summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit_fsnotify.c1
-rw-r--r--kernel/auditsc.c25
-rw-r--r--kernel/bpf/reuseport_array.c2
-rw-r--r--kernel/cgroup/cgroup-v1.c2
-rw-r--r--kernel/cgroup/cgroup.c80
-rw-r--r--kernel/cgroup/cpuset.c3
-rw-r--r--kernel/configs/xen.config1
-rw-r--r--kernel/kprobes.c9
-rw-r--r--kernel/module/main.c2
-rw-r--r--kernel/sched/psi.c10
-rw-r--r--kernel/sys_ni.c1
-rw-r--r--kernel/time/posix-stubs.c3
-rw-r--r--kernel/time/time.c4
-rw-r--r--kernel/trace/ftrace.c89
-rw-r--r--kernel/trace/trace_eprobe.c93
-rw-r--r--kernel/trace/trace_event_perf.c7
-rw-r--r--kernel/trace/trace_events.c1
-rw-r--r--kernel/trace/trace_probe.c29
18 files changed, 227 insertions, 135 deletions
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index 6432a37ac1c9..c565fbf66ac8 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -102,6 +102,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa
ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, 0);
if (ret < 0) {
+ audit_mark->path = NULL;
fsnotify_put_mark(&audit_mark->mark);
audit_mark = ERR_PTR(ret);
}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 3a8c9d744800..dd8d9ab747c3 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1073,31 +1073,6 @@ int audit_alloc(struct task_struct *tsk)
return 0;
}
-/**
- * audit_alloc_kernel - allocate an audit_context for a kernel task
- * @tsk: the kernel task
- *
- * Similar to the audit_alloc() function, but intended for kernel private
- * threads. Returns zero on success, negative values on failure.
- */
-int audit_alloc_kernel(struct task_struct *tsk)
-{
- /*
- * At the moment we are just going to call into audit_alloc() to
- * simplify the code, but there two things to keep in mind with this
- * approach:
- *
- * 1. Filtering internal kernel tasks is a bit laughable in almost all
- * cases, but there is at least one case where there is a benefit:
- * the '-a task,never' case allows the admin to effectively disable
- * task auditing at runtime.
- *
- * 2. The {set,clear}_task_syscall_work() ops likely have zero effect
- * on these internal kernel tasks, but they probably don't hurt either.
- */
- return audit_alloc(tsk);
-}
-
static inline void audit_free_context(struct audit_context *context)
{
/* resetting is extra work, but it is likely just noise */
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 85fa9dbfa8bf..82c61612f382 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -24,7 +24,7 @@ void bpf_sk_reuseport_detach(struct sock *sk)
struct sock __rcu **socks;
write_lock_bh(&sk->sk_callback_lock);
- socks = __rcu_dereference_sk_user_data_with_flags(sk, SK_USER_DATA_BPF);
+ socks = __locked_read_sk_user_data_with_flags(sk, SK_USER_DATA_BPF);
if (socks) {
WRITE_ONCE(sk->sk_user_data, NULL);
/*
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 2ade21b54dc4..ff6a8099eb2a 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -59,6 +59,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
int retval = 0;
mutex_lock(&cgroup_mutex);
+ cpus_read_lock();
percpu_down_write(&cgroup_threadgroup_rwsem);
for_each_root(root) {
struct cgroup *from_cgrp;
@@ -72,6 +73,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
break;
}
percpu_up_write(&cgroup_threadgroup_rwsem);
+ cpus_read_unlock();
mutex_unlock(&cgroup_mutex);
return retval;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index ffaccd6373f1..e4bb5d57f4d1 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1820,6 +1820,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
if (ss->css_rstat_flush) {
list_del_rcu(&css->rstat_css_node);
+ synchronize_rcu();
list_add_rcu(&css->rstat_css_node,
&dcgrp->rstat_css_list);
}
@@ -2370,6 +2371,47 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
EXPORT_SYMBOL_GPL(task_cgroup_path);
/**
+ * cgroup_attach_lock - Lock for ->attach()
+ * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem
+ *
+ * cgroup migration sometimes needs to stabilize threadgroups against forks and
+ * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach()
+ * implementations (e.g. cpuset), also need to disable CPU hotplug.
+ * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can
+ * lead to deadlocks.
+ *
+ * Bringing up a CPU may involve creating and destroying tasks which requires
+ * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside
+ * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while
+ * write-locking threadgroup_rwsem, the locking order is reversed and we end up
+ * waiting for an on-going CPU hotplug operation which in turn is waiting for
+ * the threadgroup_rwsem to be released to create new tasks. For more details:
+ *
+ * http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu
+ *
+ * Resolve the situation by always acquiring cpus_read_lock() before optionally
+ * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that
+ * CPU hotplug is disabled on entry.
+ */
+static void cgroup_attach_lock(bool lock_threadgroup)
+{
+ cpus_read_lock();
+ if (lock_threadgroup)
+ percpu_down_write(&cgroup_threadgroup_rwsem);
+}
+
+/**
+ * cgroup_attach_unlock - Undo cgroup_attach_lock()
+ * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem
+ */
+static void cgroup_attach_unlock(bool lock_threadgroup)
+{
+ if (lock_threadgroup)
+ percpu_up_write(&cgroup_threadgroup_rwsem);
+ cpus_read_unlock();
+}
+
+/**
* cgroup_migrate_add_task - add a migration target task to a migration context
* @task: target task
* @mgctx: target migration context
@@ -2841,8 +2883,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
}
struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
- bool *locked)
- __acquires(&cgroup_threadgroup_rwsem)
+ bool *threadgroup_locked)
{
struct task_struct *tsk;
pid_t pid;
@@ -2859,12 +2900,8 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
* Therefore, we can skip the global lock.
*/
lockdep_assert_held(&cgroup_mutex);
- if (pid || threadgroup) {
- percpu_down_write(&cgroup_threadgroup_rwsem);
- *locked = true;
- } else {
- *locked = false;
- }
+ *threadgroup_locked = pid || threadgroup;
+ cgroup_attach_lock(*threadgroup_locked);
rcu_read_lock();
if (pid) {
@@ -2895,17 +2932,14 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
goto out_unlock_rcu;
out_unlock_threadgroup:
- if (*locked) {
- percpu_up_write(&cgroup_threadgroup_rwsem);
- *locked = false;
- }
+ cgroup_attach_unlock(*threadgroup_locked);
+ *threadgroup_locked = false;
out_unlock_rcu:
rcu_read_unlock();
return tsk;
}
-void cgroup_procs_write_finish(struct task_struct *task, bool locked)
- __releases(&cgroup_threadgroup_rwsem)
+void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked)
{
struct cgroup_subsys *ss;
int ssid;
@@ -2913,8 +2947,8 @@ void cgroup_procs_write_finish(struct task_struct *task, bool locked)
/* release reference from cgroup_procs_write_start() */
put_task_struct(task);
- if (locked)
- percpu_up_write(&cgroup_threadgroup_rwsem);
+ cgroup_attach_unlock(threadgroup_locked);
+
for_each_subsys(ss, ssid)
if (ss->post_attach)
ss->post_attach();
@@ -3000,8 +3034,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
* write-locking can be skipped safely.
