain data from a previous kernel where the strings addresses are different. One solution is to copy the event content and update the pointers by the recorded delta, but a simpler solution (for now) is to just use the print_fields() function to print these events. The print_fields() function just iterates the fields and prints them according to what type they are, and ignores the TP_printk() format from the event itself. To understand the difference, when printing via TP_printk() the output looks like this: 4582.696626: kmem_cache_alloc: call_site=getname_flags+0x47/0x1f0 ptr=00000000e70e10e0 bytes_req=4096 bytes_alloc=4096 gfp_flags=GFP_KERNEL node=-1 accounted=false 4582.696629: kmem_cache_alloc: call_site=alloc_empty_file+0x6b/0x110 ptr=0000000095808002 bytes_req=360 bytes_alloc=384 gfp_flags=GFP_KERNEL node=-1 accounted=false 4582.696630: kmem_cache_alloc: call_site=security_file_alloc+0x24/0x100 ptr=00000000576339c3 bytes_req=16 bytes_alloc=16 gfp_flags=GFP_KERNEL|__GFP_ZERO node=-1 accounted=false 4582.696653: kmem_cache_free: call_site=do_sys_openat2+0xa7/0xd0 ptr=00000000e70e10e0 name=names_cache But when printing via print_fields() (echo 1 > /sys/kernel/tracing/options/fields) the same event output looks like this: 4582.696626: kmem_cache_alloc: call_site=0xffffffff92d10d97 (-1831793257) ptr=0xffff9e0e8571e000 (-107689771147264) bytes_req=0x1000 (4096) bytes_alloc=0x1000 (4096) gfp_flags=0xcc0 (3264) node=0xffffffff (-1) accounted=(0) 4582.696629: kmem_cache_alloc: call_site=0xffffffff92d0250b (-1831852789) ptr=0xffff9e0e8577f800 (-107689770747904) bytes_req=0x168 (360) bytes_alloc=0x180 (384) gfp_flags=0xcc0 (3264) node=0xffffffff (-1) accounted=(0) 4582.696630: kmem_cache_alloc: call_site=0xffffffff92efca74 (-1829778828) ptr=0xffff9e0e8d35d3b0 (-107689640864848) bytes_req=0x10 (16) bytes_alloc=0x10 (16) gfp_flags=0xdc0 (3520) node=0xffffffff (-1) accounted=(0) 4582.696653: kmem_cache_free: call_site=0xffffffff92cfbea7 (-1831879001) ptr=0xffff9e0e8571e000 (-107689771147264) name=names_cache Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Linus Torvalds Link: https://lore.kernel.org/20241218141507.28389a1d@gandalf.local.home Fixes: 07714b4bb3f98 ("tracing: Handle old buffer mappings for event strings and functions") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index be62f0ea1814..6581cb2bc67f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4353,6 +4353,15 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) if (event) { if (tr->trace_flags & TRACE_ITER_FIELDS) return print_event_fields(iter, event); + /* + * For TRACE_EVENT() events, the print_fmt is not + * safe to use if the array has delta offsets + * Force printing via the fields. + */ + if ((tr->text_delta || tr->data_delta) && + event->type > __TRACE_LAST_TYPE) + return print_event_fields(iter, event); + return event->funcs->trace(iter, sym_flags, event); } -- cgit v1.2.3 From d685d55dfc86b1a4bdcec77c3c1f8a83f181264e Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Wed, 11 Dec 2024 09:10:55 +0900 Subject: tracing/kprobe: Make trace_kprobe's module callback called after jump_label update Make sure the trace_kprobe's module notifer callback function is called after jump_label's callback is called. Since the trace_kprobe's callback eventually checks jump_label address during registering new kprobe on the loading module, jump_label must be updated before this registration happens. Link: https://lore.kernel.org/all/173387585556.995044.3157941002975446119.stgit@devnote2/ Fixes: 614243181050 ("tracing/kprobes: Support module init function probing") Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/trace_kprobe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 263fac44d3ca..935a886af40c 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -725,7 +725,7 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, static struct notifier_block trace_kprobe_module_nb = { .notifier_call = trace_kprobe_module_callback, - .priority = 1 /* Invoked after kprobe module callback */ + .priority = 2 /* Invoked after kprobe and jump_label module callback */ }; static int trace_kprobe_register_module_notifier(void) { -- cgit v1.2.3 From fd9b0244f5c5f63461ca9752eebd2423ae02bb59 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 28 Nov 2024 20:50:26 +0800 Subject: blktrace: don't centralize grabbing q->debugfs_mutex in blk_trace_ioctl Call each handler directly and the handler do grab q->debugfs_mutex, prepare for killing dependency between ->debug_mutex and ->mmap_lock. Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20241128125029.4152292-2-ming.lei@redhat.com Signed-off-by: Jens Axboe --- kernel/trace/blktrace.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 8fd292d34d89..f01aae3a2f7b 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -732,34 +732,32 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) int ret, start = 0; char b[BDEVNAME_SIZE]; - mutex_lock(&q->debugfs_mutex); - switch (cmd) { case BLKTRACESETUP: snprintf(b, sizeof(b), "%pg", bdev); - ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); + ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); break; #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) case BLKTRACESETUP32: snprintf(b, sizeof(b), "%pg", bdev); + mutex_lock(&q->debugfs_mutex); ret = compat_blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); + mutex_unlock(&q->debugfs_mutex); break; #endif case BLKTRACESTART: start = 1; fallthrough; case BLKTRACESTOP: - ret = __blk_trace_startstop(q, start); + ret = blk_trace_startstop(q, start); break; case BLKTRACETEARDOWN: - ret = __blk_trace_remove(q); + ret = blk_trace_remove(q); break; default: ret = -ENOTTY; break; } - - mutex_unlock(&q->debugfs_mutex); return ret; } -- cgit v1.2.3 From b769a2f409e7a356db852a1bb62a32f7809b3a3c Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 28 Nov 2024 20:50:27 +0800 Subject: blktrace: move copy_[to|from]_user() out of ->debugfs_lock Move copy_[to|from]_user() out of ->debugfs_lock and cut the dependency between mm->mmap_lock and q->debugfs_lock, then we avoids lots of lockdep false positive warning. Obviously ->debug_lock isn't needed for copy_[to|from]_user(). The only behavior change is to call blk_trace_remove() in case of setup failure handling by re-grabbing ->debugfs_lock, and this way is just fine since we do cover concurrent setup() & remove(). Reported-by: syzbot+91585b36b538053343e4@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-block/67450fd4.050a0220.1286eb.0007.GAE@google.com/ Closes: https://lore.kernel.org/linux-block/6742e584.050a0220.1cc393.0038.GAE@google.com/ Closes: https://lore.kernel.org/linux-block/6742a600.050a0220.1cc393.002e.GAE@google.com/ Closes: https://lore.kernel.org/linux-block/67420102.050a0220.1cc393.0019.GAE@google.com/ Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20241128125029.4152292-3-ming.lei@redhat.com Signed-off-by: Jens Axboe --- kernel/trace/blktrace.c | 26 +++++++++----------------- 1 file changed, 9 insertions(+), 17 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index f01aae3a2f7b..18c81e6aa496 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -617,8 +617,9 @@ err: return ret; } -static int __blk_trace_setup(struct request_queue *q, char *name, dev_t dev, - struct block_device *bdev, char __user *arg) +int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, + struct block_device *bdev, + char __user *arg) { struct blk_user_trace_setup buts; int ret; @@ -627,26 +628,17 @@ static int __blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (ret) return -EFAULT; + mutex_lock(&q->debugfs_mutex); ret = do_blk_trace_setup(q, name, dev, bdev, &buts); + mutex_unlock(&q->debugfs_mutex); if (ret) return ret; if (copy_to_user(arg, &buts, sizeof(buts))) { - __blk_trace_remove(q); + blk_trace_remove(q); return -EFAULT; } return 0; -} - -int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, - struct block_device *bdev, - char __user *arg) -{ - int ret; - - mutex_lock(&q->debugfs_mutex); - ret = __blk_trace_setup(q, name, dev, bdev, arg); - mutex_unlock(&q->debugfs_mutex); return ret; } @@ -673,12 +665,14 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name, .pid = cbuts.pid, }; + mutex_lock(&q->debugfs_mutex); ret = do_blk_trace_setup(q, name, dev, bdev, &buts); + mutex_unlock(&q->debugfs_mutex); if (ret) return ret; if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) { - __blk_trace_remove(q); + blk_trace_remove(q); return -EFAULT; } @@ -740,9 +734,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) case BLKTRACESETUP32: snprintf(b, sizeof(b), "%pg", bdev); - mutex_lock(&q->debugfs_mutex); ret = compat_blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); - mutex_unlock(&q->debugfs_mutex); break; #endif case BLKTRACESTART: -- cgit v1.2.3 From ccb9868ab7f4b253440b8723a3487b8b9a16d371 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 4 Dec 2024 15:04:50 +0000 Subject: blktrace: remove redundant return at end of function A recent change added return 0 before an existing return statement at the end of function blk_trace_setup. The final return is now redundant, so remove it. Fixes: 64d124798244 ("blktrace: move copy_[to|from]_user() out of ->debugfs_lock") Signed-off-by: Colin Ian King Link: https://lore.kernel.org/r/20241204150450.399005-1-colin.i.king@gmail.com Signed-off-by: Jens Axboe --- kernel/trace/blktrace.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 18c81e6aa496..3679a6d18934 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -639,8 +639,6 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, return -EFAULT; } return 0; - - return ret; } EXPORT_SYMBOL_GPL(blk_trace_setup); -- cgit v1.2.3 From 7d137e604aaacf2723ced2fca0b46b3f563e1d5e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 23 Dec 2024 13:46:19 -0500 Subject: fgraph: Remove unnecessary disabling of interrupts and recursion The function graph tracer disables interrupts as well as prevents recursion via NMIs when recording the graph tracer code. There's no reason to do this today. That disabling goes back to 2008 when the function graph tracer was first introduced and recursion protection wasn't part of the code. Today, there's no reason to disable interrupts or prevent the code from recursing as the infrastructure can easily handle it. Before this change: ~# echo function_graph > /sys/kernel/tracing/current_tracer ~# perf stat -r 10 ./hackbench 10 Time: 4.240 Time: 4.236 Time: 4.106 Time: 4.014 Time: 4.314 Time: 3.830 Time: 4.063 Time: 4.323 Time: 3.763 Time: 3.727 Performance counter stats for '/work/c/hackbench 10' (10 runs): 33,937.20 msec task-clock # 7.008 CPUs utilized ( +- 1.85% ) 18,220 context-switches # 536.874 /sec ( +- 6.41% ) 624 cpu-migrations # 18.387 /sec ( +- 9.07% ) 11,319 page-faults # 333.528 /sec ( +- 1.97% ) 76,657,643,617 cycles # 2.259 GHz ( +- 0.40% ) 141,403,302,768 instructions # 1.84 insn per cycle ( +- 0.37% ) 25,518,463,888 branches # 751.932 M/sec ( +- 0.35% ) 156,151,050 branch-misses # 0.61% of all branches ( +- 0.63% ) 4.8423 +- 0.0892 seconds time elapsed ( +- 1.84% ) After this change: ~# echo function_graph > /sys/kernel/tracing/current_tracer ~# perf stat -r 10 ./hackbench 10 Time: 3.340 Time: 3.192 Time: 3.129 Time: 2.579 Time: 2.589 Time: 2.798 Time: 2.791 Time: 2.955 Time: 3.044 Time: 3.065 Performance counter stats for './hackbench 10' (10 runs): 24,416.30 msec task-clock # 6.996 CPUs utilized ( +- 2.74% ) 16,764 context-switches # 686.590 /sec ( +- 5.85% ) 469 cpu-migrations # 19.208 /sec ( +- 6.14% ) 11,519 page-faults # 471.775 /sec ( +- 1.92% ) 53,895,628,450 cycles # 2.207 GHz ( +- 0.52% ) 105,552,664,638 instructions # 1.96 insn per cycle ( +- 0.47% ) 17,808,672,667 branches # 729.376 M/sec ( +- 0.48% ) 133,075,435 branch-misses # 0.75% of all branches ( +- 0.59% ) 3.490 +- 0.112 seconds time elapsed ( +- 3.22% ) Also removed unneeded "unlikely()" around the retaddr code. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://lore.kernel.org/20241223184941.204074053@goodmis.org Fixes: 9cd2992f2d6c8 ("fgraph: Have set_graph_notrace only affect function_graph tracer") # Performance only Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_functions_graph.c | 37 +++++++++++++++--------------------- 1 file changed, 15 insertions(+), 22 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 5504b5e4e7b4..f513603d7df9 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -181,10 +181,9 @@ int trace_graph_entry(struct ftrace_graph_ent *trace, struct trace_array *tr = gops->private; struct trace_array_cpu *data; struct fgraph_times *ftimes; - unsigned long flags; unsigned int trace_ctx; long disabled; - int ret; + int ret = 0; int cpu; if (*task_var & TRACE_GRAPH_NOTRACE) @@ -235,25 +234,21 @@ int trace_graph_entry(struct ftrace_graph_ent *trace, if (tracing_thresh) return 1; - local_irq_save(flags); + preempt_disable_notrace(); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->array_buffer.data, cpu); - disabled = atomic_inc_return(&data->disabled); - if (likely(disabled == 1)) { - trace_ctx = tracing_gen_ctx_flags(flags); - if (unlikely(IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) && - tracer_flags_is_set(TRACE_GRAPH_PRINT_RETADDR))) { + disabled = atomic_read(&data->disabled); + if (likely(!disabled)) { + trace_ctx = tracing_gen_ctx(); + if (IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) && + tracer_flags_is_set(TRACE_GRAPH_PRINT_RETADDR)) { unsigned long retaddr = ftrace_graph_top_ret_addr(current); - ret = __trace_graph_retaddr_entry(tr, trace, trace_ctx, retaddr); - } else + } else { ret = __trace_graph_entry(tr, trace, trace_ctx); - } else { - ret = 0; + } } - - atomic_dec(&data->disabled); - local_irq_restore(flags); + preempt_enable_notrace(); return ret; } @@ -320,7 +315,6 @@ void trace_graph_return(struct ftrace_graph_ret *trace, struct trace_array *tr = gops->private; struct trace_array_cpu *data; struct fgraph_times *ftimes; - unsigned long flags; unsigned int trace_ctx; long disabled; int size; @@ -341,16 +335,15 @@ void trace_graph_return(struct ftrace_graph_ret *trace, trace->calltime = ftimes->calltime; - local_irq_save(flags); + preempt_disable_notrace(); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->array_buffer.data, cpu); - disabled = atomic_inc_return(&data->disabled); - if (likely(disabled == 1)) { - trace_ctx = tracing_gen_ctx_flags(flags); + disabled = atomic_read(&data->disabled); + if (likely(!disabled)) { + trace_ctx = tracing_gen_ctx(); __trace_graph_return(tr, trace, trace_ctx); } - atomic_dec(&data->disabled); - local_irq_restore(flags); + preempt_enable_notrace(); } static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, -- cgit v1.2.3 From ac8c3b02fc33be9deda48532326d301333d39f16 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 23 Dec 2024 13:46:20 -0500 Subject: ftrace: Do not disable interrupts in profiler The function profiler disables interrupts before processing. This was there since the profiler was introduced back in 2009 when there were recursion issues to deal with. The function tracer is much more robust today and has its own internal recursion protection. There's no reason to disable interrupts in the function profiler. Instead, just disable preemption and use the guard() infrastructure while at it. Before this change: ~# echo 1 > /sys/kernel/tracing/function_profile_enabled ~# perf stat -r 10 ./hackbench 10 Time: 3.099 Time: 2.556 Time: 2.500 Time: 2.705 Time: 2.985 Time: 2.959 Time: 2.859 Time: 2.621 Time: 2.742 Time: 2.631 Performance counter stats for '/work/c/hackbench 10' (10 runs): 23,156.77 msec task-clock # 6.951 CPUs utilized ( +- 2.36% ) 18,306 context-switches # 790.525 /sec ( +- 5.95% ) 495 cpu-migrations # 21.376 /sec ( +- 8.61% ) 11,522 page-faults # 497.565 /sec ( +- 1.80% ) 47,967,124,606 cycles # 2.071 GHz ( +- 0.41% ) 80,009,078,371 instructions # 1.67 insn per cycle ( +- 0.34% ) 16,389,249,798 branches # 707.752 M/sec ( +- 0.36% ) 139,943,109 branch-misses # 0.85% of all branches ( +- 0.61% ) 3.332 +- 0.101 seconds time elapsed ( +- 3.04% ) After this change: ~# echo 1 > /sys/kernel/tracing/function_profile_enabled ~# perf stat -r 10 ./hackbench 10 Time: 1.869 Time: 1.428 Time: 1.575 Time: 1.569 Time: 1.685 Time: 1.511 Time: 1.611 Time: 1.672 Time: 1.724 Time: 1.715 Performance counter stats for '/work/c/hackbench 10' (10 runs): 13,578.21 msec task-clock # 6.931 CPUs utilized ( +- 2.23% ) 12,736 context-switches # 937.973 /sec ( +- 3.86% ) 341 cpu-migrations # 25.114 /sec ( +- 5.27% ) 11,378 page-faults # 837.960 /sec ( +- 1.74% ) 27,638,039,036 cycles # 2.035 GHz ( +- 0.27% ) 45,107,762,498 instructions # 1.63 insn per cycle ( +- 0.23% ) 8,623,868,018 branches # 635.125 M/sec ( +- 0.27% ) 125,738,443 branch-misses # 1.46% of all branches ( +- 0.32% ) 1.9590 +- 0.0484 seconds time elapsed ( +- 2.47% ) Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://lore.kernel.org/20241223184941.373853944@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 20 +++++++------------- 1 file changed, 7 insertions(+), 13 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 9b17efb1a87d..63a9ffa65e17 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -789,27 +789,24 @@ function_profile_call(unsigned long ip, unsigned long parent_ip, { struct ftrace_profile_stat *stat; struct ftrace_profile *rec; - unsigned long flags; if (!ftrace_profile_enabled) return; - local_irq_save(flags); + guard(preempt_notrace)(); stat = this_cpu_ptr(&ftrace_profile_stats); if (!stat->hash || !ftrace_profile_enabled) - goto out; + return; rec = ftrace_find_profiled_func(stat, ip); if (!rec) { rec = ftrace_profile_alloc(stat, ip); if (!rec) - goto out; + return; } rec->counter++; - out: - local_irq_restore(flags); } #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -856,19 +853,19 @@ static void profile_graph_return(struct ftrace_graph_ret *trace, unsigned long long calltime; unsigned long long rettime = trace_clock_local(); struct ftrace_profile *rec; - unsigned long flags; int size; - local_irq_save(flags); + guard(preempt_notrace)(); + stat = this_cpu_ptr(&ftrace_profile_stats); if (!stat->hash || !ftrace_profile_enabled) - goto out; + return; profile_data = fgraph_retrieve_data(gops->idx, &size); /* If the calltime was zero'd ignore it */ if (!profile_data || !profile_data->calltime) - goto out; + return; calltime = rettime - profile_data->calltime; @@ -896,9 +893,6 @@ static void profile_graph_return(struct ftrace_graph_ret *trace, rec->time += calltime; rec->time_squared += calltime * calltime; } - - out: - local_irq_restore(flags); } static struct fgraph_ops fprofiler_ops = { -- cgit v1.2.3 From 77e53cb2fcf2c5e81f06f4a41783d8752cf9d038 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 23 Dec 2024 13:46:21 -0500 Subject: ftrace: Remove unneeded goto jumps There are some goto jumps to exit a program to just return a value. The code after the label doesn't free anything nor does it do any unlocks. It simply returns the variable that was set before the jump. Remove these unneeded goto jumps. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://lore.kernel.org/20241223184941.544855549@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 63a9ffa65e17..2c1691aa1d2f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1669,14 +1669,12 @@ unsigned long ftrace_location(unsigned long ip) loc = ftrace_location_range(ip, ip); if (!loc) { if (!kallsyms_lookup_size_offset(ip, &size, &offset)) - goto out; + return 0; /* map sym+0 to __fentry__ */ if (!offset) loc = ftrace_location_range(ip, ip + size - 1); } - -out: return loc; } @@ -2071,7 +2069,7 @@ rollback: continue; if (rec == end) - goto err_out; + return -EBUSY; in_old = !!ftrace_lookup_ip(old_hash, rec->ip); in_new = !!ftrace_lookup_ip(new_hash, rec->ip); @@ -2084,7 +2082,6 @@ rollback: rec->flags |= FTRACE_FL_IPMODIFY; } while_for_each_ftrace_rec(); -err_out: return -EBUSY; } @@ -5720,12 +5717,10 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, parser->idx, enable); trace_parser_clear(parser); if (ret < 0) - goto out; + return ret; } - ret = read; - out: - return ret; + return read; } ssize_t -- cgit v1.2.3 From 1d95fd9d6b1a1750da2dec1485a4c58f5a7d3ebd Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 23 Dec 2024 13:46:22 -0500 Subject: ftrace: Switch ftrace.c code over to use guard() There are a few functions in ftrace.c that have "goto out" or equivalent on error in order to release locks that were taken. This can be error prone or just simply make the code more complex. Switch every location that ends with unlocking a mutex on error over to using the guard(mutex)() infrastructure to let the compiler worry about releasing locks. This makes the code easier to read and understand. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://lore.kernel.org/20241223184941.718001540@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 97 ++++++++++++++++++--------------------------------- 1 file changed, 34 insertions(+), 63 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 2c1691aa1d2f..6ebc76bafd38 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -536,24 +536,21 @@ static int function_stat_show(struct seq_file *m, void *v) { struct ftrace_profile *rec = v; char str[KSYM_SYMBOL_LEN]; - int ret = 0; #ifdef CONFIG_FUNCTION_GRAPH_TRACER static struct trace_seq s; unsigned long long avg; unsigned long long stddev; #endif - mutex_lock(&ftrace_profile_lock); + guard(mutex)(&ftrace_profile_lock); /* we raced with function_profile_reset() */ - if (unlikely(rec->counter == 0)) { - ret = -EBUSY; - goto out; - } + if (unlikely(rec->counter == 0)) + return -EBUSY; #ifdef CONFIG_FUNCTION_GRAPH_TRACER avg = div64_ul(rec->time, rec->counter); if (tracing_thresh && (avg < tracing_thresh)) - goto out; + return 0; #endif kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); @@ -590,10 +587,8 @@ static int function_stat_show(struct seq_file *m, void *v) trace_print_seq(m, &s); #endif seq_putc(m, '\n'); -out: - mutex_unlock(&ftrace_profile_lock); - return ret; + return 0; } static void ftrace_profile_reset(struct ftrace_profile_stat *stat) @@ -944,20 +939,16 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf, val = !!val; - mutex_lock(&ftrace_profile_lock); + guard(mutex)(&ftrace_profile_lock); if (ftrace_profile_enabled ^ val) { if (val) { ret = ftrace_profile_init(); - if (ret < 0) { - cnt = ret; - goto out; - } + if (ret < 0) + return ret; ret = register_ftrace_profiler(); - if (ret < 0) { - cnt = ret; - goto out; - } + if (ret < 0) + return ret; ftrace_profile_enabled = 1; } else { ftrace_profile_enabled = 0; @@ -968,8 +959,6 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf, unregister_ftrace_profiler(); } } - out: - mutex_unlock(&ftrace_profile_lock); *ppos += cnt; @@ -5610,20 +5599,15 @@ static DEFINE_MUTEX(ftrace_cmd_mutex); __init int register_ftrace_command(struct ftrace_func_command *cmd) { struct ftrace_func_command *p; - int ret = 0; - mutex_lock(&ftrace_cmd_mutex); + guard(mutex)(&ftrace_cmd_mutex); list_for_each_entry(p, &ftrace_commands, list) { - if (strcmp(cmd->name, p->name) == 0) { - ret = -EBUSY; - goto out_unlock; - } + if (strcmp(cmd->name, p->name) == 0) + return -EBUSY; } list_add(&cmd->list, &ftrace_commands); - out_unlock: - mutex_unlock(&ftrace_cmd_mutex); - return ret; + return 0; } /* @@ -5633,20 +5617,17 @@ __init int register_ftrace_command(struct ftrace_func_command *cmd) __init int unregister_ftrace_command(struct ftrace_func_command *cmd) { struct ftrace_func_command *p, *n; - int ret = -ENODEV; - mutex_lock(&ftrace_cmd_mutex); + guard(mutex)(&ftrace_cmd_mutex); + list_for_each_entry_safe(p, n, &ftrace_commands, list) { if (strcmp(cmd->name, p->name) == 0) { - ret = 0; list_del_init(&p->list); - goto out_unlock; + return 0; } } - out_unlock: - mutex_unlock(&ftrace_cmd_mutex); - return ret; + return -ENODEV; } static int ftrace_process_regex(struct ftrace_iterator *iter, @@ -5656,7 +5637,7 @@ static int ftrace_process_regex(struct ftrace_iterator *iter, struct trace_array *tr = iter->ops->private; char *func, *command, *next = buff; struct ftrace_func_command *p; - int ret = -EINVAL; + int ret; func = strsep(&next, ":"); @@ -5673,17 +5654,14 @@ static int ftrace_process_regex(struct ftrace_iterator *iter, command = strsep(&next, ":"); - mutex_lock(&ftrace_cmd_mutex); + guard(mutex)(&ftrace_cmd_mutex); + list_for_each_entry(p, &ftrace_commands, list) { - if (strcmp(p->name, command) == 0) { - ret = p->func(tr, hash, func, command, next, enable); - goto out_unlock; - } + if (strcmp(p->name, command) == 0) + return p->func(tr, hash, func, command, next, enable); } - out_unlock: - mutex_unlock(&ftrace_cmd_mutex); - return ret; + return -EINVAL; } static ssize_t @@ -8280,7 +8258,7 @@ pid_write(struct file *filp, const char __user *ubuf, if (!cnt) return 0; - mutex_lock(&ftrace_lock); + guard(mutex)(&ftrace_lock); switch (type) { case TRACE_PIDS: @@ -8296,14 +8274,13 @@ pid_write(struct file *filp, const char __user *ubuf, lockdep_is_held(&ftrace_lock)); break; default: - ret = -EINVAL; WARN_ON_ONCE(1); - goto out; + return -EINVAL; } ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt); if (ret < 0) - goto out; + return ret; switch (type) { case TRACE_PIDS: @@ -8332,11 +8309,8 @@ pid_write(struct file *filp, const char __user *ubuf, ftrace_update_pid_func(); ftrace_startup_all(0); - out: - mutex_unlock(&ftrace_lock); - if (ret > 0) - *ppos += ret; + *ppos += ret; return ret; } @@ -8739,17 +8713,17 @@ static int ftrace_enable_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - int ret = -ENODEV; + int ret; - mutex_lock(&ftrace_lock); + guard(mutex)(&ftrace_lock); if (unlikely(ftrace_disabled)) - goto out; + return -ENODEV; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) - goto out; + return ret; if (ftrace_enabled) { @@ -8763,8 +8737,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write, } else { if (is_permanent_ops_registered()) { ftrace_enabled = true; - ret = -EBUSY; - goto out; + return -EBUSY; } /* stopping ftrace calls (just send to ftrace_stub) */ @@ -8774,9 +8747,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write, } last_ftrace_enabled = !!ftrace_enabled; - out: - mutex_unlock(&ftrace_lock); - return ret; + return 0; } static struct ctl_table ftrace_sysctls[] = { -- cgit v1.2.3 From d576aec24df9f58ed0ebe2ff854daafe837f0225 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Tue, 10 Dec 2024 11:08:57 +0900 Subject: fgraph: Get ftrace recursion lock in function_graph_enter Get the ftrace recursion lock in the generic function_graph_enter() instead of each architecture code. This changes all function_graph tracer callbacks running in non-preemptive state. On x86 and powerpc, this is by default, but on the other architecutres, this will be new. Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: Naveen N Rao Cc: Madhavan Srinivasan Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173379653720.973433.18438622234884980494.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- arch/powerpc/kernel/trace/ftrace.c | 6 ------ arch/powerpc/kernel/trace/ftrace_64_pg.c | 6 ------ arch/x86/kernel/ftrace.c | 7 ------- kernel/trace/fgraph.c | 8 +++++++- 4 files changed, 7 insertions(+), 20 deletions(-) (limited to 'kernel/trace') diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 5ccd791761e8..e41daf2c4a31 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -658,7 +658,6 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { unsigned long sp = arch_ftrace_regs(fregs)->regs.gpr[1]; - int bit; if (unlikely(ftrace_graph_is_dead())) goto out; @@ -666,14 +665,9 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) - goto out; - if (!function_graph_enter(parent_ip, ip, 0, (unsigned long *)sp)) parent_ip = ppc_function_entry(return_to_handler); - ftrace_test_recursion_unlock(bit); out: arch_ftrace_regs(fregs)->regs.link = parent_ip; } diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c index 98787376eb87..8fb860b90ae1 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_pg.c +++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c @@ -790,7 +790,6 @@ static unsigned long __prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp) { unsigned long return_hooker; - int bit; if (unlikely(ftrace_graph_is_dead())) goto out; @@ -798,16 +797,11 @@ __prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; - bit = ftrace_test_recursion_trylock(ip, parent); - if (bit < 0) - goto out; - return_hooker = ppc_function_entry(return_to_handler); if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp)) parent = return_hooker; - ftrace_test_recursion_unlock(bit); out: return parent; } diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 4dd0ad6c94d6..33f50c80f481 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -615,7 +615,6 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent, unsigned long frame_pointer) { unsigned long return_hooker = (unsigned long)&return_to_handler; - int bit; /* * When resuming from suspend-to-ram, this function can be indirectly @@ -635,14 +634,8 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent, if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; - bit = ftrace_test_recursion_trylock(ip, *parent); - if (bit < 0) - return; - if (!function_graph_enter(*parent, ip, frame_pointer, parent)) *parent = return_hooker; - - ftrace_test_recursion_unlock(bit); } #ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index ddedcb50917f..5c68d6109119 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -650,8 +650,13 @@ int function_graph_enter(unsigned long ret, unsigned long func, struct ftrace_graph_ent trace; unsigned long bitmap = 0; int offset; + int bit; int i; + bit = ftrace_test_recursion_trylock(func, ret); + if (bit < 0) + return -EBUSY; + trace.func = func; trace.depth = ++current->curr_ret_depth; @@ -697,12 +702,13 @@ int function_graph_enter(unsigned long ret, unsigned long func, * flag, set that bit always. */ set_bitmap(current, offset, bitmap | BIT(0)); - + ftrace_test_recursion_unlock(bit); return 0; out_ret: current->curr_ret_stack -= FGRAPH_FRAME_OFFSET + 1; out: current->curr_ret_depth--; + ftrace_test_recursion_unlock(bit); return -EBUSY; } -- cgit v1.2.3 From 98feccbf32cfdde8c722bc4587aaa60ee5ac33f0 Mon Sep 17 00:00:00 2001 From: Lizhi Xu Date: Mon, 16 Dec 2024 15:32:38 +0800 Subject: tracing: Prevent bad count for tracing_cpumask_write If a large count is provided, it will trigger a warning in bitmap_parse_user. Also check zero for it. Cc: stable@vger.kernel.org Fixes: 9e01c1b74c953 ("cpumask: convert kernel trace functions") Link: https://lore.kernel.org/20241216073238.2573704-1-lizhi.xu@windriver.com Reported-by: syzbot+0aecfd34fb878546f3fd@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=0aecfd34fb878546f3fd Tested-by: syzbot+0aecfd34fb878546f3fd@syzkaller.appspotmail.com Signed-off-by: Lizhi Xu Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 957f941a08e7..f8aebcb01e62 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5087,6 +5087,9 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, cpumask_var_t tracing_cpumask_new; int err; + if (count == 0 || count > KMALLOC_MAX_SIZE) + return -EINVAL; + if (!zalloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) return -ENOMEM; -- cgit v1.2.3 From d33b10c0c73adca00f72bf4a153a07b7f5f34715 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 24 Dec 2024 22:14:13 -0500 Subject: tracing: Switch trace.c code over to use guard() There are several functions in trace.c that have "goto out;" or equivalent on error in order to release locks or free values that were allocated. This can be error prone or just simply make the code more complex. Switch every location that ends with unlocking a mutex or freeing on error over to using the guard(mutex)() and __free() infrastructure to let the compiler worry about releasing locks. This makes the code easier to read and understand. There's one place that should probably return an error but instead return 0. This does not change the return as the only changes are to do the conversion without changing the logic. Fixing that location will have to come later. Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Peter Zijlstra Cc: Andrew Morton Acked-by: Masami Hiramatsu (Google) Link: https://lore.kernel.org/20241224221413.7b8c68c3@batman.local.home Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 266 ++++++++++++++++++--------------------------------- 1 file changed, 94 insertions(+), 172 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 957f941a08e7..e6e1de69af01 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -535,19 +536,16 @@ LIST_HEAD(ftrace_trace_arrays); int trace_array_get(struct trace_array *this_tr) { struct trace_array *tr; - int ret = -ENODEV; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (tr == this_tr) { tr->ref++; - ret = 0; - break; + return 0; } } - mutex_unlock(&trace_types_lock); - return ret; + return -ENODEV; } static void __trace_array_put(struct trace_array *this_tr) @@ -1443,22 +1441,20 @@ EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update) { - struct cond_snapshot *cond_snapshot; - int ret = 0; + struct cond_snapshot *cond_snapshot __free(kfree) = + kzalloc(sizeof(*cond_snapshot), GFP_KERNEL); + int ret; - cond_snapshot = kzalloc(sizeof(*cond_snapshot), GFP_KERNEL); if (!cond_snapshot) return -ENOMEM; cond_snapshot->cond_data = cond_data; cond_snapshot->update = update; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); - if (tr->current_trace->use_max_tr) { - ret = -EBUSY; - goto fail_unlock; - } + if (tr->current_trace->use_max_tr) + return -EBUSY; /* * The cond_snapshot can only change to NULL without the @@ -1468,29 +1464,20 @@ int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, * do safely with only holding the trace_types_lock and not * having to take the max_lock. */ - if (tr->cond_snapshot) { - ret = -EBUSY; - goto fail_unlock; - } + if (tr->cond_snapshot) + return -EBUSY; ret = tracing_arm_snapshot_locked(tr); if (ret) - goto fail_unlock; + return ret; local_irq_disable(); arch_spin_lock(&tr->max_lock); - tr->cond_snapshot = cond_snapshot; + tr->cond_snapshot = no_free_ptr(cond_snapshot); arch_spin_unlock(&tr->max_lock); local_irq_enable(); - mutex_unlock(&trace_types_lock); - - return ret; - - fail_unlock: - mutex_unlock(&trace_types_lock); - kfree(cond_snapshot); - return ret; + return 0; } EXPORT_SYMBOL_GPL(tracing_snapshot_cond_enable); @@ -2203,10 +2190,10 @@ static __init int init_trace_selftests(void) selftests_can_run = true; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); if (list_empty(&postponed_selftests)) - goto out; + return 0; pr_info("Running postponed tracer tests:\n"); @@ -2235,9 +2222,6 @@ static __init int init_trace_selftests(void) } tracing_selftest_running = false; - out: - mutex_unlock(&trace_types_lock); - return 0; } core_initcall(init_trace_selftests); @@ -2807,7 +2791,7 @@ int tracepoint_printk_sysctl(const struct ctl_table *table, int write, int save_tracepoint_printk; int ret; - mutex_lock(&tracepoint_printk_mutex); + guard(mutex)(&tracepoint_printk_mutex); save_tracepoint_printk = tracepoint_printk; ret = proc_dointvec(table, write, buffer, lenp, ppos); @@ -2820,16 +2804,13 @@ int tracepoint_printk_sysctl(const struct ctl_table *table, int write, tracepoint_printk = 0; if (save_tracepoint_printk == tracepoint_printk) - goto out; + return ret; if (tracepoint_printk) static_key_enable(&tracepoint_printk_key.key); else static_key_disable(&tracepoint_printk_key.key); - out: - mutex_unlock(&tracepoint_printk_mutex); - return ret; } @@ -5123,7 +5104,8 @@ static int tracing_trace_options_show(struct seq_file *m, void *v) u32 tracer_flags; int i; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); + tracer_flags = tr->current_trace->flags->val; trace_opts = tr->current_trace->flags->opts; @@ -5140,7 +5122,6 @@ static int tracing_trace_options_show(struct seq_file *m, void *v) else seq_printf(m, "no%s\n", trace_opts[i].name); } - mutex_unlock(&trace_types_lock); return 0; } @@ -5805,7 +5786,7 @@ trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start, return; } - mutex_lock(&trace_eval_mutex); + guard(mutex)(&trace_eval_mutex); if (!trace_eval_maps) trace_eval_maps = map_array; @@ -5829,8 +5810,6 @@ trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start, map_array++; } memset(map_array, 0, sizeof(*map_array)); - - mutex_unlock(&trace_eval_mutex); } static void trace_create_eval_file(struct dentry *d_tracer) @@ -5994,23 +5973,18 @@ ssize_t tracing_resize_ring_buffer(struct trace_array *tr, { int ret; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); if (cpu_id != RING_BUFFER_ALL_CPUS) { /* make sure, this cpu is enabled in the mask */ - if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) { - ret = -EINVAL; - goto out; - } + if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) + return -EINVAL; } ret = __tracing_resize_ring_buffer(tr, size, cpu_id); if (ret < 0) ret = -ENOMEM; -out: - mutex_unlock(&trace_types_lock); - return ret; } @@ -6102,9 +6076,9 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) #ifdef CONFIG_TRACER_MAX_TRACE bool had_max_tr; #endif - int ret = 0; + int ret; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); update_last_data(tr); @@ -6112,7 +6086,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) ret = __tracing_resize_ring_buffer(tr, trace_buf_size, RING_BUFFER_ALL_CPUS); if (ret < 0) - goto out; + return ret; ret = 0; } @@ -6120,12 +6094,11 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) if (strcmp(t->name, buf) == 0) break; } - if (!t) { - ret = -EINVAL; - goto out; - } + if (!t) + return -EINVAL; + if (t == tr->current_trace) - goto out; + return 0; #ifdef CONFIG_TRACER_SNAPSHOT if (t->use_max_tr) { @@ -6136,27 +6109,23 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) arch_spin_unlock(&tr->max_lock); local_irq_enable(); if (ret) - goto out; + return ret; } #endif /* Some tracers won't work on kernel command line */ if (system_state < SYSTEM_RUNNING && t->noboot) { pr_warn("Tracer '%s' is not allowed on command line, ignored\n", t->name); - goto out; + return 0; } /* Some tracers are only allowed for the top level buffer */ - if (!trace_ok_for_array(t, tr)) { - ret = -EINVAL; - goto out; - } + if (!trace_ok_for_array(t, tr)) + return -EINVAL; /* If trace pipe files are being read, we can't change the tracer */ - if (tr->trace_ref) { - ret = -EBUSY; - goto out; - } + if (tr->trace_ref) + return -EBUSY; trace_branch_disable(); @@ -6187,7 +6156,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) if (!had_max_tr && t->use_max_tr) { ret = tracing_arm_snapshot_locked(tr); if (ret) - goto out; + return ret; } #else tr->current_trace = &nop_trace; @@ -6200,17 +6169,15 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) if (t->use_max_tr) tracing_disarm_snapshot(tr); #endif - goto out; + return ret; } } tr->current_trace = t; tr->current_trace->enabled++; trace_branch_enable(tr); - out: - mutex_unlock(&trace_types_lock); - return ret; + return 0; } static ssize_t @@ -6288,22 +6255,18 @@ tracing_thresh_write(struct file *filp, const char __user *ubuf, struct trace_array *tr = filp->private_data; int ret; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); ret = tracing_nsecs_write(&tracing_thresh, ubuf, cnt, ppos); if (ret < 0) - goto out; + return ret; if (tr->current_trace->update_thresh) { ret = tr->current_trace->update_thresh(tr); if (ret < 0) - goto out; + return ret; } - ret = cnt; -out: - mutex_unlock(&trace_types_lock); - - return ret; + return cnt; } #ifdef CONFIG_TRACER_MAX_TRACE @@ -6522,31 +6485,29 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, * This is just a matter of traces coherency, the ring buffer itself * is protected. */ - mutex_lock(&iter->mutex); + guard(mutex)(&iter->mutex); /* return any leftover data */ sret = trace_seq_to_user(&iter->seq, ubuf, cnt); if (sret != -EBUSY) - goto out; + return sret; trace_seq_init(&iter->seq); if (iter->trace->read) { sret = iter->trace->read(iter, filp, ubuf, cnt, ppos); if (sret) - goto out; + return sret; } waitagain: sret = tracing_wait_pipe(filp); if (sret <= 0) - goto out; + return sret; /* stop when tracing is finished */ - if (trace_empty(iter)) { - sret = 0; - goto out; - } + if (trace_empty(iter)) + return 0; if (cnt >= TRACE_SEQ_BUFFER_SIZE) cnt = TRACE_SEQ_BUFFER_SIZE - 1; @@ -6610,9 +6571,6 @@ waitagain: if (sret == -EBUSY) goto waitagain; -out: - mutex_unlock(&iter->mutex); - return sret; } @@ -7204,25 +7162,19 @@ u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_eve */ int tracing_set_filter_buffering(struct trace_array *tr, bool set) { - int ret = 0; - - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); if (set && tr->no_filter_buffering_ref++) - goto out; + return 0; if (!set) { - if (WARN_ON_ONCE(!tr->no_filter_buffering_ref)) { - ret = -EINVAL; - goto out; - } + if (WARN_ON_ONCE(!tr->no_filter_buffering_ref)) + return -EINVAL; --tr->no_filter_buffering_ref; } - out: - mutex_unlock(&trace_types_lock); - return ret; + return 0; } struct ftrace_buffer_info { @@ -7298,12 +7250,10 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, if (ret) return ret; - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); - if (tr->current_trace->use_max_tr) { - ret = -EBUSY; - goto out; - } + if (tr->current_trace->use_max_tr) + return -EBUSY; local_irq_disable(); arch_spin_lock(&tr->max_lock); @@ -7312,24 +7262,20 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, arch_spin_unlock(&tr->max_lock); local_irq_enable(); if (ret) - goto out; + return ret; switch (val) { case 0: - if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { - ret = -EINVAL; - break; - } + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) + return -EINVAL; if (tr->allocated_snapshot) free_snapshot(tr); break; case 1: /* Only allow per-cpu swap if the ring buffer supports it */ #ifndef CONFIG_RING_BUFFER_ALLOW_SWAP - if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { - ret = -EINVAL; - break; - } + if (iter->cpu_file != RING_BUFFER_ALL_CPUS) + return -EINVAL; #endif if (tr->allocated_snapshot) ret = resize_buffer_duplicate_size(&tr->max_buffer, @@ -7337,7 +7283,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, ret = tracing_arm_snapshot_locked(tr); if (ret) - break; + return ret; /* Now, we're going to swap */ if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { @@ -7364,8 +7310,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, *ppos += cnt; ret = cnt; } -out: - mutex_unlock(&trace_types_lock); + return ret; } @@ -7751,12 +7696,11 @@ void tracing_log_err(struct trace_array *tr, len += sizeof(CMD_PREFIX) + 2 * sizeof("\n") + strlen(cmd) + 1; - mutex_lock(&tracing_err_log_lock); + guard(mutex)(&tracing_err_log_lock); + err = get_tracing_log_err(tr, len); - if (PTR_ERR(err) == -ENOMEM) { - mutex_unlock(&tracing_err_log_lock); + if (PTR_ERR(err) == -ENOMEM) return; - } snprintf(err->loc, TRACING_LOG_LOC_MAX, "%s: error: ", loc); snprintf(err->cmd, len, "\n" CMD_PREFIX "%s\n", cmd); @@ -7767,7 +7711,6 @@ void tracing_log_err(struct trace_array *tr, err->info.ts = local_clock(); list_add_tail(&err->list, &tr->err_log); - mutex_unlock(&tracing_err_log_lock); } static void clear_tracing_err_log(struct trace_array *tr) @@ -9511,20 +9454,17 @@ static int instance_mkdir(const char *name) struct trace_array *tr; int ret; - mutex_lock(&event_mutex); - mutex_lock(&trace_types_lock); + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); ret = -EEXIST; if (trace_array_find(name)) - goto out_unlock; + return -EEXIST; tr = trace_array_create(name); ret = PTR_ERR_OR_ZERO(tr); -out_unlock: - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); return ret; } @@ -9574,24 +9514,23 @@ struct trace_array *trace_array_get_by_name(const char *name, const char *system { struct trace_array *tr; - mutex_lock(&event_mutex); - mutex_lock(&trace_types_lock); + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { - if (tr->name && strcmp(tr->name, name) == 0) - goto out_unlock; + if (tr->name && strcmp(tr->name, name) == 0) { + tr->ref++; + return tr; + } } tr = trace_array_create_systems(name, systems, 0, 0); if (IS_ERR(tr)) tr = NULL; -out_unlock: - if (tr) + else tr->ref++; - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); return tr; } EXPORT_SYMBOL_GPL(trace_array_get_by_name); @@ -9642,48 +9581,36 @@ static int __remove_instance(struct trace_array *tr) int trace_array_destroy(struct trace_array *this_tr) { struct trace_array *tr; - int ret; if (!this_tr) return -EINVAL; - mutex_lock(&event_mutex); - mutex_lock(&trace_types_lock); + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); - 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; - } + if (tr == this_tr) + return __remove_instance(tr); } - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); - - return ret; + return -ENODEV; } EXPORT_SYMBOL_GPL(trace_array_destroy); static int instance_rmdir(const char *name) { struct trace_array *tr; - int ret; - mutex_lock(&event_mutex); - mutex_lock(&trace_types_lock); + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); - ret = -ENODEV; tr = trace_array_find(name); - if (tr) - ret = __remove_instance(tr); - - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); + if (!tr) + return -ENODEV; - return ret; + return __remove_instance(tr); } static __init void create_trace_instances(struct dentry *d_tracer) @@ -9696,19 +9623,16 @@ static __init void create_trace_instances(struct dentry *d_tracer) if (MEM_FAIL(!trace_instance_dir, "Failed to create instances directory\n")) return; - mutex_lock(&event_mutex); - mutex_lock(&trace_types_lock); + guard(mutex)(&event_mutex); + guard(mutex)(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (!tr->name) continue; if (MEM_FAIL(trace_array_create_dir(tr) < 0, "Failed to create instance directory\n")) - break; + return; } - - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); } static void @@ -9922,7 +9846,7 @@ static void trace_module_remove_evals(struct module *mod) if (!mod->num_trace_evals) return; - mutex_lock(&trace_eval_mutex); + guard(mutex)(&trace_eval_mutex); map = trace_eval_maps; @@ -9934,12 +9858,10 @@ static void trace_module_remove_evals(struct module *mod) map = map->tail.next; } if (!map) - goto out; + return; *last = trace_eval_jmp_to_tail(map)->tail.next; kfree(map); - out: - mutex_unlock(&trace_eval_mutex); } #else static inline void trace_module_remove_evals(struct module *mod) { } -- cgit v1.2.3 From d1e27ee9c6f21ccbb3f2d910171427ceb66a0af1 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 19 Dec 2024 15:12:00 -0500 Subject: tracing: Return -EINVAL if a boot tracer tries to enable the mmiotracer at boot The mmiotracer is not set to be enabled at boot up from the kernel command line. If the boot command line tries to enable that tracer, it will fail to be enabled. The return code is currently zero when that happens so the caller just thinks it was enabled. Return -EINVAL in this case. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Link: https://lore.kernel.org/20241219201344.854254394@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index e6e1de69af01..0aaf442271e9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6116,7 +6116,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) if (system_state < SYSTEM_RUNNING && t->noboot) { pr_warn("Tracer '%s' is not allowed on command line, ignored\n", t->name); - return 0; + return -EINVAL; } /* Some tracers are only allowed for the top level buffer */ -- cgit v1.2.3 From cad1d5bd2cb9921189749b5d796026c768f56236 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 19 Dec 2024 15:12:01 -0500 Subject: tracing: Have event_enable_write() just return error on error The event_enable_write() function is inconsistent in how it returns errors. Sometimes it updates the ppos parameter and sometimes it doesn't. Simplify the code to just return an error or the count if there isn't an error. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Link: https://lore.kernel.org/20241219201345.025284170@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 1545cc8b49d0..f4eff49faef6 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1549,18 +1549,18 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, switch (val) { case 0: case 1: - ret = -ENODEV; mutex_lock(&event_mutex); file = event_file_file(filp); if (likely(file)) { ret = tracing_update_buffers(file->tr); - if (ret < 0) { - mutex_unlock(&event_mutex); - return ret; - } - ret = ftrace_event_enable_disable(file, val); + if (ret >= 0) + ret = ftrace_event_enable_disable(file, val); + } else { + ret = -ENODEV; } mutex_unlock(&event_mutex); + if (ret < 0) + return ret; break; default: @@ -1569,7 +1569,7 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, *ppos += cnt; - return ret ? ret : cnt; + return cnt; } static ssize_t -- cgit v1.2.3 From c949dfb97443b0aee0cfe138049a17e66bbc62e9 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 19 Dec 2024 15:12:02 -0500 Subject: tracing: Simplify event_enable_func() goto out_free logic The event_enable_func() function allocates the data descriptor early in the function just to assign its data->count value via: kstrtoul(number, 0, &data->count); This makes the code more complex as there are several error paths before the data descriptor is actually used. This means there needs to be a goto out_free; to clean it up. Use a local variable "count" to do the update and move the data allocation just before it is used. This removes the "out_free" label as the data can be freed on the failure path of where it is used. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Link: https://lore.kernel.org/20241219201345.190820140@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f4eff49faef6..43e9545b5cf3 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -3758,6 +3758,7 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, struct trace_event_file *file; struct ftrace_probe_ops *ops; struct event_probe_data *data; + unsigned long count = -1; const char *system; const char *event; char *number; @@ -3798,14 +3799,6 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, ret = -ENOMEM; - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) - goto out; - - data->enable = enable; - data->count = -1; - data->file = file; - if (!param) goto out_reg; @@ -3813,28 +3806,36 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, ret = -EINVAL; if (!strlen(number)) - goto out_free; + goto out; /* * We use the callback data field (which is a pointer) * as our counter. */ - ret = kstrtoul(number, 0, &data->count); + ret = kstrtoul(number, 0, &count); if (ret) - goto out_free; + goto out; out_reg: /* Don't let event modules unload while probe registered */ ret = trace_event_try_get_ref(file->event_call); if (!ret) { ret = -EBUSY; - goto out_free; + goto out; } ret = __ftrace_event_enable_disable(file, 1, 1); if (ret < 0) goto out_put; + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto out_put; + + data->enable = enable; + data->count = count; + data->file = file; + ret = register_ftrace_function_probe(glob, tr, ops, data); /* * The above returns on success the # of functions enabled, @@ -3853,11 +3854,10 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, return ret; out_disable: + kfree(data); __ftrace_event_enable_disable(file, 0, 1); out_put: trace_event_put_ref(file->event_call); - out_free: - kfree(data); goto out; } -- cgit v1.2.3 From 4b8d63e5b61dc2ee7958fb36d41c643f56de0d4d Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 19 Dec 2024 15:12:03 -0500 Subject: tracing: Simplify event_enable_func() goto_reg logic Currently there's an "out_reg:" label that gets jumped to if there's no parameters to process. Instead, make it a proper "if (param) { }" block as there's not much to do for the parameter processing, and remove the "out_reg:" label. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Link: https://lore.kernel.org/20241219201345.354746196@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 43e9545b5cf3..86db6ee6f26c 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -3799,24 +3799,22 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, ret = -ENOMEM; - if (!param) - goto out_reg; - - number = strsep(¶m, ":"); + if (param) { + number = strsep(¶m, ":"); - ret = -EINVAL; - if (!strlen(number)) - goto out; + ret = -EINVAL; + if (!strlen(number)) + goto out; - /* - * We use the callback data field (which is a pointer) - * as our counter. - */ - ret = kstrtoul(number, 0, &count); - if (ret) - goto out; + /* + * We use the callback data field (which is a pointer) + * as our counter. + */ + ret = kstrtoul(number, 0, &count); + if (ret) + goto out; + } - out_reg: /* Don't let event modules unload while probe registered */ ret = trace_event_try_get_ref(file->event_call); if (!ret) { -- cgit v1.2.3 From 59980d9b0b2dbe8945734162bb3014eac8b885bd Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 19 Dec 2024 15:12:04 -0500 Subject: tracing: Switch trace_events.c code over to use guard() There are several functions in trace_events.c that have "goto out;" or equivalent on error in order to release locks that were taken. This can be error prone or just simply make the code more complex. Switch every location that ends with unlocking a mutex on error over to using the guard(mutex)() infrastructure to let the compiler worry about releasing locks. This makes the code easier to read and understand. Some locations did some simple arithmetic after releasing the lock. As this causes no real overhead for holding a mutex while processing the file position (*ppos += cnt;) let the lock be held over this logic too. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Link: https://lore.kernel.org/20241219201345.522546095@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 103 ++++++++++++++++---------------------------- 1 file changed, 38 insertions(+), 65 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 86db6ee6f26c..047d2775184b 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1546,19 +1546,18 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, if (ret) return ret; + guard(mutex)(&event_mutex); + switch (val) { case 0: case 1: - mutex_lock(&event_mutex); file = event_file_file(filp); - if (likely(file)) { - ret = tracing_update_buffers(file->tr); - if (ret >= 0) - ret = ftrace_event_enable_disable(file, val); - } else { - ret = -ENODEV; - } - mutex_unlock(&event_mutex); + if (!file) + return -ENODEV; + ret = tracing_update_buffers(file->tr); + if (ret < 0) + return ret; + ret = ftrace_event_enable_disable(file, val); if (ret < 0) return ret; break; @@ -2145,7 +2144,7 @@ event_pid_write(struct file *filp, const char __user *ubuf, if (ret < 0) return ret; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); if (type == TRACE_PIDS) { filtered_pids = rcu_dereference_protected(tr->filtered_pids, @@ -2161,7 +2160,7 @@ event_pid_write(struct file *filp, const char __user *ubuf, ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt); if (ret < 0) - goto out; + return ret; if (type == TRACE_PIDS) rcu_assign_pointer(tr->filtered_pids, pid_list); @@ -2186,11 +2185,7 @@ event_pid_write(struct file *filp, const char __user *ubuf, */ on_each_cpu(ignore_task_cpu, tr, 1); - out: - mutex_unlock(&event_mutex); - - if (ret > 0) - *ppos += ret; + *ppos += ret; return ret; } @@ -3257,13 +3252,13 @@ int trace_add_event_call(struct trace_event_call *call) int ret; lockdep_assert_held(&event_mutex); - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); ret = __register_event(call, NULL); - if (ret >= 0) - __add_event_to_tracers(call); + if (ret < 0) + return ret; - mutex_unlock(&trace_types_lock); + __add_event_to_tracers(call); return ret; } EXPORT_SYMBOL_GPL(trace_add_event_call); @@ -3517,30 +3512,21 @@ struct trace_event_file *trace_get_event_file(const char *instance, return ERR_PTR(ret); } - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); file = find_event_file(tr, system, event); if (!file) { trace_array_put(tr); - ret = -EINVAL; - goto out; + return ERR_PTR(-EINVAL); } /* Don't let event modules unload while in use */ ret = trace_event_try_get_ref(file->event_call); if (!ret) { trace_array_put(tr); - ret = -EBUSY; - goto out; + return ERR_PTR(-EBUSY); } - ret = 0; - out: - mutex_unlock(&event_mutex); - - if (ret) - file = ERR_PTR(ret); - return file; } EXPORT_SYMBOL_GPL(trace_get_event_file); @@ -3778,12 +3764,11 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, event = strsep(¶m, ":"); - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); - ret = -EINVAL; file = find_event_file(tr, system, event); if (!file) - goto out; + return -EINVAL; enable = strcmp(cmd, ENABLE_EVENT_STR) == 0; @@ -3792,19 +3777,14 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, else ops = param ? &event_disable_count_probe_ops : &event_disable_probe_ops; - if (glob[0] == '!') { - ret = unregister_ftrace_function_probe_func(glob+1, tr, ops); - goto out; - } - - ret = -ENOMEM; + if (glob[0] == '!') + return unregister_ftrace_function_probe_func(glob+1, tr, ops); if (param) { number = strsep(¶m, ":"); - ret = -EINVAL; if (!strlen(number)) - goto out; + return -EINVAL; /* * We use the callback data field (which is a pointer) @@ -3812,20 +3792,19 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, */ ret = kstrtoul(number, 0, &count); if (ret) - goto out; + return ret; } /* Don't let event modules unload while probe registered */ ret = trace_event_try_get_ref(file->event_call); - if (!ret) { - ret = -EBUSY; - goto out; - } + if (!ret) + return -EBUSY; ret = __ftrace_event_enable_disable(file, 1, 1); if (ret < 0) goto out_put; + ret = -ENOMEM; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) goto out_put; @@ -3840,23 +3819,20 @@ event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, * but if it didn't find any functions it returns zero. * Consider no functions a failure too. */ - if (!ret) { - ret = -ENOENT; - goto out_disable; - } else if (ret < 0) - goto out_disable; + /* Just return zero, not the number of enabled functions */ - ret = 0; - out: - mutex_unlock(&event_mutex); - return ret; + if (ret > 0) + return 0; - out_disable: kfree(data); + + if (!ret) + ret = -ENOENT; + __ftrace_event_enable_disable(file, 0, 1); out_put: trace_event_put_ref(file->event_call); - goto out; + return ret; } static struct ftrace_func_command event_enable_cmd = { @@ -4079,20 +4055,17 @@ early_event_add_tracer(struct dentry *parent, struct trace_array *tr) { int ret; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); ret = create_event_toplevel_files(parent, tr); if (ret) - goto out_unlock; + return ret; down_write(&trace_event_sem); __trace_early_add_event_dirs(tr); up_write(&trace_event_sem); - out_unlock: - mutex_unlock(&event_mutex); - - return ret; + return 0; } /* Must be called with event_mutex held */ -- cgit v1.2.3 From 2b36a97aeeb71b1e4a48bfedc7f21f44aeb1e6fb Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 19 Dec 2024 15:12:05 -0500 Subject: tracing: Switch trace_events_hist.c code over to use guard() There are a couple functions in trace_events_hist.c that have "goto out" or equivalent on error in order to release locks that were taken. This can be error prone or just simply make the code more complex. Switch every location that ends with unlocking a mutex on error over to using the guard(mutex)() infrastructure to let the compiler worry about releasing locks. This makes the code easier to read and understand. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Link: https://lore.kernel.org/20241219201345.694601480@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_hist.c | 32 ++++++++++---------------------- 1 file changed, 10 insertions(+), 22 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 9c058aa8baf3..879b58892b9d 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5594,25 +5594,19 @@ static int hist_show(struct seq_file *m, void *v) { struct event_trigger_data *data; struct trace_event_file *event_file; - int n = 0, ret = 0; + int n = 0; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); event_file = event_file_file(m->private); - if (unlikely(!event_file)) { - ret = -ENODEV; - goto out_unlock; - } + if (unlikely(!event_file)) + return -ENODEV; list_for_each_entry(data, &event_file->triggers, list) { if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) hist_trigger_show(m, data, n++); } - - out_unlock: - mutex_unlock(&event_mutex); - - return ret; + return 0; } static int event_hist_open(struct inode *inode, struct file *file) @@ -5873,25 +5867,19 @@ static int hist_debug_show(struct seq_file *m, void *v) { struct event_trigger_data *data; struct trace_event_file *event_file; - int n = 0, ret = 0; + int n = 0; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); event_file = event_file_file(m->private); - if (unlikely(!event_file)) { - ret = -ENODEV; - goto out_unlock; - } + if (unlikely(!event_file)) + return -ENODEV; list_for_each_entry(data, &event_file->triggers, list) { if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) hist_trigger_debug_show(m, data, n++); } - - out_unlock: - mutex_unlock(&event_mutex); - - return ret; + return 0; } static int event_hist_debug_open(struct inode *inode, struct file *file) -- cgit v1.2.3 From 63c72641683891c5087c77e9ae7a8b43433214e7 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 20 Dec 2024 11:06:21 -0500 Subject: tracing: Switch trace_events_trigger.c code over to use guard() There are a few functions in trace_events_trigger.c that have "goto out" or equivalent on error in order to release locks that were taken. This can be error prone or just simply make the code more complex. Switch every location that ends with unlocking a mutex on error over to using the guard(mutex)() infrastructure to let the compiler worry about releasing locks. This makes the code easier to read and understand. Also use __free() for free a temporary buffer in event_trigger_regex_write(). Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Peter Zijlstra Link: https://lore.kernel.org/20241220110621.639d3bc8@gandalf.local.home Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_trigger.c | 67 +++++++++++++------------------------ 1 file changed, 23 insertions(+), 44 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index a5e3d6acf1e1..d45448947094 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -211,12 +211,10 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file) if (ret) return ret; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); - if (unlikely(!event_file_file(file))) { - mutex_unlock(&event_mutex); + if (unlikely(!event_file_file(file))) return -ENODEV; - } if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { @@ -239,8 +237,6 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file) } } - mutex_unlock(&event_mutex); - return ret; } @@ -248,7 +244,6 @@ int trigger_process_regex(struct trace_event_file *file, char *buff) { char *command, *next; struct event_command *p; - int ret = -EINVAL; next = buff = skip_spaces(buff); command = strsep(&next, ": \t"); @@ -259,17 +254,14 @@ int trigger_process_regex(struct trace_event_file *file, char *buff) } command = (command[0] != '!') ? command : command + 1; - mutex_lock(&trigger_cmd_mutex); + guard(mutex)(&trigger_cmd_mutex); + list_for_each_entry(p, &trigger_commands, list) { - if (strcmp(p->name, command) == 0) { - ret = p->parse(p, file, buff, command, next); - goto out_unlock; - } + if (strcmp(p->name, command) == 0) + return p->parse(p, file, buff, command, next); } - out_unlock: - mutex_unlock(&trigger_cmd_mutex); - return ret; + return -EINVAL; } static ssize_t event_trigger_regex_write(struct file *file, @@ -278,7 +270,7 @@ static ssize_t event_trigger_regex_write(struct file *file, { struct trace_event_file *event_file; ssize_t ret; - char *buf; + char *buf __free(kfree) = NULL; if (!cnt) return 0; @@ -292,24 +284,18 @@ static ssize_t event_trigger_regex_write(struct file *file, strim(buf); - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); + event_file = event_file_file(file); - if (unlikely(!event_file)) { - mutex_unlock(&event_mutex); - kfree(buf); + if (unlikely(!event_file)) return -ENODEV; - } - ret = trigger_process_regex(event_file, buf); - mutex_unlock(&event_mutex); - kfree(buf); + ret = trigger_process_regex(event_file, buf); if (ret < 0) - goto out; + return ret; *ppos += cnt; - ret = cnt; - out: - return ret; + return cnt; } static int event_trigger_regex_release(struct inode *inode, struct file *file) @@ -359,20 +345,16 @@ const struct file_operations event_trigger_fops = { __init int register_event_command(struct event_command *cmd) { struct event_command *p; - int ret = 0; - mutex_lock(&trigger_cmd_mutex); + guard(mutex)(&trigger_cmd_mutex); + list_for_each_entry(p, &trigger_commands, list) { - if (strcmp(cmd->name, p->name) == 0) { - ret = -EBUSY; - goto out_unlock; - } + if (strcmp(cmd->name, p->name) == 0) + return -EBUSY; } list_add(&cmd->list, &trigger_commands); - out_unlock: - mutex_unlock(&trigger_cmd_mutex); - return ret; + return 0; } /* @@ -382,20 +364,17 @@ __init int register_event_command(struct event_command *cmd) __init int unregister_event_command(struct event_command *cmd) { struct event_command *p, *n; - int ret = -ENODEV; - mutex_lock(&trigger_cmd_mutex); + guard(mutex)(&trigger_cmd_mutex); + list_for_each_entry_safe(p, n, &trigger_commands, list) { if (strcmp(cmd->name, p->name) == 0) { - ret = 0; list_del_init(&p->list); - goto out_unlock; + return 0; } } - out_unlock: - mutex_unlock(&trigger_cmd_mutex); - return ret; + return -ENODEV; } /** -- cgit v1.2.3 From 076796f74eac6eec2da6168836ff6baa8d878297 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 19 Dec 2024 15:12:08 -0500 Subject: tracing: Switch trace_events_filter.c code over to use guard() There are a couple functions in trace_events_filter.c that have "goto out" or equivalent on error in order to release locks that were taken. This can be error prone or just simply make the code more complex. Switch every location that ends with unlocking a mutex on error over to using the guard(mutex)() infrastructure to let the compiler worry about releasing locks. This makes the code easier to read and understand. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Link: https://lore.kernel.org/20241219201346.200737679@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_filter.c | 23 +++++++---------------- 1 file changed, 7 insertions(+), 16 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 78051de581e7..0993dfc1c5c1 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -2405,13 +2405,11 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir, struct event_filter *filter = NULL; int err = 0; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); /* Make sure the system still has events */ - if (!dir->nr_events) { - err = -ENODEV; - goto out_unlock; - } + if (!dir->nr_events) + return -ENODEV; if (!strcmp(strstrip(filter_string), "0")) { filter_free_subsystem_preds(dir, tr); @@ -2422,7 +2420,7 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir, tracepoint_synchronize_unregister(); filter_free_subsystem_filters(dir, tr); __free_filter(filter); - goto out_unlock; + return 0; } err = create_system_filter(dir, filter_string, &filter); @@ -2434,8 +2432,6 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir, __free_filter(system->filter); system->filter = filter; } -out_unlock: - mutex_unlock(&event_mutex); return err; } @@ -2612,17 +2608,15 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id, struct event_filter *filter = NULL; struct trace_event_call *call; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); call = event->tp_event; - err = -EINVAL; if (!call) - goto out_unlock; + return -EINVAL; - err = -EEXIST; if (event->filter) - goto out_unlock; + return -EEXIST; err = create_filter(NULL, call, filter_str, false, &filter); if (err) @@ -2637,9 +2631,6 @@ free_filter: if (err || ftrace_event_is_function(call)) __free_filter(filter); -out_unlock: - mutex_unlock(&event_mutex); - return err; } -- cgit v1.2.3 From a2e27e1bb19eb7c1790af7c8b6f7298ec524c1bb Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 19 Dec 2024 15:12:09 -0500 Subject: tracing: Switch trace_events_synth.c code over to use guard() There are a couple functions in trace_events_synth.c that have "goto out" or equivalent on error in order to release locks that were taken. This can be error prone or just simply make the code more complex. Switch every location that ends with unlocking a mutex on error over to using the guard(mutex)() infrastructure to let the compiler worry about releasing locks. This makes the code easier to read and understand. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Link: https://lore.kernel.org/20241219201346.371082515@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_synth.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index c82b401a294d..e3f7d09e5512 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -49,16 +49,11 @@ static char *last_cmd; static int errpos(const char *str) { - int ret = 0; - - mutex_lock(&lastcmd_mutex); + guard(mutex)(&lastcmd_mutex); if (!str || !last_cmd) - goto out; + return 0; - ret = err_pos(last_cmd, str); - out: - mutex_unlock(&lastcmd_mutex); - return ret; + return err_pos(last_cmd, str); } static void last_cmd_set(const char *str) @@ -74,14 +69,12 @@ static void last_cmd_set(const char *str) static void synth_err(u8 err_type, u16 err_pos) { - mutex_lock(&lastcmd_mutex); + guard(mutex)(&lastcmd_mutex); if (!last_cmd) - goto out; + return; tracing_log_err(NULL, "synthetic_events", last_cmd, err_text, err_type, err_pos); - out: - mutex_unlock(&lastcmd_mutex); } static int create_synth_event(const char *raw_command); -- cgit v1.2.3 From 930d2b32c0af6895ba4c6ca6404e7f7b6dc214ed Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 25 Dec 2024 17:25:41 -0500 Subject: tracing: Switch trace_osnoise.c code over to use guard() and __free() The osnoise_hotplug_workfn() grabs two mutexes and cpu_read_lock(). It has various gotos to handle unlocking them. Switch them over to guard() and let the compiler worry about it. The osnoise_cpus_read() has a temporary mask_str allocated and there's some gotos to make sure it gets freed on error paths. Switch that over to __free() to let the compiler worry about it. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Link: https://lore.kernel.org/20241225222931.517329690@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_osnoise.c | 40 +++++++++++++--------------------------- 1 file changed, 13 insertions(+), 27 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index b9f96c77527d..b25c30b05dd0 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -2083,26 +2083,21 @@ static void osnoise_hotplug_workfn(struct work_struct *dummy) { unsigned int cpu = smp_processor_id(); - mutex_lock(&trace_types_lock); + guard(mutex)(&trace_types_lock); if (!osnoise_has_registered_instances()) - goto out_unlock_trace; + return; - mutex_lock(&interface_lock); - cpus_read_lock(); + guard(mutex)(&interface_lock); + guard(cpus_read_lock)(); if (!cpu_online(cpu)) - goto out_unlock; + return; + if (!cpumask_test_cpu(cpu, &osnoise_cpumask)) - goto out_unlock; + return; start_kthread(cpu); - -out_unlock: - cpus_read_unlock(); - mutex_unlock(&interface_lock); -out_unlock_trace: - mutex_unlock(&trace_types_lock); } static DECLARE_WORK(osnoise_hotplug_work, osnoise_hotplug_workfn); @@ -2300,31 +2295,22 @@ static ssize_t osnoise_cpus_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { - char *mask_str; + char *mask_str __free(kfree) = NULL; int len; - mutex_lock(&interface_lock); + guard(mutex)(&interface_lock); len = snprintf(NULL, 0, "%*pbl\n", cpumask_pr_args(&osnoise_cpumask)) + 1; mask_str = kmalloc(len, GFP_KERNEL); - if (!mask_str) { - count = -ENOMEM; - goto out_unlock; - } + if (!mask_str) + return -ENOMEM; len = snprintf(mask_str, len, "%*pbl\n", cpumask_pr_args(&osnoise_cpumask)); - if (len >= count) { - count = -EINVAL; - goto out_free; - } + if (len >= count) + return -EINVAL; count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len); -out_free: - kfree(mask_str); -out_unlock: - mutex_unlock(&interface_lock); - return count; } -- cgit v1.2.3 From 6c05353e4ff5875807f1a00f8d95e68b3d1e4d7f Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 25 Dec 2024 17:25:42 -0500 Subject: tracing: Switch trace_stack.c code over to use guard() The function stack_trace_sysctl() uses a goto on the error path to jump to the mutex_unlock() code. Replace the logic to use guard() and let the compiler worry about it. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Link: https://lore.kernel.org/20241225222931.684913592@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_stack.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 7f9572a37333..14c6f272c4d8 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -520,20 +520,18 @@ stack_trace_sysctl(const struct ctl_table *table, int write, void *buffer, int was_enabled; int ret; - mutex_lock(&stack_sysctl_mutex); + guard(mutex)(&stack_sysctl_mutex); was_enabled = !!stack_tracer_enabled; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (was_enabled == !!stack_tracer_enabled)) - goto out; + return ret; if (stack_tracer_enabled) register_ftrace_function(&trace_ops); else unregister_ftrace_function(&trace_ops); - out: - mutex_unlock(&stack_sysctl_mutex); return ret; } -- cgit v1.2.3 From 08b767317192e7a20d6d95ff7eca6d9bbc48c192 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 19 Dec 2024 15:12:12 -0500 Subject: tracing: Switch trace_stat.c code over to use guard() There are a couple functions in trace_stat.c that have "goto out" or equivalent on error in order to release locks that were taken. This can be error prone or just simply make the code more complex. Switch every location that ends with unlocking a mutex on error over to using the guard(mutex)() infrastructure to let the compiler worry about releasing locks. This makes the code easier to read and understand. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Link: https://lore.kernel.org/20241219201346.870318466@goodmis.org Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_stat.c | 26 ++++++++++---------------- 1 file changed, 10 insertions(+), 16 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index bb247beec447..b3b5586f104d 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -128,7 +128,7 @@ static int stat_seq_init(struct stat_session *session) int ret = 0; int i; - mutex_lock(&session->stat_mutex); + guard(mutex)(&session->stat_mutex); __reset_stat_session(session); if (!ts->stat_cmp) @@ -136,11 +136,11 @@ static int stat_seq_init(struct stat_session *session) stat = ts->stat_start(ts); if (!stat) - goto exit; + return 0; ret = insert_stat(root, stat, ts->stat_cmp); if (ret) - goto exit; + return ret; /* * Iterate over the tracer stat entries and store them in an rbtree. @@ -157,13 +157,10 @@ static int stat_seq_init(struct stat_session *session) goto exit_free_rbtree; } -exit: - mutex_unlock(&session->stat_mutex); return ret; exit_free_rbtree: __reset_stat_session(session); - mutex_unlock(&session->stat_mutex); return ret; } @@ -308,7 +305,7 @@ static int init_stat_file(struct stat_session *session) int register_stat_tracer(struct tracer_stat *trace) { struct stat_session *session, *node; - int ret = -EINVAL; + int ret; if (!trace) return -EINVAL; @@ -316,18 +313,18 @@ int register_stat_tracer(struct tracer_stat *trace) if (!trace->stat_start || !trace->stat_next || !trace->stat_show) return -EINVAL; + guard(mutex)(&all_stat_sessions_mutex); + /* Already registered? */ - mutex_lock(&all_stat_sessions_mutex); list_for_each_entry(node, &all_stat_sessions, session_list) { if (node->ts == trace) - goto out; + return -EINVAL; } - ret = -ENOMEM; /* Init the session */ session = kzalloc(sizeof(*session), GFP_KERNEL); if (!session) - goto out; + return -ENOMEM; session->ts = trace; INIT_LIST_HEAD(&session->session_list); @@ -336,16 +333,13 @@ int register_stat_tracer(struct tracer_stat *trace) ret = init_stat_file(session); if (ret) { destroy_session(session); - goto out; + return ret; } - ret = 0; /* Register */ list_add_tail(&session->session_list, &all_stat_sessions); - out: - mutex_unlock(&all_stat_sessions_mutex); - return ret; + return 0; } void unregister_stat_tracer(struct tracer_stat *trace) -- cgit v1.2.3 From 9e49ca756d207f4313fb7af48648a67da8e4e250 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 20 Dec 2024 10:33:13 -0500 Subject: tracing/string: Create and use __free(argv_free) in trace_dynevent.c The function dyn_event_release() uses argv_split() which must be freed via argv_free(). It contains several error paths that do a goto out to call argv_free() for cleanup. This makes the code complex and error prone. Create a new __free() directive __free(argv_free) that will call argv_free() for data allocated with argv_split(), and use it in the dyn_event_release() function. Cc: Kees Cook Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Peter Zijlstra Cc: Andy Shevchenko Cc: linux-hardening@vger.kernel.org Link: https://lore.kernel.org/20241220103313.4a74ec8e@gandalf.local.home Signed-off-by: Steven Rostedt (Google) --- include/linux/string.h | 3 +++ kernel/trace/trace_dynevent.c | 23 +++++++---------------- 2 files changed, 10 insertions(+), 16 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/string.h b/include/linux/string.h index 493ac4862c77..86d5d352068b 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -4,6 +4,7 @@ #include #include +#include /* for DEFINE_FREE() */ #include /* for inline */ #include /* for size_t */ #include /* for NULL */ @@ -312,6 +313,8 @@ extern void *kmemdup_array(const void *src, size_t count, size_t element_size, g extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); +DEFINE_FREE(argv_free, char **, if (!IS_ERR_OR_NULL(_T)) argv_free(_T)) + /* lib/cmdline.c */ extern int get_option(char **str, int *pint); extern char *get_options(const char *str, int nints, int *ints); diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index 4376887e0d8a..a322e4f249a5 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -74,24 +74,19 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type struct dyn_event *pos, *n; char *system = NULL, *event, *p; int argc, ret = -ENOENT; - char **argv; + char **argv __free(argv_free) = argv_split(GFP_KERNEL, raw_command, &argc); - argv = argv_split(GFP_KERNEL, raw_command, &argc); if (!argv) return -ENOMEM; if (argv[0][0] == '-') { - if (argv[0][1] != ':') { - ret = -EINVAL; - goto out; - } + if (argv[0][1] != ':') + return -EINVAL; event = &argv[0][2]; } else { event = strchr(argv[0], ':'); - if (!event) { - ret = -EINVAL; - goto out; - } + if (!event) + return -EINVAL; event++; } @@ -101,10 +96,8 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type event = p + 1; *p = '\0'; } - if (!system && event[0] == '\0') { - ret = -EINVAL; - goto out; - } + if (!system && event[0] == '\0') + return -EINVAL; mutex_lock(&event_mutex); for_each_dyn_event_safe(pos, n) { @@ -120,8 +113,6 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type } tracing_reset_all_online_cpus(); mutex_unlock(&event_mutex); -out: - argv_free(argv); return ret; } -- cgit v1.2.3 From 41705c4262aaca49b8d9fe9b24fe048dc6c2b301 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:11:40 +0900 Subject: fgraph: Pass ftrace_regs to entryfunc Pass ftrace_regs to the fgraph_ops::entryfunc(). If ftrace_regs is not available, it passes a NULL instead. User callback function can access some registers (including return address) via this ftrace_regs. Note that the ftrace_regs can be NULL when the arch does NOT define: HAVE_DYNAMIC_FTRACE_WITH_ARGS or HAVE_DYNAMIC_FTRACE_WITH_REGS. More specifically, if HAVE_DYNAMIC_FTRACE_WITH_REGS is defined but not the HAVE_DYNAMIC_FTRACE_WITH_ARGS, and the ftrace ops used to register the function callback does not set FTRACE_OPS_FL_SAVE_REGS. In this case, ftrace_regs can be NULL in user callback. Signed-off-by: Masami Hiramatsu (Google) Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Cc: Catalin Marinas Cc: Will Deacon Cc: Huacai Chen Cc: WANG Xuerui Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: Naveen N Rao Cc: Madhavan Srinivasan Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173518990044.391279.17406984900626078579.stgit@devnote2 Signed-off-by: Steven Rostedt (Google) --- arch/arm64/kernel/ftrace.c | 15 +++++++++++- arch/loongarch/kernel/ftrace_dyn.c | 10 +++++++- arch/powerpc/kernel/trace/ftrace.c | 2 +- arch/powerpc/kernel/trace/ftrace_64_pg.c | 10 +++++--- arch/riscv/kernel/ftrace.c | 17 ++++++++++++- arch/x86/kernel/ftrace.c | 42 +++++++++++++++++++++----------- include/linux/ftrace.h | 17 ++++++++++--- kernel/trace/fgraph.c | 20 +++++++++------ kernel/trace/ftrace.c | 3 ++- kernel/trace/trace.h | 3 ++- kernel/trace/trace_functions_graph.c | 3 ++- kernel/trace/trace_irqsoff.c | 3 ++- kernel/trace/trace_sched_wakeup.c | 3 ++- kernel/trace/trace_selftest.c | 8 +++--- 14 files changed, 114 insertions(+), 42 deletions(-) (limited to 'kernel/trace') diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 245cb419ca24..570c38be833c 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -481,7 +481,20 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { - prepare_ftrace_return(ip, &arch_ftrace_regs(fregs)->lr, arch_ftrace_regs(fregs)->fp); + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long frame_pointer = arch_ftrace_regs(fregs)->fp; + unsigned long *parent = &arch_ftrace_regs(fregs)->lr; + unsigned long old; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + old = *parent; + + if (!function_graph_enter_regs(old, ip, frame_pointer, + (void *)frame_pointer, fregs)) { + *parent = return_hooker; + } } #else /* diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c index 18056229e22e..25c9a4cfd5fa 100644 --- a/arch/loongarch/kernel/ftrace_dyn.c +++ b/arch/loongarch/kernel/ftrace_dyn.c @@ -243,8 +243,16 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, { struct pt_regs *regs = &arch_ftrace_regs(fregs)->regs; unsigned long *parent = (unsigned long *)®s->regs[1]; + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long old; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + old = *parent; - prepare_ftrace_return(ip, (unsigned long *)parent); + if (!function_graph_enter_regs(old, ip, 0, parent, fregs)) + *parent = return_hooker; } #else static int ftrace_modify_graph_caller(bool enable) diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index e41daf2c4a31..2f776f137a89 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -665,7 +665,7 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; - if (!function_graph_enter(parent_ip, ip, 0, (unsigned long *)sp)) + if (!function_graph_enter_regs(parent_ip, ip, 0, (unsigned long *)sp, fregs)) parent_ip = ppc_function_entry(return_to_handler); out: diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c index 8fb860b90ae1..ac35015f04c6 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_pg.c +++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c @@ -787,7 +787,8 @@ int ftrace_disable_ftrace_graph_caller(void) * in current thread info. Return the address we want to divert to. */ static unsigned long -__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp) +__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp, + struct ftrace_regs *fregs) { unsigned long return_hooker; @@ -799,7 +800,7 @@ __prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp return_hooker = ppc_function_entry(return_to_handler); - if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp)) + if (!function_graph_enter_regs(parent, ip, 0, (unsigned long *)sp, fregs)) parent = return_hooker; out: @@ -810,13 +811,14 @@ out: void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { - arch_ftrace_regs(fregs)->regs.link = __prepare_ftrace_return(parent_ip, ip, arch_ftrace_regs(fregs)->regs.gpr[1]); + arch_ftrace_regs(fregs)->regs.link = __prepare_ftrace_return(parent_ip, ip, + arch_ftrace_regs(fregs)->regs.gpr[1], fregs); } #else unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp) { - return __prepare_ftrace_return(parent, ip, sp); + return __prepare_ftrace_return(parent, ip, sp, NULL); } #endif #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 8cb9b211611d..3524db5e4fa0 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -214,7 +214,22 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { - prepare_ftrace_return(&arch_ftrace_regs(fregs)->ra, ip, arch_ftrace_regs(fregs)->s0); + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long frame_pointer = arch_ftrace_regs(fregs)->s0; + unsigned long *parent = &arch_ftrace_regs(fregs)->ra; + unsigned long old; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + /* + * We don't suffer access faults, so no extra fault-recovery assembly + * is needed here. + */ + old = *parent; + + if (!function_graph_enter_regs(old, ip, frame_pointer, parent, fregs)) + *parent = return_hooker; } #else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ extern void ftrace_graph_call(void); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 33f50c80f481..166bc0ea3bdf 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -607,15 +607,8 @@ int ftrace_disable_ftrace_graph_caller(void) } #endif /* CONFIG_DYNAMIC_FTRACE && !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ -/* - * Hook the return address and push it in the stack of return addrs - * in current thread info. - */ -void prepare_ftrace_return(unsigned long ip, unsigned long *parent, - unsigned long frame_pointer) +static inline bool skip_ftrace_return(void) { - unsigned long return_hooker = (unsigned long)&return_to_handler; - /* * When resuming from suspend-to-ram, this function can be indirectly * called from early CPU startup code while the CPU is in real mode, @@ -625,13 +618,27 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent, * This check isn't as accurate as virt_addr_valid(), but it should be * good enough for this purpose, and it's fast. */ - if (unlikely((long)__builtin_frame_address(0) >= 0)) - return; + if ((long)__builtin_frame_address(0) >= 0) + return true; - if (unlikely(ftrace_graph_is_dead())) - return; + if (ftrace_graph_is_dead()) + return true; + + if (atomic_read(¤t->tracing_graph_pause)) + return true; + return false; +} + +/* + * Hook the return address and push it in the stack of return addrs + * in current thread info. + */ +void prepare_ftrace_return(unsigned long ip, unsigned long *parent, + unsigned long frame_pointer) +{ + unsigned long return_hooker = (unsigned long)&return_to_handler; - if (unlikely(atomic_read(¤t->tracing_graph_pause))) + if (unlikely(skip_ftrace_return())) return; if (!function_graph_enter(*parent, ip, frame_pointer, parent)) @@ -644,8 +651,15 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, { struct pt_regs *regs = &arch_ftrace_regs(fregs)->regs; unsigned long *stack = (unsigned long *)kernel_stack_pointer(regs); + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long *parent = (unsigned long *)stack; + + if (unlikely(skip_ftrace_return())) + return; + - prepare_ftrace_return(ip, (unsigned long *)stack, 0); + if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs)) + *parent = return_hooker; } #endif diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index aa9ddd1e4bb6..c86ac786da3d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1071,10 +1071,12 @@ struct fgraph_ops; typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *, struct fgraph_ops *); /* return */ typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *, - struct fgraph_ops *); /* entry */ + struct fgraph_ops *, + struct ftrace_regs *); /* entry */ extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops); + struct fgraph_ops *gops, + struct ftrace_regs *fregs); bool ftrace_pids_enabled(struct ftrace_ops *ops); #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -1114,8 +1116,15 @@ struct ftrace_ret_stack { extern void return_to_handler(void); extern int -function_graph_enter(unsigned long ret, unsigned long func, - unsigned long frame_pointer, unsigned long *retp); +function_graph_enter_regs(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp, + struct ftrace_regs *fregs); + +static inline int function_graph_enter(unsigned long ret, unsigned long func, + unsigned long fp, unsigned long *retp) +{ + return function_graph_enter_regs(ret, func, fp, retp, NULL); +} struct ftrace_ret_stack * ftrace_graph_get_ret_stack(struct task_struct *task, int skip); diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 5c68d6109119..4791fd704e28 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -292,7 +292,8 @@ static inline unsigned long make_data_type_val(int idx, int size, int offset) } /* ftrace_graph_entry set to this to tell some archs to run function graph */ -static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops) +static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops, + struct ftrace_regs *fregs) { return 0; } @@ -520,7 +521,8 @@ int __weak ftrace_disable_ftrace_graph_caller(void) #endif int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { return 0; } @@ -644,8 +646,9 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, #endif /* If the caller does not use ftrace, call this function. */ -int function_graph_enter(unsigned long ret, unsigned long func, - unsigned long frame_pointer, unsigned long *retp) +int function_graph_enter_regs(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp, + struct ftrace_regs *fregs) { struct ftrace_graph_ent trace; unsigned long bitmap = 0; @@ -668,7 +671,7 @@ int function_graph_enter(unsigned long ret, unsigned long func, if (static_branch_likely(&fgraph_do_direct)) { int save_curr_ret_stack = current->curr_ret_stack; - if (static_call(fgraph_func)(&trace, fgraph_direct_gops)) + if (static_call(fgraph_func)(&trace, fgraph_direct_gops, fregs)) bitmap |= BIT(fgraph_direct_gops->idx); else /* Clear out any saved storage */ @@ -686,7 +689,7 @@ int function_graph_enter(unsigned long ret, unsigned long func, save_curr_ret_stack = current->curr_ret_stack; if (ftrace_ops_test(&gops->ops, func, NULL) && - gops->entryfunc(&trace, gops)) + gops->entryfunc(&trace, gops, fregs)) bitmap |= BIT(i); else /* Clear out any saved storage */ @@ -1180,7 +1183,8 @@ void ftrace_graph_exit_task(struct task_struct *t) #ifdef CONFIG_DYNAMIC_FTRACE static int fgraph_pid_func(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = gops->ops.private; int pid; @@ -1194,7 +1198,7 @@ static int fgraph_pid_func(struct ftrace_graph_ent *trace, return 0; } - return gops->saved_func(trace, gops); + return gops->saved_func(trace, gops, fregs); } void fgraph_update_pid_func(void) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6ebc76bafd38..ae29e1c4177d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -819,7 +819,8 @@ struct profile_fgraph_data { }; static int profile_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct profile_fgraph_data *profile_data; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 9691b47b5f3d..0f38f36a5a8a 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -694,7 +694,8 @@ void trace_default_header(struct seq_file *m); void print_trace_header(struct seq_file *m, struct trace_iterator *iter); void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops); -int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops); +int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs); void tracing_start_cmdline_record(void); void tracing_stop_cmdline_record(void); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index f513603d7df9..676cf3e38f51 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -175,7 +175,8 @@ struct fgraph_times { }; int trace_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { unsigned long *task_var = fgraph_get_task_var(gops); struct trace_array *tr = gops->private; diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index fce064e20570..ad739d76fc86 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -176,7 +176,8 @@ static int irqsoff_display_graph(struct trace_array *tr, int set) } static int irqsoff_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index d6c7f18daa15..0d9e1075d815 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -113,7 +113,8 @@ static int wakeup_display_graph(struct trace_array *tr, int set) } static int wakeup_graph_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 38b5754790c9..f54493f8783d 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -774,7 +774,8 @@ struct fgraph_fixture { }; static __init int store_entry(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct fgraph_fixture *fixture = container_of(gops, struct fgraph_fixture, gops); const char *type = fixture->store_type_name; @@ -1025,7 +1026,8 @@ static unsigned int graph_hang_thresh; /* Wrap the real function entry probe to avoid possible hanging */ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { /* This is harmlessly racy, we want to approximately detect a hang */ if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) { @@ -1039,7 +1041,7 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace, return 0; } - return trace_graph_entry(trace, gops); + return trace_graph_entry(trace, gops, fregs); } static struct fgraph_ops fgraph_ops __initdata = { -- cgit v1.2.3 From a3ed4157b7d89800a0008de0c9e46a438a5c3745 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:11:55 +0900 Subject: fgraph: Replace fgraph_ret_regs with ftrace_regs Use ftrace_regs instead of fgraph_ret_regs for tracing return value on function_graph tracer because of simplifying the callback interface. The CONFIG_HAVE_FUNCTION_GRAPH_RETVAL is also replaced by CONFIG_HAVE_FUNCTION_GRAPH_FREGS. Signed-off-by: Masami Hiramatsu (Google) Acked-by: Heiko Carstens Acked-by: Will Deacon Cc: Catalin Marinas Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Cc: Huacai Chen Cc: WANG Xuerui Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Vasily Gorbik Cc: Alexander Gordeev Cc: Heiko Carstens Cc: Christian Borntraeger Cc: Sven Schnelle Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173518991508.391279.16635322774382197642.stgit@devnote2 Signed-off-by: Steven Rostedt (Google) --- arch/arm64/Kconfig | 1 + arch/arm64/include/asm/ftrace.h | 23 ++++++----------------- arch/arm64/kernel/asm-offsets.c | 12 ------------ arch/arm64/kernel/entry-ftrace.S | 32 ++++++++++++++++++-------------- arch/loongarch/Kconfig | 2 +- arch/loongarch/include/asm/ftrace.h | 26 ++++---------------------- arch/loongarch/kernel/asm-offsets.c | 12 ------------ arch/loongarch/kernel/mcount.S | 17 ++++++++++------- arch/loongarch/kernel/mcount_dyn.S | 14 +++++++------- arch/riscv/Kconfig | 2 +- arch/riscv/include/asm/ftrace.h | 26 +++++--------------------- arch/riscv/kernel/mcount.S | 24 +++++++++++++----------- arch/s390/Kconfig | 2 +- arch/s390/include/asm/ftrace.h | 24 +++++++----------------- arch/s390/kernel/asm-offsets.c | 6 ------ arch/s390/kernel/mcount.S | 12 ++++++------ arch/x86/Kconfig | 2 +- arch/x86/include/asm/ftrace.h | 20 -------------------- arch/x86/kernel/ftrace_32.S | 13 +++++++------ arch/x86/kernel/ftrace_64.S | 17 +++++++++-------- include/linux/ftrace.h | 12 +++++++++--- include/linux/ftrace_regs.h | 2 ++ kernel/trace/Kconfig | 4 ++-- kernel/trace/fgraph.c | 21 +++++++++------------ 24 files changed, 119 insertions(+), 207 deletions(-) (limited to 'kernel/trace') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 100570a048c5..5f086777dad9 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -219,6 +219,7 @@ config ARM64 select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_ERROR_INJECTION + select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_GRAPH_RETVAL select HAVE_GCC_PLUGINS diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 5ccff4de7f09..b5fa57b61378 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -129,6 +129,12 @@ ftrace_override_function_with_return(struct ftrace_regs *fregs) arch_ftrace_regs(fregs)->pc = arch_ftrace_regs(fregs)->lr; } +static __always_inline unsigned long +ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->fp; +} + int ftrace_regs_query_register_offset(const char *name); int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); @@ -186,23 +192,6 @@ static inline bool arch_syscall_match_sym_name(const char *sym, #ifndef __ASSEMBLY__ #ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - /* x0 - x7 */ - unsigned long regs[8]; - - unsigned