*/
has_tasks = !list_empty(&mgctx.preloaded_src_csets);
- if (has_tasks)
- percpu_down_write(&cgroup_threadgroup_rwsem);
+ cgroup_attach_lock(has_tasks);
/* NULL dst indicates self on default hierarchy */
ret = cgroup_migrate_prepare_dst(&mgctx);
@@ -3022,8 +3055,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
ret = cgroup_migrate_execute(&mgctx);
out_finish:
cgroup_migrate_finish(&mgctx);
- if (has_tasks)
- percpu_up_write(&cgroup_threadgroup_rwsem);
+ cgroup_attach_unlock(has_tasks);
return ret;
}
@@ -3698,7 +3730,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
}
psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
- new = psi_trigger_create(psi, buf, nbytes, res);
+ new = psi_trigger_create(psi, buf, res);
if (IS_ERR(new)) {
cgroup_put(cgrp);
return PTR_ERR(new);
@@ -4971,13 +5003,13 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
struct task_struct *task;
const struct cred *saved_cred;
ssize_t ret;
- bool locked;
+ bool threadgroup_locked;
dst_cgrp = cgroup_kn_lock_live(of->kn, false);
if (!dst_cgrp)
return -ENODEV;
- task = cgroup_procs_write_start(buf, threadgroup, &locked);
+ task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked);
ret = PTR_ERR_OR_ZERO(task);
if (ret)
goto out_unlock;
@@ -5003,7 +5035,7 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
ret = cgroup_attach_task(dst_cgrp, task, threadgroup);
out_finish:
- cgroup_procs_write_finish(task, locked);
+ cgroup_procs_write_finish(task, threadgroup_locked);
out_unlock:
cgroup_kn_unlock(of->kn);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 58aadfda9b8b..1f3a55297f39 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2289,7 +2289,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
cgroup_taskset_first(tset, &css);
cs = css_cs(css);
- cpus_read_lock();
+ lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */
percpu_down_write(&cpuset_rwsem);
guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
@@ -2343,7 +2343,6 @@ static void cpuset_attach(struct cgroup_taskset *tset)
wake_up(&cpuset_attach_wq);
percpu_up_write(&cpuset_rwsem);
- cpus_read_unlock();
}
/* The various types of files and directories in a cpuset file system */
diff --git a/kernel/configs/xen.config b/kernel/configs/xen.config
index ff756221f112..436f806aa1ed 100644
--- a/kernel/configs/xen.config
+++ b/kernel/configs/xen.config
@@ -34,7 +34,6 @@ CONFIG_INPUT_XEN_KBDDEV_FRONTEND=m
CONFIG_XEN_SCSI_FRONTEND=m
# others
CONFIG_XEN_BALLOON=y
-CONFIG_XEN_SCRUB_PAGES=y
CONFIG_XEN_DEV_EVTCHN=m
CONFIG_XEN_BLKDEV_FRONTEND=m
CONFIG_XEN_NETDEV_FRONTEND=m
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 80697e5e03e4..08350e35aba2 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1707,11 +1707,12 @@ static struct kprobe *__disable_kprobe(struct kprobe *p)
/* Try to disarm and disable this/parent probe */
if (p == orig_p || aggr_kprobe_disabled(orig_p)) {
/*
- * If 'kprobes_all_disarmed' is set, 'orig_p'
- * should have already been disarmed, so
- * skip unneed disarming process.
+ * Don't be lazy here. Even if 'kprobes_all_disarmed'
+ * is false, 'orig_p' might not have been armed yet.
+ * Note arm_all_kprobes() __tries__ to arm all kprobes
+ * on the best effort basis.
*/
- if (!kprobes_all_disarmed) {
+ if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) {
ret = disarm_kprobe(orig_p, true);
if (ret) {
p->flags &= ~KPROBE_FLAG_DISABLED;
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 6a477c622544..a4e4d84b6f4e 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2099,7 +2099,7 @@ static int find_module_sections(struct module *mod, struct load_info *info)
sizeof(*mod->static_call_sites),
&mod->num_static_call_sites);
#endif
-#ifdef CONFIG_KUNIT
+#if IS_ENABLED(CONFIG_KUNIT)
mod->kunit_suites = section_objs(info, ".kunit_test_suites",
sizeof(*mod->kunit_suites),
&mod->num_kunit_suites);
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index ec66b40bdd40..ecb4b4ff4ce0 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -190,12 +190,8 @@ static void group_init(struct psi_group *group)
/* Init trigger-related members */
mutex_init(&group->trigger_lock);
INIT_LIST_HEAD(&group->triggers);
- memset(group->nr_triggers, 0, sizeof(group->nr_triggers));
- group->poll_states = 0;
group->poll_min_period = U32_MAX;
- memset(group->polling_total, 0, sizeof(group->polling_total));
group->polling_next_update = ULLONG_MAX;
- group->polling_until = 0;
init_waitqueue_head(&group->poll_wait);
timer_setup(&group->poll_timer, poll_timer_fn, 0);
rcu_assign_pointer(group->poll_task, NULL);
@@ -957,7 +953,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup)
if (static_branch_likely(&psi_disabled))
return 0;
- cgroup->psi = kmalloc(sizeof(struct psi_group), GFP_KERNEL);
+ cgroup->psi = kzalloc(sizeof(struct psi_group), GFP_KERNEL);
if (!cgroup->psi)
return -ENOMEM;
@@ -1091,7 +1087,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
}
struct psi_trigger *psi_trigger_create(struct psi_group *group,
- char *buf, size_t nbytes, enum psi_res res)
+ char *buf, enum psi_res res)
{
struct psi_trigger *t;
enum psi_states state;
@@ -1320,7 +1316,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
return -EBUSY;
}
- new = psi_trigger_create(&psi_system, buf, nbytes, res);
+ new = psi_trigger_create(&psi_system, buf, res);
if (IS_ERR(new)) {
mutex_unlock(&seq->lock);
return PTR_ERR(new);
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index a492f159624f..860b2dcf3ac4 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -277,6 +277,7 @@ COND_SYSCALL(landlock_restrict_self);
/* mm/fadvise.c */
COND_SYSCALL(fadvise64_64);
+COND_SYSCALL_COMPAT(fadvise64_64);
/* mm/, CONFIG_MMU only */
COND_SYSCALL(swapon);
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index fcb3b21d8bdc..90ea5f373e50 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -70,7 +70,7 @@ SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
return do_sys_settimeofday64(&new_tp, NULL);
}
-int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
+static int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
{
switch (which_clock) {
case CLOCK_REALTIME:
@@ -90,6 +90,7 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
return 0;
}
+
SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
struct __kernel_timespec __user *, tp)
{
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 29923b20e0e4..526257b3727c 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -449,7 +449,7 @@ time64_t mktime64(const unsigned int year0, const unsigned int mon0,
}
EXPORT_SYMBOL(mktime64);
-struct __kernel_old_timeval ns_to_kernel_old_timeval(const s64 nsec)
+struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec)
{
struct timespec64 ts = ns_to_timespec64(nsec);
struct __kernel_old_timeval tv;
@@ -503,7 +503,7 @@ EXPORT_SYMBOL(set_normalized_timespec64);
*
* Returns the timespec64 representation of the nsec parameter.
*/
-struct timespec64 ns_to_timespec64(const s64 nsec)
+struct timespec64 ns_to_timespec64(s64 nsec)
{
struct timespec64 ts = { 0, 0 };
s32 rem;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index bc921a3f7ea8..439e2ab6905e 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1861,8 +1861,6 @@ static void ftrace_hash_rec_enable_modify(struct ftrace_ops *ops,
ftrace_hash_rec_update_modify(ops, filter_hash, 1);
}
-static bool ops_references_ip(struct ftrace_ops *ops, unsigned long ip);
-
/*
* Try to update IPMODIFY flag on each ftrace_rec. Return 0 if it is OK
* or no-needed to update, -EBUSY if it detects a conflict of the flag
@@ -2974,6 +2972,16 @@ int ftrace_startup(struct ftrace_ops *ops, int command)
ftrace_startup_enable(command);
+ /*
+ * If ftrace is in an undefined state, we just remove ops from list
+ * to prevent the NULL pointer, instead of totally rolling it back and
+ * free trampoline, because those actions could cause further damage.
+ */
+ if (unlikely(ftrace_disabled)) {
+ __unregister_ftrace_function(ops);
+ return -ENODEV;
+ }
+
ops->flags &= ~FTRACE_OPS_FL_ADDING;
return 0;
@@ -3108,49 +3116,6 @@ static inline int ops_traces_mod(struct ftrace_ops *ops)
ftrace_hash_empty(ops->func_hash->notrace_hash);
}
-/*
- * Check if the current ops references the given ip.