long fp; - unsigned long __unused; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->regs[0]; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->fp; -} void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long frame_pointer); diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 29bf85dacffe..eb1a840e4110 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -179,18 +179,6 @@ int main(void) DEFINE(FTRACE_OPS_FUNC, offsetof(struct ftrace_ops, func)); #endif BLANK(); -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - DEFINE(FGRET_REGS_X0, offsetof(struct fgraph_ret_regs, regs[0])); - DEFINE(FGRET_REGS_X1, offsetof(struct fgraph_ret_regs, regs[1])); - DEFINE(FGRET_REGS_X2, offsetof(struct fgraph_ret_regs, regs[2])); - DEFINE(FGRET_REGS_X3, offsetof(struct fgraph_ret_regs, regs[3])); - DEFINE(FGRET_REGS_X4, offsetof(struct fgraph_ret_regs, regs[4])); - DEFINE(FGRET_REGS_X5, offsetof(struct fgraph_ret_regs, regs[5])); - DEFINE(FGRET_REGS_X6, offsetof(struct fgraph_ret_regs, regs[6])); - DEFINE(FGRET_REGS_X7, offsetof(struct fgraph_ret_regs, regs[7])); - DEFINE(FGRET_REGS_FP, offsetof(struct fgraph_ret_regs, fp)); - DEFINE(FGRET_REGS_SIZE, sizeof(struct fgraph_ret_regs)); -#endif #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS DEFINE(FTRACE_OPS_DIRECT_CALL, offsetof(struct ftrace_ops, direct_call)); #endif diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index f0c16640ef21..169ccf600066 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -329,24 +329,28 @@ SYM_FUNC_END(ftrace_stub_graph) * @fp is checked against the value passed by ftrace_graph_caller(). */ SYM_CODE_START(return_to_handler) - /* save return value regs */ - sub sp, sp, #FGRET_REGS_SIZE - stp x0, x1, [sp, #FGRET_REGS_X0] - stp x2, x3, [sp, #FGRET_REGS_X2] - stp x4, x5, [sp, #FGRET_REGS_X4] - stp x6, x7, [sp, #FGRET_REGS_X6] - str x29, [sp, #FGRET_REGS_FP] // parent's fp + /* Make room for ftrace_regs */ + sub sp, sp, #FREGS_SIZE + + /* Save return value regs */ + stp x0, x1, [sp, #FREGS_X0] + stp x2, x3, [sp, #FREGS_X2] + stp x4, x5, [sp, #FREGS_X4] + stp x6, x7, [sp, #FREGS_X6] + + /* Save the callsite's FP */ + str x29, [sp, #FREGS_FP] mov x0, sp - bl ftrace_return_to_handler // addr = ftrace_return_to_hander(regs); + bl ftrace_return_to_handler // addr = ftrace_return_to_hander(fregs); mov x30, x0 // restore the original return address - /* restore return value regs */ - ldp x0, x1, [sp, #FGRET_REGS_X0] - ldp x2, x3, [sp, #FGRET_REGS_X2] - ldp x4, x5, [sp, #FGRET_REGS_X4] - ldp x6, x7, [sp, #FGRET_REGS_X6] - add sp, sp, #FGRET_REGS_SIZE + /* Restore return value regs */ + ldp x0, x1, [sp, #FREGS_X0] + ldp x2, x3, [sp, #FREGS_X2] + ldp x4, x5, [sp, #FREGS_X4] + ldp x6, x7, [sp, #FREGS_X6] + add sp, sp, #FREGS_SIZE ret SYM_CODE_END(return_to_handler) diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index dae3a9104ca6..49f5bfc00e5a 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -137,7 +137,7 @@ config LOONGARCH select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION - select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h index 8f13eaeaa325..ceb3e3d9c0d3 100644 --- a/arch/loongarch/include/asm/ftrace.h +++ b/arch/loongarch/include/asm/ftrace.h @@ -57,6 +57,10 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip) instruction_pointer_set(&arch_ftrace_regs(fregs)->regs, ip); } +#undef ftrace_regs_get_frame_pointer +#define ftrace_regs_get_frame_pointer(fregs) \ + (arch_ftrace_regs(fregs)->regs.regs[22]) + #define ftrace_graph_func ftrace_graph_func void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); @@ -78,26 +82,4 @@ __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) #endif /* CONFIG_FUNCTION_TRACER */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - /* a0 - a1 */ - unsigned long regs[2]; - - unsigned long fp; - unsigned long __unused; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->regs[0]; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->fp; -} -#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */ -#endif - #endif /* _ASM_LOONGARCH_FTRACE_H */ diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c index 049c5c3e370c..8be1c38ad8eb 100644 --- a/arch/loongarch/kernel/asm-offsets.c +++ b/arch/loongarch/kernel/asm-offsets.c @@ -280,18 +280,6 @@ static void __used output_pbe_defines(void) } #endif -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -static void __used output_fgraph_ret_regs_defines(void) -{ - COMMENT("LoongArch fgraph_ret_regs offsets."); - OFFSET(FGRET_REGS_A0, fgraph_ret_regs, regs[0]); - OFFSET(FGRET_REGS_A1, fgraph_ret_regs, regs[1]); - OFFSET(FGRET_REGS_FP, fgraph_ret_regs, fp); - DEFINE(FGRET_REGS_SIZE, sizeof(struct fgraph_ret_regs)); - BLANK(); -} -#endif - static void __used output_kvm_defines(void) { COMMENT("KVM/LoongArch Specific offsets."); diff --git a/arch/loongarch/kernel/mcount.S b/arch/loongarch/kernel/mcount.S index 3015896016a0..b6850503e061 100644 --- a/arch/loongarch/kernel/mcount.S +++ b/arch/loongarch/kernel/mcount.S @@ -79,10 +79,11 @@ SYM_FUNC_START(ftrace_graph_caller) SYM_FUNC_END(ftrace_graph_caller) SYM_FUNC_START(return_to_handler) - PTR_ADDI sp, sp, -FGRET_REGS_SIZE - PTR_S a0, sp, FGRET_REGS_A0 - PTR_S a1, sp, FGRET_REGS_A1 - PTR_S zero, sp, FGRET_REGS_FP + /* Save return value regs */ + PTR_ADDI sp, sp, -PT_SIZE + PTR_S a0, sp, PT_R4 + PTR_S a1, sp, PT_R5 + PTR_S zero, sp, PT_R22 move a0, sp bl ftrace_return_to_handler @@ -90,9 +91,11 @@ SYM_FUNC_START(return_to_handler) /* Restore the real parent address: a0 -> ra */ move ra, a0 - PTR_L a0, sp, FGRET_REGS_A0 - PTR_L a1, sp, FGRET_REGS_A1 - PTR_ADDI sp, sp, FGRET_REGS_SIZE + /* Restore return value regs */ + PTR_L a0, sp, PT_R4 + PTR_L a1, sp, PT_R5 + PTR_ADDI sp, sp, PT_SIZE + jr ra SYM_FUNC_END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/loongarch/kernel/mcount_dyn.S b/arch/loongarch/kernel/mcount_dyn.S index 0c65cf09110c..d6b474ad1d5e 100644 --- a/arch/loongarch/kernel/mcount_dyn.S +++ b/arch/loongarch/kernel/mcount_dyn.S @@ -140,19 +140,19 @@ SYM_CODE_END(ftrace_graph_caller) SYM_CODE_START(return_to_handler) UNWIND_HINT_UNDEFINED /* Save return value regs */ - PTR_ADDI sp, sp, -FGRET_REGS_SIZE - PTR_S a0, sp, FGRET_REGS_A0 - PTR_S a1, sp, FGRET_REGS_A1 - PTR_S zero, sp, FGRET_REGS_FP + PTR_ADDI sp, sp, -PT_SIZE + PTR_S a0, sp, PT_R4 + PTR_S a1, sp, PT_R5 + PTR_S zero, sp, PT_R22 move a0, sp bl ftrace_return_to_handler move ra, a0 /* Restore return value regs */ - PTR_L a0, sp, FGRET_REGS_A0 - PTR_L a1, sp, FGRET_REGS_A1 - PTR_ADDI sp, sp, FGRET_REGS_SIZE + PTR_L a0, sp, PT_R4 + PTR_L a1, sp, PT_R5 + PTR_ADDI sp, sp, PT_SIZE jr ra SYM_CODE_END(return_to_handler) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index d4a7ca0388c0..1e807c61258f 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -148,7 +148,7 @@ config RISCV select HAVE_DYNAMIC_FTRACE_WITH_ARGS if HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION select HAVE_EBPF_JIT if MMU select HAVE_GUP_FAST if MMU diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index 3d66437a1029..9372f8d7036f 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -168,6 +168,11 @@ static __always_inline unsigned long ftrace_regs_get_stack_pointer(const struct return arch_ftrace_regs(fregs)->sp; } +static __always_inline unsigned long ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->s0; +} + static __always_inline unsigned long ftrace_regs_get_argument(struct ftrace_regs *fregs, unsigned int n) { @@ -208,25 +213,4 @@ static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsi #endif /* CONFIG_DYNAMIC_FTRACE */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - unsigned long a1; - unsigned long a0; - unsigned long s0; - unsigned long ra; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->a0; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->s0; -} -#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */ -#endif - #endif /* _ASM_RISCV_FTRACE_H */ diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S index 3a42f6287909..068168046e0e 100644 --- a/arch/riscv/kernel/mcount.S +++ b/arch/riscv/kernel/mcount.S @@ -12,6 +12,8 @@ #include #include +#define ABI_SIZE_ON_STACK 80 + .text .macro SAVE_ABI_STATE @@ -26,12 +28,12 @@ * register if a0 was not saved. */ .macro SAVE_RET_ABI_STATE - addi sp, sp, -4*SZREG - REG_S s0, 2*SZREG(sp) - REG_S ra, 3*SZREG(sp) - REG_S a0, 1*SZREG(sp) - REG_S a1, 0*SZREG(sp) - addi s0, sp, 4*SZREG + addi sp, sp, -ABI_SIZE_ON_STACK + REG_S ra, 1*SZREG(sp) + REG_S s0, 8*SZREG(sp) + REG_S a0, 10*SZREG(sp) + REG_S a1, 11*SZREG(sp) + addi s0, sp, ABI_SIZE_ON_STACK .endm .macro RESTORE_ABI_STATE @@ -41,11 +43,11 @@ .endm .macro RESTORE_RET_ABI_STATE - REG_L ra, 3*SZREG(sp) - REG_L s0, 2*SZREG(sp) - REG_L a0, 1*SZREG(sp) - REG_L a1, 0*SZREG(sp) - addi sp, sp, 4*SZREG + REG_L ra, 1*SZREG(sp) + REG_L s0, 8*SZREG(sp) + REG_L a0, 10*SZREG(sp) + REG_L a1, 11*SZREG(sp) + addi sp, sp, ABI_SIZE_ON_STACK .endm SYM_TYPED_FUNC_START(ftrace_stub) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 0077969170e8..102029e56cf0 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -192,7 +192,7 @@ config S390 select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION - select HAVE_FUNCTION_GRAPH_RETVAL + select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index fc97d75dc752..5c94c1fc1bc1 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -62,23 +62,6 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs * return NULL; } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - unsigned long gpr2; - unsigned long fp; -}; - -static __always_inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->gpr2; -} - -static __always_inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->fp; -} -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ - static __always_inline void ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip) @@ -86,6 +69,13 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, arch_ftrace_regs(fregs)->regs.psw.addr = ip; } +#undef ftrace_regs_get_frame_pointer +static __always_inline unsigned long +ftrace_regs_get_frame_pointer(struct ftrace_regs *fregs) +{ + return ftrace_regs_get_stack_pointer(fregs); +} + #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS /* * When an ftrace registered caller is tracing a function that is diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 862a9140528e..36709112ae7a 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -175,12 +175,6 @@ int main(void) DEFINE(OLDMEM_SIZE, PARMAREA + offsetof(struct parmarea, oldmem_size)); DEFINE(COMMAND_LINE, PARMAREA + offsetof(struct parmarea, command_line)); DEFINE(MAX_COMMAND_LINE_SIZE, PARMAREA + offsetof(struct parmarea, max_command_line_size)); -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* function graph return value tracing */ - OFFSET(__FGRAPH_RET_GPR2, fgraph_ret_regs, gpr2); - OFFSET(__FGRAPH_RET_FP, fgraph_ret_regs, fp); - DEFINE(__FGRAPH_RET_SIZE, sizeof(struct fgraph_ret_regs)); -#endif OFFSET(__FTRACE_REGS_PT_REGS, __arch_ftrace_regs, regs); DEFINE(__FTRACE_REGS_SIZE, sizeof(struct __arch_ftrace_regs)); diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 7e267ef63a7f..2b628aa3d809 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -134,14 +134,14 @@ SYM_CODE_END(ftrace_common) SYM_FUNC_START(return_to_handler) stmg %r2,%r5,32(%r15) lgr %r1,%r15 - aghi %r15,-(STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE) + # allocate ftrace_regs and stack frame for ftrace_return_to_handler + aghi %r15,-STACK_FRAME_SIZE_FREGS stg %r1,__SF_BACKCHAIN(%r15) - la %r3,STACK_FRAME_OVERHEAD(%r15) - stg %r1,__FGRAPH_RET_FP(%r3) - stg %r2,__FGRAPH_RET_GPR2(%r3) - lgr %r2,%r3 + stg %r2,(STACK_FREGS_PTREGS_GPRS+2*8)(%r15) + stg %r1,(STACK_FREGS_PTREGS_GPRS+15*8)(%r15) + la %r2,STACK_FRAME_OVERHEAD(%r15) brasl %r14,ftrace_return_to_handler - aghi %r15,STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE + aghi %r15,STACK_FRAME_SIZE_FREGS lgr %r14,%r2 lmg %r2,%r5,32(%r15) BR_EX %r14 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9d7bd0ae48c4..ff0d7e07c611 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -235,7 +235,7 @@ config X86 select HAVE_GUP_FAST select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD - select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_GRAPH_FREGS if HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_GRAPH_TRACER if X86_32 || (X86_64 && DYNAMIC_FTRACE) select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 6e8cf0fa48fc..d61407c680c2 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -134,24 +134,4 @@ static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs) #endif /* !COMPILE_OFFSETS */ #endif /* !__ASSEMBLY__ */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - unsigned long ax; - unsigned long dx; - unsigned long bp; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->ax; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->bp; -} -#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */ -#endif - #endif /* _ASM_X86_FTRACE_H */ diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index 58d9ed50fe61..f4e0c3361234 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -187,14 +187,15 @@ SYM_CODE_END(ftrace_graph_caller) .globl return_to_handler return_to_handler: - pushl $0 - pushl %edx - pushl %eax + subl $(PTREGS_SIZE), %esp + movl $0, PT_EBP(%esp) + movl %edx, PT_EDX(%esp) + movl %eax, PT_EAX(%esp) movl %esp, %eax call ftrace_return_to_handler movl %eax, %ecx - popl %eax - popl %edx - addl $4, %esp # skip ebp + movl PT_EAX(%esp), %eax + movl PT_EDX(%esp), %edx + addl $(PTREGS_SIZE), %esp JMP_NOSPEC ecx #endif diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 214f30e9f0c0..d51647228596 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -348,21 +348,22 @@ STACK_FRAME_NON_STANDARD_FP(__fentry__) SYM_CODE_START(return_to_handler) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR - subq $24, %rsp - /* Save the return values */ - movq %rax, (%rsp) - movq %rdx, 8(%rsp) - movq %rbp, 16(%rsp) + /* Save ftrace_regs for function exit context */ + subq $(FRAME_SIZE), %rsp + + movq %rax, RAX(%rsp) + movq %rdx, RDX(%rsp) + movq %rbp, RBP(%rsp) movq %rsp, %rdi call ftrace_return_to_handler movq %rax, %rdi - movq 8(%rsp), %rdx - movq (%rsp), %rax + movq RDX(%rsp), %rdx + movq RAX(%rsp), %rax - addq $24, %rsp + addq $(FRAME_SIZE), %rsp /* * Jump back to the old return address. This cannot be JMP_NOSPEC rdi * since IBT would demand that contain ENDBR, which simply isn't so for diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index c86ac786da3d..069f270bd7ae 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -43,9 +43,8 @@ struct dyn_ftrace; char *arch_ftrace_match_adjust(char *str, const char *search); -#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL -struct fgraph_ret_regs; -unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs); +#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS +unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs); #else unsigned long ftrace_return_to_handler(unsigned long frame_pointer); #endif @@ -134,6 +133,13 @@ extern int ftrace_enabled; * Also, architecture dependent fields can be used for internal process. * (e.g. orig_ax on x86_64) * + * Basically, ftrace_regs stores the registers related to the context. + * On function entry, registers for function parameters and hooking the + * function call are stored, and on function exit, registers for function + * return value and frame pointers are stored. + * + * And also, it dpends on the context that which registers are restored + * from the ftrace_regs. * On the function entry, those registers will be restored except for * the stack pointer, so that user can change the function parameters * and instruction pointer (e.g. live patching.) diff --git a/include/linux/ftrace_regs.h b/include/linux/ftrace_regs.h index be1ed0c891d0..bbc1873ca6b8 100644 --- a/include/linux/ftrace_regs.h +++ b/include/linux/ftrace_regs.h @@ -30,6 +30,8 @@ struct ftrace_regs; override_function_with_return(&arch_ftrace_regs(fregs)->regs) #define ftrace_regs_query_register_offset(name) \ regs_query_register_offset(name) +#define ftrace_regs_get_frame_pointer(fregs) \ + frame_pointer(&arch_ftrace_regs(fregs)->regs) #endif /* HAVE_ARCH_FTRACE_REGS */ diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 74c2b1d43bb9..c5ab2a561272 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -31,7 +31,7 @@ config HAVE_FUNCTION_GRAPH_TRACER help See Documentation/trace/ftrace-design.rst -config HAVE_FUNCTION_GRAPH_RETVAL +config HAVE_FUNCTION_GRAPH_FREGS bool config HAVE_DYNAMIC_FTRACE @@ -232,7 +232,7 @@ config FUNCTION_GRAPH_TRACER config FUNCTION_GRAPH_RETVAL bool "Kernel Function Graph Return Value" - depends on HAVE_FUNCTION_GRAPH_RETVAL + depends on HAVE_FUNCTION_GRAPH_FREGS depends on FUNCTION_GRAPH_TRACER default n help diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 4791fd704e28..51196f10d96e 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -801,15 +801,12 @@ static struct notifier_block ftrace_suspend_notifier = { .notifier_call = ftrace_suspend_notifier_call, }; -/* fgraph_ret_regs is not defined without CONFIG_FUNCTION_GRAPH_RETVAL */ -struct fgraph_ret_regs; - /* * Send the trace to the ring-buffer. * @return the original return address. */ -static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs, - unsigned long frame_pointer) +static inline unsigned long +__ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointer) { struct ftrace_ret_stack *ret_stack; struct ftrace_graph_ret trace; @@ -829,7 +826,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs trace.rettime = trace_clock_local(); #ifdef CONFIG_FUNCTION_GRAPH_RETVAL - trace.retval = fgraph_ret_regs_return_value(ret_regs); + trace.retval = ftrace_regs_get_return_value(fregs); #endif bitmap = get_bitmap_bits(current, offset); @@ -864,14 +861,14 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs } /* - * After all architecures have selected HAVE_FUNCTION_GRAPH_RETVAL, we can - * leave only ftrace_return_to_handler(ret_regs). + * After all architecures have selected HAVE_FUNCTION_GRAPH_FREGS, we can + * leave only ftrace_return_to_handler(fregs). */ -#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL -unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs) +#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS +unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs) { - return __ftrace_return_to_handler(ret_regs, - fgraph_ret_regs_frame_pointer(ret_regs)); + return __ftrace_return_to_handler(fregs, + ftrace_regs_get_frame_pointer(fregs)); } #else unsigned long ftrace_return_to_handler(unsigned long frame_pointer) -- cgit v1.2.3 From 2ca8c112c9676e2394d76760db78ffddf21d93b5 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:12:09 +0900 Subject: fgraph: Pass ftrace_regs to retfunc Pass ftrace_regs to the fgraph_ops::retfunc(). If ftrace_regs is not available, it passes a NULL instead. User callback function can access some registers (including return address) via this ftrace_regs. Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Link: https://lore.kernel.org/173518992972.391279.14055405490327765506.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 3 ++- kernel/trace/fgraph.c | 16 +++++++++++----- kernel/trace/ftrace.c | 3 ++- kernel/trace/trace.h | 3 ++- kernel/trace/trace_functions_graph.c | 7 ++++--- kernel/trace/trace_irqsoff.c | 3 ++- kernel/trace/trace_sched_wakeup.c | 3 ++- kernel/trace/trace_selftest.c | 3 ++- 8 files changed, 27 insertions(+), 14 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 069f270bd7ae..9a1e768e47da 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1075,7 +1075,8 @@ struct fgraph_ops; /* Type of the callback handlers for tracing function graph*/ typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *, - struct fgraph_ops *); /* return */ + struct fgraph_ops *, + struct ftrace_regs *); /* return */ typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *, struct fgraph_ops *, struct ftrace_regs *); /* entry */ diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 51196f10d96e..c928527251e3 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -299,7 +299,8 @@ static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops, } /* ftrace_graph_return set to this to tell some archs to run function graph */ -static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops) +static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops, + struct ftrace_regs *fregs) { } @@ -528,7 +529,8 @@ int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, } static void ftrace_graph_ret_stub(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { } @@ -825,6 +827,9 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe } trace.rettime = trace_clock_local(); + if (fregs) + ftrace_regs_set_instruction_pointer(fregs, ret); + #ifdef CONFIG_FUNCTION_GRAPH_RETVAL trace.retval = ftrace_regs_get_return_value(fregs); #endif @@ -834,7 +839,7 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe #ifdef CONFIG_HAVE_STATIC_CALL if (static_branch_likely(&fgraph_do_direct)) { if (test_bit(fgraph_direct_gops->idx, &bitmap)) - static_call(fgraph_retfunc)(&trace, fgraph_direct_gops); + static_call(fgraph_retfunc)(&trace, fgraph_direct_gops, fregs); } else #endif { @@ -844,7 +849,7 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe if (gops == &fgraph_stub) continue; - gops->retfunc(&trace, gops); + gops->retfunc(&trace, gops, fregs); } } @@ -1016,7 +1021,8 @@ void ftrace_graph_sleep_time_control(bool enable) * Simply points to ftrace_stub, but with the proper protocol. * Defined by the linker script in linux/vmlinux.lds.h */ -void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops); +void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs); /* The callbacks that hook a function */ trace_func_graph_ret_t ftrace_graph_return = ftrace_stub_graph; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ae29e1c4177d..f054343be026 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -842,7 +842,8 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace, } static void profile_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct profile_fgraph_data *profile_data; struct ftrace_profile_stat *stat; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 0f38f36a5a8a..5f3e68a8d8a0 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -693,7 +693,8 @@ void trace_latency_header(struct seq_file *m); void trace_default_header(struct seq_file *m); void print_trace_header(struct seq_file *m, struct trace_iterator *iter); -void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops); +void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs); int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, struct ftrace_regs *fregs); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 676cf3e38f51..dc62eb93837a 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -310,7 +310,7 @@ static void handle_nosleeptime(struct ftrace_graph_ret *trace, } void trace_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, struct ftrace_regs *fregs) { unsigned long *task_var = fgraph_get_task_var(gops); struct trace_array *tr = gops->private; @@ -348,7 +348,8 @@ void trace_graph_return(struct ftrace_graph_ret *trace, } static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct fgraph_times *ftimes; int size; @@ -372,7 +373,7 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, (trace->rettime - ftimes->calltime < tracing_thresh)) return; else - trace_graph_return(trace, gops); + trace_graph_return(trace, gops, fregs); } static struct fgraph_ops funcgraph_ops = { diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index ad739d76fc86..504de7a05498 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -208,7 +208,8 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace, } static void irqsoff_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 0d9e1075d815..8165382a174a 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -144,7 +144,8 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace, } static void wakeup_graph_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index f54493f8783d..d88c44f1dfa5 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -808,7 +808,8 @@ static __init int store_entry(struct ftrace_graph_ent *trace, } static __init void store_return(struct ftrace_graph_ret *trace, - struct fgraph_ops *gops) + struct fgraph_ops *gops, + struct ftrace_regs *fregs) { struct fgraph_fixture *fixture = container_of(gops, struct fgraph_fixture, gops); const char *type = fixture->store_type_name; -- cgit v1.2.3 From 46bc082388560a95e3649b698a4675e5ea3262e6 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:12:20 +0900 Subject: fprobe: Use ftrace_regs in fprobe entry handler This allows fprobes to be available with CONFIG_DYNAMIC_FTRACE_WITH_ARGS instead of CONFIG_DYNAMIC_FTRACE_WITH_REGS, then we can enable fprobe on arm64. Cc: Alexei Starovoitov Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Link: https://lore.kernel.org/173518994037.391279.2786805566359674586.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Acked-by: Florent Revest Signed-off-by: Steven Rostedt (Google) --- include/linux/fprobe.h | 2 +- kernel/trace/Kconfig | 3 ++- kernel/trace/bpf_trace.c | 10 +++++++--- kernel/trace/fprobe.c | 3 ++- kernel/trace/trace_fprobe.c | 11 ++++++++--- lib/test_fprobe.c | 4 ++-- samples/fprobe/fprobe_example.c | 2 +- 7 files changed, 23 insertions(+), 12 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index f39869588117..ca64ee5e45d2 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -10,7 +10,7 @@ struct fprobe; typedef int (*fprobe_entry_cb)(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *regs, void *entry_data); typedef void (*fprobe_exit_cb)(struct fprobe *fp, unsigned long entry_ip, diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index c5ab2a561272..f10ca86fbfad 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -297,7 +297,7 @@ config DYNAMIC_FTRACE_WITH_ARGS config FPROBE bool "Kernel Function Probe (fprobe)" depends on FUNCTION_TRACER - depends on DYNAMIC_FTRACE_WITH_REGS + depends on DYNAMIC_FTRACE_WITH_REGS || DYNAMIC_FTRACE_WITH_ARGS depends on HAVE_RETHOOK select RETHOOK default n @@ -682,6 +682,7 @@ config FPROBE_EVENTS select TRACING select PROBE_EVENTS select DYNAMIC_EVENTS + depends on DYNAMIC_FTRACE_WITH_REGS default y help This allows user to add tracing events on the function entry and diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 1b8db5aee9d3..7bb2e6ecd31f 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2561,7 +2561,7 @@ struct bpf_session_run_ctx { void *data; }; -#ifdef CONFIG_FPROBE +#if defined(CONFIG_FPROBE) && defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) struct bpf_kprobe_multi_link { struct bpf_link link; struct fprobe fp; @@ -2813,12 +2813,16 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, static int kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *data) { + struct pt_regs *regs = ftrace_get_regs(fregs); struct bpf_kprobe_multi_link *link; int err; + if (!regs) + return 0; + link = container_of(fp, struct bpf_kprobe_multi_link, fp); err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, false, data); return is_kprobe_session(link->link.prog) ? err : 0; @@ -3093,7 +3097,7 @@ error: kvfree(cookies); return err; } -#else /* !CONFIG_FPROBE */ +#else /* !CONFIG_FPROBE || !CONFIG_DYNAMIC_FTRACE_WITH_REGS */ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 9ff018245840..3d3789283873 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -46,7 +46,7 @@ static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip, } if (fp->entry_handler) - ret = fp->entry_handler(fp, ip, parent_ip, ftrace_get_regs(fregs), entry_data); + ret = fp->entry_handler(fp, ip, parent_ip, fregs, entry_data); /* If entry_handler returns !0, nmissed is not counted. */ if (rh) { @@ -182,6 +182,7 @@ static void fprobe_init(struct fprobe *fp) fp->ops.func = fprobe_kprobe_handler; else fp->ops.func = fprobe_handler; + fp->ops.flags |= FTRACE_OPS_FL_SAVE_REGS; } diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index c62d1629cffe..0f254685e26a 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -217,12 +217,13 @@ NOKPROBE_SYMBOL(fentry_trace_func); /* function exit handler */ static int trace_fprobe_entry_handler(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); + struct pt_regs *regs = ftrace_get_regs(fregs); - if (tf->tp.entry_arg) + if (regs && tf->tp.entry_arg) store_trace_entry_data(entry_data, &tf->tp, regs); return 0; @@ -339,12 +340,16 @@ NOKPROBE_SYMBOL(fexit_perf_func); #endif /* CONFIG_PERF_EVENTS */ static int fentry_dispatcher(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); + struct pt_regs *regs = ftrace_get_regs(fregs); int ret = 0; + if (!regs) + return 0; + if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE)) fentry_trace_func(tf, entry_ip, regs); #ifdef CONFIG_PERF_EVENTS diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c index 24de0e5ff859..ff607babba18 100644 --- a/lib/test_fprobe.c +++ b/lib/test_fprobe.c @@ -40,7 +40,7 @@ static noinline u32 fprobe_selftest_nest_target(u32 value, u32 (*nest)(u32)) static notrace int fp_entry_handler(struct fprobe *fp, unsigned long ip, unsigned long ret_ip, - struct pt_regs *regs, void *data) + struct ftrace_regs *fregs, void *data) { KUNIT_EXPECT_FALSE(current_test, preemptible()); /* This can be called on the fprobe_selftest_target and the fprobe_selftest_target2 */ @@ -81,7 +81,7 @@ static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, static notrace int nest_entry_handler(struct fprobe *fp, unsigned long ip, unsigned long ret_ip, - struct pt_regs *regs, void *data) + struct ftrace_regs *fregs, void *data) { KUNIT_EXPECT_FALSE(current_test, preemptible()); return 0; diff --git a/samples/fprobe/fprobe_example.c b/samples/fprobe/fprobe_example.c index 0a50b05add96..c234afae52d6 100644 --- a/samples/fprobe/fprobe_example.c +++ b/samples/fprobe/fprobe_example.c @@ -50,7 +50,7 @@ static void show_backtrace(void) static int sample_entry_handler(struct fprobe *fp, unsigned long ip, unsigned long ret_ip, - struct pt_regs *regs, void *data) + struct ftrace_regs *fregs, void *data) { if (use_trace) /* -- cgit v1.2.3 From 762abbc0d09f7ae123c82d315eb1a961c1a2cf7b Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:12:31 +0900 Subject: fprobe: Use ftrace_regs in fprobe exit handler Change the fprobe exit handler to use ftrace_regs structure instead of pt_regs. This also introduce HAVE_FTRACE_REGS_HAVING_PT_REGS which means the ftrace_regs is including the pt_regs so that ftrace_regs can provide pt_regs without memory allocation. Fprobe introduces a new dependency with that. Signed-off-by: Masami Hiramatsu (Google) Acked-by: Heiko Carstens # s390 Cc: Huacai Chen Cc: Alexei Starovoitov Cc: Florent Revest Cc: bpf Cc: Alan Maguire Cc: Heiko Carstens Cc: WANG Xuerui Cc: Vasily Gorbik Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Sven Schnelle Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Song Liu Cc: Jiri Olsa Cc: KP Singh Cc: Matt Bobrowski Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Andrii Nakryiko Cc: Martin KaFai Lau Cc: Eduard Zingerman Cc: Yonghong Song Cc: John Fastabend Cc: Stanislav Fomichev Cc: Hao Luo Cc: Andrew Morton Link: https://lore.kernel.org/173518995092.391279.6765116450352977627.stgit@devnote2 Signed-off-by: Steven Rostedt (Google) --- arch/loongarch/Kconfig | 1 + arch/s390/Kconfig | 1 + arch/x86/Kconfig | 1 + include/linux/fprobe.h | 2 +- include/linux/ftrace.h | 6 ++++++ kernel/trace/Kconfig | 7 +++++++ kernel/trace/bpf_trace.c | 6 +++++- kernel/trace/fprobe.c | 3 ++- kernel/trace/trace_fprobe.c | 6 +++++- lib/test_fprobe.c | 6 +++--- samples/fprobe/fprobe_example.c | 2 +- 11 files changed, 33 insertions(+), 8 deletions(-) (limited to 'kernel/trace') diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 49f5bfc00e5a..6396615ec035 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -128,6 +128,7 @@ config LOONGARCH select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_ARGS + select HAVE_FTRACE_REGS_HAVING_PT_REGS select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 102029e56cf0..d8eee56c10b6 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -183,6 +183,7 @@ config S390 select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_ARGS + select HAVE_FTRACE_REGS_HAVING_PT_REGS select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT if HAVE_MARCH_Z196_FEATURES diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ff0d7e07c611..6cb420783ef3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -225,6 +225,7 @@ config X86 select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_DYNAMIC_FTRACE_WITH_ARGS if X86_64 + select HAVE_FTRACE_REGS_HAVING_PT_REGS if X86_64 select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_SAMPLE_FTRACE_DIRECT if X86_64 select HAVE_SAMPLE_FTRACE_DIRECT_MULTI if X86_64 diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index ca64ee5e45d2..ef609bcca0f9 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -14,7 +14,7 @@ typedef int (*fprobe_entry_cb)(struct fprobe *fp, unsigned long entry_ip, void *entry_data); typedef void (*fprobe_exit_cb)(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *regs, void *entry_data); /** diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9a1e768e47da..bf8bb6c10553 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -176,6 +176,12 @@ static inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs) #define ftrace_regs_set_instruction_pointer(fregs, ip) do { } while (0) #endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ +#ifdef CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS + +static_assert(sizeof(struct pt_regs) == ftrace_regs_size()); + +#endif /* CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */ + static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs) { if (!fregs) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index f10ca86fbfad..7f8165f2049a 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -57,6 +57,12 @@ config HAVE_DYNAMIC_FTRACE_WITH_ARGS This allows for use of ftrace_regs_get_argument() and ftrace_regs_get_stack_pointer(). +config HAVE_FTRACE_REGS_HAVING_PT_REGS + bool + help + If this is set, ftrace_regs has pt_regs, thus it can convert to + pt_regs without allocating memory. + config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE bool help @@ -298,6 +304,7 @@ config FPROBE bool "Kernel Function Probe (fprobe)" depends on FUNCTION_TRACER depends on DYNAMIC_FTRACE_WITH_REGS || DYNAMIC_FTRACE_WITH_ARGS + depends on HAVE_FTRACE_REGS_HAVING_PT_REGS || !HAVE_DYNAMIC_FTRACE_WITH_ARGS depends on HAVE_RETHOOK select RETHOOK default n diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7bb2e6ecd31f..e469fcbed210 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2830,10 +2830,14 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, static void kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *data) { struct bpf_kprobe_multi_link *link; + struct pt_regs *regs = ftrace_get_regs(fregs); + + if (!regs) + return; link = container_of(fp, struct bpf_kprobe_multi_link, fp); kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, true, data); diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 3d3789283873..90a3c8e2bbdf 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -124,6 +124,7 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data, { struct fprobe *fp = (struct fprobe *)data; struct fprobe_rethook_node *fpr; + struct ftrace_regs *fregs = (struct ftrace_regs *)regs; int bit; if (!fp || fprobe_disabled(fp)) @@ -141,7 +142,7 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data, return; } - fp->exit_handler(fp, fpr->entry_ip, ret_ip, regs, + fp->exit_handler(fp, fpr->entry_ip, ret_ip, fregs, fp->entry_data_size ? (void *)fpr->data : NULL); ftrace_test_recursion_unlock(bit); } diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index 0f254685e26a..ed49d21269cf 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -361,10 +361,14 @@ static int fentry_dispatcher(struct fprobe *fp, unsigned long entry_ip, NOKPROBE_SYMBOL(fentry_dispatcher); static void fexit_dispatcher(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); + struct pt_regs *regs = ftrace_get_regs(fregs); + + if (!regs) + return; if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE)) fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data); diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c index ff607babba18..271ce0caeec0 100644 --- a/lib/test_fprobe.c +++ b/lib/test_fprobe.c @@ -59,9 +59,9 @@ static notrace int fp_entry_handler(struct fprobe *fp, unsigned long ip, static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, unsigned long ret_ip, - struct pt_regs *regs, void *data) + struct ftrace_regs *fregs, void *data) { - unsigned long ret = regs_return_value(regs); + unsigned long ret = ftrace_regs_get_return_value(fregs); KUNIT_EXPECT_FALSE(current_test, preemptible()); if (ip != target_ip) { @@ -89,7 +89,7 @@ static notrace int nest_entry_handler(struct fprobe *fp, unsigned long ip, static notrace void nest_exit_handler(struct fprobe *fp, unsigned long ip, unsigned long ret_ip, - struct pt_regs *regs, void *data) + struct ftrace_regs *fregs, void *data) { KUNIT_EXPECT_FALSE(current_test, preemptible()); KUNIT_EXPECT_EQ(current_test, ip, target_nest_ip); diff --git a/samples/fprobe/fprobe_example.c b/samples/fprobe/fprobe_example.c index c234afae52d6..bfe98ce826f3 100644 --- a/samples/fprobe/fprobe_example.c +++ b/samples/fprobe/fprobe_example.c @@ -67,7 +67,7 @@ static int sample_entry_handler(struct fprobe *fp, unsigned long ip, } static void sample_exit_handler(struct fprobe *fp, unsigned long ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *regs, void *data) { unsigned long rip = ret_ip; -- cgit v1.2.3 From 0566cefe73b9a6ea38357b428d27460db032a03d Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:13:13 +0900 Subject: tracing/fprobe: Enable fprobe events with CONFIG_DYNAMIC_FTRACE_WITH_ARGS Allow fprobe events to be enabled with CONFIG_DYNAMIC_FTRACE_WITH_ARGS. With this change, fprobe events mostly use ftrace_regs instead of pt_regs. Note that if the arch doesn't enable HAVE_FTRACE_REGS_HAVING_PT_REGS, fprobe events will not be able to be used from perf. Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Link: https://lore.kernel.org/173518999352.391279.13332699755290175168.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 17 +++++++ kernel/trace/Kconfig | 1 - kernel/trace/trace_fprobe.c | 108 +++++++++++++++++++++++++--------------- kernel/trace/trace_probe_tmpl.h | 2 +- 4 files changed, 86 insertions(+), 42 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 6d29c640697c..4c553fe9c026 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -250,6 +250,23 @@ static __always_inline bool ftrace_regs_has_args(struct ftrace_regs *fregs) return ftrace_get_regs(fregs) != NULL; } +#ifdef CONFIG_HAVE_REGS_AND_STACK_ACCESS_API +static __always_inline unsigned long +ftrace_regs_get_kernel_stack_nth(struct ftrace_regs *fregs, unsigned int nth) +{ + unsigned long *stackp; + + stackp = (unsigned long *)ftrace_regs_get_stack_pointer(fregs); + if (((unsigned long)(stackp + nth) & ~(THREAD_SIZE - 1)) == + ((unsigned long)stackp & ~(THREAD_SIZE - 1))) + return *(stackp + nth); + + return 0; +} +#else /* !CONFIG_HAVE_REGS_AND_STACK_ACCESS_API */ +#define ftrace_regs_get_kernel_stack_nth(fregs, nth) (0L) +#endif /* CONFIG_HAVE_REGS_AND_STACK_ACCESS_API */ + typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 7f8165f2049a..82654bbfad9a 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -689,7 +689,6 @@ config FPROBE_EVENTS select TRACING select PROBE_EVENTS select DYNAMIC_EVENTS - depends on DYNAMIC_FTRACE_WITH_REGS default y help This allows user to add tracing events on the function entry and diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index ed49d21269cf..5030aaae8183 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -134,7 +134,7 @@ static int process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, void *dest, void *base) { - struct pt_regs *regs = rec; + struct ftrace_regs *fregs = rec; unsigned long val; int ret; @@ -142,17 +142,17 @@ retry: /* 1st stage: get value from context */ switch (code->op) { case FETCH_OP_STACK: - val = regs_get_kernel_stack_nth(regs, code->param); + val = ftrace_regs_get_kernel_stack_nth(fregs, code->param); break; case FETCH_OP_STACKP: - val = kernel_stack_pointer(regs); + val = ftrace_regs_get_stack_pointer(fregs); break; case FETCH_OP_RETVAL: - val = regs_return_value(regs); + val = ftrace_regs_get_return_value(fregs); break; #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API case FETCH_OP_ARG: - val = regs_get_kernel_argument(regs, code->param); + val = ftrace_regs_get_argument(fregs, code->param); break; case FETCH_OP_EDATA: val = *(unsigned long *)((unsigned long)edata + code->offset); @@ -175,7 +175,7 @@ NOKPROBE_SYMBOL(process_fetch_insn) /* function entry handler */ static nokprobe_inline void __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - struct pt_regs *regs, + struct ftrace_regs *fregs, struct trace_event_file *trace_file) { struct fentry_trace_entry_head *entry; @@ -189,42 +189,71 @@ __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tf->tp, regs, NULL); + dsize = __get_data_size(&tf->tp, fregs, NULL); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tf->tp.size + dsize); if (!entry) return; - fbuffer.regs = regs; + fbuffer.regs = ftrace_get_regs(fregs); entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); entry->ip = entry_ip; - store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, NULL, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } static void fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - struct pt_regs *regs) + struct ftrace_regs *fregs) { struct event_file_link *link; trace_probe_for_each_link_rcu(link, &tf->tp) - __fentry_trace_func(tf, entry_ip, regs, link->file); + __fentry_trace_func(tf, entry_ip, fregs, link->file); } NOKPROBE_SYMBOL(fentry_trace_func); +static nokprobe_inline +void store_fprobe_entry_data(void *edata, struct trace_probe *tp, struct ftrace_regs *fregs) +{ + struct probe_entry_arg *earg = tp->entry_arg; + unsigned long val = 0; + int i; + + if (!earg) + return; + + for (i = 0; i < earg->size; i++) { + struct fetch_insn *code = &earg->code[i]; + + switch (code->op) { + case FETCH_OP_ARG: + val = ftrace_regs_get_argument(fregs, code->param); + break; + case FETCH_OP_ST_EDATA: + *(unsigned long *)((unsigned long)edata + code->offset) = val; + break; + case FETCH_OP_END: + goto end; + default: + break; + } + } +end: + return; +} + /* function exit handler */ static int trace_fprobe_entry_handler(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); - struct pt_regs *regs = ftrace_get_regs(fregs); - if (regs && tf->tp.entry_arg) - store_trace_entry_data(entry_data, &tf->tp, regs); + if (tf->tp.entry_arg) + store_fprobe_entry_data(entry_data, &tf->tp, fregs); return 0; } @@ -232,7 +261,7 @@ NOKPROBE_SYMBOL(trace_fprobe_entry_handler) static nokprobe_inline void __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data, struct trace_event_file *trace_file) { struct fexit_trace_entry_head *entry; @@ -246,60 +275,63 @@ __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tf->tp, regs, entry_data); + dsize = __get_data_size(&tf->tp, fregs, entry_data); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tf->tp.size + dsize); if (!entry) return; - fbuffer.regs = regs; + fbuffer.regs = ftrace_get_regs(fregs); entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); entry->func = entry_ip; entry->ret_ip = ret_ip; - store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, entry_data, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } static void fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, void *entry_data) + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct event_file_link *link; trace_probe_for_each_link_rcu(link, &tf->tp) - __fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data, link->file); + __fexit_trace_func(tf, entry_ip, ret_ip, fregs, entry_data, link->file); } NOKPROBE_SYMBOL(fexit_trace_func); #ifdef CONFIG_PERF_EVENTS static int fentry_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, - struct pt_regs *regs) + struct ftrace_regs *fregs) { struct trace_event_call *call = trace_probe_event_call(&tf->tp); struct fentry_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; + struct pt_regs *regs; int rctx; head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) return 0; - dsize = __get_data_size(&tf->tp, regs, NULL); + dsize = __get_data_size(&tf->tp, fregs, NULL); __size = sizeof(*entry) + tf->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_alloc(size, NULL, &rctx); + entry = perf_trace_buf_alloc(size, ®s, &rctx); if (!entry) return 0; + regs = ftrace_fill_perf_regs(fregs, regs); + entry->ip = entry_ip; memset(&entry[1], 0, dsize); - store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, NULL, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); return 0; @@ -308,31 +340,34 @@ NOKPROBE_SYMBOL(fentry_perf_func); static void fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, + unsigned long ret_ip, struct ftrace_regs *fregs, void *entry_data) { struct trace_event_call *call = trace_probe_event_call(&tf->tp); struct fexit_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; + struct pt_regs *regs; int rctx; head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) return; - dsize = __get_data_size(&tf->tp, regs, entry_data); + dsize = __get_data_size(&tf->tp, fregs, entry_data); __size = sizeof(*entry) + tf->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_alloc(size, NULL, &rctx); + entry = perf_trace_buf_alloc(size, ®s, &rctx); if (!entry) return; + regs = ftrace_fill_perf_regs(fregs, regs); + entry->func = entry_ip; entry->ret_ip = ret_ip; - store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, fregs, entry_data, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); } @@ -344,17 +379,14 @@ static int fentry_dispatcher(struct fprobe *fp, unsigned long entry_ip, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); - struct pt_regs *regs = ftrace_get_regs(fregs); int ret = 0; - if (!regs) - return 0; - if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE)) - fentry_trace_func(tf, entry_ip, regs); + fentry_trace_func(tf, entry_ip, fregs); + #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE)) - ret = fentry_perf_func(tf, entry_ip, regs); + ret = fentry_perf_func(tf, entry_ip, fregs); #endif return ret; } @@ -365,16 +397,12 @@ static void fexit_dispatcher(struct fprobe *fp, unsigned long entry_ip, void *entry_data) { struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); - struct pt_regs *regs = ftrace_get_regs(fregs); - - if (!regs) - return; if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE)) - fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data); + fexit_trace_func(tf, entry_ip, ret_ip, fregs, entry_data); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE)) - fexit_perf_func(tf, entry_ip, ret_ip, regs, entry_data); + fexit_perf_func(tf, entry_ip, ret_ip, fregs, entry_data); #endif } NOKPROBE_SYMBOL(fexit_dispatcher); diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index 2caf0d2afb32..f39b37fcdb3b 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -232,7 +232,7 @@ array: /* Sum up total data length for dynamic arrays (strings) */ static nokprobe_inline int -__get_data_size(struct trace_probe *tp, struct pt_regs *regs, void *edata) +__get_data_size(struct trace_probe *tp, void *regs, void *edata) { struct probe_arg *arg; int i, len, ret = 0; -- cgit v1.2.3 From 8e2759da9378120a53078077a44b5a4f6dc95018 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:13:24 +0900 Subject: bpf: Enable kprobe_multi feature if CONFIG_FPROBE is enabled Enable kprobe_multi feature if CONFIG_FPROBE is enabled. The pt_regs is converted from ftrace_regs by ftrace_partial_regs(), thus some registers may always returns 0. But it should be enough for function entry (access arguments) and exit (access return value). Cc: Alexei Starovoitov Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Link: https://lore.kernel.org/173519000417.391279.14011193569589886419.