- *
- * If the ops traces all functions, then it was already accounted for.
- * If the ops does not trace the current record function, skip it.
- * If the ops ignores the function via notrace filter, skip it.
- */
-static bool
-ops_references_ip(struct ftrace_ops *ops, unsigned long ip)
-{
- /* If ops isn't enabled, ignore it */
- if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
- return false;
-
- /* If ops traces all then it includes this function */
- if (ops_traces_mod(ops))
- return true;
-
- /* The function must be in the filter */
- if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
- !__ftrace_lookup_ip(ops->func_hash->filter_hash, ip))
- return false;
-
- /* If in notrace hash, we ignore it too */
- if (ftrace_lookup_ip(ops->func_hash->notrace_hash, ip))
- return false;
-
- return true;
-}
-
-/*
- * Check if the current ops references the record.
- *
- * If the ops traces all functions, then it was already accounted for.
- * If the ops does not trace the current record function, skip it.
- * If the ops ignores the function via notrace filter, skip it.
- */
-static bool
-ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec)
-{
- return ops_references_ip(ops, rec->ip);
-}
-
static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
{
bool init_nop = ftrace_need_init_nop();
@@ -6812,6 +6777,38 @@ static int ftrace_get_trampoline_kallsym(unsigned int symnum,
return -ERANGE;
}
+#if defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS) || defined(CONFIG_MODULES)
+/*
+ * Check if the current ops references the given ip.
+ *
+ * If the ops traces all functions, then it was already accounted for.
+ * If the ops does not trace the current record function, skip it.
+ * If the ops ignores the function via notrace filter, skip it.
+ */
+static bool
+ops_references_ip(struct ftrace_ops *ops, unsigned long ip)
+{
+ /* If ops isn't enabled, ignore it */
+ if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+ return false;
+
+ /* If ops traces all then it includes this function */
+ if (ops_traces_mod(ops))
+ return true;
+
+ /* The function must be in the filter */
+ if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
+ !__ftrace_lookup_ip(ops->func_hash->filter_hash, ip))
+ return false;
+
+ /* If in notrace hash, we ignore it too */
+ if (ftrace_lookup_ip(ops->func_hash->notrace_hash, ip))
+ return false;
+
+ return true;
+}
+#endif
+
#ifdef CONFIG_MODULES
#define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next)
@@ -6824,7 +6821,7 @@ static int referenced_filters(struct dyn_ftrace *rec)
int cnt = 0;
for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) {
- if (ops_references_rec(ops, rec)) {
+ if (ops_references_ip(ops, rec->ip)) {
if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_DIRECT))
continue;
if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_IPMODIFY))
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 4a0e9d927443..1783e3478912 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -227,6 +227,7 @@ static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i)
struct probe_arg *parg = &ep->tp.args[i];
struct ftrace_event_field *field;
struct list_head *head;
+ int ret = -ENOENT;
head = trace_get_fields(ep->event);
list_for_each_entry(field, head, link) {
@@ -236,9 +237,20 @@ static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i)
return 0;
}
}
+
+ /*
+ * Argument not found on event. But allow for comm and COMM
+ * to be used to get the current->comm.
+ */
+ if (strcmp(parg->code->data, "COMM") == 0 ||
+ strcmp(parg->code->data, "comm") == 0) {
+ parg->code->op = FETCH_OP_COMM;
+ ret = 0;
+ }
+
kfree(parg->code->data);
parg->code->data = NULL;
- return -ENOENT;
+ return ret;
}
static int eprobe_event_define_fields(struct trace_event_call *event_call)
@@ -311,6 +323,27 @@ static unsigned long get_event_field(struct fetch_insn *code, void *rec)
addr = rec + field->offset;
+ if (is_string_field(field)) {
+ switch (field->filter_type) {
+ case FILTER_DYN_STRING:
+ val = (unsigned long)(rec + (*(unsigned int *)addr & 0xffff));
+ break;
+ case FILTER_RDYN_STRING:
+ val = (unsigned long)(addr + (*(unsigned int *)addr & 0xffff));
+ break;
+ case FILTER_STATIC_STRING:
+ val = (unsigned long)addr;
+ break;
+ case FILTER_PTR_STRING:
+ val = (unsigned long)(*(char *)addr);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ return 0;
+ }
+ return val;
+ }
+
switch (field->size) {
case 1:
if (field->is_signed)
@@ -342,16 +375,38 @@ static unsigned long get_event_field(struct fetch_insn *code, void *rec)
static int get_eprobe_size(struct trace_probe *tp, void *rec)
{
+ struct fetch_insn *code;
struct probe_arg *arg;
int i, len, ret = 0;
for (i = 0; i < tp->nr_args; i++) {
arg = tp->args + i;
- if (unlikely(arg->dynamic)) {
+ if (arg->dynamic) {
unsigned long val;
- val = get_event_field(arg->code, rec);
- len = process_fetch_insn_bottom(arg->code + 1, val, NULL, NULL);
+ code = arg->code;
+ retry:
+ switch (code->op) {
+ case FETCH_OP_TP_ARG:
+ val = get_event_field(code, rec);
+ break;
+ case FETCH_OP_IMM:
+ val = code->immediate;
+ break;
+ case FETCH_OP_COMM:
+ val = (unsigned long)current->comm;
+ break;
+ case FETCH_OP_DATA:
+ val = (unsigned long)code->data;
+ break;
+ case FETCH_NOP_SYMBOL: /* Ignore a place holder */
+ code++;
+ goto retry;
+ default:
+ continue;
+ }
+ code++;
+ len = process_fetch_insn_bottom(code, val, NULL, NULL);
if (len > 0)
ret += len;
}
@@ -369,8 +424,28 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *dest,
{
unsigned long val;
- val = get_event_field(code, rec);
- return process_fetch_insn_bottom(code + 1, val, dest, base);
+ retry:
+ switch (code->op) {
+ case FETCH_OP_TP_ARG:
+ val = get_event_field(code, rec);
+ break;
+ case FETCH_OP_IMM:
+ val = code->immediate;
+ break;
+ case FETCH_OP_COMM:
+ val = (unsigned long)current->comm;
+ break;
+ case FETCH_OP_DATA:
+ val = (unsigned long)code->data;
+ break;
+ case FETCH_NOP_SYMBOL: /* Ignore a place holder */
+ code++;
+ goto retry;
+ default:
+ return -EILSEQ;
+ }
+ code++;
+ return process_fetch_insn_bottom(code, val, dest, base);
}
NOKPROBE_SYMBOL(process_fetch_insn)
@@ -845,6 +920,10 @@ static int trace_eprobe_tp_update_arg(struct trace_eprobe *ep, const char *argv[
trace_probe_log_err(0, BAD_ATTACH_ARG);
}
+ /* Handle symbols "@" */
+ if (!ret)
+ ret = traceprobe_update_arg(&ep->tp.args[i]);
+
return ret;
}
@@ -883,7 +962,7 @@ static int __trace_eprobe_create(int argc, const char *argv[])
trace_probe_log_set_index(1);
sys_event = argv[1];
ret = traceprobe_parse_event_name(&sys_event, &sys_name, buf2, 0);
- if (!sys_event || !sys_name) {
+ if (ret || !sys_event || !sys_name) {
trace_probe_log_err(0, NO_EVENT_INFO);
goto parse_error;
}
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index a114549720d6..61e3a2620fa3 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -157,7 +157,7 @@ static void perf_trace_event_unreg(struct perf_event *p_event)
int i;
if (--tp_event->perf_refcount > 0)
- goto out;
+ return;
tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL);