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Acked-by: Florent Revest Signed-off-by: Steven Rostedt (Google) --- kernel/trace/bpf_trace.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index e469fcbed210..863351559334 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2561,7 +2561,7 @@ struct bpf_session_run_ctx { void *data; }; -#if defined(CONFIG_FPROBE) && defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) +#ifdef CONFIG_FPROBE struct bpf_kprobe_multi_link { struct bpf_link link; struct fprobe fp; @@ -2584,6 +2584,13 @@ struct user_syms { char *buf; }; +#ifndef CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS +static DEFINE_PER_CPU(struct pt_regs, bpf_kprobe_multi_pt_regs); +#define bpf_kprobe_multi_pt_regs_ptr() this_cpu_ptr(&bpf_kprobe_multi_pt_regs) +#else +#define bpf_kprobe_multi_pt_regs_ptr() (NULL) +#endif + static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 cnt) { unsigned long __user usymbol; @@ -2778,7 +2785,7 @@ static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx) static int kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, - unsigned long entry_ip, struct pt_regs *regs, + unsigned long entry_ip, struct ftrace_regs *fregs, bool is_return, void *data) { struct bpf_kprobe_multi_run_ctx run_ctx = { @@ -2790,6 +2797,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, .entry_ip = entry_ip, }; struct bpf_run_ctx *old_run_ctx; + struct pt_regs *regs; int err; if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { @@ -2800,6 +2808,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, migrate_disable(); rcu_read_lock(); + regs = ftrace_partial_regs(fregs, bpf_kprobe_multi_pt_regs_ptr()); old_run_ctx = bpf_set_run_ctx(&run_ctx.session_ctx.run_ctx); err = bpf_prog_run(link->link.prog, regs); bpf_reset_run_ctx(old_run_ctx); @@ -2816,15 +2825,11 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, unsigned long ret_ip, struct ftrace_regs *fregs, void *data) { - struct pt_regs *regs = ftrace_get_regs(fregs); struct bpf_kprobe_multi_link *link; int err; - if (!regs) - return 0; - link = container_of(fp, struct bpf_kprobe_multi_link, fp); - err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, false, data); + err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), fregs, false, data); return is_kprobe_session(link->link.prog) ? err : 0; } @@ -2834,13 +2839,9 @@ kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip, void *data) { struct bpf_kprobe_multi_link *link; - struct pt_regs *regs = ftrace_get_regs(fregs); - - if (!regs) - return; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, true, data); + kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), fregs, true, data); } static int symbols_cmp_r(const void *a, const void *b, const void *priv) @@ -3101,7 +3102,7 @@ error: kvfree(cookies); return err; } -#else /* !CONFIG_FPROBE || !CONFIG_DYNAMIC_FTRACE_WITH_REGS */ +#else /* !CONFIG_FPROBE */ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; -- cgit v1.2.3 From a762e9267dca843ced943ec24f20e110ba7c8431 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:13:34 +0900 Subject: ftrace: Add CONFIG_HAVE_FTRACE_GRAPH_FUNC Add CONFIG_HAVE_FTRACE_GRAPH_FUNC kconfig in addition to ftrace_graph_func macro check. This is for the other feature (e.g. FPROBE) which requires to access ftrace_regs from fgraph_ops::entryfunc() can avoid compiling if the fgraph can not pass the valid ftrace_regs. Signed-off-by: Masami Hiramatsu (Google) Cc: Catalin Marinas Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Cc: Will Deacon Cc: Huacai Chen Cc: WANG Xuerui Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: Naveen N Rao Cc: Madhavan Srinivasan Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173519001472.391279.1174901685282588467.stgit@devnote2 Signed-off-by: Steven Rostedt (Google) --- arch/arm64/Kconfig | 1 + arch/loongarch/Kconfig | 1 + arch/powerpc/Kconfig | 1 + arch/riscv/Kconfig | 1 + arch/x86/Kconfig | 1 + kernel/trace/Kconfig | 5 +++++ 6 files changed, 10 insertions(+) (limited to 'kernel/trace') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 5f086777dad9..a8644a5af9fb 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -216,6 +216,7 @@ config ARM64 select HAVE_SAMPLE_FTRACE_DIRECT_MULTI select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_GUP_FAST + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_ERROR_INJECTION diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 6396615ec035..fe0d9e549ca9 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -135,6 +135,7 @@ config LOONGARCH select HAVE_EFFICIENT_UNALIGNED_ACCESS if !ARCH_STRICT_ALIGN select HAVE_EXIT_THREAD select HAVE_GUP_FAST + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a0ce777f9706..c28349ad1ac2 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -240,6 +240,7 @@ config PPC select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_GUP_FAST + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_DESCRIPTORS if PPC64_ELF_ABI_V1 diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 1e807c61258f..c736e349f222 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -146,6 +146,7 @@ config RISCV select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE) select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_DYNAMIC_FTRACE_WITH_ARGS if HAVE_DYNAMIC_FTRACE + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_GRAPH_FREGS diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6cb420783ef3..db435d159c1b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -235,6 +235,7 @@ config X86 select HAVE_EXIT_THREAD select HAVE_GUP_FAST select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE + select HAVE_FTRACE_GRAPH_FUNC if HAVE_FUNCTION_GRAPH_TRACER select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_FREGS if HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_GRAPH_TRACER if X86_32 || (X86_64 && DYNAMIC_FTRACE) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 82654bbfad9a..2fc55a1a88aa 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -34,6 +34,11 @@ config HAVE_FUNCTION_GRAPH_TRACER config HAVE_FUNCTION_GRAPH_FREGS bool +config HAVE_FTRACE_GRAPH_FUNC + bool + help + True if ftrace_graph_func() is defined. + config HAVE_DYNAMIC_FTRACE bool help -- cgit v1.2.3 From 4346ba1604093305a287e08eb465a9c15ba05b80 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:13:59 +0900 Subject: fprobe: Rewrite fprobe on function-graph tracer Rewrite fprobe implementation on function-graph tracer. Major API changes are: - 'nr_maxactive' field is deprecated. - This depends on CONFIG_DYNAMIC_FTRACE_WITH_ARGS or !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS, and CONFIG_HAVE_FUNCTION_GRAPH_FREGS. So currently works only on x86_64. - Currently the entry size is limited in 15 * sizeof(long). - If there is too many fprobe exit handler set on the same function, it will fail to probe. Signed-off-by: Masami Hiramatsu (Google) Acked-by: Heiko Carstens # s390 Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Heiko Carstens Cc: Mark Rutland Cc: Catalin Marinas Cc: Will Deacon Cc: Huacai Chen Cc: WANG Xuerui Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: Naveen N Rao Cc: Madhavan Srinivasan Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Vasily Gorbik Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Sven Schnelle Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://lore.kernel.org/173519003970.391279.14406792285453830996.stgit@devnote2 Signed-off-by: Steven Rostedt (Google) --- arch/arm64/include/asm/ftrace.h | 6 + arch/loongarch/include/asm/ftrace.h | 6 + arch/powerpc/include/asm/ftrace.h | 6 + arch/riscv/include/asm/ftrace.h | 5 + arch/s390/include/asm/ftrace.h | 6 + arch/x86/include/asm/ftrace.h | 6 + include/linux/fprobe.h | 58 +++- kernel/trace/Kconfig | 8 +- kernel/trace/fprobe.c | 637 ++++++++++++++++++++++++++---------- lib/test_fprobe.c | 45 --- 10 files changed, 538 insertions(+), 245 deletions(-) (limited to 'kernel/trace') diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 10e56522122a..876e88ad4119 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -135,6 +135,12 @@ ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs) return arch_ftrace_regs(fregs)->fp; } +static __always_inline unsigned long +ftrace_regs_get_return_address(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->lr; +} + static __always_inline struct pt_regs * ftrace_partial_regs(const struct ftrace_regs *fregs, struct pt_regs *regs) { diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h index ceb3e3d9c0d3..6e0a99763a9a 100644 --- a/arch/loongarch/include/asm/ftrace.h +++ b/arch/loongarch/include/asm/ftrace.h @@ -61,6 +61,12 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip) #define ftrace_regs_get_frame_pointer(fregs) \ (arch_ftrace_regs(fregs)->regs.regs[22]) +static __always_inline unsigned long +ftrace_regs_get_return_address(struct ftrace_regs *fregs) +{ + return *(unsigned long *)(arch_ftrace_regs(fregs)->regs.regs[1]); +} + #define ftrace_graph_func ftrace_graph_func void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index fe181bafdca4..82da7c7a1d12 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -57,6 +57,12 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, regs_set_return_ip(&arch_ftrace_regs(fregs)->regs, ip); } +static __always_inline unsigned long +ftrace_regs_get_return_address(struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->regs.link; +} + struct ftrace_ops; #define ftrace_graph_func ftrace_graph_func diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index 7064a530794b..c4721ce44ca4 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -186,6 +186,11 @@ static __always_inline unsigned long ftrace_regs_get_return_value(const struct f return arch_ftrace_regs(fregs)->a0; } +static __always_inline unsigned long ftrace_regs_get_return_address(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->ra; +} + static __always_inline void ftrace_regs_set_return_value(struct ftrace_regs *fregs, unsigned long ret) { diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index fd3f0fe9f7b3..a3b73a4f626e 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -77,6 +77,12 @@ ftrace_regs_get_frame_pointer(struct ftrace_regs *fregs) return ftrace_regs_get_stack_pointer(fregs); } +static __always_inline unsigned long +ftrace_regs_get_return_address(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->regs.gprs[14]; +} + #define arch_ftrace_fill_perf_regs(fregs, _regs) do { \ (_regs)->psw.mask = 0; \ (_regs)->psw.addr = arch_ftrace_regs(fregs)->regs.psw.addr; \ diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 7e06f8c7937a..cc92c99ef276 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -58,6 +58,12 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs) do { arch_ftrace_regs(fregs)->regs.ip = (_ip); } while (0) +static __always_inline unsigned long +ftrace_regs_get_return_address(struct ftrace_regs *fregs) +{ + return *(unsigned long *)ftrace_regs_get_stack_pointer(fregs); +} + struct ftrace_ops; #define ftrace_graph_func ftrace_graph_func void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index ef609bcca0f9..91337bcb452f 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -5,10 +5,11 @@ #include #include -#include +#include +#include +#include struct fprobe; - typedef int (*fprobe_entry_cb)(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct ftrace_regs *regs, void *entry_data); @@ -17,35 +18,57 @@ typedef void (*fprobe_exit_cb)(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct ftrace_regs *regs, void *entry_data); +/** + * struct fprobe_hlist_node - address based hash list node for fprobe. + * + * @hlist: The hlist node for address search hash table. + * @addr: One of the probing address of @fp. + * @fp: The fprobe which owns this. + */ +struct fprobe_hlist_node { + struct hlist_node hlist; + unsigned long addr; + struct fprobe *fp; +}; + +/** + * struct fprobe_hlist - hash list nodes for fprobe. + * + * @hlist: The hlist node for existence checking hash table. + * @rcu: rcu_head for RCU deferred release. + * @fp: The fprobe which owns this fprobe_hlist. + * @size: The size of @array. + * @array: The fprobe_hlist_node for each address to probe. + */ +struct fprobe_hlist { + struct hlist_node hlist; + struct rcu_head rcu; + struct fprobe *fp; + int size; + struct fprobe_hlist_node array[] __counted_by(size); +}; + /** * struct fprobe - ftrace based probe. - * @ops: The ftrace_ops. + * * @nmissed: The counter for missing events. * @flags: The status flag. - * @rethook: The rethook data structure. (internal data) * @entry_data_size: The private data storage size. - * @nr_maxactive: The max number of active functions. + * @nr_maxactive: The max number of active functions. (*deprecated) * @entry_handler: The callback function for function entry. * @exit_handler: The callback function for function exit. + * @hlist_array: The fprobe_hlist for fprobe search from IP hash table. */ struct fprobe { -#ifdef CONFIG_FUNCTION_TRACER - /* - * If CONFIG_FUNCTION_TRACER is not set, CONFIG_FPROBE is disabled too. - * But user of fprobe may keep embedding the struct fprobe on their own - * code. To avoid build error, this will keep the fprobe data structure - * defined here, but remove ftrace_ops data structure. - */ - struct ftrace_ops ops; -#endif unsigned long nmissed; unsigned int flags; - struct rethook *rethook; size_t entry_data_size; int nr_maxactive; fprobe_entry_cb entry_handler; fprobe_exit_cb exit_handler; + + struct fprobe_hlist *hlist_array; }; /* This fprobe is soft-disabled. */ @@ -121,4 +144,9 @@ static inline void enable_fprobe(struct fprobe *fp) fp->flags &= ~FPROBE_FL_DISABLED; } +/* The entry data size is 4 bits (=16) * sizeof(long) in maximum */ +#define FPROBE_DATA_SIZE_BITS 4 +#define MAX_FPROBE_DATA_SIZE_WORD ((1L << FPROBE_DATA_SIZE_BITS) - 1) +#define MAX_FPROBE_DATA_SIZE (MAX_FPROBE_DATA_SIZE_WORD * sizeof(long)) + #endif diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 2fc55a1a88aa..d570b8b9c0a9 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -307,11 +307,9 @@ config DYNAMIC_FTRACE_WITH_ARGS config FPROBE bool "Kernel Function Probe (fprobe)" - depends on FUNCTION_TRACER - depends on DYNAMIC_FTRACE_WITH_REGS || DYNAMIC_FTRACE_WITH_ARGS - depends on HAVE_FTRACE_REGS_HAVING_PT_REGS || !HAVE_DYNAMIC_FTRACE_WITH_ARGS - depends on HAVE_RETHOOK - select RETHOOK + depends on HAVE_FUNCTION_GRAPH_FREGS && HAVE_FTRACE_GRAPH_FUNC + depends on DYNAMIC_FTRACE_WITH_ARGS + select FUNCTION_GRAPH_TRACER default n help This option enables kernel function probe (fprobe) based on ftrace. diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 90a3c8e2bbdf..ed9c1d79426a 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -8,98 +8,195 @@ #include #include #include -#include +#include +#include #include #include #include "trace.h" -struct fprobe_rethook_node { - struct rethook_node node; - unsigned long entry_ip; - unsigned long entry_parent_ip; - char data[]; -}; +#define FPROBE_IP_HASH_BITS 8 +#define FPROBE_IP_TABLE_SIZE (1 << FPROBE_IP_HASH_BITS) -static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) -{ - struct fprobe_rethook_node *fpr; - struct rethook_node *rh = NULL; - struct fprobe *fp; - void *entry_data = NULL; - int ret = 0; +#define FPROBE_HASH_BITS 6 +#define FPROBE_TABLE_SIZE (1 << FPROBE_HASH_BITS) - fp = container_of(ops, struct fprobe, ops); +#define SIZE_IN_LONG(x) ((x + sizeof(long) - 1) >> (sizeof(long) == 8 ? 3 : 2)) - if (fp->exit_handler) { - rh = rethook_try_get(fp->rethook); - if (!rh) { - fp->nmissed++; - return; - } - fpr = container_of(rh, struct fprobe_rethook_node, node); - fpr->entry_ip = ip; - fpr->entry_parent_ip = parent_ip; - if (fp->entry_data_size) - entry_data = fpr->data; +/* + * fprobe_table: hold 'fprobe_hlist::hlist' for checking the fprobe still + * exists. The key is the address of fprobe instance. + * fprobe_ip_table: hold 'fprobe_hlist::array[*]' for searching the fprobe + * instance related to the funciton address. The key is the ftrace IP + * address. + * + * When unregistering the fprobe, fprobe_hlist::fp and fprobe_hlist::array[*].fp + * are set NULL and delete those from both hash tables (by hlist_del_rcu). + * After an RCU grace period, the fprobe_hlist itself will be released. + * + * fprobe_table and fprobe_ip_table can be accessed from either + * - Normal hlist traversal and RCU add/del under 'fprobe_mutex' is held. + * - RCU hlist traversal under disabling preempt + */ +static struct hlist_head fprobe_table[FPROBE_TABLE_SIZE]; +static struct hlist_head fprobe_ip_table[FPROBE_IP_TABLE_SIZE]; +static DEFINE_MUTEX(fprobe_mutex); + +/* + * Find first fprobe in the hlist. It will be iterated twice in the entry + * probe, once for correcting the total required size, the second time is + * calling back the user handlers. + * Thus the hlist in the fprobe_table must be sorted and new probe needs to + * be added *before* the first fprobe. + */ +static struct fprobe_hlist_node *find_first_fprobe_node(unsigned long ip) +{ + struct fprobe_hlist_node *node; + struct hlist_head *head; + + head = &fprobe_ip_table[hash_ptr((void *)ip, FPROBE_IP_HASH_BITS)]; + hlist_for_each_entry_rcu(node, head, hlist, + lockdep_is_held(&fprobe_mutex)) { + if (node->addr == ip) + return node; } + return NULL; +} +NOKPROBE_SYMBOL(find_first_fprobe_node); - if (fp->entry_handler) - ret = fp->entry_handler(fp, ip, parent_ip, fregs, entry_data); +/* Node insertion and deletion requires the fprobe_mutex */ +static void insert_fprobe_node(struct fprobe_hlist_node *node) +{ + unsigned long ip = node->addr; + struct fprobe_hlist_node *next; + struct hlist_head *head; - /* If entry_handler returns !0, nmissed is not counted. */ - if (rh) { - if (ret) - rethook_recycle(rh); - else - rethook_hook(rh, ftrace_get_regs(fregs), true); + lockdep_assert_held(&fprobe_mutex); + + next = find_first_fprobe_node(ip); + if (next) { + hlist_add_before_rcu(&node->hlist, &next->hlist); + return; } + head = &fprobe_ip_table[hash_ptr((void *)ip, FPROBE_IP_HASH_BITS)]; + hlist_add_head_rcu(&node->hlist, head); } -static void fprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) +/* Return true if there are synonims */ +static bool delete_fprobe_node(struct fprobe_hlist_node *node) { - struct fprobe *fp; - int bit; + lockdep_assert_held(&fprobe_mutex); - fp = container_of(ops, struct fprobe, ops); - if (fprobe_disabled(fp)) - return; + WRITE_ONCE(node->fp, NULL); + hlist_del_rcu(&node->hlist); + return !!find_first_fprobe_node(node->addr); +} - /* recursion detection has to go before any traceable function and - * all functions before this point should be marked as notrace - */ - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) { - fp->nmissed++; - return; +/* Check existence of the fprobe */ +static bool is_fprobe_still_exist(struct fprobe *fp) +{ + struct hlist_head *head; + struct fprobe_hlist *fph; + + head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)]; + hlist_for_each_entry_rcu(fph, head, hlist, + lockdep_is_held(&fprobe_mutex)) { + if (fph->fp == fp) + return true; } - __fprobe_handler(ip, parent_ip, ops, fregs); - ftrace_test_recursion_unlock(bit); + return false; +} +NOKPROBE_SYMBOL(is_fprobe_still_exist); + +static int add_fprobe_hash(struct fprobe *fp) +{ + struct fprobe_hlist *fph = fp->hlist_array; + struct hlist_head *head; + + lockdep_assert_held(&fprobe_mutex); + + if (WARN_ON_ONCE(!fph)) + return -EINVAL; + + if (is_fprobe_still_exist(fp)) + return -EEXIST; + head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)]; + hlist_add_head_rcu(&fp->hlist_array->hlist, head); + return 0; } -NOKPROBE_SYMBOL(fprobe_handler); -static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) +static int del_fprobe_hash(struct fprobe *fp) { + struct fprobe_hlist *fph = fp->hlist_array; + + lockdep_assert_held(&fprobe_mutex); + + if (WARN_ON_ONCE(!fph)) + return -EINVAL; + + if (!is_fprobe_still_exist(fp)) + return -ENOENT; + + fph->fp = NULL; + hlist_del_rcu(&fph->hlist); + return 0; +} + +/* Generic fprobe_header */ +struct __fprobe_header { struct fprobe *fp; - int bit; + unsigned long size_words; +} __packed; - fp = container_of(ops, struct fprobe, ops); - if (fprobe_disabled(fp)) - return; +#define FPROBE_HEADER_SIZE_IN_LONG SIZE_IN_LONG(sizeof(struct __fprobe_header)) - /* recursion detection has to go before any traceable function and - * all functions called before this point should be marked as notrace - */ - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) { - fp->nmissed++; - return; - } +static inline bool write_fprobe_header(unsigned long *stack, + struct fprobe *fp, unsigned int size_words) +{ + struct __fprobe_header *fph = (struct __fprobe_header *)stack; + if (WARN_ON_ONCE(size_words > MAX_FPROBE_DATA_SIZE_WORD)) + return false; + + fph->fp = fp; + fph->size_words = size_words; + return true; +} + +static inline void read_fprobe_header(unsigned long *stack, + struct fprobe **fp, unsigned int *size_words) +{ + struct __fprobe_header *fph = (struct __fprobe_header *)stack; + + *fp = fph->fp; + *size_words = fph->size_words; +} + +/* + * fprobe shadow stack management: + * Since fprobe shares a single fgraph_ops, it needs to share the stack entry + * among the probes on the same function exit. Note that a new probe can be + * registered before a target function is returning, we can not use the hash + * table to find the corresponding probes. Thus the probe address is stored on + * the shadow stack with its entry data size. + * + */ +static inline int __fprobe_handler(unsigned long ip, unsigned long parent_ip, + struct fprobe *fp, struct ftrace_regs *fregs, + void *data) +{ + if (!fp->entry_handler) + return 0; + + return fp->entry_handler(fp, ip, parent_ip, fregs, data); +} + +static inline int __fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, + struct fprobe *fp, struct ftrace_regs *fregs, + void *data) +{ + int ret; /* * This user handler is shared with other kprobes and is not expected to be * called recursively. So if any other kprobe handler is running, this will @@ -108,45 +205,183 @@ static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, */ if (unlikely(kprobe_running())) { fp->nmissed++; - goto recursion_unlock; + return 0; } kprobe_busy_begin(); - __fprobe_handler(ip, parent_ip, ops, fregs); + ret = __fprobe_handler(ip, parent_ip, fp, fregs, data); kprobe_busy_end(); - -recursion_unlock: - ftrace_test_recursion_unlock(bit); + return ret; } -static void fprobe_exit_handler(struct rethook_node *rh, void *data, - unsigned long ret_ip, struct pt_regs *regs) +static int fprobe_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs) { - struct fprobe *fp = (struct fprobe *)data; - struct fprobe_rethook_node *fpr; - struct ftrace_regs *fregs = (struct ftrace_regs *)regs; - int bit; + struct fprobe_hlist_node *node, *first; + unsigned long *fgraph_data = NULL; + unsigned long func = trace->func; + unsigned long ret_ip; + int reserved_words; + struct fprobe *fp; + int used, ret; - if (!fp || fprobe_disabled(fp)) - return; + if (WARN_ON_ONCE(!fregs)) + return 0; - fpr = container_of(rh, struct fprobe_rethook_node, node); + first = node = find_first_fprobe_node(func); + if (unlikely(!first)) + return 0; + + reserved_words = 0; + hlist_for_each_entry_from_rcu(node, hlist) { + if (node->addr != func) + break; + fp = READ_ONCE(node->fp); + if (!fp || !fp->exit_handler) + continue; + /* + * Since fprobe can be enabled until the next loop, we ignore the + * fprobe's disabled flag in this loop. + */ + reserved_words += + FPROBE_HEADER_SIZE_IN_LONG + SIZE_IN_LONG(fp->entry_data_size); + } + node = first; + if (reserved_words) { + fgraph_data = fgraph_reserve_data(gops->idx, reserved_words * sizeof(long)); + if (unlikely(!fgraph_data)) { + hlist_for_each_entry_from_rcu(node, hlist) { + if (node->addr != func) + break; + fp = READ_ONCE(node->fp); + if (fp && !fprobe_disabled(fp)) + fp->nmissed++; + } + return 0; + } + } /* - * we need to assure no calls to traceable functions in-between the - * end of fprobe_handler and the beginning of fprobe_exit_handler. + * TODO: recursion detection has been done in the fgraph. Thus we need + * to add a callback to increment missed counter. */ - bit = ftrace_test_recursion_trylock(fpr->entry_ip, fpr->entry_parent_ip); - if (bit < 0) { - fp->nmissed++; + ret_ip = ftrace_regs_get_return_address(fregs); + used = 0; + hlist_for_each_entry_from_rcu(node, hlist) { + int data_size; + void *data; + + if (node->addr != func) + break; + fp = READ_ONCE(node->fp); + if (!fp || fprobe_disabled(fp)) + continue; + + data_size = fp->entry_data_size; + if (data_size && fp->exit_handler) + data = fgraph_data + used + FPROBE_HEADER_SIZE_IN_LONG; + else + data = NULL; + + if (fprobe_shared_with_kprobes(fp)) + ret = __fprobe_kprobe_handler(func, ret_ip, fp, fregs, data); + else + ret = __fprobe_handler(func, ret_ip, fp, fregs, data); + + /* If entry_handler returns !0, nmissed is not counted but skips exit_handler. */ + if (!ret && fp->exit_handler) { + int size_words = SIZE_IN_LONG(data_size); + + if (write_fprobe_header(&fgraph_data[used], fp, size_words)) + used += FPROBE_HEADER_SIZE_IN_LONG + size_words; + } + } + if (used < reserved_words) + memset(fgraph_data + used, 0, reserved_words - used); + + /* If any exit_handler is set, data must be used. */ + return used != 0; +} +NOKPROBE_SYMBOL(fprobe_entry); + +static void fprobe_return(struct ftrace_graph_ret *trace, + struct fgraph_ops *gops, + struct ftrace_regs *fregs) +{ + unsigned long *fgraph_data = NULL; + unsigned long ret_ip; + struct fprobe *fp; + int size, curr; + int size_words; + + fgraph_data = (unsigned long *)fgraph_retrieve_data(gops->idx, &size); + if (WARN_ON_ONCE(!fgraph_data)) return; + size_words = SIZE_IN_LONG(size); + ret_ip = ftrace_regs_get_instruction_pointer(fregs); + + preempt_disable(); + + curr = 0; + while (size_words > curr) { + read_fprobe_header(&fgraph_data[curr], &fp, &size); + if (!fp) + break; + curr += FPROBE_HEADER_SIZE_IN_LONG; + if (is_fprobe_still_exist(fp) && !fprobe_disabled(fp)) { + if (WARN_ON_ONCE(curr + size > size_words)) + break; + fp->exit_handler(fp, trace->func, ret_ip, fregs, + size ? fgraph_data + curr : NULL); + } + curr += size; } + preempt_enable(); +} +NOKPROBE_SYMBOL(fprobe_return); + +static struct fgraph_ops fprobe_graph_ops = { + .entryfunc = fprobe_entry, + .retfunc = fprobe_return, +}; +static int fprobe_graph_active; + +/* Add @addrs to the ftrace filter and register fgraph if needed. */ +static int fprobe_graph_add_ips(unsigned long *addrs, int num) +{ + int ret; - fp->exit_handler(fp, fpr->entry_ip, ret_ip, fregs, - fp->entry_data_size ? (void *)fpr->data : NULL); - ftrace_test_recursion_unlock(bit); + lockdep_assert_held(&fprobe_mutex); + + ret = ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 0, 0); + if (ret) + return ret; + + if (!fprobe_graph_active) { + ret = register_ftrace_graph(&fprobe_graph_ops); + if (WARN_ON_ONCE(ret)) { + ftrace_free_filter(&fprobe_graph_ops.ops); + return ret; + } + } + fprobe_graph_active++; + return 0; +} + +/* Remove @addrs from the ftrace filter and unregister fgraph if possible. */ +static void fprobe_graph_remove_ips(unsigned long *addrs, int num) +{ + lockdep_assert_held(&fprobe_mutex); + + fprobe_graph_active--; + if (!fprobe_graph_active) { + /* Q: should we unregister it ? */ + unregister_ftrace_graph(&fprobe_graph_ops); + return; + } + + ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); } -NOKPROBE_SYMBOL(fprobe_exit_handler); static int symbols_cmp(const void *a, const void *b) { @@ -176,54 +411,97 @@ static unsigned long *get_ftrace_locations(const char **syms, int num) return ERR_PTR(-ENOENT); } -static void fprobe_init(struct fprobe *fp) -{ - fp->nmissed = 0; - if (fprobe_shared_with_kprobes(fp)) - fp->ops.func = fprobe_kprobe_handler; - else - fp->ops.func = fprobe_handler; - - fp->ops.flags |= FTRACE_OPS_FL_SAVE_REGS; -} +struct filter_match_data { + const char *filter; + const char *notfilter; + size_t index; + size_t size; + unsigned long *addrs; +}; -static int fprobe_init_rethook(struct fprobe *fp, int num) +static int filter_match_callback(void *data, const char *name, unsigned long addr) { - int size; + struct filter_match_data *match = data; - if (!fp->exit_handler) { - fp->rethook = NULL; + if (!glob_match(match->filter, name) || + (match->notfilter && glob_match(match->notfilter, name))) return 0; - } - /* Initialize rethook if needed */ - if (fp->nr_maxactive) - num = fp->nr_maxactive; - else - num *= num_possible_cpus() * 2; - if (num <= 0) - return -EINVAL; + if (!ftrace_location(addr)) + return 0; - size = sizeof(struct fprobe_rethook_node) + fp->entry_data_size; + if (match->addrs) + match->addrs[match->index] = addr; - /* Initialize rethook */ - fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, size, num); - if (IS_ERR(fp->rethook)) - return PTR_ERR(fp->rethook); + match->index++; + return match->index == match->size; +} - return 0; +/* + * Make IP list from the filter/no-filter glob patterns. + * Return the number of matched symbols, or -ENOENT. + */ +static int ip_list_from_filter(const char *filter, const char *notfilter, + unsigned long *addrs, size_t size) +{ + struct filter_match_data match = { .filter = filter, .notfilter = notfilter, + .index = 0, .size = size, .addrs = addrs}; + int ret; + + ret = kallsyms_on_each_symbol(filter_match_callback, &match); + if (ret < 0) + return ret; + ret = module_kallsyms_on_each_symbol(NULL, filter_match_callback, &match); + if (ret < 0) + return ret; + + return match.index ?: -ENOENT; } static void fprobe_fail_cleanup(struct fprobe *fp) { - if (!IS_ERR_OR_NULL(fp->rethook)) { - /* Don't need to cleanup rethook->handler because this is not used. */ - rethook_free(fp->rethook); - fp->rethook = NULL; + kfree(fp->hlist_array); + fp->hlist_array = NULL; +} + +/* Initialize the fprobe data structure. */ +static int fprobe_init(struct fprobe *fp, unsigned long *addrs, int num) +{ + struct fprobe_hlist *hlist_array; + unsigned long addr; + int size, i; + + if (!fp || !addrs || num <= 0) + return -EINVAL; + + size = ALIGN(fp->entry_data_size, sizeof(long)); + if (size > MAX_FPROBE_DATA_SIZE) + return -E2BIG; + fp->entry_data_size = size; + + hlist_array = kzalloc(struct_size(hlist_array, array, num), GFP_KERNEL); + if (!hlist_array) + return -ENOMEM; + + fp->nmissed = 0; + + hlist_array->size = num; + fp->hlist_array = hlist_array; + hlist_array->fp = fp; + for (i = 0; i < num; i++) { + hlist_array->array[i].fp = fp; + addr = ftrace_location(addrs[i]); + if (!addr) { + fprobe_fail_cleanup(fp); + return -ENOENT; + } + hlist_array->array[i].addr = addr; } - ftrace_free_filter(&fp->ops); + return 0; } +#define FPROBE_IPS_MAX INT_MAX + /** * register_fprobe() - Register fprobe to ftrace by pattern. * @fp: A fprobe data structure to be registered. @@ -237,46 +515,24 @@ static void fprobe_fail_cleanup(struct fprobe *fp) */ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter) { - struct ftrace_hash *hash; - unsigned char *str; - int ret, len; + unsigned long *addrs; + int ret; if (!fp || !filter) return -EINVAL; - fprobe_init(fp); - - len = strlen(filter); - str = kstrdup(filter, GFP_KERNEL); - ret = ftrace_set_filter(&fp->ops, str, len, 0); - kfree(str); - if (ret) + ret = ip_list_from_filter(filter, notfilter, NULL, FPROBE_IPS_MAX); + if (ret < 0) return ret; - if (notfilter) { - len = strlen(notfilter); - str = kstrdup(notfilter, GFP_KERNEL); - ret = ftrace_set_notrace(&fp->ops, str, len, 0); - kfree(str); - if (ret) - goto out; - } - - /* TODO: - * correctly calculate the total number of filtered symbols - * from both filter and notfilter. - */ - hash = rcu_access_pointer(fp->ops.local_hash.filter_hash); - if (WARN_ON_ONCE(!hash)) - goto out; - - ret = fprobe_init_rethook(fp, (int)hash->count); - if (!ret) - ret = register_ftrace_function(&fp->ops); + addrs = kcalloc(ret, sizeof(unsigned long), GFP_KERNEL); + if (!addrs) + return -ENOMEM; + ret = ip_list_from_filter(filter, notfilter, addrs, ret); + if (ret > 0) + ret = register_fprobe_ips(fp, addrs, ret); -out: - if (ret) - fprobe_fail_cleanup(fp); + kfree(addrs); return ret; } EXPORT_SYMBOL_GPL(register_fprobe); @@ -284,7 +540,7 @@ EXPORT_SYMBOL_GPL(register_fprobe); /** * register_fprobe_ips() - Register fprobe to ftrace by address. * @fp: A fprobe data structure to be registered. - * @addrs: An array of target ftrace location addresses. + * @addrs: An array of target function address. * @num: The number of entries of @addrs. * * Register @fp to ftrace for enabling the probe on the address given by @addrs. @@ -296,23 +552,27 @@ EXPORT_SYMBOL_GPL(register_fprobe); */ int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) { - int ret; - - if (!fp || !addrs || num <= 0) - return -EINVAL; + struct fprobe_hlist *hlist_array; + int ret, i; - fprobe_init(fp); - - ret = ftrace_set_filter_ips(&fp->ops, addrs, num, 0, 0); + ret = fprobe_init(fp, addrs, num); if (ret) return ret; - ret = fprobe_init_rethook(fp, num); - if (!ret) - ret = register_ftrace_function(&fp->ops); + mutex_lock(&fprobe_mutex); + + hlist_array = fp->hlist_array; + ret = fprobe_graph_add_ips(addrs, num); + if (!ret) { + add_fprobe_hash(fp); + for (i = 0; i < hlist_array->size; i++) + insert_fprobe_node(&hlist_array->array[i]); + } + mutex_unlock(&fprobe_mutex); if (ret) fprobe_fail_cleanup(fp); + return ret; } EXPORT_SYMBOL_GPL(register_fprobe_ips); @@ -350,14 +610,13 @@ EXPORT_SYMBOL_GPL(register_fprobe_syms); bool fprobe_is_registered(struct fprobe *fp) { - if (!fp || (fp->ops.saved_func != fprobe_handler && - fp->ops.saved_func != fprobe_kprobe_handler)) + if (!fp || !fp->hlist_array) return false; return true; } /** - * unregister_fprobe() - Unregister fprobe from ftrace + * unregister_fprobe() - Unregister fprobe. * @fp: A fprobe data structure to be unregistered. * * Unregister fprobe (and remove ftrace hooks from the function entries). @@ -366,23 +625,41 @@ bool fprobe_is_registered(struct fprobe *fp) */ int unregister_fprobe(struct fprobe *fp) { - int ret; + struct fprobe_hlist *hlist_array; + unsigned long *addrs = NULL; + int ret = 0, i, count; - if (!fprobe_is_registered(fp)) - return -EINVAL; + mutex_lock(&fprobe_mutex); + if (!fp || !is_fprobe_still_exist(fp)) { + ret = -EINVAL; + goto out; + } - if (!IS_ERR_OR_NULL(fp->rethook)) - rethook_stop(fp->rethook); + hlist_array = fp->hlist_array; + addrs = kcalloc(hlist_array->size, sizeof(unsigned long), GFP_KERNEL); + if (!addrs) { + ret = -ENOMEM; /* TODO: Fallback to one-by-one loop */ + goto out; + } - ret = unregister_ftrace_function(&fp->ops); - if (ret < 0) - return ret; + /* Remove non-synonim ips from table and hash */ + count = 0; + for (i = 0; i < hlist_array->size; i++) { + if (!delete_fprobe_node(&hlist_array->array[i])) + addrs[count++] = hlist_array->array[i].addr; + } + del_fprobe_hash(fp); - if (!IS_ERR_OR_NULL(fp->rethook)) - rethook_free(fp->rethook); + if (count) + fprobe_graph_remove_ips(addrs, count); - ftrace_free_filter(&fp->ops); + kfree_rcu(hlist_array, rcu); + fp->hlist_array = NULL; +out: + mutex_unlock(&fprobe_mutex); + + kfree(addrs); return ret; } EXPORT_SYMBOL_GPL(unregister_fprobe); diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c index 271ce0caeec0..cf92111b5c79 100644 --- a/lib/test_fprobe.c +++ b/lib/test_fprobe.c @@ -17,10 +17,8 @@ static u32 rand1, entry_val, exit_val; /* Use indirect calls to avoid inlining the target functions */ static u32 (*target)(u32 value); static u32 (*target2)(u32 value); -static u32 (*target_nest)(u32 value, u32 (*nest)(u32)); static unsigned long target_ip; static unsigned long target2_ip; -static unsigned long target_nest_ip; static int entry_return_value; static noinline u32 fprobe_selftest_target(u32 value) @@ -33,11 +31,6 @@ static noinline u32 fprobe_selftest_target2(u32 value) return (value / div_factor) + 1; } -static noinline u32 fprobe_selftest_nest_target(u32 value, u32 (*nest)(u32)) -{ - return nest(value + 2); -} - static notrace int fp_entry_handler(struct fprobe *fp, unsigned long ip, unsigned long ret_ip, struct ftrace_regs *fregs, void *data) @@ -79,22 +72,6 @@ static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, KUNIT_EXPECT_NULL(current_test, data); } -static notrace int nest_entry_handler(struct fprobe *fp, unsigned long ip, - unsigned long ret_ip, - struct ftrace_regs *fregs, void *data) -{ - KUNIT_EXPECT_FALSE(current_test, preemptible()); - return 0; -} - -static notrace void nest_exit_handler(struct fprobe *fp, unsigned long ip, - unsigned long ret_ip, - struct ftrace_regs *fregs, void *data) -{ - KUNIT_EXPECT_FALSE(current_test, preemptible()); - KUNIT_EXPECT_EQ(current_test, ip, target_nest_ip); -} - /* Test entry only (no rethook) */ static void test_fprobe_entry(struct kunit *test) { @@ -191,25 +168,6 @@ static void test_fprobe_data(struct kunit *test) KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp)); } -/* Test nr_maxactive */ -static void test_fprobe_nest(struct kunit *test) -{ - static const char *syms[] = {"fprobe_selftest_target", "fprobe_selftest_nest_target"}; - struct fprobe fp = { - .entry_handler = nest_entry_handler, - .exit_handler = nest_exit_handler, - .nr_maxactive = 1, - }; - - current_test = test; - KUNIT_EXPECT_EQ(test, 0, register_fprobe_syms(&fp, syms, 2)); - - target_nest(rand1, target); - KUNIT_EXPECT_EQ(test, 1, fp.nmissed); - - KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp)); -} - static void test_fprobe_skip(struct kunit *test) { struct fprobe fp = { @@ -247,10 +205,8 @@ static int fprobe_test_init(struct kunit *test) rand1 = get_random_u32_above(div_factor); target = fprobe_selftest_target; target2 = fprobe_selftest_target2; - target_nest = fprobe_selftest_nest_target; target_ip = get_ftrace_location(target); target2_ip = get_ftrace_location(target2); - target_nest_ip = get_ftrace_location(target_nest); return 0; } @@ -260,7 +216,6 @@ static struct kunit_case fprobe_testcases[] = { KUNIT_CASE(test_fprobe), KUNIT_CASE(test_fprobe_syms), KUNIT_CASE(test_fprobe_data), - KUNIT_CASE(test_fprobe_nest), KUNIT_CASE(test_fprobe_skip), {} }; -- cgit v1.2.3 From b5fa903b7f7c7ffc07430d1380936f72aaf09068 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:14:17 +0900 Subject: fprobe: Add fprobe_header encoding feature Fprobe store its data structure address and size on the fgraph return stack by __fprobe_header. But most 64bit architecture can combine those to one unsigned long value because 4 MSB in the kernel address are the same. With this encoding, fprobe can consume less space on ret_stack. This introduces asm/fprobe.h to define arch dependent encode/decode macros. Note that since fprobe depends on CONFIG_HAVE_FUNCTION_GRAPH_FREGS, currently only arm64, loongarch, riscv, s390 and x86 are supported. Signed-off-by: Masami Hiramatsu (Google) Acked-by: Heiko Carstens # s390 Cc: Catalin Marinas Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Cc: Heiko Carstens Cc: Will Deacon Cc: Huacai Chen Cc: WANG Xuerui Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Vasily Gorbik Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Sven Schnelle Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: Arnd Bergmann Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173519005783.391279.5307910947400277525.stgit@devnote2 Signed-off-by: Steven Rostedt (Google) --- arch/arm64/include/asm/Kbuild | 1 + arch/loongarch/include/asm/fprobe.h | 12 ++++++++++ arch/riscv/include/asm/Kbuild | 1 + arch/s390/include/asm/fprobe.h | 10 ++++++++ arch/x86/include/asm/Kbuild | 1 + include/asm-generic/fprobe.h | 46 +++++++++++++++++++++++++++++++++++++ kernel/trace/fprobe.c | 29 +++++++++++++++++++++++ 7 files changed, 100 insertions(+) create mode 100644 arch/loongarch/include/asm/fprobe.h create mode 100644 arch/s390/include/asm/fprobe.h create mode 100644 include/asm-generic/fprobe.h (limited to 'kernel/trace') diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 4e350df9a02d..d2ff8f6c3231 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -8,6 +8,7 @@ syscall-y += unistd_32.h syscall-y += unistd_compat_32.h generic-y += early_ioremap.h +generic-y += fprobe.h generic-y += mcs_spinlock.h generic-y += mmzone.h generic-y += qrwlock.h diff --git a/arch/loongarch/include/asm/fprobe.h b/arch/loongarch/include/asm/fprobe.h new file mode 100644 index 000000000000..7af3b3126caf --- /dev/null +++ b/arch/loongarch/include/asm/fprobe.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_LOONGARCH_FPROBE_H +#define _ASM_LOONGARCH_FPROBE_H + +/* + * Explicitly undef ARCH_DEFINE_ENCODE_FPROBE_HEADER, because loongarch does not + * have enough number of fixed MSBs of the address of kernel objects for + * encoding the size of data in fprobe_header. Use 2-entries encoding instead. + */ +#undef ARCH_DEFINE_ENCODE_FPROBE_HEADER + +#endif /* _ASM_LOONGARCH_FPROBE_H */ diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index de13d5a234f8..bd5fc9403295 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -4,6 +4,7 @@ syscall-y += syscall_table_64.h generic-y += early_ioremap.h generic-y += flat.h +generic-y += fprobe.h generic-y += kvm_para.h generic-y += mmzone.h generic-y += mcs_spinlock.h diff --git a/arch/s390/include/asm/fprobe.h b/arch/s390/include/asm/fprobe.h new file mode 100644 index 000000000000..5ef600b372f4 --- /dev/null +++ b/arch/s390/include/asm/fprobe.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_S390_FPROBE_H +#define _ASM_S390_FPROBE_H + +#include + +#undef FPROBE_HEADER_MSB_PATTERN +#define FPROBE_HEADER_MSB_PATTERN 0 + +#endif /* _ASM_S390_FPROBE_H */ diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 6c23d1661b17..58f4ddecc5fa 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -10,5 +10,6 @@ generated-y += unistd_64_x32.h generated-y += xen-hypercalls.h generic-y += early_ioremap.h +generic-y += fprobe.h generic-y += mcs_spinlock.h generic-y += mmzone.h diff --git a/include/asm-generic/fprobe.h b/include/asm-generic/fprobe.h new file mode 100644 index 000000000000..8659a4dc6eb6 --- /dev/null +++ b/include/asm-generic/fprobe.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Generic arch dependent fprobe macros. + */ +#ifndef __ASM_GENERIC_FPROBE_H__ +#define __ASM_GENERIC_FPROBE_H__ + +#include + +#ifdef CONFIG_64BIT +/* + * Encoding the size and the address of fprobe into one 64bit entry. + * The 32bit architectures should use 2 entries to store those info. + */ + +#define ARCH_DEFINE_ENCODE_FPROBE_HEADER + +#define FPROBE_HEADER_MSB_SIZE_SHIFT (BITS_PER_LONG - FPROBE_DATA_SIZE_BITS) +#define FPROBE_HEADER_MSB_MASK \ + GENMASK(FPROBE_HEADER_MSB_SIZE_SHIFT - 1, 0) + +/* + * By default, this expects the MSBs in the address of kprobe is 0xf. + * If any arch needs another fixed pattern (e.g. s390 is zero filled), + * override this. + */ +#define FPROBE_HEADER_MSB_PATTERN \ + GENMASK(BITS_PER_LONG - 1, FPROBE_HEADER_MSB_SIZE_SHIFT) + +#define arch_fprobe_header_encodable(fp) \ + (((unsigned long)(fp) & ~FPROBE_HEADER_MSB_MASK) == \ + FPROBE_HEADER_MSB_PATTERN) + +#define arch_encode_fprobe_header(fp, size) \ + (((unsigned long)(fp) & FPROBE_HEADER_MSB_MASK) | \ + ((unsigned long)(size) << FPROBE_HEADER_MSB_SIZE_SHIFT)) + +#define arch_decode_fprobe_header_size(val) \ + ((unsigned long)(val) >> FPROBE_HEADER_MSB_SIZE_SHIFT) + +#define arch_decode_fprobe_header_fp(val) \ + ((struct fprobe *)(((unsigned long)(val) & FPROBE_HEADER_MSB_MASK) | \ + FPROBE_HEADER_MSB_PATTERN)) +#endif /* CONFIG_64BIT */ + +#endif /* __ASM_GENERIC_FPROBE_H__ */ diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index ed9c1d79426a..2560b312ad57 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -13,6 +13,8 @@ #include #include +#include + #include "trace.h" #define FPROBE_IP_HASH_BITS 8 @@ -143,6 +145,31 @@ static int del_fprobe_hash(struct fprobe *fp) return 0; } +#ifdef ARCH_DEFINE_ENCODE_FPROBE_HEADER + +/* The arch should encode fprobe_header info into one unsigned long */ +#define FPROBE_HEADER_SIZE_IN_LONG 1 + +static inline bool write_fprobe_header(unsigned long *stack, + struct fprobe *fp, unsigned int size_words) +{ + if (WARN_ON_ONCE(size_words > MAX_FPROBE_DATA_SIZE_WORD || + !arch_fprobe_header_encodable(fp))) + return false; + + *stack = arch_encode_fprobe_header(fp, size_words); + return true; +} + +static inline void read_fprobe_header(unsigned long *stack, + struct fprobe **fp, unsigned int *size_words) +{ + *fp = arch_decode_fprobe_header_fp(*stack); + *size_words = arch_decode_fprobe_header_size(*stack); +} + +#else + /* Generic fprobe_header */ struct __fprobe_header { struct fprobe *fp; @@ -173,6 +200,8 @@ static inline void read_fprobe_header(unsigned long *stack, *size_words = fph->size_words; } +#endif + /* * fprobe shadow stack management: * Since fprobe shares a single fgraph_ops, it needs to share the stack entry -- cgit v1.2.3 From a2224559cbba1db3a998dd100c60c85a1d078ad6 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 26 Dec 2024 14:14:32 +0900 Subject: tracing/fprobe: Remove nr_maxactive from fprobe Remove depercated fprobe::nr_maxactive. This involves fprobe events to rejects the maxactive number. Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Link: https://lore.kernel.org/173519007257.391279.946804046982289337.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- include/linux/fprobe.h | 2 -- kernel/trace/trace_fprobe.c | 43 ++++++------------------------------------- 2 files changed, 6 insertions(+), 39 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 91337bcb452f..702099f08929 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -54,7 +54,6 @@ struct fprobe_hlist { * @nmissed: The counter for missing events. * @flags: The status flag. * @entry_data_size: The private data storage size. - * @nr_maxactive: The max number of active functions. (*deprecated) * @entry_handler: The callback function for function entry. * @exit_handler: The callback function for function exit. * @hlist_array: The fprobe_hlist for fprobe search from IP hash table. @@ -63,7 +62,6 @@ struct fprobe { unsigned long nmissed; unsigned int flags; size_t entry_data_size; - int nr_maxactive; fprobe_entry_cb entry_handler; fprobe_exit_cb exit_handler; diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index 5030aaae8183..f487fadc2c08 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -424,7 +424,6 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, const char *symbol, struct tracepoint *tpoint, struct module *mod, - int maxactive, int nargs, bool is_return) { struct trace_fprobe *tf; @@ -445,7 +444,6 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, tf->tpoint = tpoint; tf->mod = mod; - tf->fp.nr_maxactive = maxactive; ret = trace_probe_init(&tf->tp, event, group, false, nargs); if (ret < 0) @@ -1098,12 +1096,11 @@ static int __trace_fprobe_create(int argc, const char *argv[]) * FETCHARG:TYPE : use TYPE instead of unsigned long. */ struct trace_fprobe *tf = NULL; - int i, len, new_argc = 0, ret = 0; + int i, new_argc = 0, ret = 0; bool is_return = false; char *symbol = NULL; const char *event = NULL, *group = FPROBE_EVENT_SYSTEM; const char **new_argv = NULL; - int maxactive = 0; char buf[MAX_EVENT_NAME_LEN]; char gbuf[MAX_EVENT_NAME_LEN]; char sbuf[KSYM_NAME_LEN]; @@ -1126,33 +1123,13 @@ static int __trace_fprobe_create(int argc, const char *argv[]) trace_probe_log_init("trace_fprobe", argc, argv); - event = strchr(&argv[0][1], ':'); - if (event) - event++; - - if (isdigit(argv[0][1])) { - if (event) - len = event - &argv[0][1] - 1; - else - len = strlen(&argv[0][1]); - if (len > MAX_EVENT_NAME_LEN - 1) { - trace_probe_log_err(1, BAD_MAXACT); - goto parse_error; - } - memcpy(buf, &argv[0][1], len); - buf[len] = '\0'; - ret = kstrtouint(buf, 0, &maxactive); - if (ret || !maxactive) { + if (argv[0][1] != '\0') { + if (argv[0][1] != ':') { + trace_probe_log_set_index(0); trace_probe_log_err(1, BAD_MAXACT); goto parse_error; } - /* fprobe rethook instances are iterated over via a list. The - * maximum should stay reasonable. - */ - if (maxactive > RETHOOK_MAXACTIVE_MAX) { - trace_probe_log_err(1, MAXACT_TOO_BIG); - goto parse_error; - } + event = &argv[0][2]; } trace_probe_log_set_index(1); @@ -1162,12 +1139,6 @@ static int __trace_fprobe_create(int argc, const char *argv[]) if (ret < 0) goto parse_error; - if (!is_return && maxactive) { - trace_probe_log_set_index(0); - trace_probe_log_err(1, BAD_MAXACT_TYPE); - goto parse_error; - } - trace_probe_log_set_index(0); if (event) { ret = traceprobe_parse_event_name(&event, &group, gbuf, @@ -1235,7 +1206,7 @@ static int __trace_fprobe_create(int argc, const char *argv[]) /* setup a probe */ tf = alloc_trace_fprobe(group, event, symbol, tpoint, tp_mod, - maxactive, argc, is_return); + argc, is_return); if (IS_ERR(tf)) { ret = PTR_ERR(tf); /* This must return -ENOMEM, else there is a bug */ @@ -1315,8 +1286,6 @@ static int trace_fprobe_show(struct seq_file *m, struct dyn_event *ev) seq_putc(m, 't'); else seq_putc(m, 'f'); - if (trace_fprobe_is_return(tf) && tf->fp.nr_maxactive) - seq_printf(m, "%d", tf->fp.nr_maxactive); seq_printf(m, ":%s/%s", trace_probe_group_name(&tf->tp), trace_probe_name(&tf->tp)); -- cgit v1.2.3 From bc3d482dcc062963e7dc20565be2a887e5fc9a2d Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Fri, 27 Dec 2024 15:47:49 +0100 Subject: rv: Simplify manual steps in monitor creation While creating a new monitor in RV, besides generating code from dot2k, there are a few manual steps which can be tedious and error prone, like adding the tracepoints, makefile lines and kconfig. This patch restructures the existing monitors to keep some files in the monitor's folder itself, which can be automatically generated by future versions of dot2k. Monitors have now their own Kconfig and tracepoint snippets. For simplicity, the main tracepoint definition, is moved to the RV directory, it defines only the tracepoint classes and includes the monitor-specific tracepoints, which reside in the monitor directory. Tracepoints and Kconfig no longer need to be copied and adapted from existing ones but only need to be included in the main files. The Makefile remains untouched since there's little advantage in having a separated Makefile for each monitor with a single line and including it in the main RV Makefile. Cc: Juri Lelli Cc: Thomas Gleixner Cc: John Kacur Link: https://lore.kernel.org/20241227144752.362911-6-gmonaco@redhat.com Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- include/trace/events/rv.h | 142 ----------------------------- kernel/trace/rv/Kconfig | 25 +---- kernel/trace/rv/Makefile | 2 + kernel/trace/rv/monitors/wip/Kconfig | 12 +++ kernel/trace/rv/monitors/wip/wip.c | 2 +- kernel/trace/rv/monitors/wip/wip_trace.h | 15 +++ kernel/trace/rv/monitors/wwnr/Kconfig | 11 +++ kernel/trace/rv/monitors/wwnr/wwnr.c | 2 +- kernel/trace/rv/monitors/wwnr/wwnr_trace.h | 16 ++++ kernel/trace/rv/rv.c | 2 +- kernel/trace/rv/rv_trace.h | 128 ++++++++++++++++++++++++++ 11 files changed, 189 insertions(+), 168 deletions(-) delete mode 100644 include/trace/events/rv.h create mode 100644 kernel/trace/rv/monitors/wip/Kconfig create mode 100644 kernel/trace/rv/monitors/wip/wip_trace.h create mode 100644 kernel/trace/rv/monitors/wwnr/Kconfig create mode 100644 kernel/trace/rv/monitors/wwnr/wwnr_trace.h create mode 100644 kernel/trace/rv/rv_trace.h (limited to 'kernel/trace') diff --git a/include/trace/events/rv.h b/include/trace/events/rv.h deleted file mode 100644 index 56592da9301c..000000000000 --- a/include/trace/events/rv.h +++ /dev/null @@ -1,142 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM rv - -#if !defined(_TRACE_RV_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_RV_H - -#include -#include - -#ifdef CONFIG_DA_MON_EVENTS_IMPLICIT -DECLARE_EVENT_CLASS(event_da_monitor, - - TP_PROTO(char *state, char *event, char *next_state, bool final_state), - - TP_ARGS(state, event, next_state, final_state), - - TP_STRUCT__entry( - __array( char, state, MAX_DA_NAME_LEN ) - __array( char, event, MAX_DA_NAME_LEN ) - __array( char, next_state, MAX_DA_NAME_LEN ) - __field( bool, final_state ) - ), - - TP_fast_assign( - memcpy(__entry->state, state, MAX_DA_NAME_LEN); - memcpy(__entry->event, event, MAX_DA_NAME_LEN); - memcpy(__entry->next_state, next_state, MAX_DA_NAME_LEN); - __entry->final_state = final_state; - ), - - TP_printk("%s x %s -> %s %s", - __entry->state, - __entry->event, - __entry->next_state, - __entry->final_state ? "(final)" : "") -); - -DECLARE_EVENT_CLASS(error_da_monitor, - - TP_PROTO(char *state, char *event), - - TP_ARGS(state, event), - - TP_STRUCT__entry( - __array( char, state, MAX_DA_NAME_LEN ) - __array( char, event, MAX_DA_NAME_LEN ) - ), - - TP_fast_assign( - memcpy(__entry->state, state, MAX_DA_NAME_LEN); - memcpy(__entry->event, event, MAX_DA_NAME_LEN); - ), - - TP_printk("event %s not expected in the state %s", - __entry->event, - __entry->state) -); - -#ifdef CONFIG_RV_MON_WIP -DEFINE_EVENT(event_da_monitor, event_wip, - TP_PROTO(char *state, char *event, char *next_state, bool final_state), - TP_ARGS(state, event, next_state, final_state)); - -DEFINE_EVENT(error_da_monitor, error_wip, - TP_PROTO(char *state, char *event), - TP_ARGS(state, event)); -#endif /* CONFIG_RV_MON_WIP */ -#endif /* CONFIG_DA_MON_EVENTS_IMPLICIT */ - -#ifdef CONFIG_DA_MON_EVENTS_ID -DECLARE_EVENT_CLASS(event_da_monitor_id, - - TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state), - - TP_ARGS(id, state, event, next_state, final_state), - - TP_STRUCT__entry( - __field( int, id ) - __array( char, state, MAX_DA_NAME_LEN ) - __array( char, event, MAX_DA_NAME_LEN ) - __array( char, next_state, MAX_DA_NAME_LEN ) - __field( bool, final_state ) - ), - - TP_fast_assign( - memcpy(__entry->state, state, MAX_DA_NAME_LEN); - memcpy(__entry->event, event, MAX_DA_NAME_LEN); - memcpy(__entry->next_state, next_state, MAX_DA_NAME_LEN); - __entry->id = id; - __entry->final_state = final_state; - ), - - TP_printk("%d: %s x %s -> %s %s", - __entry->id, - __entry->state, - __entry->event, - __entry->next_state, - __entry->final_state ? "(final)" : "") -); - -DECLARE_EVENT_CLASS(error_da_monitor_id, - - TP_PROTO(int id, char *state, char *event), - - TP_ARGS(id, state, event), - - TP_STRUCT__entry( - __field( int, id ) - __array( char, state, MAX_DA_NAME_LEN ) - __array( char, event, MAX_DA_NAME_LEN ) - ), - - TP_fast_assign( - memcpy(__entry->state, state, MAX_DA_NAME_LEN); - memcpy(__entry->event, event, MAX_DA_NAME_LEN); - __entry->id = id; - ), - - TP_printk("%d: event %s not expected in the state %s", - __entry->id, - __entry->event, - __entry->state) -); - -#ifdef CONFIG_RV_MON_WWNR -/* id is the pid of the task */ -DEFINE_EVENT(event_da_monitor_id, event_wwnr, - TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state), - TP_ARGS(id, state, event, next_state, final_state)); - -DEFINE_EVENT(error_da_monitor_id, error_wwnr, - TP_PROTO(int id, char *state, char *event), - TP_ARGS(id, state, event)); -#endif /* CONFIG_RV_MON_WWNR */ - -#endif /* CONFIG_DA_MON_EVENTS_ID */ -#endif /* _TRACE_RV_H */ - -/* This part ust be outside protection */ -#undef TRACE_INCLUDE_PATH -#include diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index 831779607e84..1cca47531f00 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -25,30 +25,9 @@ menuconfig RV For further information, see: Documentation/trace/rv/runtime-verification.rst -config RV_MON_WIP - depends on RV - depends on PREEMPT_TRACER - select DA_MON_EVENTS_IMPLICIT - bool "wip monitor" - help - Enable wip (wakeup in preemptive) sample monitor that illustrates - the usage of per-cpu monitors, and one limitation of the - preempt_disable/enable events. - - For further information, see: - Documentation/trace/rv/monitor_wip.rst +source "kernel/trace/rv/monitors/wip/Kconfig" -config RV_MON_WWNR - depends on RV - select DA_MON_EVENTS_ID - bool "wwnr monitor" - help - Enable wwnr (wakeup while not running) sample monitor, this is a - sample monitor that illustrates the usage of per-task monitor. - The model is borken on purpose: it serves to test reactors. - - For further information, see: - Documentation/trace/rv/monitor_wwnr.rst +source "kernel/trace/rv/monitors/wwnr/Kconfig" config RV_REACTORS bool "Runtime verification reactors" diff --git a/kernel/trace/rv/Makefile b/kernel/trace/rv/Makefile index 963d14875b45..645434146a88 100644 --- a/kernel/trace/rv/Makefile +++ b/kernel/trace/rv/Makefile @@ -1,5 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 +ccflags-y += -I $(src) # needed for trace events + obj-$(CONFIG_RV) += rv.o obj-$(CONFIG_RV_MON_WIP) += monitors/wip/wip.o obj-$(CONFIG_RV_MON_WWNR) += monitors/wwnr/wwnr.o diff --git a/kernel/trace/rv/monitors/wip/Kconfig b/kernel/trace/rv/monitors/wip/Kconfig new file mode 100644 index 000000000000..3ef664b5cd90 --- /dev/null +++ b/kernel/trace/rv/monitors/wip/Kconfig @@ -0,0 +1,12 @@ +config RV_MON_WIP + depends on RV + depends on PREEMPT_TRACER + select DA_MON_EVENTS_IMPLICIT + bool "wip monitor" + help + Enable wip (wakeup in preemptive) sample monitor that illustrates + the usage of per-cpu monitors, and one limitation of the + preempt_disable/enable events. + + For further information, see: + Documentation/trace/rv/monitor_wip.rst diff --git a/kernel/trace/rv/monitors/wip/wip.c b/kernel/trace/rv/monitors/wip/wip.c index b2b49a27e886..db7389157c87 100644 --- a/kernel/trace/rv/monitors/wip/wip.c +++ b/kernel/trace/rv/monitors/wip/wip.c @@ -10,7 +10,7 @@ #define MODULE_NAME "wip" -#include +#include #include #include diff --git a/kernel/trace/rv/monitors/wip/wip_trace.h b/kernel/trace/rv/monitors/wip/wip_trace.h new file mode 100644 index 000000000000..aa2162f47a4c --- /dev/null +++ b/kernel/trace/rv/monitors/wip/wip_trace.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Snippet to be included in rv_trace.h + */ + +#ifdef CONFIG_RV_MON_WIP +DEFINE_EVENT(event_da_monitor, event_wip, + TP_PROTO(char *state, char *event, char *next_state, bool final_state), + TP_ARGS(state, event, next_state, final_state)); + +DEFINE_EVENT(error_da_monitor, error_wip, + TP_PROTO(char *state, char *event), + TP_ARGS(state, event)); +#endif /* CONFIG_RV_MON_WIP */ diff --git a/kernel/trace/rv/monitors/wwnr/Kconfig b/kernel/trace/rv/monitors/wwnr/Kconfig new file mode 100644 index 000000000000..ee741aa6d6b8 --- /dev/null +++ b/kernel/trace/rv/monitors/wwnr/Kconfig @@ -0,0 +1,11 @@ +config RV_MON_WWNR + depends on RV + select DA_MON_EVENTS_ID + bool "wwnr monitor" + help + Enable wwnr (wakeup while not running) sample monitor, this is a + sample monitor that illustrates the usage of per-task monitor. + The model is borken on purpose: it serves to test reactors. + + For further information, see: + Documentation/trace/rv/monitor_wwnr.rst diff --git a/kernel/trace/rv/monitors/wwnr/wwnr.c b/kernel/trace/rv/monitors/wwnr/wwnr.c index 0e43dd2db685..3b16994a9984 100644 --- a/kernel/trace/rv/monitors/wwnr/wwnr.c +++ b/kernel/trace/rv/monitors/wwnr/wwnr.c @@ -10,7 +10,7 @@ #define MODULE_NAME "wwnr" -#include +#include #include #include "wwnr.h" diff --git a/kernel/trace/rv/monitors/wwnr/wwnr_trace.h b/kernel/trace/rv/monitors/wwnr/wwnr_trace.h new file mode 100644 index 000000000000..fc97ec7476ad --- /dev/null +++ b/kernel/trace/rv/monitors/wwnr/wwnr_trace.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Snippet to be included in rv_trace.h + */ + +#ifdef CONFIG_RV_MON_WWNR +/* id is the pid of the task */ +DEFINE_EVENT(event_da_monitor_id, event_wwnr, + TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state), + TP_ARGS(id, state, event, next_state, final_state)); + +DEFINE_EVENT(error_da_monitor_id, error_wwnr, + TP_PROTO(int id, char *state, char *event), + TP_ARGS(id, state, event)); +#endif /* CONFIG_RV_MON_WWNR */ diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index 279c70e1bd74..8657fc8806e7 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -145,7 +145,7 @@ #ifdef CONFIG_DA_MON_EVENTS #define CREATE_TRACE_POINTS -#include +#include #endif #include "rv.h" diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h new file mode 100644 index 000000000000..3442dc59490f --- /dev/null +++ b/kernel/trace/rv/rv_trace.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM rv + +#if !defined(_TRACE_RV_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_RV_H + +#include +#include + +#ifdef CONFIG_DA_MON_EVENTS_IMPLICIT +DECLARE_EVENT_CLASS(event_da_monitor, + + TP_PROTO(char *state, char *event, char *next_state, bool final_state), + + TP_ARGS(state, event, next_state, final_state), + + TP_STRUCT__entry( + __array( char, state, MAX_DA_NAME_LEN ) + __array( char, event, MAX_DA_NAME_LEN ) + __array( char, next_state, MAX_DA_NAME_LEN ) + __field( bool, final_state ) + ), + + TP_fast_assign( + memcpy(__entry->state, state, MAX_DA_NAME_LEN); + memcpy(__entry->event, event, MAX_DA_NAME_LEN); + memcpy(__entry->next_state, next_state, MAX_DA_NAME_LEN); + __entry->final_state = final_state; + ), + + TP_printk("%s x %s -> %s %s", + __entry->state, + __entry->event, + __entry->next_state, + __entry->final_state ? "(final)" : "") +); + +DECLARE_EVENT_CLASS(error_da_monitor, + + TP_PROTO(char *state, char *event), + + TP_ARGS(state, event), + + TP_STRUCT__entry( + __array( char, state, MAX_DA_NAME_LEN ) + __array( char, event, MAX_DA_NAME_LEN ) + ), + + TP_fast_assign( + memcpy(__entry->state, state, MAX_DA_NAME_LEN); + memcpy(__entry->event, event, MAX_DA_NAME_LEN); + ), + + TP_printk("event %s not expected in the state %s", + __entry->event, + __entry->state) +); + +#include + +#endif /* CONFIG_DA_MON_EVENTS_IMPLICIT */ + +#ifdef CONFIG_DA_MON_EVENTS_ID +DECLARE_EVENT_CLASS(event_da_monitor_id, + + TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state), + + TP_ARGS(id, state, event, next_state, final_state), + + TP_STRUCT__entry( + __field( int, id ) + __array( char, state, MAX_DA_NAME_LEN ) + __array( char, event, MAX_DA_NAME_LEN ) + __array( char, next_state, MAX_DA_NAME_LEN ) + __field( bool, final_state ) + ), + + TP_fast_assign( + memcpy(__entry->state, state, MAX_DA_NAME_LEN); + memcpy(__entry->event, event, MAX_DA_NAME_LEN); + memcpy(__entry->next_state, next_state, MAX_DA_NAME_LEN); + __entry->id = id; + __entry->final_state = final_state; + ), + + TP_printk("%d: %s x %s -> %s %s", + __entry->id, + __entry->state, + __entry->event, + __entry->next_state, + __entry->final_state ? "(final)" : "") +); + +DECLARE_EVENT_CLASS(error_da_monitor_id, + + TP_PROTO(int id, char *state, char *event), + + TP_ARGS(id, state, event), + + TP_STRUCT__entry( + __field( int, id ) + __array( char, state, MAX_DA_NAME_LEN ) + __array( char, event, MAX_DA_NAME_LEN ) + ), + + TP_fast_assign( + memcpy(__entry->state, state, MAX_DA_NAME_LEN); + memcpy(__entry->event, event, MAX_DA_NAME_LEN); + __entry->id = id; + ), + + TP_printk("%d: event %s not expected in the state %s", + __entry->id, + __entry->event, + __entry->state) +); + +#include + +#endif /* CONFIG_DA_MON_EVENTS_ID */ +#endif /* _TRACE_RV_H */ + +/* This part ust be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE rv_trace +#include -- cgit v1.2.3 From de6f45c2dd226269fe9886290a139533c817c5bc Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Fri, 27 Dec 2024 15:47:51 +0100 Subject: verification/dot2k: Auto patch current kernel source dot2k suggests a list of changes to the kernel tree while adding a monitor: edit tracepoints header, Makefile, Kconfig and moving the monitor folder. Those changes can be easily run automatically. Add a flag to dot2k to alter the kernel source. The kernel source directory can be either assumed from the PWD, or from the running kernel, if installed. This feature works best if the kernel tree is a git repository, so that its easier to make sure there are no unintended changes. The main RV files (e.g. Makefile) have now a comment placeholder that can be useful for manual editing (e.g. to know where to add new monitors) and it is used by the script to append the required lines. We also slightly adapt the file handling functions in dot2k: __open_file is now called __read_file and also closes the file before returning the content; __create_file is now a more general __write_file, we no longer return on FileExistsError (not thrown while opening), a new __create_file simply calls __write_file specifying the monitor folder in the path. Cc: Juri Lelli Cc: Thomas Gleixner Cc: John Kacur Link: https://lore.kernel.org/20241227144752.362911-8-gmonaco@redhat.com Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/Kconfig | 2 +- kernel/trace/rv/Makefile | 1 + kernel/trace/rv/rv_trace.h | 2 + tools/verification/dot2/dot2k | 5 ++- tools/verification/dot2/dot2k.py | 92 ++++++++++++++++++++++++++++++++++------ 5 files changed, 86 insertions(+), 16 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index 1cca47531f00..8226352a0062 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -26,8 +26,8 @@ menuconfig RV Documentation/trace/rv/runtime-verification.rst source "kernel/trace/rv/monitors/wip/Kconfig" - source "kernel/trace/rv/monitors/wwnr/Kconfig" +# Add new monitors here config RV_REACTORS bool "Runtime verification reactors" diff --git a/kernel/trace/rv/Makefile b/kernel/trace/rv/Makefile index 645434146a88..188b64668e1f 100644 --- a/kernel/trace/rv/Makefile +++ b/kernel/trace/rv/Makefile @@ -5,6 +5,7 @@ ccflags-y += -I $(src) # needed for trace events obj-$(CONFIG_RV) += rv.o obj-$(CONFIG_RV_MON_WIP) += monitors/wip/wip.o obj-$(CONFIG_RV_MON_WWNR) += monitors/wwnr/wwnr.o +# Add new monitors here obj-$(CONFIG_RV_REACTORS) += rv_reactors.o obj-$(CONFIG_RV_REACT_PRINTK) += reactor_printk.o obj-$(CONFIG_RV_REACT_PANIC) += reactor_panic.o diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h index 3442dc59490f..5e65097423ba 100644 --- a/kernel/trace/rv/rv_trace.h +++ b/kernel/trace/rv/rv_trace.h @@ -58,6 +58,7 @@ DECLARE_EVENT_CLASS(error_da_monitor, ); #include +// Add new monitors based on CONFIG_DA_MON_EVENTS_IMPLICIT here #endif /* CONFIG_DA_MON_EVENTS_IMPLICIT */ @@ -117,6 +118,7 @@ DECLARE_EVENT_CLASS(error_da_monitor_id, ); #include +// Add new monitors based on CONFIG_DA_MON_EVENTS_ID here #endif /* CONFIG_DA_MON_EVENTS_ID */ #endif /* _TRACE_RV_H */ diff --git a/tools/verification/dot2/dot2k b/tools/verification/dot2/dot2k index 190c974edd0a..559ba191a1f6 100644 --- a/tools/verification/dot2/dot2k +++ b/tools/verification/dot2/dot2k @@ -21,6 +21,9 @@ if __name__ == '__main__': parser.add_argument('-t', "--monitor_type", dest="monitor_type", required=True) parser.add_argument('-n', "--model_name", dest="model_name", required=False) parser.add_argument("-D", "--description", dest="description", required=False) + parser.add_argument("-a", "--auto_patch", dest="auto_patch", + action="store_true", required=False, + help="Patch the kernel in place") params = parser.parse_args() print("Opening and parsing the dot file %s" % params.dot_file) @@ -38,4 +41,4 @@ if __name__ == '__main__': print(monitor.fill_tracepoint_tooltip()) print(monitor.fill_makefile_tooltip()) print(monitor.fill_kconfig_tooltip()) - print(" - Move %s/ to the kernel's monitor directory (%s/monitors)" % (monitor.name, monitor.rv_dir)) + print(monitor.fill_monitor_tooltip()) diff --git a/tools/verification/dot2/dot2k.py b/tools/verification/dot2/dot2k.py index dc56cd1fb0b4..83f4d49853a2 100644 --- a/tools/verification/dot2/dot2k.py +++ b/tools/verification/dot2/dot2k.py @@ -27,11 +27,14 @@ class dot2k(Dot2c): self.monitor_type = MonitorType self.__fill_rv_templates_dir() - self.main_c = self.__open_file(self.monitor_templates_dir + "main.c") - self.trace_h = self.__open_file(self.monitor_templates_dir + "trace.h") - self.kconfig = self.__open_file(self.monitor_templates_dir + "Kconfig") + self.main_c = self.__read_file(self.monitor_templates_dir + "main.c") + self.trace_h = self.__read_file(self.monitor_templates_dir + "trace.h") + self.kconfig = self.__read_file(self.monitor_templates_dir + "Kconfig") self.enum_suffix = "_%s" % self.name self.description = extra_params.get("description", self.name) or "auto-generated" + self.auto_patch = extra_params.get("auto_patch") + if self.auto_patch: + self.__fill_rv_kernel_dir() def __fill_rv_templates_dir(self): @@ -39,7 +42,7 @@ class dot2k(Dot2c): return if platform.system() != "Linux": - raise Exception("I can only run on Linux.") + raise OSError("I can only run on Linux.") kernel_path = "/lib/modules/%s/build/tools/verification/dot2/dot2k_templates/" % (platform.release()) @@ -51,17 +54,43 @@ class dot2k(Dot2c): self.monitor_templates_dir = "/usr/share/dot2/dot2k_templates/" return - raise Exception("Could not find the template directory, do you have the kernel source installed?") + raise FileNotFoundError("Could not find the template directory, do you have the kernel source installed?") + def __fill_rv_kernel_dir(self): - def __open_file(self, path): + # first try if we are running in the kernel tree root + if os.path.exists(self.rv_dir): + return + + # offset if we are running inside the kernel tree from verification/dot2 + kernel_path = os.path.join("../..", self.rv_dir) + + if os.path.exists(kernel_path): + self.rv_dir = kernel_path + return + + if platform.system() != "Linux": + raise OSError("I can only run on Linux.") + + kernel_path = os.path.join("/lib/modules/%s/build" % platform.release(), self.rv_dir) + + # if the current kernel is from a distro this may not be a full kernel tree + # verify that one of the files we are going to modify is available + if os.path.exists(os.path.join(kernel_path, "rv_trace.h")): + self.rv_dir = kernel_path + return + + raise FileNotFoundError("Could not find the rv directory, do you have the kernel source installed?") + + def __read_file(self, path): try: - fd = open(path) + fd = open(path, 'r') except OSError: raise Exception("Cannot open the file: %s" % path) content = fd.read() + fd.close() return content def __buff_to_string(self, buff): @@ -202,14 +231,32 @@ class dot2k(Dot2c): kconfig = kconfig.replace("%%DESCRIPTION%%", self.description) return kconfig + def __patch_file(self, file, marker, line): + file_to_patch = os.path.join(self.rv_dir, file) + content = self.__read_file(file_to_patch) + content = content.replace(marker, line + "\n" + marker) + self.__write_file(file_to_patch, content) + def fill_tracepoint_tooltip(self): monitor_class_type = self.fill_monitor_class_type() + if self.auto_patch: + self.__patch_file("rv_trace.h", + "// Add new monitors based on CONFIG_%s here" % monitor_class_type, + "#include " % (self.name, self.name)) + return " - Patching %s/rv_trace.h, double check the result" % self.rv_dir + return """ - Edit %s/rv_trace.h: Add this line where other tracepoints are included and %s is defined: #include """ % (self.rv_dir, monitor_class_type, self.name, self.name) def fill_kconfig_tooltip(self): + if self.auto_patch: + self.__patch_file("Kconfig", + "# Add new monitors here", + "source \"kernel/trace/rv/monitors/%s/Kconfig\"" % (self.name)) + return " - Patching %s/Kconfig, double check the result" % self.rv_dir + return """ - Edit %s/Kconfig: Add this line where other monitors are included: source \"kernel/trace/rv/monitors/%s/Kconfig\" @@ -218,32 +265,49 @@ source \"kernel/trace/rv/monitors/%s/Kconfig\" def fill_makefile_tooltip(self): name = self.name name_up = name.upper() + if self.auto_patch: + self.__patch_file("Makefile", + "# Add new monitors here", + "obj-$(CONFIG_RV_MON_%s) += monitors/%s/%s.o" % (name_up, name, name)) + return " - Patching %s/Makefile, double check the result" % self.rv_dir + return """ - Edit %s/Makefile: Add this line where other monitors are included: obj-$(CONFIG_RV_MON_%s) += monitors/%s/%s.o """ % (self.rv_dir, name_up, name, name) + def fill_monitor_tooltip(self): + if self.auto_patch: + return " - Monitor created in %s/monitors/%s" % (self.rv_dir, self. name) + return " - Move %s/ to the kernel's monitor directory (%s/monitors)" % (self.name, self.rv_dir) + def __create_directory(self): + path = self.name + if self.auto_patch: + path = os.path.join(self.rv_dir, "monitors", path) try: - os.mkdir(self.name) + os.mkdir(path) except FileExistsError: return except: print("Fail creating the output dir: %s" % self.name) - def __create_file(self, file_name, content): - path = "%s/%s" % (self.name, file_name) + def __write_file(self, file_name, content): try: - file = open(path, 'w') - except FileExistsError: - return + file = open(file_name, 'w') except: - print("Fail creating file: %s" % path) + print("Fail writing to file: %s" % file_name) file.write(content) file.close() + def __create_file(self, file_name, content): + path = "%s/%s" % (self.name, file_name) + if self.auto_patch: + path = os.path.join(self.rv_dir, "monitors", path) + self.__write_file(path, content) + def __get_main_name(self): path = "%s/%s" % (self.name, "main.c") if not os.path.exists(path): -- cgit v1.2.3 From afc6717628f959941d7b33728570568b4af1c4b8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 31 Dec 2024 00:06:46 -0500 Subject: tracing: Have process_string() also allow arrays In order to catch a common bug where a TRACE_EVENT() TP_fast_assign() assigns an address of an allocated string to the ring buffer and then references it in TP_printk(), which can be executed hours later when the string is free, the function test_event_printk() runs on all events as they are registered to make sure there's no unwanted dereferencing. It calls process_string() to handle cases in TP_printk() format that has "%s". It returns whether or not the string is safe. But it can have some false positives. For instance, xe_bo_move() has: TP_printk("move_lacks_source:%s, migrate object %p [size %zu] from %s to %s device_id:%s", __entry->move_lacks_source ? "yes" : "no", __entry->bo, __entry->size, xe_mem_type_to_name[__entry->old_placement], xe_mem_type_to_name[__entry->new_placement], __get_str(device_id)) Where the "%s" references into xe_mem_type_to_name[]. This is an array of pointers that should be safe for the event to access. Instead of flagging this as a bad reference, if a reference points to an array, where the record field is the index, consider it safe. Link: https://lore.kernel.org/all/9dee19b6185d325d0e6fa5f7cbba81d007d99166.camel@sapience.com/ Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20241231000646.324fb5f7@gandalf.local.home Fixes: 65a25d9f7ac02 ("tracing: Add "%s" check in test_event_printk()") Reported-by: Genes Lists Tested-by: Gene C Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 1545cc8b49d0..770e7ed91716 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -364,6 +364,18 @@ static bool process_string(const char *fmt, int len, struct trace_event_call *ca s = r + 1; } while (s < e); + /* + * Check for arrays. If the argument has: foo[REC->val] + * then it is very likely that foo is an array of strings + * that are safe to use. + */ + r = strstr(s, "["); + if (r && r < e) { + r = strstr(r, "REC->"); + if (r && r < e) + return true; + } + /* * If there's any strings in the argument consider this arg OK as it * could be: REC->field ? "foo" : "bar" and we don't want to get into -- cgit v1.2.3 From d65474033740ded0a4fe9a097fce72328655b41d Mon Sep 17 00:00:00 2001 From: Zilin Guan Date: Tue, 31 Dec 2024 11:37:31 +0000 Subject: fgraph: Add READ_ONCE() when accessing fgraph_array[] In __ftrace_return_to_handler(), a loop iterates over the fgraph_array[] elements, which are fgraph_ops. The loop checks if an element is a fgraph_stub to prevent using a fgraph_stub afterward. However, if the compiler reloads fgraph_array[] after this check, it might race with an update to fgraph_array[] that introduces a fgraph_stub. This could result in the stub being processed, but the stub contains a null "func_hash" field, leading to a NULL pointer dereference. To ensure that the gops compared against the fgraph_stub matches the gops processed later, add a READ_ONCE(). A similar patch appears in commit 63a8dfb ("function_graph: Add READ_ONCE() when accessing fgraph_array[]"). Cc: stable@vger.kernel.org Fixes: 37238abe3cb47 ("ftrace/function_graph: Pass fgraph_ops to function graph callbacks") Link: https://lore.kernel.org/20241231113731.277668-1-zilin@seu.edu.cn Signed-off-by: Zilin Guan Signed-off-by: Steven Rostedt (Google) --- kernel/trace/fgraph.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index ddedcb50917f..30e3ddc8a8a8 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -833,7 +833,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs #endif { for_each_set_bit(i, &bitmap, sizeof(bitmap) * BITS_PER_BYTE) { - struct fgraph_ops *gops = fgraph_array[i]; + struct fgraph_ops *gops = READ_ONCE(fgraph_array[i]); if (gops == &fgraph_stub) continue; -- cgit v1.2.3 From 789a8cff8d2dbe4b5c617c3004b5eb63fa7a3b35 Mon Sep 17 00:00:00 2001 From: Kohei Enju Date: Thu, 2 Jan 2025 04:08:20 +0900 Subject: ftrace: Fix function profiler's filtering functionality Commit c132be2c4fcc ("function_graph: Have the instances use their own ftrace_ops for filtering"), function profiler (enabled via function_profile_enabled) has been showing statistics for all functions, ignoring set_ftrace_filter settings. While tracers are instantiated, the function profiler is not. Therefore, it should use the global set_ftrace_filter for consistency. This patch modifies the function profiler to use the global filter, fixing the filtering functionality. Before (filtering not working): ``` root@localhost:~# echo 'vfs*' > /sys/kernel/tracing/set_ftrace_filter root@localhost:~# echo 1 > /sys/kernel/tracing/function_profile_enabled root@localhost:~# sleep 1 root@localhost:~# echo 0 > /sys/kernel/tracing/function_profile_enabled root@localhost:~# head /sys/kernel/tracing/trace_stat/* Function Hit Time Avg s^2 -------- --- ---- --- --- schedule 314 22290594 us 70989.15 us 40372231 us x64_sys_call 1527 8762510 us 5738.382 us 3414354 us schedule_hrtimeout_range 176 8665356 us 49234.98 us 405618876 us __x64_sys_ppoll 324 5656635 us 17458.75 us 19203976 us do_sys_poll 324 5653747 us 17449.83 us 19214945 us schedule_timeout 67 5531396 us 82558.15 us 2136740827 us __x64_sys_pselect6 12 3029540 us 252461.7 us 63296940171 us do_pselect.constprop.0 12 3029532 us 252461.0 us 63296952931 us ``` After (filtering working): ``` root@localhost:~# echo 'vfs*' > /sys/kernel/tracing/set_ftrace_filter root@localhost:~# echo 1 > /sys/kernel/tracing/function_profile_enabled root@localhost:~# sleep 1 root@localhost:~# echo 0 > /sys/kernel/tracing/function_profile_enabled root@localhost:~# head /sys/kernel/tracing/trace_stat/* Function Hit Time Avg s^2 -------- --- ---- --- --- vfs_write 462 68476.43 us 148.217 us 25874.48 us vfs_read 641 9611.356 us 14.994 us 28868.07 us vfs_fstat 890 878.094 us 0.986 us 1.667 us vfs_fstatat 227 757.176 us 3.335 us 18.928 us vfs_statx 226 610.610 us 2.701 us 17.749 us vfs_getattr_nosec 1187 460.919 us 0.388 us 0.326 us vfs_statx_path 297 343.287 us 1.155 us 11.116 us vfs_rename 6 291.575 us 48.595 us 9889.236 us ``` Cc: stable@vger.kernel.org Link: https://lore.kernel.org/20250101190820.72534-1-enjuk@amazon.com Fixes: c132be2c4fcc ("function_graph: Have the instances use their own ftrace_ops for filtering") Signed-off-by: Kohei Enju Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 9b17efb1a87d..2e113f8b13a2 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -902,16 +902,13 @@ static void profile_graph_return(struct ftrace_graph_ret *trace, } static struct fgraph_ops fprofiler_ops = { - .ops = { - .flags = FTRACE_OPS_FL_INITIALIZED, - INIT_OPS_HASH(fprofiler_ops.ops) - }, .entryfunc = &profile_graph_entry, .retfunc = &profile_graph_return, }; static int register_ftrace_profiler(void) { + ftrace_ops_set_global_filter(&fprofiler_ops.ops); return register_ftrace_graph(&fprofiler_ops); } @@ -922,12 +919,11 @@ static void unregister_ftrace_profiler(void) #else static struct ftrace_ops ftrace_profile_ops __read_mostly = { .func = function_profile_call, - .flags = FTRACE_OPS_FL_INITIALIZED, - INIT_OPS_HASH(ftrace_profile_ops) }; static int register_ftrace_profiler(void) { + ftrace_ops_set_global_filter(&ftrace_profile_ops); return register_ftrace_function(&ftrace_profile_ops); } -- cgit v1.2.3 From 22bec11a569983f39c6061cb82279e7de9e3bdfc Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 6 Jan 2025 11:11:43 -0500 Subject: tracing: Fix using ret variable in tracing_set_tracer() When the function tracing_set_tracer() switched over to using the guard() infrastructure, it did not need to save the 'ret' variable and would just return the value when an error arised, instead of setting ret and jumping to an out label. When CONFIG_TRACER_SNAPSHOT is enabled, it had code that expected the "ret" variable to be initialized to zero and had set 'ret' while holding an arch_spin_lock() (not used by guard), and then upon releasing the lock it would check 'ret' and exit if set. But because ret was only set when an error occurred while holding the locks, 'ret' would be used uninitialized if there was no error. The code in the CONFIG_TRACER_SNAPSHOT block should be self contain. Make sure 'ret' is also set when no error occurred. Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20250106111143.2f90ff65@gandalf.local.home Reported-by: kernel test robot Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/202412271654.nJVBuwmF-lkp@intel.com/ Fixes: d33b10c0c73ad ("tracing: Switch trace.c code over to use guard()") Signed-off-by: Steven Rostedt (Google) Acked-by: Masami Hiramatsu (Google) --- kernel/trace/trace.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 0aaf442271e9..5aeb898054e7 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6104,8 +6104,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) if (t->use_max_tr) { local_irq_disable(); arch_spin_lock(&tr->max_lock); - if (tr->cond_snapshot) - ret = -EBUSY; + ret = tr->cond_snapshot ? -EBUSY : 0; arch_spin_unlock(&tr->max_lock); local_irq_enable(); if (ret) -- cgit v1.2.3 From 1bd13edbbed6e7e396f1aab92b224a4775218e68 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 27 Dec 2024 13:07:57 +0900 Subject: tracing/hist: Add poll(POLLIN) support on hist file Add poll syscall support on the `hist` file. The Waiter will be waken up when the histogram is updated with POLLIN. Currently, there is no way to wait for a specific event in userspace. So user needs to peek the `trace` periodicaly, or wait on `trace_pipe`. But it is not a good idea to peek at the `trace` for an event that randomly happens. And `trace_pipe` is not coming back until a page is filled with events. This allows a user to wait for a specific event on the `hist` file. User can set a histogram trigger on the event which they want to monitor and poll() on its `hist` file. Since this poll() returns POLLIN, the next poll() will return soon unless a read() happens on that hist file. NOTE: To read the hist file again, you must set the file offset to 0, but just for monitoring the event, you may not need to read the histogram. Cc: Shuah Khan Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173527247756.464571.14236296701625509931.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (Google) --- include/linux/trace_events.h | 14 ++++++++ kernel/trace/trace_events.c | 14 ++++++++ kernel/trace/trace_events_hist.c | 70 ++++++++++++++++++++++++++++++++++++++-- 3 files changed, 95 insertions(+), 3 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 91b8ffbdfa8c..02cde1174487 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -673,6 +673,20 @@ struct trace_event_file { atomic_t tm_ref; /* trigger-mode reference counter */ }; +#ifdef CONFIG_HIST_TRIGGERS +extern struct irq_work hist_poll_work; +extern wait_queue_head_t hist_poll_wq; + +static inline void hist_poll_wakeup(void) +{ + if (wq_has_sleeper(&hist_poll_wq)) + irq_work_queue(&hist_poll_work); +} + +#define hist_poll_wait(file, wait) \ + poll_wait(file, &hist_poll_wq, wait) +#endif + #define __TRACE_EVENT_FLAGS(name, value) \ static int __init trace_init_flags_##name(void) \ { \ diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 047d2775184b..2b9222e7bd5a 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -3094,6 +3094,20 @@ static bool event_in_systems(struct trace_event_call *call, return !*p || isspace(*p) || *p == ','; } +#ifdef CONFIG_HIST_TRIGGERS +/* + * Wake up waiter on the hist_poll_wq from irq_work because the hist trigger + * may happen in any context. + */ +static void hist_poll_event_irq_work(struct irq_work *work) +{ + wake_up_all(&hist_poll_wq); +} + +DEFINE_IRQ_WORK(hist_poll_work, hist_poll_event_irq_work); +DECLARE_WAIT_QUEUE_HEAD(hist_poll_wq); +#endif + static struct trace_event_file * trace_create_new_event(struct trace_event_call *call, struct trace_array *tr) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 879b58892b9d..af4be28f01e0 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5311,6 +5311,8 @@ static void event_hist_trigger(struct event_trigger_data *data, if (resolve_var_refs(hist_data, key, var_ref_vals, true)) hist_trigger_actions(hist_data, elt, buffer, rec, rbe, key, var_ref_vals); + + hist_poll_wakeup(); } static void hist_trigger_stacktrace_print(struct seq_file *m, @@ -5590,15 +5592,36 @@ static void hist_trigger_show(struct seq_file *m, n_entries, (u64)atomic64_read(&hist_data->map->drops)); } +struct hist_file_data { + struct file *file; + u64 last_read; +}; + +static u64 get_hist_hit_count(struct trace_event_file *event_file) +{ + struct hist_trigger_data *hist_data; + struct event_trigger_data *data; + u64 ret = 0; + + list_for_each_entry(data, &event_file->triggers, list) { + if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) { + hist_data = data->private_data; + ret += atomic64_read(&hist_data->map->hits); + } + } + return ret; +} + static int hist_show(struct seq_file *m, void *v) { + struct hist_file_data *hist_file = m->private; struct event_trigger_data *data; struct trace_event_file *event_file; int n = 0; guard(mutex)(&event_mutex); - event_file = event_file_file(m->private); + event_file = event_file_file(hist_file->file); if (unlikely(!event_file)) return -ENODEV; @@ -5606,27 +5629,68 @@ static int hist_show(struct seq_file *m, void *v) if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) hist_trigger_show(m, data, n++); } + hist_file->last_read = get_hist_hit_count(event_file); + return 0; } +static __poll_t event_hist_poll(struct file *file, struct poll_table_struct *wait) +{ + struct trace_event_file *event_file; + struct seq_file *m = file->private_data; + struct hist_file_data *hist_file = m->private; + + guard(mutex)(&event_mutex); + + event_file = event_file_data(file); + if (!event_file) + return EPOLLERR; + + hist_poll_wait(file, wait); + + if (hist_file->last_read != get_hist_hit_count(event_file)) + return EPOLLIN | EPOLLRDNORM; + + return 0; +} + +static int event_hist_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + struct hist_file_data *hist_file = m->private; + + kfree(hist_file); + return tracing_single_release_file_tr(inode, file); +} + static int event_hist_open(struct inode *inode, struct file *file) { + struct hist_file_data *hist_file; int ret; ret = tracing_open_file_tr(inode, file); if (ret) return ret; + hist_file = kzalloc(sizeof(*hist_file), GFP_KERNEL); + if (!hist_file) + return -ENOMEM; + hist_file->file = file; + /* Clear private_data to avoid warning in single_open() */ file->private_data = NULL; - return single_open(file, hist_show, file); + ret = single_open(file, hist_show, hist_file); + if (ret) + kfree(hist_file); + return ret; } const struct file_operations event_hist_fops = { .open = event_hist_open, .read = seq_read, .llseek = seq_lseek, - .release = tracing_single_release_file_tr, + .release = event_hist_release, + .poll = event_hist_poll, }; #ifdef CONFIG_HIST_TRIGGERS_DEBUG -- cgit v1.2.3 From 66fc6f521a0b91051ce6968a216a30bc52267bf8 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 27 Dec 2024 13:08:07 +0900 Subject: tracing/hist: Support POLLPRI event for poll on histogram Since POLLIN will not be flushed until the hist file is read, the user needs to repeatedly read() and poll() on the hist file for monitoring the event continuously. But the read() is somewhat redundant when the user is only monitoring for event updates. Add POLLPRI poll event on the hist file so the event returns when a histogram is updated after open(), poll() or read(). Thus it is possible to wait for the next event without having to issue a read(). Cc: Shuah Khan Cc: Mathieu Desnoyers Link: https://lore.kernel.org/173527248770.464571.2536902137325258133.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_hist.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index af4be28f01e0..261163b00137 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5595,6 +5595,7 @@ static void hist_trigger_show(struct seq_file *m, struct hist_file_data { struct file *file; u64 last_read; + u64 last_act; }; static u64 get_hist_hit_count(struct trace_event_file *event_file) @@ -5630,6 +5631,11 @@ static int hist_show(struct seq_file *m, void *v) hist_trigger_show(m, data, n++); } hist_file->last_read = get_hist_hit_count(event_file); + /* + * Update last_act too so that poll()/POLLPRI can wait for the next + * event after any syscall on hist file. + */ + hist_file->last_act = hist_file->last_read; return 0; } @@ -5639,6 +5645,8 @@ static __poll_t event_hist_poll(struct file *file, struct poll_table_struct *wai struct trace_event_file *event_file; struct seq_file *m = file->private_data; struct hist_file_data *hist_file = m->private; + __poll_t ret = 0; + u64 cnt; guard(mutex)(&event_mutex); @@ -5648,10 +5656,15 @@ static __poll_t event_hist_poll(struct file *file, struct poll_table_struct *wai hist_poll_wait(file, wait); - if (hist_file->last_read != get_hist_hit_count(event_file)) - return EPOLLIN | EPOLLRDNORM; + cnt = get_hist_hit_count(event_file); + if (hist_file->last_read != cnt) + ret |= EPOLLIN | EPOLLRDNORM; + if (hist_file->last_act != cnt) { + hist_file->last_act = cnt; + ret |= EPOLLPRI; + } - return 0; + return ret; } static int event_hist_release(struct inode *inode, struct file *file) @@ -5665,6 +5678,7 @@ static int event_hist_release(struct inode *inode, struct file *file) static int event_hist_open(struct inode *inode, struct file *file) { + struct trace_event_file *event_file; struct hist_file_data *hist_file; int ret; @@ -5672,16 +5686,25 @@ static int event_hist_open(struct inode *inode, struct file *file) if (ret) return ret; + guard(mutex)(&event_mutex); + + event_file = event_file_data(file); + if (!event_file) + return -ENODEV; + hist_file = kzalloc(sizeof(*hist_file), GFP_KERNEL); if (!hist_file) return -ENOMEM; + hist_file->file = file; + hist_file->last_act = get_hist_hit_count(event_file); /* Clear private_data to avoid warning in single_open() */ file->private_data = NULL; ret = single_open(file, hist_show, hist_file); if (ret) kfree(hist_file); + return ret; } -- cgit v1.2.3 From ca3c4f646a9fc7d23b30c70e6663eaa38ac746af Mon Sep 17 00:00:00 2001 From: Pu Lehui Date: Sat, 4 Jan 2025 01:39:46 +0000 Subject: bpf: Move out synchronize_rcu_tasks_trace from mutex CS Commit ef1b808e3b7c ("bpf: Fix UAF via mismatching bpf_prog/attachment RCU flavors") resolved a possible UAF issue in uprobes that attach non-sleepable bpf prog by explicitly waiting for a tasks-trace-RCU grace period. But, in the current implementation, synchronize_rcu_tasks_trace is included within the mutex critical section, which increases the length of the critical section and may affect performance. So let's move out synchronize_rcu_tasks_trace from mutex CS. Signed-off-by: Pu Lehui Reviewed-by: Jiri Olsa Link: https://lore.kernel.org/r/20250104013946.1111785-1-pulehui@huaweicloud.com Signed-off-by: Alexei Starovoitov --- kernel/trace/bpf_trace.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 48db147c6c7d..a90880f475af 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2245,6 +2245,7 @@ void perf_event_detach_bpf_prog(struct perf_event *event) { struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; + struct bpf_prog *prog = NULL; int ret; mutex_lock(&bpf_event_mutex); @@ -2265,18 +2266,22 @@ void perf_event_detach_bpf_prog(struct perf_event *event) } put: - /* - * It could be that the bpf_prog is not sleepable (and will be freed - * via normal RCU), but is called from a point that supports sleepable - * programs and uses tasks-trace-RCU. - */ - synchronize_rcu_tasks_trace(); - - bpf_prog_put(event->prog); + prog = event->prog; event->prog = NULL; unlock: mutex_unlock(&bpf_event_mutex); + + if (prog) { + /* + * It could be that the bpf_prog is not sleepable (and will be freed + * via normal RCU), but is called from a point that supports sleepable + * programs and uses tasks-trace-RCU. + */ + synchronize_rcu_tasks_trace(); + + bpf_prog_put(prog); + } } int perf_event_query_prog_array(struct perf_event *event, void __user *info) -- cgit v1.2.3 From 2ebadb60cb36f2ee74bf83930fc73a5ceeb935fc Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 6 Jan 2025 18:50:47 +0100 Subject: bpf: Return error for missed kprobe multi bpf program execution When kprobe multi bpf program can't be executed due to recursion check, we currently return 0 (success) to fprobe layer where it's ignored for standard kprobe multi probes. For kprobe session the success return value will make fprobe layer to install return probe and try to execute it as well. But the return session probe should not get executed, because the entry part did not run. FWIW the return probe bpf program most likely won't get executed, because its recursion check will likely fail as well, but we don't need to run it in the first place.. also we can make this clear and obvious. It also affects missed counts for kprobe session program execution, which are now doubled (extra count for not executed return probe). Signed-off-by: Jiri Olsa Acked-by: Masami Hiramatsu (Google) Link: https://lore.kernel.org/r/20250106175048.1443905-1-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- kernel/trace/bpf_trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index a90880f475af..fc657c0eeb3e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2802,7 +2802,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { bpf_prog_inc_misses_counter(link->link.prog); - err = 0; + err = 1; goto out; } -- cgit v1.2.3 From 30c8fd31c571db486a5331a92d03eb60a0fb277c Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 9 Jan 2025 23:29:37 +0900 Subject: tracing/kprobes: Fix to free objects when failed to copy a symbol In __trace_kprobe_create(), if something fails it must goto error block to free objects. But when strdup() a symbol, it returns without that. Fix it to goto the error block to free objects correctly. Link: https://lore.kernel.org/all/173643297743.1514810.2408159540454241947.stgit@devnote2/ Fixes: 6212dd29683e ("tracing/kprobes: Use dyn_event framework for kprobe events") Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt (Google) --- kernel/trace/trace_kprobe.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 935a886af40c..0642ea174849 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -940,8 +940,10 @@ static int __trace_kprobe_create(int argc, const char *argv[]) } /* a symbol specified */ symbol = kstrdup(argv[1], GFP_KERNEL); - if (!symbol) - return -ENOMEM; + if (!symbol) { + ret = -ENOMEM; + goto error; + } tmp = strchr(symbol, '%'); if (tmp) { -- cgit v1.2.3 From 2cba0070cd0cf25f7f7cfee3447beba8106f682f Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Sat, 30 Nov 2024 01:48:08 +0900 Subject: tracing/kprobe: Adopt guard() and scoped_guard() Use guard() or scoped_guard() in kprobe events for critical sections rather than discrete lock/unlock pairs. Link: https://lore.kernel.org/all/173289888883.73724.6586200652276577583.stgit@devnote2/ Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/trace_kprobe.