@@ -176,8 +176,6 @@ static void perf_trace_event_unreg(struct perf_event *p_event)
perf_trace_buf[i] = NULL;
}
}
-out:
- trace_event_put_ref(tp_event);
}
static int perf_trace_event_open(struct perf_event *p_event)
@@ -241,6 +239,7 @@ void perf_trace_destroy(struct perf_event *p_event)
mutex_lock(&event_mutex);
perf_trace_event_close(p_event);
perf_trace_event_unreg(p_event);
+ trace_event_put_ref(p_event->tp_event);
mutex_unlock(&event_mutex);
}
@@ -292,6 +291,7 @@ void perf_kprobe_destroy(struct perf_event *p_event)
mutex_lock(&event_mutex);
perf_trace_event_close(p_event);
perf_trace_event_unreg(p_event);
+ trace_event_put_ref(p_event->tp_event);
mutex_unlock(&event_mutex);
destroy_local_trace_kprobe(p_event->tp_event);
@@ -347,6 +347,7 @@ void perf_uprobe_destroy(struct perf_event *p_event)
mutex_lock(&event_mutex);
perf_trace_event_close(p_event);
perf_trace_event_unreg(p_event);
+ trace_event_put_ref(p_event->tp_event);
mutex_unlock(&event_mutex);
destroy_local_trace_uprobe(p_event->tp_event);
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 181f08186d32..0356cae0cf74 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -176,6 +176,7 @@ static int trace_define_generic_fields(void)
__generic_field(int, CPU, FILTER_CPU);
__generic_field(int, cpu, FILTER_CPU);
+ __generic_field(int, common_cpu, FILTER_CPU);
__generic_field(char *, COMM, FILTER_COMM);
__generic_field(char *, comm, FILTER_COMM);
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 850a88abd33b..36dff277de46 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -283,7 +283,14 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
int ret = 0;
int len;
- if (strcmp(arg, "retval") == 0) {
+ if (flags & TPARG_FL_TPOINT) {
+ if (code->data)
+ return -EFAULT;
+ code->data = kstrdup(arg, GFP_KERNEL);
+ if (!code->data)
+ return -ENOMEM;
+ code->op = FETCH_OP_TP_ARG;
+ } else if (strcmp(arg, "retval") == 0) {
if (flags & TPARG_FL_RETURN) {
code->op = FETCH_OP_RETVAL;
} else {
@@ -307,7 +314,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
}
} else
goto inval_var;
- } else if (strcmp(arg, "comm") == 0) {
+ } else if (strcmp(arg, "comm") == 0 || strcmp(arg, "COMM") == 0) {
code->op = FETCH_OP_COMM;
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
} else if (((flags & TPARG_FL_MASK) ==
@@ -323,13 +330,6 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
code->op = FETCH_OP_ARG;
code->param = (unsigned int)param - 1;
#endif
- } else if (flags & TPARG_FL_TPOINT) {
- if (code->data)
- return -EFAULT;
- code->data = kstrdup(arg, GFP_KERNEL);
- if (!code->data)
- return -ENOMEM;
- code->op = FETCH_OP_TP_ARG;
} else
goto inval_var;
@@ -384,6 +384,11 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
break;
case '%': /* named register */
+ if (flags & TPARG_FL_TPOINT) {
+ /* eprobes do not handle registers */
+ trace_probe_log_err(offs, BAD_VAR);
+ break;
+ }
ret = regs_query_register_offset(arg + 1);
if (ret >= 0) {
code->op = FETCH_OP_REG;
@@ -617,9 +622,11 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
/*
* Since $comm and immediate string can not be dereferenced,
- * we can find those by strcmp.
+ * we can find those by strcmp. But ignore for eprobes.
*/
- if (strcmp(arg, "$comm") == 0 || strncmp(arg, "\\\"", 2) == 0) {
+ if (!(flags & TPARG_FL_TPOINT) &&
+ (strcmp(arg, "$comm") == 0 || strcmp(arg, "$COMM") == 0 ||
+ strncmp(arg, "\\\"", 2) == 0)) {
/* The type of $comm must be "string", and not an array. */
if (parg->count || (t && strcmp(t, "string")))
goto out;
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-24 12:10:45 +0000