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 0642ea174849..7090f4a82990 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -634,7 +634,7 @@ static int register_trace_kprobe(struct trace_kprobe *tk) struct trace_kprobe *old_tk; int ret; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); old_tk = find_trace_kprobe(trace_probe_name(&tk->tp), trace_probe_group_name(&tk->tp)); @@ -642,11 +642,9 @@ static int register_trace_kprobe(struct trace_kprobe *tk) if (trace_kprobe_is_return(tk) != trace_kprobe_is_return(old_tk)) { trace_probe_log_set_index(0); trace_probe_log_err(0, DIFF_PROBE_TYPE); - ret = -EEXIST; - } else { - ret = append_trace_kprobe(tk, old_tk); + return -EEXIST; } - goto end; + return append_trace_kprobe(tk, old_tk); } /* Register new event */ @@ -657,7 +655,7 @@ static int register_trace_kprobe(struct trace_kprobe *tk) trace_probe_log_err(0, EVENT_EXIST); } else pr_warn("Failed to register probe event(%d)\n", ret); - goto end; + return ret; } /* Register k*probe */ @@ -672,8 +670,6 @@ static int register_trace_kprobe(struct trace_kprobe *tk) else dyn_event_add(&tk->devent, trace_probe_event_call(&tk->tp)); -end: - mutex_unlock(&event_mutex); return ret; } @@ -706,7 +702,7 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, return NOTIFY_DONE; /* Update probes on coming module */ - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); for_each_trace_kprobe(tk, pos) { if (trace_kprobe_within_module(tk, mod)) { /* Don't need to check busy - this should have gone. */ @@ -718,7 +714,6 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, module_name(mod), ret); } } - mutex_unlock(&event_mutex); return NOTIFY_DONE; } @@ -1970,13 +1965,12 @@ static __init void enable_boot_kprobe_events(void) struct trace_kprobe *tk; struct dyn_event *pos; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); for_each_trace_kprobe(tk, pos) { list_for_each_entry(file, &tr->events, list) if (file->event_call == trace_probe_event_call(&tk->tp)) trace_event_enable_disable(file, 1, 0); } - mutex_unlock(&event_mutex); } static __init void setup_boot_kprobe_events(void) -- cgit v1.2.3 From f8821732dcf066b7b6bf4b8bc98abe8f8fcda021 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Sat, 30 Nov 2024 01:48:19 +0900 Subject: tracing/uprobe: Adopt guard() and scoped_guard() Use guard() or scoped_guard() in uprobe events for critical sections rather than discrete lock/unlock pairs. Link: https://lore.kernel.org/all/173289889911.73724.12457932738419630525.stgit@devnote2/ Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/trace_uprobe.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 4875e7f5de3d..ccc762fbb69c 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -498,11 +498,11 @@ static int register_trace_uprobe(struct trace_uprobe *tu) struct trace_uprobe *old_tu; int ret; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); ret = validate_ref_ctr_offset(tu); if (ret) - goto end; + return ret; /* register as an event */ old_tu = find_probe_event(trace_probe_name(&tu->tp), @@ -511,11 +511,9 @@ static int register_trace_uprobe(struct trace_uprobe *tu) if (is_ret_probe(tu) != is_ret_probe(old_tu)) { trace_probe_log_set_index(0); trace_probe_log_err(0, DIFF_PROBE_TYPE); - ret = -EEXIST; - } else { - ret = append_trace_uprobe(tu, old_tu); + return -EEXIST; } - goto end; + return append_trace_uprobe(tu, old_tu); } ret = register_uprobe_event(tu); @@ -525,14 +523,11 @@ static int register_trace_uprobe(struct trace_uprobe *tu) trace_probe_log_err(0, EVENT_EXIST); } else pr_warn("Failed to register probe event(%d)\n", ret); - goto end; + return ret; } dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp)); -end: - mutex_unlock(&event_mutex); - return ret; } -- cgit v1.2.3 From 4e83017e4c229d7fa368d6974fd06aa59aeef04f Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Sat, 30 Nov 2024 01:48:30 +0900 Subject: tracing/eprobe: Adopt guard() and scoped_guard() Use guard() or scoped_guard() in eprobe events for critical sections rather than discrete lock/unlock pairs. Link: https://lore.kernel.org/all/173289890996.73724.17421347964110362029.stgit@devnote2/ Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/trace_eprobe.c | 36 +++++++++++++++++------------------- 1 file changed, 17 insertions(+), 19 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index be8be0c1aaf0..82fd637cfc19 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -917,10 +917,10 @@ static int __trace_eprobe_create(int argc, const char *argv[]) goto error; } - mutex_lock(&event_mutex); - event_call = find_and_get_event(sys_name, sys_event); - ep = alloc_event_probe(group, event, event_call, argc - 2); - mutex_unlock(&event_mutex); + scoped_guard(mutex, &event_mutex) { + event_call = find_and_get_event(sys_name, sys_event); + ep = alloc_event_probe(group, event, event_call, argc - 2); + } if (IS_ERR(ep)) { ret = PTR_ERR(ep); @@ -952,23 +952,21 @@ static int __trace_eprobe_create(int argc, const char *argv[]) if (ret < 0) goto error; init_trace_eprobe_call(ep); - mutex_lock(&event_mutex); - ret = trace_probe_register_event_call(&ep->tp); - if (ret) { - if (ret == -EEXIST) { - trace_probe_log_set_index(0); - trace_probe_log_err(0, EVENT_EXIST); + scoped_guard(mutex, &event_mutex) { + ret = trace_probe_register_event_call(&ep->tp); + if (ret) { + if (ret == -EEXIST) { + trace_probe_log_set_index(0); + trace_probe_log_err(0, EVENT_EXIST); + } + goto error; + } + ret = dyn_event_add(&ep->devent, &ep->tp.event->call); + if (ret < 0) { + trace_probe_unregister_event_call(&ep->tp); + goto error; } - mutex_unlock(&event_mutex); - goto error; - } - ret = dyn_event_add(&ep->devent, &ep->tp.event->call); - if (ret < 0) { - trace_probe_unregister_event_call(&ep->tp); - mutex_unlock(&event_mutex); - goto error; } - mutex_unlock(&event_mutex); return ret; parse_error: ret = -EINVAL; -- cgit v1.2.3 From 4af0532a0f4799d5944ea966c10890dcb4390d19 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 9 Jan 2025 23:29:48 +0900 Subject: tracing: Use __free() in trace_probe for cleanup Use __free() in trace_probe to cleanup some gotos. Link: https://lore.kernel.org/all/173643298860.1514810.7267350121047606213.stgit@devnote2/ Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt (Google) --- kernel/trace/trace_probe.c | 51 ++++++++++++++++------------------------------ 1 file changed, 17 insertions(+), 34 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 16a5e368e7b7..8f58ee1e8858 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -1409,7 +1409,7 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, struct traceprobe_parse_context *ctx) { struct fetch_insn *code, *tmp = NULL; - char *type, *arg; + char *type, *arg __free(kfree) = NULL; int ret, len; len = strlen(argv); @@ -1426,22 +1426,16 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, return -ENOMEM; parg->comm = kstrdup(arg, GFP_KERNEL); - if (!parg->comm) { - ret = -ENOMEM; - goto out; - } + if (!parg->comm) + return -ENOMEM; type = parse_probe_arg_type(arg, parg, ctx); - if (IS_ERR(type)) { - ret = PTR_ERR(type); - goto out; - } + if (IS_ERR(type)) + return PTR_ERR(type); code = tmp = kcalloc(FETCH_INSN_MAX, sizeof(*code), GFP_KERNEL); - if (!code) { - ret = -ENOMEM; - goto out; - } + if (!code) + return -ENOMEM; code[FETCH_INSN_MAX - 1].op = FETCH_OP_END; ctx->last_type = NULL; @@ -1497,8 +1491,6 @@ fail: kfree(code->data); } kfree(tmp); -out: - kfree(arg); return ret; } @@ -1668,7 +1660,7 @@ const char **traceprobe_expand_meta_args(int argc, const char *argv[], { const struct btf_param *params = NULL; int i, j, n, used, ret, args_idx = -1; - const char **new_argv = NULL; + const char **new_argv __free(kfree) = NULL; ret = argv_has_var_arg(argc, argv, &args_idx, ctx); if (ret < 0) @@ -1707,7 +1699,7 @@ const char **traceprobe_expand_meta_args(int argc, const char *argv[], ret = sprint_nth_btf_arg(n, "", buf + used, bufsize - used, ctx); if (ret < 0) - goto error; + return ERR_PTR(ret); new_argv[j++] = buf + used; used += ret + 1; @@ -1721,25 +1713,20 @@ const char **traceprobe_expand_meta_args(int argc, const char *argv[], n = simple_strtoul(argv[i] + 4, &type, 10); if (type && !(*type == ':' || *type == '\0')) { trace_probe_log_err(0, BAD_VAR); - ret = -ENOENT; - goto error; + return ERR_PTR(-ENOENT); } /* Note: $argN starts from $arg1 */ ret = sprint_nth_btf_arg(n - 1, type, buf + used, bufsize - used, ctx); if (ret < 0) - goto error; + return ERR_PTR(ret); new_argv[j++] = buf + used; used += ret + 1; } else new_argv[j++] = argv[i]; } - return new_argv; - -error: - kfree(new_argv); - return ERR_PTR(ret); + return_ptr(new_argv); } /* @buf: *buf must be equal to NULL. Caller must to free *buf */ @@ -1747,14 +1734,14 @@ int traceprobe_expand_dentry_args(int argc, const char *argv[], char **buf) { int i, used, ret; const int bufsize = MAX_DENTRY_ARGS_LEN; - char *tmpbuf = NULL; + char *tmpbuf __free(kfree) = NULL; if (*buf) return -EINVAL; used = 0; for (i = 0; i < argc; i++) { - char *tmp; + char *tmp __free(kfree) = NULL; char *equal; size_t arg_len; @@ -1769,7 +1756,7 @@ int traceprobe_expand_dentry_args(int argc, const char *argv[], char **buf) tmp = kstrdup(argv[i], GFP_KERNEL); if (!tmp) - goto nomem; + return -ENOMEM; equal = strchr(tmp, '='); if (equal) @@ -1790,18 +1777,14 @@ int traceprobe_expand_dentry_args(int argc, const char *argv[], char **buf) offsetof(struct file, f_path.dentry), equal ? equal + 1 : tmp); - kfree(tmp); if (ret >= bufsize - used) - goto nomem; + return -ENOMEM; argv[i] = tmpbuf + used; used += ret + 1; } - *buf = tmpbuf; + *buf = no_free_ptr(tmpbuf); return 0; -nomem: - kfree(tmpbuf); - return -ENOMEM; } void traceprobe_finish_parse(struct traceprobe_parse_context *ctx) -- cgit v1.2.3 From 7dcc35207890451519c9ca4cf4207ac2be84fc83 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 9 Jan 2025 23:29:59 +0900 Subject: tracing: Use __free() for kprobe events to cleanup Use __free() in trace_kprobe.c to cleanup code. Link: https://lore.kernel.org/all/173643299989.1514810.2924926552980462072.stgit@devnote2/ Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt (Google) --- kernel/trace/trace_kprobe.c | 62 +++++++++++++++++++++------------------------ 1 file changed, 29 insertions(+), 33 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 7090f4a82990..18a5ee24dcef 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -8,6 +8,7 @@ #define pr_fmt(fmt) "trace_kprobe: " fmt #include +#include #include #include #include @@ -257,6 +258,9 @@ static void free_trace_kprobe(struct trace_kprobe *tk) } } +DEFINE_FREE(free_trace_kprobe, struct trace_kprobe *, + if (!IS_ERR_OR_NULL(_T)) free_trace_kprobe(_T)) + /* * Allocate new trace_probe and initialize it (including kprobes). */ @@ -268,7 +272,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, int maxactive, int nargs, bool is_return) { - struct trace_kprobe *tk; + struct trace_kprobe *tk __free(free_trace_kprobe) = NULL; int ret = -ENOMEM; tk = kzalloc(struct_size(tk, tp.args, nargs), GFP_KERNEL); @@ -277,12 +281,12 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, tk->nhit = alloc_percpu(unsigned long); if (!tk->nhit) - goto error; + return ERR_PTR(ret); if (symbol) { tk->symbol = kstrdup(symbol, GFP_KERNEL); if (!tk->symbol) - goto error; + return ERR_PTR(ret); tk->rp.kp.symbol_name = tk->symbol; tk->rp.kp.offset = offs; } else @@ -299,13 +303,10 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, ret = trace_probe_init(&tk->tp, event, group, false, nargs); if (ret < 0) - goto error; + return ERR_PTR(ret); dyn_event_init(&tk->devent, &trace_kprobe_ops); - return tk; -error: - free_trace_kprobe(tk); - return ERR_PTR(ret); + return_ptr(tk); } static struct trace_kprobe *find_trace_kprobe(const char *event, @@ -861,11 +862,12 @@ static int __trace_kprobe_create(int argc, const char *argv[]) * Type of args: * FETCHARG:TYPE : use TYPE instead of unsigned long. */ - struct trace_kprobe *tk = NULL; + struct trace_kprobe *tk __free(free_trace_kprobe) = NULL; int i, len, new_argc = 0, ret = 0; bool is_return = false; - char *symbol = NULL, *tmp = NULL; - const char **new_argv = NULL; + char *symbol __free(kfree) = NULL; + char *tmp = NULL; + const char **new_argv __free(kfree) = NULL; const char *event = NULL, *group = KPROBE_EVENT_SYSTEM; enum probe_print_type ptype; int maxactive = 0; @@ -874,7 +876,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) char buf[MAX_EVENT_NAME_LEN]; char gbuf[MAX_EVENT_NAME_LEN]; char abuf[MAX_BTF_ARGS_LEN]; - char *dbuf = NULL; + char *dbuf __free(kfree) = NULL; struct traceprobe_parse_context ctx = { .flags = TPARG_FL_KERNEL }; switch (argv[0][0]) { @@ -931,13 +933,13 @@ static int __trace_kprobe_create(int argc, const char *argv[]) /* Check whether uprobe event specified */ if (strchr(argv[1], '/') && strchr(argv[1], ':')) { ret = -ECANCELED; - goto error; + goto out; } /* a symbol specified */ symbol = kstrdup(argv[1], GFP_KERNEL); if (!symbol) { ret = -ENOMEM; - goto error; + goto out; } tmp = strchr(symbol, '%'); @@ -1035,7 +1037,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) ctx.offset = 0; ret = traceprobe_parse_probe_arg(&tk->tp, i, argv[i], &ctx); if (ret) - goto error; /* This can be -ENOMEM */ + goto out; /* This can be -ENOMEM */ } /* entry handler for kretprobe */ if (is_return && tk->tp.entry_arg) { @@ -1046,7 +1048,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) ptype = is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL; ret = traceprobe_set_print_fmt(&tk->tp, ptype); if (ret < 0) - goto error; + goto out; ret = register_trace_kprobe(tk); if (ret) { @@ -1057,21 +1059,20 @@ static int __trace_kprobe_create(int argc, const char *argv[]) trace_probe_log_err(0, BAD_PROBE_ADDR); else if (ret != -ENOMEM && ret != -EEXIST) trace_probe_log_err(0, FAIL_REG_PROBE); - goto error; - } + } else + /* + * Here, 'tk' has been registered to the list successfully, + * so we don't need to free it. + */ + tk = NULL; out: traceprobe_finish_parse(&ctx); trace_probe_log_clear(); - kfree(new_argv); - kfree(symbol); - kfree(dbuf); return ret; parse_error: ret = -EINVAL; -error: - free_trace_kprobe(tk); goto out; } @@ -1893,7 +1894,7 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs, bool is_return) { enum probe_print_type ptype; - struct trace_kprobe *tk; + struct trace_kprobe *tk __free(free_trace_kprobe) = NULL; int ret; char *event; @@ -1924,19 +1925,14 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs, ptype = trace_kprobe_is_return(tk) ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL; - if (traceprobe_set_print_fmt(&tk->tp, ptype) < 0) { - ret = -ENOMEM; - goto error; - } + if (traceprobe_set_print_fmt(&tk->tp, ptype) < 0) + return ERR_PTR(-ENOMEM); ret = __register_trace_kprobe(tk); if (ret < 0) - goto error; + return ERR_PTR(ret); - return trace_probe_event_call(&tk->tp); -error: - free_trace_kprobe(tk); - return ERR_PTR(ret); + return trace_probe_event_call(&(no_free_ptr(tk)->tp)); } void destroy_local_trace_kprobe(struct trace_event_call *event_call) -- cgit v1.2.3 From 927054606d08d95827f854246293f8379480ed15 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 9 Jan 2025 23:30:11 +0900 Subject: tracing/kprobes: Simplify __trace_kprobe_create() by removing gotos Simplify __trace_kprobe_create() by removing gotos. Link: https://lore.kernel.org/all/173643301102.1514810.6149004416601259466.stgit@devnote2/ Signed-off-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt (Google) --- kernel/trace/trace_kprobe.c | 97 +++++++++++++++++++++++---------------------- 1 file changed, 49 insertions(+), 48 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 18a5ee24dcef..d8d5f18a141a 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -836,7 +836,8 @@ out: static int trace_kprobe_entry_handler(struct kretprobe_instance *ri, struct pt_regs *regs); -static int __trace_kprobe_create(int argc, const char *argv[]) +static int trace_kprobe_create_internal(int argc, const char *argv[], + struct traceprobe_parse_context *ctx) { /* * Argument syntax: @@ -877,7 +878,6 @@ static int __trace_kprobe_create(int argc, const char *argv[]) char gbuf[MAX_EVENT_NAME_LEN]; char abuf[MAX_BTF_ARGS_LEN]; char *dbuf __free(kfree) = NULL; - struct traceprobe_parse_context ctx = { .flags = TPARG_FL_KERNEL }; switch (argv[0][0]) { case 'r': @@ -891,8 +891,6 @@ static int __trace_kprobe_create(int argc, const char *argv[]) if (argc < 2) return -ECANCELED; - trace_probe_log_init("trace_kprobe", argc, argv); - event = strchr(&argv[0][1], ':'); if (event) event++; @@ -900,7 +898,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) if (isdigit(argv[0][1])) { if (!is_return) { trace_probe_log_err(1, BAD_MAXACT_TYPE); - goto parse_error; + return -EINVAL; } if (event) len = event - &argv[0][1] - 1; @@ -908,21 +906,21 @@ static int __trace_kprobe_create(int argc, const char *argv[]) len = strlen(&argv[0][1]); if (len > MAX_EVENT_NAME_LEN - 1) { trace_probe_log_err(1, BAD_MAXACT); - goto parse_error; + return -EINVAL; } memcpy(buf, &argv[0][1], len); buf[len] = '\0'; ret = kstrtouint(buf, 0, &maxactive); if (ret || !maxactive) { trace_probe_log_err(1, BAD_MAXACT); - goto parse_error; + return -EINVAL; } /* kretprobes instances are iterated over via a list. The * maximum should stay reasonable. */ if (maxactive > KRETPROBE_MAXACTIVE_MAX) { trace_probe_log_err(1, MAXACT_TOO_BIG); - goto parse_error; + return -EINVAL; } } @@ -931,16 +929,13 @@ static int __trace_kprobe_create(int argc, const char *argv[]) if (kstrtoul(argv[1], 0, (unsigned long *)&addr)) { trace_probe_log_set_index(1); /* Check whether uprobe event specified */ - if (strchr(argv[1], '/') && strchr(argv[1], ':')) { - ret = -ECANCELED; - goto out; - } + if (strchr(argv[1], '/') && strchr(argv[1], ':')) + return -ECANCELED; + /* a symbol specified */ symbol = kstrdup(argv[1], GFP_KERNEL); - if (!symbol) { - ret = -ENOMEM; - goto out; - } + if (!symbol) + return -ENOMEM; tmp = strchr(symbol, '%'); if (tmp) { @@ -949,7 +944,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) is_return = true; } else { trace_probe_log_err(tmp - symbol, BAD_ADDR_SUFFIX); - goto parse_error; + return -EINVAL; } } @@ -957,7 +952,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) ret = traceprobe_split_symbol_offset(symbol, &offset); if (ret || offset < 0 || offset > UINT_MAX) { trace_probe_log_err(0, BAD_PROBE_ADDR); - goto parse_error; + return -EINVAL; } ret = validate_probe_symbol(symbol); if (ret) { @@ -965,17 +960,17 @@ static int __trace_kprobe_create(int argc, const char *argv[]) trace_probe_log_err(0, NON_UNIQ_SYMBOL); else trace_probe_log_err(0, BAD_PROBE_ADDR); - goto parse_error; + return -EINVAL; } if (is_return) - ctx.flags |= TPARG_FL_RETURN; + ctx->flags |= TPARG_FL_RETURN; ret = kprobe_on_func_entry(NULL, symbol, offset); if (ret == 0 && !is_return) - ctx.flags |= TPARG_FL_FENTRY; + ctx->flags |= TPARG_FL_FENTRY; /* Defer the ENOENT case until register kprobe */ if (ret == -EINVAL && is_return) { trace_probe_log_err(0, BAD_RETPROBE); - goto parse_error; + return -EINVAL; } } @@ -984,7 +979,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) ret = traceprobe_parse_event_name(&event, &group, gbuf, event - argv[0]); if (ret) - goto parse_error; + return ret; } if (!event) { @@ -1000,26 +995,24 @@ static int __trace_kprobe_create(int argc, const char *argv[]) } argc -= 2; argv += 2; - ctx.funcname = symbol; + ctx->funcname = symbol; new_argv = traceprobe_expand_meta_args(argc, argv, &new_argc, - abuf, MAX_BTF_ARGS_LEN, &ctx); + abuf, MAX_BTF_ARGS_LEN, ctx); if (IS_ERR(new_argv)) { ret = PTR_ERR(new_argv); new_argv = NULL; - goto out; + return ret; } if (new_argv) { argc = new_argc; argv = new_argv; } - if (argc > MAX_TRACE_ARGS) { - ret = -E2BIG; - goto out; - } + if (argc > MAX_TRACE_ARGS) + return -E2BIG; ret = traceprobe_expand_dentry_args(argc, argv, &dbuf); if (ret) - goto out; + return ret; /* setup a probe */ tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive, @@ -1028,16 +1021,16 @@ static int __trace_kprobe_create(int argc, const char *argv[]) ret = PTR_ERR(tk); /* This must return -ENOMEM, else there is a bug */ WARN_ON_ONCE(ret != -ENOMEM); - goto out; /* We know tk is not allocated */ + return ret; /* We know tk is not allocated */ } /* parse arguments */ for (i = 0; i < argc; i++) { trace_probe_log_set_index(i + 2); - ctx.offset = 0; - ret = traceprobe_parse_probe_arg(&tk->tp, i, argv[i], &ctx); + ctx->offset = 0; + ret = traceprobe_parse_probe_arg(&tk->tp, i, argv[i], ctx); if (ret) - goto out; /* This can be -ENOMEM */ + return ret; /* This can be -ENOMEM */ } /* entry handler for kretprobe */ if (is_return && tk->tp.entry_arg) { @@ -1048,7 +1041,7 @@ static int __trace_kprobe_create(int argc, const char *argv[]) ptype = is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL; ret = traceprobe_set_print_fmt(&tk->tp, ptype); if (ret < 0) - goto out; + return ret; ret = register_trace_kprobe(tk); if (ret) { @@ -1059,26 +1052,34 @@ static int __trace_kprobe_create(int argc, const char *argv[]) trace_probe_log_err(0, BAD_PROBE_ADDR); else if (ret != -ENOMEM && ret != -EEXIST) trace_probe_log_err(0, FAIL_REG_PROBE); - } else - /* - * Here, 'tk' has been registered to the list successfully, - * so we don't need to free it. - */ - tk = NULL; + return ret; + } + /* + * Here, 'tk' has been registered to the list successfully, + * so we don't need to free it. + */ + tk = NULL; + + return 0; +} + +static int trace_kprobe_create_cb(int argc, const char *argv[]) +{ + struct traceprobe_parse_context ctx = { .flags = TPARG_FL_KERNEL }; + int ret; + + trace_probe_log_init("trace_kprobe", argc, argv); + + ret = trace_kprobe_create_internal(argc, argv, &ctx); -out: traceprobe_finish_parse(&ctx); trace_probe_log_clear(); return ret; - -parse_error: - ret = -EINVAL; - goto out; } static int trace_kprobe_create(const char *raw_command) { - return trace_probe_create(raw_command, __trace_kprobe_create); + return trace_probe_create(raw_command, trace_kprobe_create_cb); } static int create_or_delete_trace_kprobe(const char *raw_command) -- cgit v1.2.3 From 4f7caaa2f92b47e9d27d85f8a60bb7634becd669 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Wed, 1 Jan 2025 01:00:14 +0900 Subject: bpf: Use ftrace_get_symaddr() for kprobe_multi probes Add ftrace_get_entry_ip() which is only for ftrace based probes, and use it for kprobe multi probes because they are based on fprobe which uses ftrace instead of kprobes. Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Alan Maguire Cc: Mark Rutland Link: https://lore.kernel.org/173566081414.878879.10631096557346094362.stgit@devnote2 Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/bpf_trace.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 863351559334..9bfd52913a5b 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2591,6 +2591,13 @@ static DEFINE_PER_CPU(struct pt_regs, bpf_kprobe_multi_pt_regs); #define bpf_kprobe_multi_pt_regs_ptr() (NULL) #endif +static unsigned long ftrace_get_entry_ip(unsigned long fentry_ip) +{ + unsigned long ip = ftrace_get_symaddr(fentry_ip); + + return ip ? : fentry_ip; +} + static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 cnt) { unsigned long __user usymbol; @@ -2829,7 +2836,8 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, int err; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), fregs, false, data); + err = kprobe_multi_link_prog_run(link, ftrace_get_entry_ip(fentry_ip), + fregs, false, data); return is_kprobe_session(link->link.prog) ? err : 0; } @@ -2841,7 +2849,8 @@ kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip, struct bpf_kprobe_multi_link *link; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), fregs, true, data); + kprobe_multi_link_prog_run(link, ftrace_get_entry_ip(fentry_ip), + fregs, true, data); } static int symbols_cmp_r(const void *a, const void *b, const void *priv) -- cgit v1.2.3 From 0568c6ebf072d913c437dbb5271f889a5e329007 Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Wed, 8 Jan 2025 11:45:25 +0000 Subject: ring-buffer: Check for empty ring-buffer with rb_num_of_entries() Currently there are two ways of identifying an empty ring-buffer. One relying on the current status of the commit / reader page (rb_per_cpu_empty()) and the other on the write and read counters (rb_num_of_entries() used in rb_get_reader_page()). with rb_num_of_entries(). This intends to ease later introduction of ring-buffer writers which are out of the kernel control and with whom, the only information available is through the meta-page counters. Link: https://lore.kernel.org/20250108114536.627715-2-vdonnefort@google.com Signed-off-by: Vincent Donnefort Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 59 +++++++++++----------------------------------- 1 file changed, 14 insertions(+), 45 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 60210fb5b211..479bbbcbf61b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4682,40 +4682,22 @@ int ring_buffer_write(struct trace_buffer *buffer, } EXPORT_SYMBOL_GPL(ring_buffer_write); -static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) +/* + * The total entries in the ring buffer is the running counter + * of entries entered into the ring buffer, minus the sum of + * the entries read from the ring buffer and the number of + * entries that were overwritten. + */ +static inline unsigned long +rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer) { - struct buffer_page *reader = cpu_buffer->reader_page; - struct buffer_page *head = rb_set_head_page(cpu_buffer); - struct buffer_page *commit = cpu_buffer->commit_page; - - /* In case of error, head will be NULL */ - if (unlikely(!head)) - return true; - - /* Reader should exhaust content in reader page */ - if (reader->read != rb_page_size(reader)) - return false; - - /* - * If writers are committing on the reader page, knowing all - * committed content has been read, the ring buffer is empty. - */ - if (commit == reader) - return true; - - /* - * If writers are committing on a page other than reader page - * and head page, there should always be content to read. - */ - if (commit != head) - return false; + return local_read(&cpu_buffer->entries) - + (local_read(&cpu_buffer->overrun) + cpu_buffer->read); +} - /* - * Writers are committing on the head page, we just need - * to care about there're committed data, and the reader will - * swap reader page with head page when it is to read data. - */ - return rb_page_commit(commit) == 0; +static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) +{ + return !rb_num_of_entries(cpu_buffer); } /** @@ -4861,19 +4843,6 @@ void ring_buffer_record_enable_cpu(struct trace_buffer *buffer, int cpu) } EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu); -/* - * The total entries in the ring buffer is the running counter - * of entries entered into the ring buffer, minus the sum of - * the entries read from the ring buffer and the number of - * entries that were overwritten. - */ -static inline unsigned long -rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer) -{ - return local_read(&cpu_buffer->entries) - - (local_read(&cpu_buffer->overrun) + cpu_buffer->read); -} - /** * ring_buffer_oldest_event_ts - get the oldest event timestamp from the buffer * @buffer: The ring buffer -- cgit v1.2.3 From 6e31b759b076eebb4184117234f0c4eb9e4bc460 Mon Sep 17 00:00:00 2001 From: Jeongjun Park Date: Sat, 11 Jan 2025 01:26:12 +0900 Subject: ring-buffer: Make reading page consistent with the code logic In the loop of __rb_map_vma(), the 's' variable is calculated from the same logic that nr_pages is and they both come from nr_subbufs. But the relationship is not obvious and there's a WARN_ON_ONCE() around the 's' variable to make sure it never becomes equal to nr_subbufs within the loop. If that happens, then the code is buggy and needs to be fixed. The 'page' variable is calculated from cpu_buffer->subbuf_ids[s] which is an array of 'nr_subbufs' entries. If the code becomes buggy and 's' becomes equal to or greater than 'nr_subbufs' then this will be an out of bounds hit before the WARN_ON() is triggered and the code exiting safely. Make the 'page' initialization consistent with the code logic and assign it after the out of bounds check. Link: https://lore.kernel.org/20250110162612.13983-1-aha310510@gmail.com Signed-off-by: Jeongjun Park [ sdr: rewrote change log ] Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 479bbbcbf61b..6d61ff78926b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7028,7 +7028,7 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, } while (p < nr_pages) { - struct page *page = virt_to_page((void *)cpu_buffer->subbuf_ids[s]); + struct page *page; int off = 0; if (WARN_ON_ONCE(s >= nr_subbufs)) { @@ -7036,6 +7036,8 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, goto out; } + page = virt_to_page((void *)cpu_buffer->subbuf_ids[s]); + for (; off < (1 << (subbuf_order)); off++, page++) { if (p >= nr_pages) break; -- cgit v1.2.3 From a485ea9e3ef31ac4e3a2245cdb11fa73352b950f Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 13 Jan 2025 18:31:24 -0500 Subject: tracing: Fix irqsoff and wakeup latency tracers when using function graph The function graph tracer has become generic so that kretprobes and BPF can use it along with function graph tracing itself. Some of the infrastructure was specific for function graph tracing such as recording the calltime and return time of the functions. Calling the clock code on a high volume function does add overhead. The calculation of the calltime was removed from the generic code and placed into the function graph tracer itself so that the other users did not incur this overhead as they did not need that timestamp. The calltime field was still kept in the generic return entry structure and the function graph return entry callback filled it as that structure was passed to other code. But this broke both irqsoff and wakeup latency tracer as they still depended on the trace structure containing the calltime when the option display-graph is set as it used some of those same functions that the function graph tracer used. But now the calltime was not set and was just zero. This caused the calculation of the function time to be the absolute value of the return timestamp and not the length of the function. # cd /sys/kernel/tracing # echo 1 > options/display-graph # echo irqsoff > current_tracer The tracers went from: # REL TIME CPU TASK/PID |||| DURATION FUNCTION CALLS # | | | | |||| | | | | | | 0 us | 4) -0 | d..1. | 0.000 us | irqentry_enter(); 3 us | 4) -0 | d..2. | | irq_enter_rcu() { 4 us | 4) -0 | d..2. | 0.431 us | preempt_count_add(); 5 us | 4) -0 | d.h2. | | tick_irq_enter() { 5 us | 4) -0 | d.h2. | 0.433 us | tick_check_oneshot_broadcast_this_cpu(); 6 us | 4) -0 | d.h2. | 2.426 us | ktime_get(); 9 us | 4) -0 | d.h2. | | tick_nohz_stop_idle() { 10 us | 4) -0 | d.h2. | 0.398 us | nr_iowait_cpu(); 11 us | 4) -0 | d.h1. | 1.903 us | } 11 us | 4) -0 | d.h2. | | tick_do_update_jiffies64() { 12 us | 4) -0 | d.h2. | | _raw_spin_lock() { 12 us | 4) -0 | d.h2. | 0.360 us | preempt_count_add(); 13 us | 4) -0 | d.h3. | 0.354 us | do_raw_spin_lock(); 14 us | 4) -0 | d.h2. | 2.207 us | } 15 us | 4) -0 | d.h3. | 0.428 us | calc_global_load(); 16 us | 4) -0 | d.h3. | | _raw_spin_unlock() { 16 us | 4) -0 | d.h3. | 0.380 us | do_raw_spin_unlock(); 17 us | 4) -0 | d.h3. | 0.334 us | preempt_count_sub(); 18 us | 4) -0 | d.h1. | 1.768 us | } 18 us | 4) -0 | d.h2. | | update_wall_time() { [..] To: # REL TIME CPU TASK/PID |||| DURATION FUNCTION CALLS # | | | | |||| | | | | | | 0 us | 5) -0 | d.s2. | 0.000 us | _raw_spin_lock_irqsave(); 0 us | 5) -0 | d.s3. | 312159583 us | preempt_count_add(); 2 us | 5) -0 | d.s4. | 312159585 us | do_raw_spin_lock(); 3 us | 5) -0 | d.s4. | | _raw_spin_unlock() { 3 us | 5) -0 | d.s4. | 312159586 us | do_raw_spin_unlock(); 4 us | 5) -0 | d.s4. | 312159587 us | preempt_count_sub(); 4 us | 5) -0 | d.s2. | 312159587 us | } 5 us | 5) -0 | d.s3. | | _raw_spin_lock() { 5 us | 5) -0 | d.s3. | 312159588 us | preempt_count_add(); 6 us | 5) -0 | d.s4. | 312159589 us | do_raw_spin_lock(); 7 us | 5) -0 | d.s3. | 312159590 us | } 8 us | 5) -0 | d.s4. | 312159591 us | calc_wheel_index(); 9 us | 5) -0 | d.s4. | | enqueue_timer() { 9 us | 5) -0 | d.s4. | | wake_up_nohz_cpu() { 11 us | 5) -0 | d.s4. | | native_smp_send_reschedule() { 11 us | 5) -0 | d.s4. | 312171987 us | default_send_IPI_single_phys(); 12408 us | 5) -0 | d.s3. | 312171990 us | } 12408 us | 5) -0 | d.s3. | 312171991 us | } 12409 us | 5) -0 | d.s3. | 312171991 us | } Where the calculation of the time for each function was the return time minus zero and not the time of when the function returned. Have these tracers also save the calltime in the fgraph data section and retrieve it again on the return to get the correct timings again. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Mark Rutland Link: https://lore.kernel.org/20250113183124.61767419@gandalf.local.home Fixes: f1f36e22bee9 ("ftrace: Have calltime be saved in the fgraph storage") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_irqsoff.c | 14 ++++++++++++++ kernel/trace/trace_sched_wakeup.c | 14 ++++++++++++++ 2 files changed, 28 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index fce064e20570..a4e799c1e767 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -182,6 +182,7 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace, struct trace_array_cpu *data; unsigned long flags; unsigned int trace_ctx; + u64 *calltime; int ret; if (ftrace_graph_ignore_func(gops, trace)) @@ -199,6 +200,12 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace, if (!func_prolog_dec(tr, &data, &flags)) return 0; + calltime = fgraph_reserve_data(gops->idx, sizeof(*calltime)); + if (!calltime) + return 0; + + *calltime = trace_clock_local(); + trace_ctx = tracing_gen_ctx_flags(flags); ret = __trace_graph_entry(tr, trace, trace_ctx); atomic_dec(&data->disabled); @@ -213,12 +220,19 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace, struct trace_array_cpu *data; unsigned long flags; unsigned int trace_ctx; + u64 *calltime; + int size; ftrace_graph_addr_finish(gops, trace); if (!func_prolog_dec(tr, &data, &flags)) return; + calltime = fgraph_retrieve_data(gops->idx, &size); + if (!calltime) + return; + trace->calltime = *calltime; + trace_ctx = tracing_gen_ctx_flags(flags); __trace_graph_return(tr, trace, trace_ctx); atomic_dec(&data->disabled); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index d6c7f18daa15..c58292e424d5 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -118,6 +118,7 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace, struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; unsigned int trace_ctx; + u64 *calltime; int ret = 0; if (ftrace_graph_ignore_func(gops, trace)) @@ -135,6 +136,12 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace, if (!func_prolog_preempt_disable(tr, &data, &trace_ctx)) return 0; + calltime = fgraph_reserve_data(gops->idx, sizeof(*calltime)); + if (!calltime) + return 0; + + *calltime = trace_clock_local(); + ret = __trace_graph_entry(tr, trace, trace_ctx); atomic_dec(&data->disabled); preempt_enable_notrace(); @@ -148,12 +155,19 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace, struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; unsigned int trace_ctx; + u64 *calltime; + int size; ftrace_graph_addr_finish(gops, trace); if (!func_prolog_preempt_disable(tr, &data, &trace_ctx)) return; + calltime = fgraph_retrieve_data(gops->idx, &size); + if (!calltime) + return; + trace->calltime = *calltime; + __trace_graph_return(tr, trace, trace_ctx); atomic_dec(&data->disabled); -- cgit v1.2.3 From 24e0e610400aa2c765ee87b1b3c1401732b20fc5 Mon Sep 17 00:00:00 2001 From: Shrikanth Hegde Date: Fri, 3 Jan 2025 15:06:47 +0530 Subject: tracing: Print lazy preemption model Print lazy preemption model in ftrace header when latency-format=1. # cat /sys/kernel/debug/sched/preempt none voluntary full (lazy) Without patch: latency: 0 us, #232946/232946, CPU#40 | (M:unknown VP:0, KP:0, SP:0 HP:0 #P:80) ^^^^^^^ With Patch: latency: 0 us, #1897938/25566788, CPU#16 | (M:lazy VP:0, KP:0, SP:0 HP:0 #P:80) ^^^^ Now that lazy preemption is part of the kernel, make sure the tracing infrastructure reflects that. Link: https://lore.kernel.org/20250103093647.575919-1-sshegde@linux.ibm.com Signed-off-by: Shrikanth Hegde Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f8aebcb01e62..b6e40e8791fa 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4122,6 +4122,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) preempt_model_none() ? "server" : preempt_model_voluntary() ? "desktop" : preempt_model_full() ? "preempt" : + preempt_model_lazy() ? "lazy" : preempt_model_rt() ? "preempt_rt" : "unknown", /* These are reserved for later use */ -- cgit v1.2.3 From 87c544108b612512b254c8f79aa5c0a8546e2cc4 Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Wed, 15 Jan 2025 10:36:47 +0000 Subject: bpf: Send signals asynchronously if !preemptible BPF programs can execute in all kinds of contexts and when a program running in a non-preemptible context uses the bpf_send_signal() kfunc, it will cause issues because this kfunc can sleep. Change `irqs_disabled()` to `!preemptible()`. Reported-by: syzbot+97da3d7e0112d59971de@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/67486b09.050a0220.253251.0084.GAE@google.com/ Fixes: 1bc7896e9ef4 ("bpf: Fix deadlock with rq_lock in bpf_send_signal()") Signed-off-by: Puranjay Mohan Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20250115103647.38487-1-puranjay@kernel.org Signed-off-by: Alexei Starovoitov --- kernel/trace/bpf_trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index fc657c0eeb3e..71c1c02ca7a3 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -842,7 +842,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type, struct task_struc if (unlikely(is_global_init(task))) return -EPERM; - if (irqs_disabled()) { + if (!preemptible()) { /* Do an early check on signal validity. Otherwise, * the error is lost in deferred irq_work. */ -- cgit v1.2.3 From 4c86bc531e60900053384867c082675bba82c29f Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 16 Jan 2025 09:33:35 -0500 Subject: tracing: Add :mod: command to enabled module events Add a :mod: command to enable only events from a given module from the set_events file. echo '*:mod:' > set_events Or echo ':mod:' > set_events Will enable all events for that module. Specific events can also be enabled via: echo ':mod:' > set_events Or echo '::mod:' > set_events Or echo '*::mod:' > set_events The ":mod:" keyword is consistent with the function tracing filter to enable functions from a given module. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://lore.kernel.org/20250116143533.214496360@goodmis.org Signed-off-by: Steven Rostedt (Google) --- Documentation/trace/events.rst | 22 ++++++++++++++++ kernel/trace/trace.c | 2 ++ kernel/trace/trace_events.c | 59 ++++++++++++++++++++++++++++++++---------- 3 files changed, 70 insertions(+), 13 deletions(-) (limited to 'kernel/trace') diff --git a/Documentation/trace/events.rst b/Documentation/trace/events.rst index 759907c20e75..3db57516eb86 100644 --- a/Documentation/trace/events.rst +++ b/Documentation/trace/events.rst @@ -55,6 +55,28 @@ command:: # echo 'irq:*' > /sys/kernel/tracing/set_event +The set_event file may also be used to enable events associated to only +a specific module:: + + # echo ':mod:' > /sys/kernel/tracing/set_event + +Will enable all events in the module ````. + +The text before ``:mod:`` will be parsed to specify specific events that the +module creates:: + + # echo ':mod:' > /sys/kernel/tracing/set_event + +The above will enable any system or event that ```` matches. If +```` is ``"*"`` then it will match all events. + +To enable only a specific event within a system:: + + # echo '::mod:' > /sys/kernel/tracing/set_event + +If ```` is ``"*"`` then it will match all events within the system +for a given module. + 2.2 Via the 'enable' toggle --------------------------- diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5aeb898054e7..cb85ee4a8807 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5514,6 +5514,8 @@ static const char readme_msg[] = "\t efield: For event probes ('e' types), the field is on of the fields\n" "\t of the /.\n" #endif + " set_event\t\t- Enables events by name written into it\n" + "\t\t\t Can enable module events via: :mod:\n" " events/\t\t- Directory containing all trace event subsystems:\n" " enable\t\t- Write 0/1 to enable/disable tracing of all events\n" " events//\t- Directory containing all trace events for :\n" diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 2b9222e7bd5a..5c7d0e07618d 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1153,17 +1153,36 @@ static void remove_event_file_dir(struct trace_event_file *file) */ static int __ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match, - const char *sub, const char *event, int set) + const char *sub, const char *event, int set, + const char *mod) { struct trace_event_file *file; struct trace_event_call *call; + char *module __free(kfree) = NULL; const char *name; int ret = -EINVAL; int eret = 0; + if (mod) { + char *p; + + module = kstrdup(mod, GFP_KERNEL); + if (!module) + return -ENOMEM; + + /* Replace all '-' with '_' as that's what modules do */ + for (p = strchr(module, '-'); p; p = strchr(p + 1, '-')) + *p = '_'; + } + list_for_each_entry(file, &tr->events, list) { call = file->event_call; + + /* If a module is specified, skip events that are not that module */ + if (module && (!call->module || strcmp(module_name(call->module), module))) + continue; + name = trace_event_name(call); if (!name || !call->class || !call->class->reg) @@ -1200,12 +1219,13 @@ __ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match, } static int __ftrace_set_clr_event(struct trace_array *tr, const char *match, - const char *sub, const char *event, int set) + const char *sub, const char *event, int set, + const char *mod) { int ret; mutex_lock(&event_mutex); - ret = __ftrace_set_clr_event_nolock(tr, match, sub, event, set); + ret = __ftrace_set_clr_event_nolock(tr, match, sub, event, set, mod); mutex_unlock(&event_mutex); return ret; @@ -1213,11 +1233,20 @@ static int __ftrace_set_clr_event(struct trace_array *tr, const char *match, int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) { - char *event = NULL, *sub = NULL, *match; + char *event = NULL, *sub = NULL, *match, *mod; int ret; if (!tr) return -ENOENT; + + /* Modules events can be appened with :mod: */ + mod = strstr(buf, ":mod:"); + if (mod) { + *mod = '\0'; + /* move to the module name */ + mod += 5; + } + /* * The buf format can be : * *: means any event by that name. @@ -1240,9 +1269,13 @@ int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) sub = NULL; if (!strlen(event) || strcmp(event, "*") == 0) event = NULL; + } else if (mod) { + /* Allow wildcard for no length or star */ + if (!strlen(match) || strcmp(match, "*") == 0) + match = NULL; } - ret = __ftrace_set_clr_event(tr, match, sub, event, set); + ret = __ftrace_set_clr_event(tr, match, sub, event, set, mod); /* Put back the colon to allow this to be called again */ if (buf) @@ -1270,7 +1303,7 @@ int trace_set_clr_event(const char *system, const char *event, int set) if (!tr) return -ENODEV; - return __ftrace_set_clr_event(tr, NULL, system, event, set); + return __ftrace_set_clr_event(tr, NULL, system, event, set, NULL); } EXPORT_SYMBOL_GPL(trace_set_clr_event); @@ -1296,7 +1329,7 @@ int trace_array_set_clr_event(struct trace_array *tr, const char *system, return -ENOENT; set = (enable == true) ? 1 : 0; - return __ftrace_set_clr_event(tr, NULL, system, event, set); + return __ftrace_set_clr_event(tr, NULL, system, event, set, NULL); } EXPORT_SYMBOL_GPL(trace_array_set_clr_event); @@ -1646,7 +1679,7 @@ system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, if (system) name = system->name; - ret = __ftrace_set_clr_event(dir->tr, NULL, name, NULL, val); + ret = __ftrace_set_clr_event(dir->tr, NULL, name, NULL, val, NULL); if (ret) goto out; @@ -4094,7 +4127,7 @@ int event_trace_del_tracer(struct trace_array *tr) __ftrace_clear_event_pids(tr, TRACE_PIDS | TRACE_NO_PIDS); /* Disable any running events */ - __ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0); + __ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0, NULL); /* Make sure no more events are being executed */ tracepoint_synchronize_unregister(); @@ -4378,7 +4411,7 @@ static __init void event_trace_self_tests(void) pr_info("Testing event system %s: ", system->name); - ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 1); + ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 1, NULL); if (WARN_ON_ONCE(ret)) { pr_warn("error enabling system %s\n", system->name); @@ -4387,7 +4420,7 @@ static __init void event_trace_self_tests(void) event_test_stuff(); - ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 0); + ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 0, NULL); if (WARN_ON_ONCE(ret)) { pr_warn("error disabling system %s\n", system->name); @@ -4402,7 +4435,7 @@ static __init void event_trace_self_tests(void) pr_info("Running tests on all trace events:\n"); pr_info("Testing all events: "); - ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 1); + ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 1, NULL); if (WARN_ON_ONCE(ret)) { pr_warn("error enabling all events\n"); return; @@ -4411,7 +4444,7 @@ static __init void event_trace_self_tests(void) event_test_stuff(); /* reset sysname */ - ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0); + ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0, NULL); if (WARN_ON_ONCE(ret)) { pr_warn("error disabling all events\n"); return; -- cgit v1.2.3 From b355247df104ef6644288884afd2c08b7bf49897 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 16 Jan 2025 09:33:36 -0500 Subject: tracing: Cache ":mod:" events for modules not loaded yet When the :mod: command is written into /sys/kernel/tracing/set_event (or that file within an instance), if the module specified after the ":mod:" is not yet loaded, it will store that string internally. When the module is loaded, it will enable the events as if the module was loaded when the string was written into the set_event file. This can also be useful to enable events that are in the init section of the module, as the events are enabled before the init section is executed. This also works on the kernel command line: trace_event=:mod: Will enable the events for when it is loaded. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://lore.kernel.org/20250116143533.514730995@goodmis.org Signed-off-by: Steven Rostedt (Google) --- Documentation/admin-guide/kernel-parameters.txt | 8 + Documentation/trace/events.rst | 4 +- kernel/trace/ftrace.c | 17 -- kernel/trace/trace.c | 26 +++ kernel/trace/trace.h | 12 ++ kernel/trace/trace_events.c | 241 ++++++++++++++++++++++-- 6 files changed, 279 insertions(+), 29 deletions(-) (limited to 'kernel/trace') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 3872bc6ec49d..4f563cb0ca0f 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6858,6 +6858,14 @@ comma-separated list of trace events to enable. See also Documentation/trace/events.rst + To enable modules, use :mod: keyword: + + trace_event=:mod: + + The value before :mod: will only enable specific events + that are part of the module. See the above mentioned + document for more information. + trace_instance=[instance-info] [FTRACE] Create a ring buffer instance early in boot up. This will be listed in: diff --git a/Documentation/trace/events.rst b/Documentation/trace/events.rst index 3db57516eb86..2d88a2acacc0 100644 --- a/Documentation/trace/events.rst +++ b/Documentation/trace/events.rst @@ -60,7 +60,9 @@ a specific module:: # echo ':mod:' > /sys/kernel/tracing/set_event -Will enable all events in the module ````. +Will enable all events in the module ````. If the module is not yet +loaded, the string will be saved and when a module is that matches ```` +is loaded, then it will apply the enabling of events then. The text before ``:mod:`` will be parsed to specify specific events that the module creates:: diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 9b17efb1a87d..cafcfc97ff2a 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4930,23 +4930,6 @@ static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops, return __ftrace_hash_move_and_update_ops(ops, orig_hash, hash, enable); } -static bool module_exists(const char *module) -{ - /* All modules have the symbol __this_module */ - static const char this_mod[] = "__this_module"; - char modname[MAX_PARAM_PREFIX_LEN + sizeof(this_mod) + 2]; - unsigned long val; - int n; - - n = snprintf(modname, sizeof(modname), "%s:%s", module, this_mod); - - if (n > sizeof(modname) - 1) - return false; - - val = module_kallsyms_lookup_name(modname); - return val != 0; -} - static int cache_mod(struct trace_array *tr, const char *func, char *module, int enable) { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index cb85ee4a8807..87402b6e8c58 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9407,6 +9407,10 @@ trace_array_create_systems(const char *name, const char *systems, INIT_LIST_HEAD(&tr->hist_vars); INIT_LIST_HEAD(&tr->err_log); +#ifdef CONFIG_MODULES + INIT_LIST_HEAD(&tr->mod_events); +#endif + if (allocate_trace_buffers(tr, trace_buf_size) < 0) goto out_free_tr; @@ -9823,6 +9827,24 @@ late_initcall_sync(trace_eval_sync); #ifdef CONFIG_MODULES + +bool module_exists(const char *module) +{ + /* All modules have the symbol __this_module */ + static const char this_mod[] = "__this_module"; + char modname[MAX_PARAM_PREFIX_LEN + sizeof(this_mod) + 2]; + unsigned long val; + int n; + + n = snprintf(modname, sizeof(modname), "%s:%s", module, this_mod); + + if (n > sizeof(modname) - 1) + return false; + + val = module_kallsyms_lookup_name(modname); + return val != 0; +} + static void trace_module_add_evals(struct module *mod) { if (!mod->num_trace_evals) @@ -10535,6 +10557,10 @@ __init static int tracer_alloc_buffers(void) #endif ftrace_init_global_array_ops(&global_trace); +#ifdef CONFIG_MODULES + INIT_LIST_HEAD(&global_trace.mod_events); +#endif + init_trace_flags_index(&global_trace); register_tracer(&nop_trace); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 9691b47b5f3d..05ea0ebf5eba 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -400,6 +400,9 @@ struct trace_array { cpumask_var_t pipe_cpumask; int ref; int trace_ref; +#ifdef CONFIG_MODULES + struct list_head mod_events; +#endif #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops *ops; struct trace_pid_list __rcu *function_pids; @@ -434,6 +437,15 @@ enum { TRACE_ARRAY_FL_BOOT = BIT(1), }; +#ifdef CONFIG_MODULES +bool module_exists(const char *module); +#else +static inline bool module_exists(const char *module) +{ + return false; +} +#endif + extern struct list_head ftrace_trace_arrays; extern struct mutex trace_types_lock; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 5c7d0e07618d..f762e554fad4 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -857,6 +857,120 @@ static int ftrace_event_enable_disable(struct trace_event_file *file, return __ftrace_event_enable_disable(file, enable, 0); } +#if CONFIG_MODULES +struct event_mod_load { + struct list_head list; + char *module; + char *match; + char *system; + char *event; +}; + +static void free_event_mod(struct event_mod_load *event_mod) +{ + list_del(&event_mod->list); + kfree(event_mod->module); + kfree(event_mod->match); + kfree(event_mod->system); + kfree(event_mod->event); + kfree(event_mod); +} + +static void clear_mod_events(struct trace_array *tr) +{ + struct event_mod_load *event_mod, *n; + + list_for_each_entry_safe(event_mod, n, &tr->mod_events, list) { + free_event_mod(event_mod); + } +} + +static int remove_cache_mod(struct trace_array *tr, const char *mod, + const char *match, const char *system, const char *event) +{ + struct event_mod_load *event_mod, *n; + int ret = -EINVAL; + + list_for_each_entry_safe(event_mod, n, &tr->mod_events, list) { + if (strcmp(event_mod->module, mod) != 0) + continue; + + if (match && strcmp(event_mod->match, match) != 0) + continue; + + if (system && + (!event_mod->system || strcmp(event_mod->system, system) != 0)) + continue; + + if (event && + (!event_mod->event || strcmp(event_mod->event, event) != 0)) + continue; + + free_event_mod(event_mod); + ret = 0; + } + + return ret; +} + +static int cache_mod(struct trace_array *tr, const char *mod, int set, + const char *match, const char *system, const char *event) +{ + struct event_mod_load *event_mod; + + /* If the module exists, then this just failed to find an event */ + if (module_exists(mod)) + return -EINVAL; + + /* See if this is to remove a cached filter */ + if (!set) + return remove_cache_mod(tr, mod, match, system, event); + + event_mod = kzalloc(sizeof(*event_mod), GFP_KERNEL); + if (!event_mod) + return -ENOMEM; + + INIT_LIST_HEAD(&event_mod->list); + event_mod->module = kstrdup(mod, GFP_KERNEL); + if (!event_mod->module) + goto out_free; + + if (match) { + event_mod->match = kstrdup(match, GFP_KERNEL); + if (!event_mod->match) + goto out_free; + } + + if (system) { + event_mod->system = kstrdup(system, GFP_KERNEL); + if (!event_mod->system) + goto out_free; + } + + if (event) { + event_mod->event = kstrdup(event, GFP_KERNEL); + if (!event_mod->event) + goto out_free; + } + + list_add(&event_mod->list, &tr->mod_events); + + return 0; + + out_free: + free_event_mod(event_mod); + + return -ENOMEM; +} +#else /* CONFIG_MODULES */ +static inline void clear_mod_events(struct trace_array *tr) { } +static int cache_mod(struct trace_array *tr, const char *mod, int set, + const char *match, const char *system, const char *event) +{ + return -EINVAL; +} +#endif + static void ftrace_clear_events(struct trace_array *tr) { struct trace_event_file *file; @@ -865,6 +979,7 @@ static void ftrace_clear_events(struct trace_array *tr) list_for_each_entry(file, &tr->events, list) { ftrace_event_enable_disable(file, 0); } + clear_mod_events(tr); mutex_unlock(&event_mutex); } @@ -1215,6 +1330,13 @@ __ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match, ret = eret; } + /* + * If this is a module setting and nothing was found, + * check if the module was loaded. If it wasn't cache it. + */ + if (module && ret == -EINVAL && !eret) + ret = cache_mod(tr, module, set, match, sub, event); + return ret; } @@ -1416,37 +1538,71 @@ static void *t_start(struct seq_file *m, loff_t *pos) return file; } +enum set_event_iter_type { + SET_EVENT_FILE, + SET_EVENT_MOD, +}; + +struct set_event_iter { + enum set_event_iter_type type; + union { + struct trace_event_file *file; + struct event_mod_load *event_mod; + }; +}; + static void * s_next(struct seq_file *m, void *v, loff_t *pos) { - struct trace_event_file *file = v; + struct set_event_iter *iter = v; + struct trace_event_file *file; struct trace_array *tr = m->private; (*pos)++; - list_for_each_entry_continue(file, &tr->events, list) { - if (file->flags & EVENT_FILE_FL_ENABLED) - return file; + if (iter->type == SET_EVENT_FILE) { + file = iter->file; + list_for_each_entry_continue(file, &tr->events, list) { + if (file->flags & EVENT_FILE_FL_ENABLED) { + iter->file = file; + return iter; + } + } +#ifdef CONFIG_MODULES + iter->type = SET_EVENT_MOD; + iter->event_mod = list_entry(&tr->mod_events, struct event_mod_load, list); +#endif } +#ifdef CONFIG_MODULES + list_for_each_entry_continue(iter->event_mod, &tr->mod_events, list) + return iter; +#endif + return NULL; } static void *s_start(struct seq_file *m, loff_t *pos) { - struct trace_event_file *file; struct trace_array *tr = m->private; + struct set_event_iter *iter; loff_t l; + iter = kzalloc(sizeof(iter), GFP_KERNEL); + if (!iter) + return NULL; + mutex_lock(&event_mutex); - file = list_entry(&tr->events, struct trace_event_file, list); + iter->type = SET_EVENT_FILE; + iter->file = list_entry(&tr->events, struct trace_event_file, list); + for (l = 0; l <= *pos; ) { - file = s_next(m, file, &l); - if (!file) + iter = s_next(m, iter, &l); + if (!iter) break; } - return file; + return iter; } static int t_show(struct seq_file *m, void *v) @@ -1466,6 +1622,45 @@ static void t_stop(struct seq_file *m, void *p) mutex_unlock(&event_mutex); } +#ifdef CONFIG_MODULES +static int s_show(struct seq_file *m, void *v) +{ + struct set_event_iter *iter = v; + const char *system; + const char *event; + + if (iter->type == SET_EVENT_FILE) + return t_show(m, iter->file); + + /* When match is set, system and event are not */ + if (iter->event_mod->match) { + seq_printf(m, "%s:mod:%s", iter->event_mod->match, + iter->event_mod->module); + return 0; + } + + system = iter->event_mod->system ? : "*"; + event = iter->event_mod->event ? : "*"; + + seq_printf(m, "%s:%s:mod:%s\n", system, event, iter->event_mod->module); + + return 0; +} +#else /* CONFIG_MODULES */ +static int s_show(struct seq_file *m, void *v) +{ + struct set_event_iter *iter = v; + + return t_show(m, iter->file); +} +#endif + +static void s_stop(struct seq_file *m, void *p) +{ + kfree(p); + t_stop(m, NULL); +} + static void * __next(struct seq_file *m, void *v, loff_t *pos, int type) { @@ -2253,8 +2448,8 @@ static const struct seq_operations show_event_seq_ops = { static const struct seq_operations show_set_event_seq_ops = { .start = s_start, .next = s_next, - .show = t_show, - .stop = t_stop, + .show = s_show, + .stop = s_stop, }; static const struct seq_operations show_set_pid_seq_ops = { @@ -3385,6 +3580,28 @@ EXPORT_SYMBOL_GPL(trace_remove_event_call); event++) #ifdef CONFIG_MODULES +static void update_cache(struct trace_array *tr, struct module *mod) +{ + struct event_mod_load *event_mod, *n; + + list_for_each_entry_safe(event_mod, n, &tr->mod_events, list) { + if (strcmp(event_mod->module, mod->name) != 0) + continue; + + __ftrace_set_clr_event_nolock(tr, event_mod->match, + event_mod->system, + event_mod->event, 1, mod->name); + free_event_mod(event_mod); + } +} + +static void update_cache_events(struct module *mod) +{ + struct trace_array *tr; + + list_for_each_entry(tr, &ftrace_trace_arrays, list) + update_cache(tr, mod); +} static void trace_module_add_events(struct module *mod) { @@ -3407,6 +3624,8 @@ static void trace_module_add_events(struct module *mod) __register_event(*call, mod); __add_event_to_tracers(*call); } + + update_cache_events(mod); } static void trace_module_remove_events(struct module *mod) -- cgit v1.2.3 From 8275637215bd3d447b31d37f9b8231a013adb042 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 17 Jan 2025 11:20:34 +0900 Subject: tracing: Adopt __free() and guard() for trace_fprobe.c Adopt __free() and guard() for trace_fprobe.c to remove gotos. Link: https://lore.kernel.org/173708043449.319651.12242878905778792182.stgit@mhiramat.roam.corp.google.com Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_fprobe.c | 124 +++++++++++++++++++++----------------------- 1 file changed, 58 insertions(+), 66 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index f487fadc2c08..b8f3c4ba309b 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -416,6 +416,9 @@ static void free_trace_fprobe(struct trace_fprobe *tf) } } +/* Since alloc_trace_fprobe() can return error, check the pointer is ERR too. */ +DEFINE_FREE(free_trace_fprobe, struct trace_fprobe *, if (!IS_ERR_OR_NULL(_T)) free_trace_fprobe(_T)) + /* * Allocate new trace_probe and initialize it (including fprobe). */ @@ -426,7 +429,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, struct module *mod, int nargs, bool is_return) { - struct trace_fprobe *tf; + struct trace_fprobe *tf __free(free_trace_fprobe) = NULL; int ret = -ENOMEM; tf = kzalloc(struct_size(tf, tp.args, nargs), GFP_KERNEL); @@ -435,7 +438,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, tf->symbol = kstrdup(symbol, GFP_KERNEL); if (!tf->symbol) - goto error; + return ERR_PTR(-ENOMEM); if (is_return) tf->fp.exit_handler = fexit_dispatcher; @@ -447,13 +450,10 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, ret = trace_probe_init(&tf->tp, event, group, false, nargs); if (ret < 0) - goto error; + return ERR_PTR(ret); dyn_event_init(&tf->devent, &trace_fprobe_ops); - return tf; -error: - free_trace_fprobe(tf); - return ERR_PTR(ret); + return_ptr(tf); } static struct trace_fprobe *find_trace_fprobe(const char *event, @@ -880,14 +880,12 @@ static int register_trace_fprobe(struct trace_fprobe *tf) struct trace_fprobe *old_tf; int ret; - mutex_lock(&event_mutex); + guard(mutex)(&event_mutex); old_tf = find_trace_fprobe(trace_probe_name(&tf->tp), trace_probe_group_name(&tf->tp)); - if (old_tf) { - ret = append_trace_fprobe(tf, old_tf); - goto end; - } + if (old_tf) + return append_trace_fprobe(tf, old_tf); /* Register new event */ ret = register_fprobe_event(tf); @@ -897,7 +895,7 @@ static int register_trace_fprobe(struct trace_fprobe *tf) trace_probe_log_err(0, EVENT_EXIST); } else pr_warn("Failed to register probe event(%d)\n", ret); - goto end; + return ret; } /* Register fprobe */ @@ -907,8 +905,6 @@ static int register_trace_fprobe(struct trace_fprobe *tf) else dyn_event_add(&tf->devent, trace_probe_event_call(&tf->tp)); -end: - mutex_unlock(&event_mutex); return ret; } @@ -1069,7 +1065,10 @@ static int parse_symbol_and_return(int argc, const char *argv[], return 0; } -static int __trace_fprobe_create(int argc, const char *argv[]) +DEFINE_FREE(module_put, struct module *, if (_T) module_put(_T)) + +static int trace_fprobe_create_internal(int argc, const char *argv[], + struct traceprobe_parse_context *ctx) { /* * Argument syntax: @@ -1095,23 +1094,20 @@ static int __trace_fprobe_create(int argc, const char *argv[]) * Type of args: * FETCHARG:TYPE : use TYPE instead of unsigned long. */ - struct trace_fprobe *tf = NULL; + struct trace_fprobe *tf __free(free_trace_fprobe) = NULL; int i, new_argc = 0, ret = 0; bool is_return = false; - char *symbol = NULL; + char *symbol __free(kfree) = NULL; const char *event = NULL, *group = FPROBE_EVENT_SYSTEM; - const char **new_argv = NULL; + const char **new_argv __free(kfree) = NULL; char buf[MAX_EVENT_NAME_LEN]; char gbuf[MAX_EVENT_NAME_LEN]; char sbuf[KSYM_NAME_LEN]; char abuf[MAX_BTF_ARGS_LEN]; - char *dbuf = NULL; + char *dbuf __free(kfree) = NULL; bool is_tracepoint = false; - struct module *tp_mod = NULL; + struct module *tp_mod __free(module_put) = NULL; struct tracepoint *tpoint = NULL; - struct traceprobe_parse_context ctx = { - .flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE, - }; if ((argv[0][0] != 'f' && argv[0][0] != 't') || argc < 2) return -ECANCELED; @@ -1121,13 +1117,11 @@ static int __trace_fprobe_create(int argc, const char *argv[]) group = TRACEPOINT_EVENT_SYSTEM; } - trace_probe_log_init("trace_fprobe", argc, argv); - if (argv[0][1] != '\0') { if (argv[0][1] != ':') { trace_probe_log_set_index(0); trace_probe_log_err(1, BAD_MAXACT); - goto parse_error; + return -EINVAL; } event = &argv[0][2]; } @@ -1137,14 +1131,14 @@ static int __trace_fprobe_create(int argc, const char *argv[]) /* a symbol(or tracepoint) must be specified */ ret = parse_symbol_and_return(argc, argv, &symbol, &is_return, is_tracepoint); if (ret < 0) - goto parse_error; + return -EINVAL; trace_probe_log_set_index(0); if (event) { ret = traceprobe_parse_event_name(&event, &group, gbuf, event - argv[0]); if (ret) - goto parse_error; + return -EINVAL; } if (!event) { @@ -1160,49 +1154,44 @@ static int __trace_fprobe_create(int argc, const char *argv[]) } if (is_return) - ctx.flags |= TPARG_FL_RETURN; + ctx->flags |= TPARG_FL_RETURN; else - ctx.flags |= TPARG_FL_FENTRY; + ctx->flags |= TPARG_FL_FENTRY; if (is_tracepoint) { - ctx.flags |= TPARG_FL_TPOINT; + ctx->flags |= TPARG_FL_TPOINT; tpoint = find_tracepoint(symbol, &tp_mod); if (tpoint) { - ctx.funcname = kallsyms_lookup( + ctx->funcname = kallsyms_lookup( (unsigned long)tpoint->probestub, NULL, NULL, NULL, sbuf); } else if (IS_ENABLED(CONFIG_MODULES)) { /* This *may* be loaded afterwards */ tpoint = TRACEPOINT_STUB; - ctx.funcname = symbol; + ctx->funcname = symbol; } else { trace_probe_log_set_index(1); trace_probe_log_err(0, NO_TRACEPOINT); - goto parse_error; + return -EINVAL; } } else - ctx.funcname = symbol; + ctx->funcname = symbol; argc -= 2; argv += 2; new_argv = traceprobe_expand_meta_args(argc, argv, &new_argc, - abuf, MAX_BTF_ARGS_LEN, &ctx); - if (IS_ERR(new_argv)) { - ret = PTR_ERR(new_argv); - new_argv = NULL; - goto out; - } + abuf, MAX_BTF_ARGS_LEN, ctx); + if (IS_ERR(new_argv)) + return PTR_ERR(new_argv); if (new_argv) { argc = new_argc; argv = new_argv; } - if (argc > MAX_TRACE_ARGS) { - ret = -E2BIG; - goto out; - } + if (argc > MAX_TRACE_ARGS) + return -E2BIG; ret = traceprobe_expand_dentry_args(argc, argv, &dbuf); if (ret) - goto out; + return ret; /* setup a probe */ tf = alloc_trace_fprobe(group, event, symbol, tpoint, tp_mod, @@ -1211,16 +1200,16 @@ static int __trace_fprobe_create(int argc, const char *argv[]) ret = PTR_ERR(tf); /* This must return -ENOMEM, else there is a bug */ WARN_ON_ONCE(ret != -ENOMEM); - goto out; /* We know tf is not allocated */ + return ret; } /* parse arguments */ for (i = 0; i < argc; i++) { trace_probe_log_set_index(i + 2); - ctx.offset = 0; - ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], &ctx); + ctx->offset = 0; + ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], ctx); if (ret) - goto error; /* This can be -ENOMEM */ + return ret; /* This can be -ENOMEM */ } if (is_return && tf->tp.entry_arg) { @@ -1231,7 +1220,7 @@ static int __trace_fprobe_create(int argc, const char *argv[]) ret = traceprobe_set_print_fmt(&tf->tp, is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL); if (ret < 0) - goto error; + return ret; ret = register_trace_fprobe(tf); if (ret) { @@ -1242,29 +1231,32 @@ static int __trace_fprobe_create(int argc, const char *argv[]) trace_probe_log_err(0, BAD_PROBE_ADDR); else if (ret != -ENOMEM && ret != -EEXIST) trace_probe_log_err(0, FAIL_REG_PROBE); - goto error; + return -EINVAL; } -out: - if (tp_mod) - module_put(tp_mod); + /* 'tf' is successfully registered. To avoid freeing, assign NULL. */ + tf = NULL; + + return 0; +} + +static int trace_fprobe_create_cb(int argc, const char *argv[]) +{ + struct traceprobe_parse_context ctx = { + .flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE, + }; + int ret; + + trace_probe_log_init("trace_fprobe", argc, argv); + ret = trace_fprobe_create_internal(argc, argv, &ctx); traceprobe_finish_parse(&ctx); trace_probe_log_clear(); - kfree(new_argv); - kfree(symbol); - kfree(dbuf); return ret; - -parse_error: - ret = -EINVAL; -error: - free_trace_fprobe(tf); - goto out; } static int trace_fprobe_create(const char *raw_command) { - return trace_probe_create(raw_command, __trace_fprobe_create); + return trace_probe_create(raw_command, trace_fprobe_create_cb); } static int trace_fprobe_release(struct dyn_event *ev) -- cgit v1.2.3 From 31f505dc70331243fbb54af868c14bb5f44a15bc Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 16 Jan 2025 17:58:32 -0500 Subject: ftrace: Implement :mod: cache filtering on kernel command line Module functions can be set to set_ftrace_filter before the module is loaded. # echo :mod:snd_hda_intel > set_ftrace_filter This will enable all the functions for the module snd_hda_intel. If that module is not loaded, it is "cached" in the trace array for when the module is loaded, its functions will be traced. But this is not implemented in the kernel command line. That's because the kernel command line filtering is added very early in boot up as it is needed to be done before boot time function tracing can start, which is also available very early in boot up. The code used by the "set_ftrace_filter" file can not be used that early as it depends on some other initialization to occur first. But some of the functions can. Implement the ":mod:" feature of "set_ftrace_filter" in the kernel command line parsing. Now function tracing on just a single module that is loaded at boot up can be done. Adding: ftrace=function ftrace_filter=:mod:sna_hda_intel To the kernel command line will only enable the sna_hda_intel module functions when the module is loaded, and it will start tracing. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20250116175832.34e39779@gandalf.local.home Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 67 ++++++++++++++++++++++++++++++++++++++++++++------- kernel/trace/trace.c | 8 ++++++ kernel/trace/trace.h | 2 ++ 3 files changed, 68 insertions(+), 9 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f054343be026..9387e2865ca8 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4968,10 +4968,6 @@ static int cache_mod(struct trace_array *tr, return ftrace_add_mod(tr, func, module, enable); } -static int -ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, - int reset, int enable); - #ifdef CONFIG_MODULES static void process_mod_list(struct list_head *head, struct ftrace_ops *ops, char *mod, bool enable) @@ -5761,7 +5757,7 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long *ips, static int ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, unsigned long *ips, unsigned int cnt, - int remove, int reset, int enable) + int remove, int reset, int enable, char *mod) { struct ftrace_hash **orig_hash; struct ftrace_hash *hash; @@ -5787,7 +5783,15 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, goto out_regex_unlock; } - if (buf && !ftrace_match_records(hash, buf, len)) { + if (buf && !match_records(hash, buf, len, mod)) { + /* If this was for a module and nothing was enabled, flag it */ + if (mod) + (*orig_hash)->flags |= FTRACE_HASH_FL_MOD; + + /* + * Even if it is a mod, return error to let caller know + * nothing was added + */ ret = -EINVAL; goto out_regex_unlock; } @@ -5812,7 +5816,7 @@ static int ftrace_set_addr(struct ftrace_ops *ops, unsigned long *ips, unsigned int cnt, int remove, int reset, int enable) { - return ftrace_set_hash(ops, NULL, 0, ips, cnt, remove, reset, enable); + return ftrace_set_hash(ops, NULL, 0, ips, cnt, remove, reset, enable, NULL); } #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS @@ -6190,7 +6194,38 @@ static int ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, int reset, int enable) { - return ftrace_set_hash(ops, buf, len, NULL, 0, 0, reset, enable); + char *mod = NULL, *func, *command, *next = buf; + char *tmp __free(kfree) = NULL; + struct trace_array *tr = ops->private; + int ret; + + func = strsep(&next, ":"); + + /* This can also handle :mod: parsing */ + if (next) { + if (!tr) + return -EINVAL; + + command = strsep(&next, ":"); + if (strcmp(command, "mod") != 0) + return -EINVAL; + + mod = next; + len = command - func; + /* Save the original func as ftrace_set_hash() can modify it */ + tmp = kstrdup(func, GFP_KERNEL); + } + + ret = ftrace_set_hash(ops, func, len, NULL, 0, 0, reset, enable, mod); + + if (tr && mod && ret < 0) { + /* Did tmp fail to allocate? */ + if (!tmp) + return -ENOMEM; + ret = cache_mod(tr, tmp, mod, enable); + } + + return ret; } /** @@ -6354,6 +6389,14 @@ ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable) ftrace_ops_init(ops); + /* The trace_array is needed for caching module function filters */ + if (!ops->private) { + struct trace_array *tr = trace_get_global_array(); + + ops->private = tr; + ftrace_init_trace_array(tr); + } + while (buf) { func = strsep(&buf, ","); ftrace_set_regex(ops, func, strlen(func), 0, enable); @@ -7787,9 +7830,14 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops) void ftrace_init_trace_array(struct trace_array *tr) { + if (tr->flags & TRACE_ARRAY_FL_MOD_INIT) + return; + INIT_LIST_HEAD(&tr->func_probes); INIT_LIST_HEAD(&tr->mod_trace); INIT_LIST_HEAD(&tr->mod_notrace); + + tr->flags |= TRACE_ARRAY_FL_MOD_INIT; } #else @@ -7818,7 +7866,8 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops) __init void ftrace_init_global_array_ops(struct trace_array *tr) { tr->ops = &global_ops; - tr->ops->private = tr; + if (!global_ops.private) + global_ops.private = tr; ftrace_init_trace_array(tr); init_array_fgraph_ops(tr, tr->ops); } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 957f941a08e7..a553f1e7a057 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -10657,6 +10657,14 @@ out: return ret; } +#ifdef CONFIG_FUNCTION_TRACER +/* Used to set module cached ftrace filtering at boot up */ +__init struct trace_array *trace_get_global_array(void) +{ + return &global_trace; +} +#endif + void __init ftrace_boot_snapshot(void) { #ifdef CONFIG_TRACER_MAX_TRACE diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 5f3e68a8d8a0..ba68a5a54092 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -432,6 +432,7 @@ struct trace_array { enum { TRACE_ARRAY_FL_GLOBAL = BIT(0), TRACE_ARRAY_FL_BOOT = BIT(1), + TRACE_ARRAY_FL_MOD_INIT = BIT(2), }; extern struct list_head ftrace_trace_arrays; @@ -1116,6 +1117,7 @@ void ftrace_destroy_function_files(struct trace_array *tr); int ftrace_allocate_ftrace_ops(struct trace_array *tr); void ftrace_free_ftrace_ops(struct trace_array *tr); void ftrace_init_global_array_ops(struct trace_array *tr); +struct trace_array *trace_get_global_array(void); void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func); void ftrace_reset_array_ops(struct trace_array *tr); void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer); -- cgit v1.2.3 From a925df6f5036013b6592eef28f7ec4a45bf465a9 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 20 Jan 2025 12:57:45 -0500 Subject: tracing: Fix #if CONFIG_MODULES to #ifdef CONFIG_MODULES A typo was introduced when adding the ":mod:" command that did a "#if CONFIG_MODULES" instead of a "#ifdef CONFIG_MODULES". Fix it. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Linus Torvalds Link: https://lore.kernel.org/20250120125745.4ac90ca6@gandalf.local.home Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202501190121.E2CIJuUj-lkp@intel.com/ Fixes: b355247df104e ("tracing: Cache ":mod:" events for modules not loaded yet") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f762e554fad4..bb1406719c3f 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -857,7 +857,7 @@ static int ftrace_event_enable_disable(struct trace_event_file *file, return __ftrace_event_enable_disable(file, enable, 0); } -#if CONFIG_MODULES +#ifdef CONFIG_MODULES struct event_mod_load { struct list_head list; char *module; -- cgit v1.2.3 From 22412b72cafd1b2570c2f9f14b7a133bdff8b80c Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 20 Jan 2025 17:27:56 -0500 Subject: tracing: Rename update_cache() to update_mod_cache() The static function in trace_events.c called update_cache() is too generic and conflicts with the function defined in arch/openrisc/include/asm/pgtable.h Rename it to update_mod_cache() to make it less generic. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20250120172756.4ecfb43f@batman.local.home Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202501210550.Ufrj5CRn-lkp@intel.com/ Fixes: b355247df104e ("tracing: Cache ":mod:" events for modules not loaded yet") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index bb1406719c3f..51c5014877e8 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -3580,7 +3580,7 @@ EXPORT_SYMBOL_GPL(trace_remove_event_call); event++) #ifdef CONFIG_MODULES -static void update_cache(struct trace_array *tr, struct module *mod) +static void update_mod_cache(struct trace_array *tr, struct module *mod) { struct event_mod_load *event_mod, *n; @@ -3600,7 +3600,7 @@ static void update_cache_events(struct module *mod) struct trace_array *tr; list_for_each_entry(tr, &ftrace_trace_arrays, list) - update_cache(tr, mod); + update_mod_cache(tr, mod); } static void trace_module_add_events(struct module *mod) -- cgit v1.2.3 From cd2375a3567fd3d93aa6c68e0027a5756213bda0 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 20 Jan 2025 18:56:56 -0500 Subject: ring-buffer: Do not allow events in NMI with generic atomic64 cmpxchg() Some architectures can not safely do atomic64 operations in NMI context. Since the ring buffer relies on atomic64 operations to do its time keeping, if an event is requested in NMI context, reject it for these architectures. Cc: stable@vger.kernel.org Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Linus Torvalds Cc: Andreas Larsson Link: https://lore.kernel.org/20250120235721.407068250@goodmis.org Fixes: c84897c0ff592 ("ring-buffer: Remove 32bit timestamp logic") Closes: https://lore.kernel.org/all/86fb4f86-a0e4-45a2-a2df-3154acc4f086@gaisler.com/ Reported-by: Ludwig Rydberg Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 6d61ff78926b..b8e0ae15ca5b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4398,8 +4398,13 @@ rb_reserve_next_event(struct trace_buffer *buffer, int nr_loops = 0; int add_ts_default; - /* ring buffer does cmpxchg, make sure it is safe in NMI context */ - if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) && + /* + * ring buffer does cmpxchg as well as atomic64 operations + * (which some archs use locking for atomic64), make sure this + * is safe in NMI context + */ + if ((!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) || + IS_ENABLED(CONFIG_GENERIC_ATOMIC64)) && (unlikely(in_nmi()))) { return NULL; } -- cgit v1.2.3 From f95ee542947d748d4ca01b4d3103dbdc4fdc8889 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 21 Jan 2025 15:12:36 -0500 Subject: tracing: Fix allocation of printing set_event file content The adding of cached events for modules not loaded yet required a descriptor to separate the iteration of events with the iteration of cached events for a module. But the allocation used the size of the pointer and not the size of the contents to allocate its data and caused a slab-out-of-bounds. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Linus Torvalds Link: https://lore.kernel.org/20250121151236.47fcf433@gandalf.local.home Reported-by: Sasha Levin Closes: https://lore.kernel.org/all/Z4_OHKESRSiJcr-b@lappy/ Fixes: b355247df104e ("tracing: Cache ":mod:" events for modules not loaded yet") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 51c5014877e8..5217dcddcb4c 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1588,7 +1588,7 @@ static void *s_start(struct seq_file *m, loff_t *pos) struct set_event_iter *iter; loff_t l; - iter = kzalloc(sizeof(iter), GFP_KERNEL); + iter = kzalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return NULL; -- cgit v1.2.3 From 8f21943e101a15f56a8f02970a80edc936de8ec8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 21 Jan 2025 15:13:36 -0500 Subject: tracing: Fix output of set_event for some cached module events The following works fine: ~# echo ':mod:trace_events_sample' > /sys/kernel/tracing/set_event ~# cat /sys/kernel/tracing/set_event *:*:mod:trace_events_sample ~# But if a name is given without a ':' where it can match an event name or system name, the output of the cached events does not include a new line: ~# echo 'foo_bar:mod:trace_events_sample' > /sys/kernel/tracing/set_event ~# cat /sys/kernel/tracing/set_event foo_bar:mod:trace_events_sample~# Add the '\n' to that as well. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20250121151336.6c491844@gandalf.local.home Fixes: b355247df104e ("tracing: Cache ":mod:" events for modules not loaded yet") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 5217dcddcb4c..a9d7d02bbb20 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1634,7 +1634,7 @@ static int s_show(struct seq_file *m, void *v) /* When match is set, system and event are not */ if (iter->event_mod->match) { - seq_printf(m, "%s:mod:%s", iter->event_mod->match, + seq_printf(m, "%s:mod:%s\n", iter->event_mod->match, iter->event_mod->module); return 0; } -- cgit v1.2.3 From 66611c0475709607f398e2a5d691b1fc72fe9dfc Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 21 Jan 2025 19:44:36 -0500 Subject: fgraph: Remove calltime and rettime from generic operations The function graph infrastructure is now generic so that kretprobes, fprobes and BPF can use it. But there is still some leftover logic that only the function graph tracer itself uses. This is the calculation of the calltime and return time of the functions. The calculation of the calltime has been moved into the function graph tracer and those users that need it so that it doesn't cause overhead to the other users. But the return function timestamp was still called. Instead of just moving the taking of the timestamp into the function graph trace remove the calltime and rettime completely from the ftrace_graph_ret structure. Instead, move it into the function graph return entry event structure and this also moves all the calltime and rettime logic out of the generic fgraph.c code and into the tracing code that uses it. This has been reported to decrease the overhead by ~27%. Link: https://lore.kernel.org/all/Z3aSuql3fnXMVMoM@krava/ Link: https://lore.kernel.org/all/173665959558.1629214.16724136597211810729.stgit@devnote2/ Cc: Mark Rutland Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20250121194436.15bdf71a@gandalf.local.home Reported-by: Jiri Olsa Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 2 -- kernel/trace/fgraph.c | 1 - kernel/trace/trace.h | 4 +++- kernel/trace/trace_entries.h | 8 ++++---- kernel/trace/trace_functions_graph.c | 33 +++++++++++++++++++-------------- kernel/trace/trace_irqsoff.c | 5 +++-- kernel/trace/trace_sched_wakeup.c | 6 ++++-- 7 files changed, 33 insertions(+), 26 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 07092dfb21a4..fbabc3d848b3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1151,8 +1151,6 @@ struct ftrace_graph_ret { int depth; /* Number of functions that overran the depth limit for current task */ unsigned int overrun; - unsigned long long calltime; - unsigned long long rettime; } __packed; struct fgraph_ops; diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 9e6b5a71555b..5dddfc2149f6 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -826,7 +826,6 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe return (unsigned long)panic; } - trace.rettime = trace_clock_local(); if (fregs) ftrace_regs_set_instruction_pointer(fregs, ret); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 04058a9889b7..2742d14df383 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -912,7 +912,9 @@ extern int __trace_graph_retaddr_entry(struct trace_array *tr, unsigned long retaddr); extern void __trace_graph_return(struct trace_array *tr, struct ftrace_graph_ret *trace, - unsigned int trace_ctx); + unsigned int trace_ctx, + u64 calltime, u64 rettime); + extern void init_array_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops); extern int allocate_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops); extern void free_fgraph_ops(struct trace_array *tr); diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index 82fd174ebbe0..fbfb396905a6 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -124,8 +124,8 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, __field_packed( unsigned long, ret, retval ) __field_packed( int, ret, depth ) __field_packed( unsigned int, ret, overrun ) - __field_packed( unsigned long long, ret, calltime) - __field_packed( unsigned long long, ret, rettime ) + __field(unsigned long long, calltime ) + __field(unsigned long long, rettime ) ), F_printk("<-- %ps (%d) (start: %llx end: %llx) over: %d retval: %lx", @@ -146,8 +146,8 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, __field_packed( unsigned long, ret, func ) __field_packed( int, ret, depth ) __field_packed( unsigned int, ret, overrun ) - __field_packed( unsigned long long, ret, calltime) - __field_packed( unsigned long long, ret, rettime ) + __field(unsigned long long, calltime ) + __field(unsigned long long, rettime ) ), F_printk("<-- %ps (%d) (start: %llx end: %llx) over: %d", diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index dc62eb93837a..54d850997c0a 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -266,12 +266,10 @@ __trace_graph_function(struct trace_array *tr, struct ftrace_graph_ret ret = { .func = ip, .depth = 0, - .calltime = time, - .rettime = time, }; __trace_graph_entry(tr, &ent, trace_ctx); - __trace_graph_return(tr, &ret, trace_ctx); + __trace_graph_return(tr, &ret, trace_ctx, time, time); } void @@ -283,8 +281,9 @@ trace_graph_function(struct trace_array *tr, } void __trace_graph_return(struct trace_array *tr, - struct ftrace_graph_ret *trace, - unsigned int trace_ctx) + struct ftrace_graph_ret *trace, + unsigned int trace_ctx, + u64 calltime, u64 rettime) { struct ring_buffer_event *event; struct trace_buffer *buffer = tr->array_buffer.buffer; @@ -296,6 +295,8 @@ void __trace_graph_return(struct trace_array *tr, return; entry = ring_buffer_event_data(event); entry->ret = *trace; + entry->calltime = calltime; + entry->rettime = rettime; trace_buffer_unlock_commit_nostack(buffer, event); } @@ -317,10 +318,13 @@ void trace_graph_return(struct ftrace_graph_ret *trace, struct trace_array_cpu *data; struct fgraph_times *ftimes; unsigned int trace_ctx; + u64 calltime, rettime; long disabled; int size; int cpu; + rettime = trace_clock_local(); + ftrace_graph_addr_finish(gops, trace); if (*task_var & TRACE_GRAPH_NOTRACE) { @@ -334,7 +338,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace, handle_nosleeptime(trace, ftimes, size); - trace->calltime = ftimes->calltime; + calltime = ftimes->calltime; preempt_disable_notrace(); cpu = raw_smp_processor_id(); @@ -342,7 +346,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace, disabled = atomic_read(&data->disabled); if (likely(!disabled)) { trace_ctx = tracing_gen_ctx(); - __trace_graph_return(tr, trace, trace_ctx); + __trace_graph_return(tr, trace, trace_ctx, calltime, rettime); } preempt_enable_notrace(); } @@ -367,10 +371,8 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, handle_nosleeptime(trace, ftimes, size); - trace->calltime = ftimes->calltime; - if (tracing_thresh && - (trace->rettime - ftimes->calltime < tracing_thresh)) + (trace_clock_local() - ftimes->calltime < tracing_thresh)) return; else trace_graph_return(trace, gops, fregs); @@ -856,7 +858,7 @@ print_graph_entry_leaf(struct trace_iterator *iter, graph_ret = &ret_entry->ret; call = &entry->graph_ent; - duration = graph_ret->rettime - graph_ret->calltime; + duration = ret_entry->rettime - ret_entry->calltime; func = call->func + iter->tr->text_delta; @@ -1137,11 +1139,14 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s, } static enum print_line_t -print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, +print_graph_return(struct ftrace_graph_ret_entry *retentry, struct trace_seq *s, struct trace_entry *ent, struct trace_iterator *iter, u32 flags) { - unsigned long long duration = trace->rettime - trace->calltime; + struct ftrace_graph_ret *trace = &retentry->ret; + u64 calltime = retentry->calltime; + u64 rettime = retentry->rettime; + unsigned long long duration = rettime - calltime; struct fgraph_data *data = iter->private; struct trace_array *tr = iter->tr; unsigned long func; @@ -1342,7 +1347,7 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags) case TRACE_GRAPH_RET: { struct ftrace_graph_ret_entry *field; trace_assign_type(field, entry); - return print_graph_return(&field->ret, s, entry, iter, flags); + return print_graph_return(field, s, entry, iter, flags); } case TRACE_STACK: case TRACE_FN: diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 08786c59d397..7294ad676379 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -223,6 +223,7 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace, unsigned long flags; unsigned int trace_ctx; u64 *calltime; + u64 rettime; int size; ftrace_graph_addr_finish(gops, trace); @@ -230,13 +231,13 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace, if (!func_prolog_dec(tr, &data, &flags)) return; + rettime = trace_clock_local(); calltime = fgraph_retrieve_data(gops->idx, &size); if (!calltime) return; - trace->calltime = *calltime; trace_ctx = tracing_gen_ctx_flags(flags); - __trace_graph_return(tr, trace, trace_ctx); + __trace_graph_return(tr, trace, trace_ctx, *calltime, rettime); atomic_dec(&data->disabled); } diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index f372252dc8bb..af30586f1aea 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -158,6 +158,7 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace, struct trace_array_cpu *data; unsigned int trace_ctx; u64 *calltime; + u64 rettime; int size; ftrace_graph_addr_finish(gops, trace); @@ -165,12 +166,13 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace, if (!func_prolog_preempt_disable(tr, &data, &trace_ctx)) return; + rettime = trace_clock_local(); + calltime = fgraph_retrieve_data(gops->idx, &size); if (!calltime) return; - trace->calltime = *calltime; - __trace_graph_return(tr, trace, trace_ctx); + __trace_graph_return(tr, trace, trace_ctx, *calltime, rettime); atomic_dec(&data->disabled); preempt_enable_notrace(); -- cgit v1.2.3 From e3ff4245928f948f3eb2e852aa350b870421c358 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 23 Jan 2025 20:41:59 -0500 Subject: tracing/osnoise: Fix resetting of tracepoints If a timerlat tracer is started with the osnoise option OSNOISE_WORKLOAD disabled, but then that option is enabled and timerlat is removed, the tracepoints that were enabled on timerlat registration do not get disabled. If the option is disabled again and timelat is started, then it triggers a warning in the tracepoint code due to registering the tracepoint again without ever disabling it. Do not use the same user space defined options to know to disable the tracepoints when timerlat is removed. Instead, set a global flag when it is enabled and use that flag to know to disable the events. ~# echo NO_OSNOISE_WORKLOAD > /sys/kernel/tracing/osnoise/options ~# echo timerlat > /sys/kernel/tracing/current_tracer ~# echo OSNOISE_WORKLOAD > /sys/kernel/tracing/osnoise/options ~# echo nop > /sys/kernel/tracing/current_tracer ~# echo NO_OSNOISE_WORKLOAD > /sys/kernel/tracing/osnoise/options ~# echo timerlat > /sys/kernel/tracing/current_tracer Triggers: ------------[ cut here ]------------ WARNING: CPU: 6 PID: 1337 at kernel/tracepoint.c:294 tracepoint_add_func+0x3b6/0x3f0 Modules linked in: CPU: 6 UID: 0 PID: 1337 Comm: rtla Not tainted 6.13.0-rc4-test-00018-ga867c441128e-dirty #73 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 RIP: 0010:tracepoint_add_func+0x3b6/0x3f0 Code: 48 8b 53 28 48 8b 73 20 4c 89 04 24 e8 23 59 11 00 4c 8b 04 24 e9 36 fe ff ff 0f 0b b8 ea ff ff ff 45 84 e4 0f 84 68 fe ff ff <0f> 0b e9 61 fe ff ff 48 8b 7b 18 48 85 ff 0f 84 4f ff ff ff 49 8b RSP: 0018:ffffb9b003a87ca0 EFLAGS: 00010202 RAX: 00000000ffffffef RBX: ffffffff92f30860 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9bf59e91ccd0 RDI: ffffffff913b6410 RBP: 000000000000000a R08: 00000000000005c7 R09: 0000000000000002 R10: ffffb9b003a87ce0 R11: 0000000000000002 R12: 0000000000000001 R13: ffffb9b003a87ce0 R14: ffffffffffffffef R15: 0000000000000008 FS: 00007fce81209240(0000) GS:ffff9bf6fdd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055e99b728000 CR3: 00000001277c0002 CR4: 0000000000172ef0 Call Trace: ? __warn.cold+0xb7/0x14d ? tracepoint_add_func+0x3b6/0x3f0 ? report_bug+0xea/0x170 ? handle_bug+0x58/0x90 ? exc_invalid_op+0x17/0x70 ? asm_exc_invalid_op+0x1a/0x20 ? __pfx_trace_sched_migrate_callback+0x10/0x10 ? tracepoint_add_func+0x3b6/0x3f0 ? __pfx_trace_sched_migrate_callback+0x10/0x10 ? __pfx_trace_sched_migrate_callback+0x10/0x10 tracepoint_probe_register+0x78/0xb0 ? __pfx_trace_sched_migrate_callback+0x10/0x10 osnoise_workload_start+0x2b5/0x370 timerlat_tracer_init+0x76/0x1b0 tracing_set_tracer+0x244/0x400 tracing_set_trace_write+0xa0/0xe0 vfs_write+0xfc/0x570 ? do_sys_openat2+0x9c/0xe0 ksys_write+0x72/0xf0 do_syscall_64+0x79/0x1c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Tomas Glozar Cc: Gabriele Monaco Cc: Luis Goncalves Cc: John Kacur Link: https://lore.kernel.org/20250123204159.4450c88e@gandalf.local.home Fixes: e88ed227f639e ("tracing/timerlat: Add user-space interface") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_osnoise.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index b9f96c77527d..23cbc24ed292 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1229,6 +1229,8 @@ static void trace_sched_migrate_callback(void *data, struct task_struct *p, int } } +static bool monitor_enabled; + static int register_migration_monitor(void) { int ret = 0; @@ -1237,16 +1239,25 @@ static int register_migration_monitor(void) * Timerlat thread migration check is only required when running timerlat in user-space. * Thus, enable callback only if timerlat is set with no workload. */ - if (timerlat_enabled() && !test_bit(OSN_WORKLOAD, &osnoise_options)) + if (timerlat_enabled() && !test_bit(OSN_WORKLOAD, &osnoise_options)) { + if (WARN_ON_ONCE(monitor_enabled)) + return 0; + ret = register_trace_sched_migrate_task(trace_sched_migrate_callback, NULL); + if (!ret) + monitor_enabled = true; + } return ret; } static void unregister_migration_monitor(void) { - if (timerlat_enabled() && !test_bit(OSN_WORKLOAD, &osnoise_options)) - unregister_trace_sched_migrate_task(trace_sched_migrate_callback, NULL); + if (!monitor_enabled) + return; + + unregister_trace_sched_migrate_task(trace_sched_migrate_callback, NULL); + monitor_enabled = false; } #else static int register_migration_monitor(void) -- cgit v1.2.3 From 1751f872cc97f992ed5c4c72c55588db1f0021e1 Mon Sep 17 00:00:00 2001 From: Joel Granados Date: Tue, 28 Jan 2025 13:48:37 +0100 Subject: treewide: const qualify ctl_tables where applicable Add the const qualifier to all the ctl_tables in the tree except for watchdog_hardlockup_sysctl, memory_allocation_profiling_sysctls, loadpin_sysctl_table and the ones calling register_net_sysctl (./net, drivers/inifiniband dirs). These are special cases as they use a registration function with a non-const qualified ctl_table argument or modify the arrays before passing them on to the registration function. Constifying ctl_table structs will prevent the modification of proc_handler function pointers as the arrays would reside in .rodata. This is made possible after commit 78eb4ea25cd5 ("sysctl: treewide: constify the ctl_table argument of proc_handlers") constified all the proc_handlers. Created this by running an spatch followed by a sed command: Spatch: virtual patch @ depends on !(file in "net") disable optional_qualifier @ identifier table_name != { watchdog_hardlockup_sysctl, iwcm_ctl_table, ucma_ctl_table, memory_allocation_profiling_sysctls, loadpin_sysctl_table }; @@ + const struct ctl_table table_name [] = { ... }; sed: sed --in-place \ -e "s/struct ctl_table .table = &uts_kern/const struct ctl_table *table = \&uts_kern/" \ kernel/utsname_sysctl.c Reviewed-by: Song Liu Acked-by: Steven Rostedt (Google) # for kernel/trace/ Reviewed-by: Martin K. Petersen # SCSI Reviewed-by: Darrick J. Wong # xfs Acked-by: Jani Nikula Acked-by: Corey Minyard Acked-by: Wei Liu Acked-by: Thomas Gleixner Reviewed-by: Bill O'Donnell Acked-by: Baoquan He Acked-by: Ashutosh Dixit Acked-by: Anna Schumaker Signed-off-by: Joel Granados --- arch/arm/kernel/isa.c | 2 +- arch/arm64/kernel/fpsimd.c | 4 ++-- arch/arm64/kernel/process.c | 2 +- arch/powerpc/kernel/idle.c | 2 +- arch/powerpc/platforms/pseries/mobility.c | 2 +- arch/riscv/kernel/process.c | 2 +- arch/riscv/kernel/vector.c | 2 +- arch/s390/appldata/appldata_base.c | 2 +- arch/s390/kernel/debug.c | 2 +- arch/s390/kernel/hiperdispatch.c | 2 +- arch/s390/kernel/topology.c | 2 +- arch/s390/mm/cmm.c | 2 +- arch/s390/mm/pgalloc.c | 2 +- arch/x86/entry/vdso/vdso32-setup.c | 2 +- arch/x86/kernel/cpu/bus_lock.c | 2 +- crypto/fips.c | 2 +- drivers/base/firmware_loader/fallback_table.c | 2 +- drivers/cdrom/cdrom.c | 2 +- drivers/char/hpet.c | 2 +- drivers/char/ipmi/ipmi_poweroff.c | 2 +- drivers/char/random.c | 2 +- drivers/gpu/drm/i915/i915_perf.c | 2 +- drivers/gpu/drm/xe/xe_observation.c | 2 +- drivers/hv/hv_common.c | 2 +- drivers/md/md.c | 2 +- drivers/misc/sgi-xp/xpc_main.c | 4 ++-- drivers/perf/arm_pmuv3.c | 2 +- drivers/perf/riscv_pmu_sbi.c | 2 +- drivers/scsi/scsi_sysctl.c | 2 +- drivers/scsi/sg.c | 2 +- drivers/tty/tty_io.c | 2 +- drivers/xen/balloon.c | 2 +- fs/aio.c | 2 +- fs/cachefiles/error_inject.c | 2 +- fs/coda/sysctl.c | 2 +- fs/coredump.c | 2 +- fs/dcache.c | 2 +- fs/devpts/inode.c | 2 +- fs/eventpoll.c | 2 +- fs/exec.c | 2 +- fs/file_table.c | 2 +- fs/fuse/sysctl.c | 2 +- fs/inode.c | 2 +- fs/lockd/svc.c | 2 +- fs/locks.c | 2 +- fs/namei.c | 2 +- fs/namespace.c | 2 +- fs/nfs/nfs4sysctl.c | 2 +- fs/nfs/sysctl.c | 2 +- fs/notify/dnotify/dnotify.c | 2 +- fs/notify/fanotify/fanotify_user.c | 2 +- fs/notify/inotify/inotify_user.c | 2 +- fs/ocfs2/stackglue.c | 2 +- fs/pipe.c | 2 +- fs/quota/dquot.c | 2 +- fs/sysctls.c | 2 +- fs/userfaultfd.c | 2 +- fs/verity/init.c | 2 +- fs/xfs/xfs_sysctl.c | 2 +- init/do_mounts_initrd.c | 2 +- io_uring/io_uring.c | 2 +- ipc/ipc_sysctl.c | 2 +- ipc/mq_sysctl.c | 2 +- kernel/acct.c | 2 +- kernel/bpf/syscall.c | 2 +- kernel/delayacct.c | 2 +- kernel/exit.c | 2 +- kernel/hung_task.c | 2 +- kernel/kexec_core.c | 2 +- kernel/kprobes.c | 2 +- kernel/latencytop.c | 2 +- kernel/locking/lockdep.c | 2 +- kernel/panic.c | 2 +- kernel/pid.c | 2 +- kernel/pid_namespace.c | 2 +- kernel/pid_sysctl.h | 2 +- kernel/printk/sysctl.c | 2 +- kernel/reboot.c | 2 +- kernel/sched/autogroup.c | 2 +- kernel/sched/core.c | 2 +- kernel/sched/deadline.c | 2 +- kernel/sched/fair.c | 2 +- kernel/sched/rt.c | 2 +- kernel/sched/topology.c | 2 +- kernel/seccomp.c | 2 +- kernel/signal.c | 2 +- kernel/stackleak.c | 2 +- kernel/sysctl-test.c | 6 +++--- kernel/sysctl.c | 4 ++-- kernel/time/timer.c | 2 +- kernel/trace/ftrace.c | 2 +- kernel/trace/trace_events_user.c | 2 +- kernel/umh.c | 2 +- kernel/utsname_sysctl.c | 4 ++-- kernel/watchdog.c | 2 +- lib/test_sysctl.c | 6 +++--- mm/compaction.c | 2 +- mm/hugetlb.c | 2 +- mm/hugetlb_vmemmap.c | 2 +- mm/memory-failure.c | 2 +- mm/oom_kill.c | 2 +- mm/page-writeback.c | 2 +- mm/page_alloc.c | 2 +- security/apparmor/lsm.c | 2 +- security/keys/sysctl.c | 2 +- security/yama/yama_lsm.c | 2 +- 106 files changed, 114 insertions(+), 114 deletions(-) (limited to 'kernel/trace') diff --git a/arch/arm/kernel/isa.c b/arch/arm/kernel/isa.c index 905b1b191546..db8be609fab2 100644 --- a/arch/arm/kernel/isa.c +++ b/arch/arm/kernel/isa.c @@ -16,7 +16,7 @@ static unsigned int isa_membase, isa_portbase, isa_portshift; -static struct ctl_table ctl_isa_vars[] = { +static const struct ctl_table ctl_isa_vars[] = { { .procname = "membase", .data = &isa_membase, diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 8c4c1a2186cc..2b601d88762d 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -562,7 +562,7 @@ static int vec_proc_do_default_vl(const struct ctl_table *table, int write, return 0; } -static struct ctl_table sve_default_vl_table[] = { +static const struct ctl_table sve_default_vl_table[] = { { .procname = "sve_default_vector_length", .mode = 0644, @@ -585,7 +585,7 @@ static int __init sve_sysctl_init(void) { return 0; } #endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ #if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL) -static struct ctl_table sme_default_vl_table[] = { +static const struct ctl_table sme_default_vl_table[] = { { .procname = "sme_default_vector_length", .mode = 0644, diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 2968a33bb3bc..42faebb7b712 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -859,7 +859,7 @@ long get_tagged_addr_ctrl(struct task_struct *task) * disable it for tasks that already opted in to the relaxed ABI. */ -static struct ctl_table tagged_addr_sysctl_table[] = { +static const struct ctl_table tagged_addr_sysctl_table[] = { { .procname = "tagged_addr_disabled", .mode = 0644, diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 30b56c67fa61..e527cd3ef128 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -97,7 +97,7 @@ void power4_idle(void) /* * Register the sysctl to set/clear powersave_nap. */ -static struct ctl_table powersave_nap_ctl_table[] = { +static const struct ctl_table powersave_nap_ctl_table[] = { { .procname = "powersave-nap", .data = &powersave_nap, diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 1798f0f14d58..62bd8e2d5d4c 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -53,7 +53,7 @@ struct update_props_workarea { static unsigned int nmi_wd_lpm_factor = 200; #ifdef CONFIG_SYSCTL -static struct ctl_table nmi_wd_lpm_factor_ctl_table[] = { +static const struct ctl_table nmi_wd_lpm_factor_ctl_table[] = { { .procname = "nmi_wd_lpm_factor", .data = &nmi_wd_lpm_factor, diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 58b6482c2bf6..7891294abf49 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -364,7 +364,7 @@ static bool try_to_set_pmm(unsigned long value) * disable it for tasks that already opted in to the relaxed ABI. */ -static struct ctl_table tagged_addr_sysctl_table[] = { +static const struct ctl_table tagged_addr_sysctl_table[] = { { .procname = "tagged_addr_disabled", .mode = 0644, diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c index 821818886fab..d022b028ac3f 100644 --- a/arch/riscv/kernel/vector.c +++ b/arch/riscv/kernel/vector.c @@ -287,7 +287,7 @@ long riscv_v_vstate_ctrl_set_current(unsigned long arg) #ifdef CONFIG_SYSCTL -static struct ctl_table riscv_v_default_vstate_table[] = { +static const struct ctl_table riscv_v_default_vstate_table[] = { { .procname = "riscv_v_default_allow", .data = &riscv_v_implicit_uacc, diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 91a30e017d65..dd7ba7587dd5 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -52,7 +52,7 @@ static int appldata_interval_handler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static struct ctl_table_header *appldata_sysctl_header; -static struct ctl_table appldata_table[] = { +static const struct ctl_table appldata_table[] = { { .procname = "timer", .mode = S_IRUGO | S_IWUSR, diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index ba6b7329a10e..ce038e9205f7 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -1122,7 +1122,7 @@ static int s390dbf_procactive(const struct ctl_table *table, int write, return 0; } -static struct ctl_table s390dbf_table[] = { +static const struct ctl_table s390dbf_table[] = { { .procname = "debug_stoppable", .data = &debug_stoppable, diff --git a/arch/s390/kernel/hiperdispatch.c b/arch/s390/kernel/hiperdispatch.c index 2a99a216ab62..7857a7e8e56c 100644 --- a/arch/s390/kernel/hiperdispatch.c +++ b/arch/s390/kernel/hiperdispatch.c @@ -292,7 +292,7 @@ static int hiperdispatch_ctl_handler(const struct ctl_table *ctl, int write, return 0; } -static struct ctl_table hiperdispatch_ctl_table[] = { +static const struct ctl_table hiperdispatch_ctl_table[] = { { .procname = "hiperdispatch", .mode = 0644, diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 3808f942a433..211cc8382e4a 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -667,7 +667,7 @@ static int polarization_ctl_handler(const struct ctl_table *ctl, int write, return set_polarization(polarization); } -static struct ctl_table topology_ctl_table[] = { +static const struct ctl_table topology_ctl_table[] = { { .procname = "topology", .mode = 0644, diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 7bf0f691827b..39f44b6256e0 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -332,7 +332,7 @@ static int cmm_timeout_handler(const struct ctl_table *ctl, int write, return 0; } -static struct ctl_table cmm_table[] = { +static const struct ctl_table cmm_table[] = { { .procname = "cmm_pages", .mode = 0644, diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index d33f55b7ee98..cd2fef79ad2c 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -21,7 +21,7 @@ int page_table_allocate_pgste = 0; EXPORT_SYMBOL(page_table_allocate_pgste); -static struct ctl_table page_table_sysctl[] = { +static const struct ctl_table page_table_sysctl[] = { { .procname = "allocate_pgste", .data = &page_table_allocate_pgste, diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 76e4e74f35b5..f6d2d8aba643 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -57,7 +57,7 @@ __setup_param("vdso=", vdso_setup, vdso32_setup, 0); /* Register vsyscall32 into the ABI table */ #include -static struct ctl_table abi_table2[] = { +static const struct ctl_table abi_table2[] = { { .procname = "vsyscall32", .data = &vdso32_enabled, diff --git a/arch/x86/kernel/cpu/bus_lock.c b/arch/x86/kernel/cpu/bus_lock.c index 704e9241b964..6cba85c79d42 100644 --- a/arch/x86/kernel/cpu/bus_lock.c +++ b/arch/x86/kernel/cpu/bus_lock.c @@ -49,7 +49,7 @@ static unsigned int sysctl_sld_mitigate = 1; static DEFINE_SEMAPHORE(buslock_sem, 1); #ifdef CONFIG_PROC_SYSCTL -static struct ctl_table sld_sysctls[] = { +static const struct ctl_table sld_sysctls[] = { { .procname = "split_lock_mitigate", .data = &sysctl_sld_mitigate, diff --git a/crypto/fips.c b/crypto/fips.c index a58e7750f532..2fa3a9ee61a1 100644 --- a/crypto/fips.c +++ b/crypto/fips.c @@ -41,7 +41,7 @@ __setup("fips=", fips_enable); static char fips_name[] = FIPS_MODULE_NAME; static char fips_version[] = FIPS_MODULE_VERSION; -static struct ctl_table crypto_sysctl_table[] = { +static const struct ctl_table crypto_sysctl_table[] = { { .procname = "fips_enabled", .data = &fips_enabled, diff --git a/drivers/base/firmware_loader/fallback_table.c b/drivers/base/firmware_loader/fallback_table.c index ddb70e29eb42..c8afc501a8a4 100644 --- a/drivers/base/firmware_loader/fallback_table.c +++ b/drivers/base/firmware_loader/fallback_table.c @@ -25,7 +25,7 @@ struct firmware_fallback_config fw_fallback_config = { EXPORT_SYMBOL_NS_GPL(fw_fallback_config, "FIRMWARE_LOADER_PRIVATE"); #ifdef CONFIG_SYSCTL -static struct ctl_table firmware_config_table[] = { +static const struct ctl_table firmware_config_table[] = { { .procname = "force_sysfs_fallback", .data = &fw_fallback_config.force_sysfs_fallback, diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 51745ed1bbab..b163e043c687 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -3612,7 +3612,7 @@ static int cdrom_sysctl_handler(const struct ctl_table *ctl, int write, } /* Place files in /proc/sys/dev/cdrom */ -static struct ctl_table cdrom_table[] = { +static const struct ctl_table cdrom_table[] = { { .procname = "info", .data = &cdrom_sysctl_settings.info, diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 48fe96ab4649..e110857824fc 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -724,7 +724,7 @@ static int hpet_is_known(struct hpet_data *hdp) return 0; } -static struct ctl_table hpet_table[] = { +static const struct ctl_table hpet_table[] = { { .procname = "max-user-freq", .data = &hpet_max_freq, diff --git a/drivers/char/ipmi/ipmi_poweroff.c b/drivers/char/ipmi/ipmi_poweroff.c index 05f17e3e6207..e63c316d8aaa 100644 --- a/drivers/char/ipmi/ipmi_poweroff.c +++ b/drivers/char/ipmi/ipmi_poweroff.c @@ -650,7 +650,7 @@ static struct ipmi_smi_watcher smi_watcher = { #ifdef CONFIG_PROC_FS #include -static struct ctl_table ipmi_table[] = { +static const struct ctl_table ipmi_table[] = { { .procname = "poweroff_powercycle", .data = &poweroff_powercycle, .maxlen = sizeof(poweroff_powercycle), diff --git a/drivers/char/random.c b/drivers/char/random.c index 23ee76bbb4aa..2581186fa61b 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1665,7 +1665,7 @@ static int proc_do_rointvec(const struct ctl_table *table, int write, void *buf, return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos); } -static struct ctl_table random_table[] = { +static const struct ctl_table random_table[] = { { .procname = "poolsize", .data = &sysctl_poolsize, diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 2406cda75b7b..5384d1bb4923 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -4802,7 +4802,7 @@ err_unlock: return ret; } -static struct ctl_table oa_table[] = { +static const struct ctl_table oa_table[] = { { .procname = "perf_stream_paranoid", .data = &i915_perf_stream_paranoid, diff --git a/drivers/gpu/drm/xe/xe_observation.c b/drivers/gpu/drm/xe/xe_observation.c index 8ec1b84cbb9e..57cf01efc07f 100644 --- a/drivers/gpu/drm/xe/xe_observation.c +++ b/drivers/gpu/drm/xe/xe_observation.c @@ -56,7 +56,7 @@ int xe_observation_ioctl(struct drm_device *dev, void *data, struct drm_file *fi } } -static struct ctl_table observation_ctl_table[] = { +static const struct ctl_table observation_ctl_table[] = { { .procname = "observation_paranoid", .data = &xe_observation_paranoid, diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index af5d1dc451f6..f2e6f55d6ca6 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -141,7 +141,7 @@ static int sysctl_record_panic_msg = 1; * sysctl option to allow the user to control whether kmsg data should be * reported to Hyper-V on panic. */ -static struct ctl_table hv_ctl_table[] = { +static const struct ctl_table hv_ctl_table[] = { { .procname = "hyperv_record_panic_msg", .data = &sysctl_record_panic_msg, diff --git a/drivers/md/md.c b/drivers/md/md.c index 866015b681af..22f7bd3b94d5 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -294,7 +294,7 @@ void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev) static struct ctl_table_header *raid_table_header; -static struct ctl_table raid_table[] = { +static const struct ctl_table raid_table[] = { { .procname = "speed_limit_min", .data = &sysctl_speed_limit_min, diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c index 61b66e318488..7a3c34306de9 100644 --- a/drivers/misc/sgi-xp/xpc_main.c +++ b/drivers/misc/sgi-xp/xpc_main.c @@ -93,7 +93,7 @@ int xpc_disengage_timelimit = XPC_DISENGAGE_DEFAULT_TIMELIMIT; static int xpc_disengage_min_timelimit; /* = 0 */ static int xpc_disengage_max_timelimit = 120; -static struct ctl_table xpc_sys_xpc_hb[] = { +static const struct ctl_table xpc_sys_xpc_hb[] = { { .procname = "hb_interval", .data = &xpc_hb_interval, @@ -111,7 +111,7 @@ static struct ctl_table xpc_sys_xpc_hb[] = { .extra1 = &xpc_hb_check_min_interval, .extra2 = &xpc_hb_check_max_interval}, }; -static struct ctl_table xpc_sys_xpc[] = { +static const struct ctl_table xpc_sys_xpc[] = { { .procname = "disengage_timelimit", .data = &xpc_disengage_timelimit, diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c index b5cc11abc962..0e360feb3432 100644 --- a/drivers/perf/arm_pmuv3.c +++ b/drivers/perf/arm_pmuv3.c @@ -1279,7 +1279,7 @@ static int armv8pmu_proc_user_access_handler(const struct ctl_table *table, int return 0; } -static struct ctl_table armv8_pmu_sysctl_table[] = { +static const struct ctl_table armv8_pmu_sysctl_table[] = { { .procname = "perf_user_access", .data = &sysctl_perf_user_access, diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 194c153e5d71..698de8ddf895 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -1317,7 +1317,7 @@ static int riscv_pmu_proc_user_access_handler(const struct ctl_table *table, return 0; } -static struct ctl_table sbi_pmu_sysctl_table[] = { +static const struct ctl_table sbi_pmu_sysctl_table[] = { { .procname = "perf_user_access", .data = &sysctl_perf_user_access, diff --git a/drivers/scsi/scsi_sysctl.c b/drivers/scsi/scsi_sysctl.c index 093774d77534..be4aef0f4f99 100644 --- a/drivers/scsi/scsi_sysctl.c +++ b/drivers/scsi/scsi_sysctl.c @@ -12,7 +12,7 @@ #include "scsi_priv.h" -static struct ctl_table scsi_table[] = { +static const struct ctl_table scsi_table[] = { { .procname = "logging_level", .data = &scsi_logging_level, .maxlen = sizeof(scsi_logging_level), diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 94127868bedf..effb7e768165 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1639,7 +1639,7 @@ MODULE_PARM_DESC(allow_dio, "allow direct I/O (default: 0 (disallow))"); #ifdef CONFIG_SYSCTL #include -static struct ctl_table sg_sysctls[] = { +static const struct ctl_table sg_sysctls[] = { { .procname = "sg-big-buff", .data = &sg_big_buff, diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 50c0c23ae678..449dbd216460 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -3617,7 +3617,7 @@ void console_sysfs_notify(void) sysfs_notify(&consdev->kobj, NULL, "active"); } -static struct ctl_table tty_table[] = { +static const struct ctl_table tty_table[] = { { .procname = "legacy_tiocsti", .data = &tty_legacy_tiocsti, diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 528395133b4f..163f7f1d70f1 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -84,7 +84,7 @@ module_param(balloon_boot_timeout, uint, 0444); #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG static int xen_hotplug_unpopulated; -static struct ctl_table balloon_table[] = { +static const struct ctl_table balloon_table[] = { { .procname = "hotplug_unpopulated", .data = &xen_hotplug_unpopulated, diff --git a/fs/aio.c b/fs/aio.c index 50671640b588..7b976b564cfc 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -224,7 +224,7 @@ static unsigned long aio_nr; /* current system wide number of aio requests */ static unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */ /*----end sysctl variables---*/ #ifdef CONFIG_SYSCTL -static struct ctl_table aio_sysctls[] = { +static const struct ctl_table aio_sysctls[] = { { .procname = "aio-nr", .data = &aio_nr, diff --git a/fs/cachefiles/error_inject.c b/fs/cachefiles/error_inject.c index 1715d5ca2b2d..e341ade47dd8 100644 --- a/fs/cachefiles/error_inject.c +++ b/fs/cachefiles/error_inject.c @@ -11,7 +11,7 @@ unsigned int cachefiles_error_injection_state; static struct ctl_table_header *cachefiles_sysctl; -static struct ctl_table cachefiles_sysctls[] = { +static const struct ctl_table cachefiles_sysctls[] = { { .procname = "error_injection", .data = &cachefiles_error_injection_state, diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c index 9f2d5743e2c8..0df46f09b6cc 100644 --- a/fs/coda/sysctl.c +++ b/fs/coda/sysctl.c @@ -14,7 +14,7 @@ static struct ctl_table_header *fs_table_header; -static struct ctl_table coda_table[] = { +static const struct ctl_table coda_table[] = { { .procname = "timeout", .data = &coda_timeout, diff --git a/fs/coredump.c b/fs/coredump.c index d48edb37bc35..591700e1b2ce 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -995,7 +995,7 @@ static int proc_dostring_coredump(const struct ctl_table *table, int write, static const unsigned int core_file_note_size_min = CORE_FILE_NOTE_SIZE_DEFAULT; static const unsigned int core_file_note_size_max = CORE_FILE_NOTE_SIZE_MAX; -static struct ctl_table coredump_sysctls[] = { +static const struct ctl_table coredump_sysctls[] = { { .procname = "core_uses_pid", .data = &core_uses_pid, diff --git a/fs/dcache.c b/fs/dcache.c index 1a01d7a6a7a9..1cd929f17eec 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -192,7 +192,7 @@ static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table fs_dcache_sysctls[] = { +static const struct ctl_table fs_dcache_sysctls[] = { { .procname = "dentry-state", .data = &dentry_stat, diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index b20e565b9c5e..1096ff8562fa 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -45,7 +45,7 @@ static int pty_limit_min; static int pty_limit_max = INT_MAX; static atomic_t pty_count = ATOMIC_INIT(0); -static struct ctl_table pty_table[] = { +static const struct ctl_table pty_table[] = { { .procname = "max", .maxlen = sizeof(int), diff --git a/fs/eventpoll.c b/fs/eventpoll.c index f9898e60dd8b..7c0980db77b3 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -318,7 +318,7 @@ static void unlist_file(struct epitems_head *head) static long long_zero; static long long_max = LONG_MAX; -static struct ctl_table epoll_table[] = { +static const struct ctl_table epoll_table[] = { { .procname = "max_user_watches", .data = &max_user_watches, diff --git a/fs/exec.c b/fs/exec.c index a49839174472..506cd411f4ac 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -2159,7 +2159,7 @@ static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int writ return error; } -static struct ctl_table fs_exec_sysctls[] = { +static const struct ctl_table fs_exec_sysctls[] = { { .procname = "suid_dumpable", .data = &suid_dumpable, diff --git a/fs/file_table.c b/fs/file_table.c index a32171d2b83f..7f7c378c6e31 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -106,7 +106,7 @@ static int proc_nr_files(const struct ctl_table *table, int write, void *buffer, return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table fs_stat_sysctls[] = { +static const struct ctl_table fs_stat_sysctls[] = { { .procname = "file-nr", .data = &files_stat, diff --git a/fs/fuse/sysctl.c b/fs/fuse/sysctl.c index b272bb333005..63fb1e5bee30 100644 --- a/fs/fuse/sysctl.c +++ b/fs/fuse/sysctl.c @@ -13,7 +13,7 @@ static struct ctl_table_header *fuse_table_header; /* Bound by fuse_init_out max_pages, which is a u16 */ static unsigned int sysctl_fuse_max_pages_limit = 65535; -static struct ctl_table fuse_sysctl_table[] = { +static const struct ctl_table fuse_sysctl_table[] = { { .procname = "max_pages_limit", .data = &fuse_max_pages_limit, diff --git a/fs/inode.c b/fs/inode.c index 6b4c77268fc0..5587aabdaa5e 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -184,7 +184,7 @@ static int proc_nr_inodes(const struct ctl_table *table, int write, void *buffer return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table inodes_sysctls[] = { +static const struct ctl_table inodes_sysctls[] = { { .procname = "inode-nr", .data = &inodes_stat, diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 7ded57ec3a60..2c8eedc6c2cc 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -412,7 +412,7 @@ EXPORT_SYMBOL_GPL(lockd_down); * Sysctl parameters (same as module parameters, different interface). */ -static struct ctl_table nlm_sysctls[] = { +static const struct ctl_table nlm_sysctls[] = { { .procname = "nlm_grace_period", .data = &nlm_grace_period, diff --git a/fs/locks.c b/fs/locks.c index 25afc8d9c9d1..1619cddfa7a4 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -97,7 +97,7 @@ static int leases_enable = 1; static int lease_break_time = 45; #ifdef CONFIG_SYSCTL -static struct ctl_table locks_sysctls[] = { +static const struct ctl_table locks_sysctls[] = { { .procname = "leases-enable", .data = &leases_enable, diff --git a/fs/namei.c b/fs/namei.c index e56c29a22d26..8c82afddd2ad 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1099,7 +1099,7 @@ static int sysctl_protected_fifos __read_mostly; static int sysctl_protected_regular __read_mostly; #ifdef CONFIG_SYSCTL -static struct ctl_table namei_sysctls[] = { +static const struct ctl_table namei_sysctls[] = { { .procname = "protected_symlinks", .data = &sysctl_protected_symlinks, diff --git a/fs/namespace.c b/fs/namespace.c index 4013fbac354a..a3ed3f2980cb 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -5985,7 +5985,7 @@ const struct proc_ns_operations mntns_operations = { }; #ifdef CONFIG_SYSCTL -static struct ctl_table fs_namespace_sysctls[] = { +static const struct ctl_table fs_namespace_sysctls[] = { { .procname = "mount-max", .data = &sysctl_mount_max, diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c index 886a7c4c60b3..d1a92d8f8ba4 100644 --- a/fs/nfs/nfs4sysctl.c +++ b/fs/nfs/nfs4sysctl.c @@ -17,7 +17,7 @@ static const int nfs_set_port_min; static const int nfs_set_port_max = 65535; static struct ctl_table_header *nfs4_callback_sysctl_table; -static struct ctl_table nfs4_cb_sysctls[] = { +static const struct ctl_table nfs4_cb_sysctls[] = { { .procname = "nfs_callback_tcpport", .data = &nfs_callback_set_tcpport, diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c index e645be1a3381..f579df0e8d67 100644 --- a/fs/nfs/sysctl.c +++ b/fs/nfs/sysctl.c @@ -14,7 +14,7 @@ static struct ctl_table_header *nfs_callback_sysctl_table; -static struct ctl_table nfs_cb_sysctls[] = { +static const struct ctl_table nfs_cb_sysctls[] = { { .procname = "nfs_mountpoint_timeout", .data = &nfs_mountpoint_expiry_timeout, diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index 6004dfdfdf0f..c4cdaf5fa7ed 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -20,7 +20,7 @@ static int dir_notify_enable __read_mostly = 1; #ifdef CONFIG_SYSCTL -static struct ctl_table dnotify_sysctls[] = { +static const struct ctl_table dnotify_sysctls[] = { { .procname = "dir-notify-enable", .data = &dir_notify_enable, diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 6ff94e312232..ba3e2d09eb44 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -58,7 +58,7 @@ static int fanotify_max_queued_events __read_mostly; static long ft_zero = 0; static long ft_int_max = INT_MAX; -static struct ctl_table fanotify_table[] = { +static const struct ctl_table fanotify_table[] = { { .procname = "max_user_groups", .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS], diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index e0c48956608a..b372fb2c56bd 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -58,7 +58,7 @@ struct kmem_cache *inotify_inode_mark_cachep __ro_after_init; static long it_zero = 0; static long it_int_max = INT_MAX; -static struct ctl_table inotify_table[] = { +static const struct ctl_table inotify_table[] = { { .procname = "max_user_instances", .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES], diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 20aa37b67cfb..ddd761cf44c8 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -650,7 +650,7 @@ error: * and easier to preserve the name. */ -static struct ctl_table ocfs2_nm_table[] = { +static const struct ctl_table ocfs2_nm_table[] = { { .procname = "hb_ctl_path", .data = ocfs2_hb_ctl_path, diff --git a/fs/pipe.c b/fs/pipe.c index 82fede0f2111..94b59045ab44 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1478,7 +1478,7 @@ static int proc_dopipe_max_size(const struct ctl_table *table, int write, do_proc_dopipe_max_size_conv, NULL); } -static struct ctl_table fs_pipe_sysctls[] = { +static const struct ctl_table fs_pipe_sysctls[] = { { .procname = "pipe-max-size", .data = &pipe_max_size, diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index f9578918cfb2..825c5c2e0962 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2926,7 +2926,7 @@ static int do_proc_dqstats(const struct ctl_table *table, int write, return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table fs_dqstats_table[] = { +static const struct ctl_table fs_dqstats_table[] = { { .procname = "lookups", .data = &dqstats.stat[DQST_LOOKUPS], diff --git a/fs/sysctls.c b/fs/sysctls.c index 8dbde9a802fa..ad429dffeb4b 100644 --- a/fs/sysctls.c +++ b/fs/sysctls.c @@ -7,7 +7,7 @@ #include #include -static struct ctl_table fs_shared_sysctls[] = { +static const struct ctl_table fs_shared_sysctls[] = { { .procname = "overflowuid", .data = &fs_overflowuid, diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 7c0bd0b55f88..97c4d71115d8 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -36,7 +36,7 @@ static int sysctl_unprivileged_userfaultfd __read_mostly; #ifdef CONFIG_SYSCTL -static struct ctl_table vm_userfaultfd_table[] = { +static const struct ctl_table vm_userfaultfd_table[] = { { .procname = "unprivileged_userfaultfd", .data = &sysctl_unprivileged_userfaultfd, diff --git a/fs/verity/init.c b/fs/verity/init.c index f440f0e61e3e..6e8d33b50240 100644 --- a/fs/verity/init.c +++ b/fs/verity/init.c @@ -10,7 +10,7 @@ #include #ifdef CONFIG_SYSCTL -static struct ctl_table fsverity_sysctl_table[] = { +static const struct ctl_table fsverity_sysctl_table[] = { #ifdef CONFIG_FS_VERITY_BUILTIN_SIGNATURES { .procname = "require_signatures", diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c index c84df23b494d..751dc74a3067 100644 --- a/fs/xfs/xfs_sysctl.c +++ b/fs/xfs/xfs_sysctl.c @@ -66,7 +66,7 @@ xfs_deprecated_dointvec_minmax( return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos); } -static struct ctl_table xfs_table[] = { +static const struct ctl_table xfs_table[] = { { .procname = "irix_sgid_inherit", .data = &xfs_params.sgid_inherit.val, diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index f86ef92a6c46..f6867bad0d78 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -21,7 +21,7 @@ phys_addr_t phys_initrd_start __initdata; unsigned long phys_initrd_size __initdata; #ifdef CONFIG_SYSCTL -static struct ctl_table kern_do_mounts_initrd_table[] = { +static const struct ctl_table kern_do_mounts_initrd_table[] = { { .procname = "real-root-dev", .data = &real_root_dev, diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 7bfbc7c22367..5a0f8a5041d6 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -157,7 +157,7 @@ static int __read_mostly sysctl_io_uring_disabled; static int __read_mostly sysctl_io_uring_group = -1; #ifdef CONFIG_SYSCTL -static struct ctl_table kernel_io_uring_disabled_table[] = { +static const struct ctl_table kernel_io_uring_disabled_table[] = { { .procname = "io_uring_disabled", .data = &sysctl_io_uring_disabled, diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 54318e0b4557..15b17e86e198 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -73,7 +73,7 @@ int ipc_mni = IPCMNI; int ipc_mni_shift = IPCMNI_SHIFT; int ipc_min_cycle = RADIX_TREE_MAP_SIZE; -static struct ctl_table ipc_sysctls[] = { +static const struct ctl_table ipc_sysctls[] = { { .procname = "shmmax", .data = &init_ipc_ns.shm_ctlmax, diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c index b70dc2ff22d8..0dd12e1c9f53 100644 --- a/ipc/mq_sysctl.c +++ b/ipc/mq_sysctl.c @@ -20,7 +20,7 @@ static int msg_max_limit_max = HARD_MSGMAX; static int msg_maxsize_limit_min = MIN_MSGSIZEMAX; static int msg_maxsize_limit_max = HARD_MSGSIZEMAX; -static struct ctl_table mq_sysctls[] = { +static const struct ctl_table mq_sysctls[] = { { .procname = "queues_max", .data = &init_ipc_ns.mq_queues_max, diff --git a/kernel/acct.c b/kernel/acct.c index 179848ad33e9..31222e8cd534 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -76,7 +76,7 @@ static int acct_parm[3] = {4, 2, 30}; #define ACCT_TIMEOUT (acct_parm[2]) /* foo second timeout between checks */ #ifdef CONFIG_SYSCTL -static struct ctl_table kern_acct_table[] = { +static const struct ctl_table kern_acct_table[] = { { .procname = "acct", .data = &acct_parm, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0daf098e3207..c420edbfb7c8 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -6128,7 +6128,7 @@ static int bpf_unpriv_handler(const struct ctl_table *table, int write, return ret; } -static struct ctl_table bpf_syscall_table[] = { +static const struct ctl_table bpf_syscall_table[] = { { .procname = "unprivileged_bpf_disabled", .data = &sysctl_unprivileged_bpf_disabled, diff --git a/kernel/delayacct.c b/kernel/delayacct.c index b238eb8c6573..eb63a021ac04 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -64,7 +64,7 @@ static int sysctl_delayacct(const struct ctl_table *table, int write, void *buff return err; } -static struct ctl_table kern_delayacct_table[] = { +static const struct ctl_table kern_delayacct_table[] = { { .procname = "task_delayacct", .data = NULL, diff --git a/kernel/exit.c b/kernel/exit.c index 1dcddfe537ee..3485e5fc499e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -85,7 +85,7 @@ static unsigned int oops_limit = 10000; #ifdef CONFIG_SYSCTL -static struct ctl_table kern_exit_table[] = { +static const struct ctl_table kern_exit_table[] = { { .procname = "oops_limit", .data = &oops_limit, diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 953169893a95..04efa7a6e69b 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -274,7 +274,7 @@ static int proc_dohung_task_timeout_secs(const struct ctl_table *table, int writ * and hung_task_check_interval_secs */ static const unsigned long hung_task_timeout_max = (LONG_MAX / HZ); -static struct ctl_table hung_task_sysctls[] = { +static const struct ctl_table hung_task_sysctls[] = { #ifdef CONFIG_SMP { .procname = "hung_task_all_cpu_backtrace", diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index b424a5c6ae87..c0bdc1686154 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -925,7 +925,7 @@ static int kexec_limit_handler(const struct ctl_table *table, int write, return proc_dointvec(&tmp, write, buffer, lenp, ppos); } -static struct ctl_table kexec_core_sysctls[] = { +static const struct ctl_table kexec_core_sysctls[] = { { .procname = "kexec_load_disabled", .data = &kexec_load_disabled, diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 030569210670..88aeac84e4c0 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -946,7 +946,7 @@ static int proc_kprobes_optimization_handler(const struct ctl_table *table, return ret; } -static struct ctl_table kprobe_sysctls[] = { +static const struct ctl_table kprobe_sysctls[] = { { .procname = "kprobes-optimization", .data = &sysctl_kprobes_optimization, diff --git a/kernel/latencytop.c b/kernel/latencytop.c index 77ee3ea8a573..d4281d1e13a6 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -77,7 +77,7 @@ static int sysctl_latencytop(const struct ctl_table *table, int write, void *buf return err; } -static struct ctl_table latencytop_sysctl[] = { +static const struct ctl_table latencytop_sysctl[] = { { .procname = "latencytop", .data = &latencytop_enabled, diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 29acd238dad7..4470680f0226 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -79,7 +79,7 @@ module_param(lock_stat, int, 0644); #endif #ifdef CONFIG_SYSCTL -static struct ctl_table kern_lockdep_table[] = { +static const struct ctl_table kern_lockdep_table[] = { #ifdef CONFIG_PROVE_LOCKING { .procname = "prove_locking", diff --git a/kernel/panic.c b/kernel/panic.c index fbc59b3b64d0..d8635d5cecb2 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -84,7 +84,7 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); #ifdef CONFIG_SYSCTL -static struct ctl_table kern_panic_table[] = { +static const struct ctl_table kern_panic_table[] = { #ifdef CONFIG_SMP { .procname = "oops_all_cpu_backtrace", diff --git a/kernel/pid.c b/kernel/pid.c index 3a10a7b6fcf8..924084713be8 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -695,7 +695,7 @@ static struct ctl_table_root pid_table_root = { .set_ownership = pid_table_root_set_ownership, }; -static struct ctl_table pid_table[] = { +static const struct ctl_table pid_table[] = { { .procname = "pid_max", .data = &init_pid_ns.pid_max, diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index f1ffa032fc32..8f6cfec87555 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -303,7 +303,7 @@ static int pid_ns_ctl_handler(const struct ctl_table *table, int write, return ret; } -static struct ctl_table pid_ns_ctl_table[] = { +static const struct ctl_table pid_ns_ctl_table[] = { { .procname = "ns_last_pid", .maxlen = sizeof(int), diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h index 18ecaef6be41..5d8f981de7c5 100644 --- a/kernel/pid_sysctl.h +++ b/kernel/pid_sysctl.h @@ -31,7 +31,7 @@ static int pid_mfd_noexec_dointvec_minmax(const struct ctl_table *table, return err; } -static struct ctl_table pid_ns_ctl_table_vm[] = { +static const struct ctl_table pid_ns_ctl_table_vm[] = { { .procname = "memfd_noexec", .data = &init_pid_ns.memfd_noexec_scope, diff --git a/kernel/printk/sysctl.c b/kernel/printk/sysctl.c index f5072dc85f7a..da77f3f5c1fe 100644 --- a/kernel/printk/sysctl.c +++ b/kernel/printk/sysctl.c @@ -20,7 +20,7 @@ static int proc_dointvec_minmax_sysadmin(const struct ctl_table *table, int writ return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table printk_sysctls[] = { +static const struct ctl_table printk_sysctls[] = { { .procname = "printk", .data = &console_loglevel, diff --git a/kernel/reboot.c b/kernel/reboot.c index a701000bab34..b5a8569e5d81 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -1287,7 +1287,7 @@ static struct attribute *reboot_attrs[] = { }; #ifdef CONFIG_SYSCTL -static struct ctl_table kern_reboot_table[] = { +static const struct ctl_table kern_reboot_table[] = { { .procname = "poweroff_cmd", .data = &poweroff_cmd, diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index db68a964e34e..83d46b9b8ec8 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -9,7 +9,7 @@ static struct autogroup autogroup_default; static atomic_t autogroup_seq_nr; #ifdef CONFIG_SYSCTL -static struct ctl_table sched_autogroup_sysctls[] = { +static const struct ctl_table sched_autogroup_sysctls[] = { { .procname = "sched_autogroup_enabled", .data = &sysctl_sched_autogroup_enabled, diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9142a0394d46..165c90ba64ea 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4654,7 +4654,7 @@ static int sysctl_schedstats(const struct ctl_table *table, int write, void *buf #endif /* CONFIG_SCHEDSTATS */ #ifdef CONFIG_SYSCTL -static struct ctl_table sched_core_sysctls[] = { +static const struct ctl_table sched_core_sysctls[] = { #ifdef CONFIG_SCHEDSTATS { .procname = "sched_schedstats", diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 62192ac79c30..38e4537790af 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -26,7 +26,7 @@ static unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */ static unsigned int sysctl_sched_dl_period_min = 100; /* 100 us */ #ifdef CONFIG_SYSCTL -static struct ctl_table sched_dl_sysctls[] = { +static const struct ctl_table sched_dl_sysctls[] = { { .procname = "sched_deadline_period_max_us", .data = &sysctl_sched_dl_period_max, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1e78caa21436..ce2e94ccad0c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -133,7 +133,7 @@ static unsigned int sysctl_numa_balancing_promote_rate_limit = 65536; #endif #ifdef CONFIG_SYSCTL -static struct ctl_table sched_fair_sysctls[] = { +static const struct ctl_table sched_fair_sysctls[] = { #ifdef CONFIG_CFS_BANDWIDTH { .procname = "sched_cfs_bandwidth_slice_us", diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index bd66a46b06ac..4b8e33c615b1 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -26,7 +26,7 @@ static int sched_rt_handler(const struct ctl_table *table, int write, void *buff size_t *lenp, loff_t *ppos); static int sched_rr_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -static struct ctl_table sched_rt_sysctls[] = { +static const struct ctl_table sched_rt_sysctls[] = { { .procname = "sched_rt_period_us", .data = &sysctl_sched_rt_period, diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index da33ec9e94ab..c49aea8c1025 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -312,7 +312,7 @@ static int sched_energy_aware_handler(const struct ctl_table *table, int write, return ret; } -static struct ctl_table sched_energy_aware_sysctls[] = { +static const struct ctl_table sched_energy_aware_sysctls[] = { { .procname = "sched_energy_aware", .data = &sysctl_sched_energy_aware, diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 385d48293a5f..f59381c4a2ff 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -2450,7 +2450,7 @@ static int seccomp_actions_logged_handler(const struct ctl_table *ro_table, int return ret; } -static struct ctl_table seccomp_sysctl_table[] = { +static const struct ctl_table seccomp_sysctl_table[] = { { .procname = "actions_avail", .data = (void *) &seccomp_actions_avail, diff --git a/kernel/signal.c b/kernel/signal.c index a2afd54303f0..875e97f6205a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -4950,7 +4950,7 @@ static inline void siginfo_buildtime_checks(void) } #if defined(CONFIG_SYSCTL) -static struct ctl_table signal_debug_table[] = { +static const struct ctl_table signal_debug_table[] = { #ifdef CONFIG_SYSCTL_EXCEPTION_TRACE { .procname = "exception-trace", diff --git a/kernel/stackleak.c b/kernel/stackleak.c index 0f4804f28c61..bb65321761b4 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -45,7 +45,7 @@ static int stack_erasing_sysctl(const struct ctl_table *table, int write, str_enabled_disabled(state)); return ret; } -static struct ctl_table stackleak_sysctls[] = { +static const struct ctl_table stackleak_sysctls[] = { { .procname = "stack_erasing", .data = NULL, diff --git a/kernel/sysctl-test.c b/kernel/sysctl-test.c index 3ac98bb7fb82..eb2842bd0557 100644 --- a/kernel/sysctl-test.c +++ b/kernel/sysctl-test.c @@ -374,7 +374,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value( struct kunit *test) { unsigned char data = 0; - struct ctl_table table_foo[] = { + const struct ctl_table table_foo[] = { { .procname = "foo", .data = &data, @@ -386,7 +386,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value( }, }; - struct ctl_table table_bar[] = { + const struct ctl_table table_bar[] = { { .procname = "bar", .data = &data, @@ -398,7 +398,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value( }, }; - struct ctl_table table_qux[] = { + const struct ctl_table table_qux[] = { { .procname = "qux", .data = &data, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 7ae7a4136855..cb57da499ebb 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1609,7 +1609,7 @@ int proc_do_static_key(const struct ctl_table *table, int write, return ret; } -static struct ctl_table kern_table[] = { +static const struct ctl_table kern_table[] = { { .procname = "panic", .data = &panic_timeout, @@ -2021,7 +2021,7 @@ static struct ctl_table kern_table[] = { #endif }; -static struct ctl_table vm_table[] = { +static const struct ctl_table vm_table[] = { { .procname = "overcommit_memory", .data = &sysctl_overcommit_memory, diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 40706cb36920..c8f776dc6ee0 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -301,7 +301,7 @@ static int timer_migration_handler(const struct ctl_table *table, int write, return ret; } -static struct ctl_table timer_sysctl[] = { +static const struct ctl_table timer_sysctl[] = { { .procname = "timer_migration", .data = &sysctl_timer_migration, diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f79eb9386c7f..728ecda6e8d4 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -8780,7 +8780,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write, return 0; } -static struct ctl_table ftrace_sysctls[] = { +static const struct ctl_table ftrace_sysctls[] = { { .procname = "ftrace_enabled", .data = &ftrace_enabled, diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 17bcad8f79de..97325fbd6283 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -2899,7 +2899,7 @@ static int set_max_user_events_sysctl(const struct ctl_table *table, int write, return ret; } -static struct ctl_table user_event_sysctls[] = { +static const struct ctl_table user_event_sysctls[] = { { .procname = "user_events_max", .data = &max_user_events, diff --git a/kernel/umh.c b/kernel/umh.c index be9234270777..b4da45a3a7cf 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -544,7 +544,7 @@ static int proc_cap_handler(const struct ctl_table *table, int write, return 0; } -static struct ctl_table usermodehelper_table[] = { +static const struct ctl_table usermodehelper_table[] = { { .procname = "bset", .data = &usermodehelper_bset, diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index 7282f61a8650..bfbaaecb1dd4 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -75,7 +75,7 @@ static DEFINE_CTL_TABLE_POLL(hostname_poll); static DEFINE_CTL_TABLE_POLL(domainname_poll); // Note: update 'enum uts_proc' to match any changes to this table -static struct ctl_table uts_kern_table[] = { +static const struct ctl_table uts_kern_table[] = { { .procname = "arch", .data = init_uts_ns.name.machine, @@ -129,7 +129,7 @@ static struct ctl_table uts_kern_table[] = { */ void uts_proc_notify(enum uts_proc proc) { - struct ctl_table *table = &uts_kern_table[proc]; + const struct ctl_table *table = &uts_kern_table[proc]; proc_sys_poll_notify(table->poll); } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 177abb7d0d4e..b2da7de39d06 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -1094,7 +1094,7 @@ static int proc_watchdog_cpumask(const struct ctl_table *table, int write, static const int sixty = 60; -static struct ctl_table watchdog_sysctls[] = { +static const struct ctl_table watchdog_sysctls[] = { { .procname = "watchdog", .data = &watchdog_user_enabled, diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c index b6696fa1d426..4249e0cc8aaf 100644 --- a/lib/test_sysctl.c +++ b/lib/test_sysctl.c @@ -71,7 +71,7 @@ static struct test_sysctl_data test_data = { }; /* These are all under /proc/sys/debug/test_sysctl/ */ -static struct ctl_table test_table[] = { +static const struct ctl_table test_table[] = { { .procname = "int_0001", .data = &test_data.int_0001, @@ -177,7 +177,7 @@ static int test_sysctl_setup_node_tests(void) } /* Used to test that unregister actually removes the directory */ -static struct ctl_table test_table_unregister[] = { +static const struct ctl_table test_table_unregister[] = { { .procname = "unregister_error", .data = &test_data.int_0001, @@ -220,7 +220,7 @@ static int test_sysctl_run_register_mount_point(void) return 0; } -static struct ctl_table test_table_empty[] = { }; +static const struct ctl_table test_table_empty[] = { }; static int test_sysctl_run_register_empty(void) { diff --git a/mm/compaction.c b/mm/compaction.c index 73e80b2fb22e..bcc0df0066dc 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -3272,7 +3272,7 @@ static int proc_dointvec_minmax_warn_RT_change(const struct ctl_table *table, return ret; } -static struct ctl_table vm_compaction[] = { +static const struct ctl_table vm_compaction[] = { { .procname = "compact_memory", .data = &sysctl_compact_memory, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 87761b042ed0..3b25b69aa94f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4867,7 +4867,7 @@ out: return ret; } -static struct ctl_table hugetlb_table[] = { +static const struct ctl_table hugetlb_table[] = { { .procname = "nr_hugepages", .data = NULL, diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 57b7f591eee8..7735972add01 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -693,7 +693,7 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l free_vmemmap_page_list(&vmemmap_pages); } -static struct ctl_table hugetlb_vmemmap_sysctls[] = { +static const struct ctl_table hugetlb_vmemmap_sysctls[] = { { .procname = "hugetlb_optimize_vmemmap", .data = &vmemmap_optimize_enabled, diff --git a/mm/memory-failure.c b/mm/memory-failure.c index a7b8ccd29b6f..995a15eb67e2 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -124,7 +124,7 @@ const struct attribute_group memory_failure_attr_group = { .attrs = memory_failure_attr, }; -static struct ctl_table memory_failure_table[] = { +static const struct ctl_table memory_failure_table[] = { { .procname = "memory_failure_early_kill", .data = &sysctl_memory_failure_early_kill, diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 044ebab2c941..1cf121ad7085 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -705,7 +705,7 @@ static void queue_oom_reaper(struct task_struct *tsk) } #ifdef CONFIG_SYSCTL -static struct ctl_table vm_oom_kill_table[] = { +static const struct ctl_table vm_oom_kill_table[] = { { .procname = "panic_on_oom", .data = &sysctl_panic_on_oom, diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 4f5970723cf2..eb55ece39c56 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2298,7 +2298,7 @@ static int page_writeback_cpu_online(unsigned int cpu) /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE; -static struct ctl_table vm_page_writeback_sysctls[] = { +static const struct ctl_table vm_page_writeback_sysctls[] = { { .procname = "dirty_background_ratio", .data = &dirty_background_ratio, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6e469c7ef9a4..579789600a3c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6166,7 +6166,7 @@ out: return ret; } -static struct ctl_table page_alloc_sysctl_table[] = { +static const struct ctl_table page_alloc_sysctl_table[] = { { .procname = "min_free_kbytes", .data = &min_free_kbytes, diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 1edc12862a7d..9b6c2f157f83 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -2038,7 +2038,7 @@ static int apparmor_dointvec(const struct ctl_table *table, int write, return proc_dointvec(table, write, buffer, lenp, ppos); } -static struct ctl_table apparmor_sysctl_table[] = { +static const struct ctl_table apparmor_sysctl_table[] = { #ifdef CONFIG_USER_NS { .procname = "unprivileged_userns_apparmor_policy", diff --git a/security/keys/sysctl.c b/security/keys/sysctl.c index 91f000eef3ad..cde08c478f32 100644 --- a/security/keys/sysctl.c +++ b/security/keys/sysctl.c @@ -9,7 +9,7 @@ #include #include "internal.h" -static struct ctl_table key_sysctls[] = { +static const struct ctl_table key_sysctls[] = { { .procname = "maxkeys", .data = &key_quota_maxkeys, diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index 1a2d02fee09b..1971710620c1 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -452,7 +452,7 @@ static int yama_dointvec_minmax(const struct ctl_table *table, int write, static int max_scope = YAMA_SCOPE_NO_ATTACH; -static struct ctl_table yama_sysctl_table[] = { +static const struct ctl_table yama_sysctl_table[] = { { .procname = "ptrace_scope", .data = &ptrace_scope, -- cgit v1.2.3