aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/trace
diff options
context:
space:
mode:
authorDmitry Torokhov <dmitry.torokhov@gmail.com>2019-11-25 13:26:56 -0800
committerDmitry Torokhov <dmitry.torokhov@gmail.com>2019-11-25 13:26:56 -0800
commit976e3645923bdd2fe7893aae33fd7a21098bfb28 (patch)
treed1cb24e4c9743beef15a4796070aca7e2c08228a /kernel/trace
parentRevert "Input: synaptics - enable RMI mode for X1 Extreme 2nd Generation" (diff)
parentInput: synaptics-rmi4 - fix various V4L2 compliance problems in F54 (diff)
Merge branch 'next' into for-linus
Prepare input updates for 5.5 merge window.
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig9
-rw-r--r--kernel/trace/bpf_trace.c36
-rw-r--r--kernel/trace/fgraph.c4
-rw-r--r--kernel/trace/ftrace.c80
-rw-r--r--kernel/trace/ftrace_internal.h8
-rw-r--r--kernel/trace/ring_buffer_benchmark.c2
-rw-r--r--kernel/trace/trace.c183
-rw-r--r--kernel/trace/trace.h13
-rw-r--r--kernel/trace/trace_dynevent.c14
-rw-r--r--kernel/trace/trace_dynevent.h7
-rw-r--r--kernel/trace/trace_event_perf.c4
-rw-r--r--kernel/trace/trace_events.c41
-rw-r--r--kernel/trace/trace_events_filter.c6
-rw-r--r--kernel/trace/trace_events_hist.c40
-rw-r--r--kernel/trace/trace_events_trigger.c8
-rw-r--r--kernel/trace/trace_hwlat.c4
-rw-r--r--kernel/trace/trace_kprobe.c284
-rw-r--r--kernel/trace/trace_output.c6
-rw-r--r--kernel/trace/trace_printk.c7
-rw-r--r--kernel/trace/trace_probe.c193
-rw-r--r--kernel/trace/trace_probe.h68
-rw-r--r--kernel/trace/trace_sched_wakeup.c3
-rw-r--r--kernel/trace/trace_stack.c120
-rw-r--r--kernel/trace/trace_stat.c6
-rw-r--r--kernel/trace/trace_uprobe.c311
25 files changed, 1153 insertions, 304 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 98da8998c25c..e08527f50d2a 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -146,7 +146,7 @@ config FUNCTION_TRACER
select GENERIC_TRACER
select CONTEXT_SWITCH_TRACER
select GLOB
- select TASKS_RCU if PREEMPT
+ select TASKS_RCU if PREEMPTION
help
Enable the kernel to trace every kernel function. This is done
by using a compiler feature to insert a small, 5-byte No-Operation
@@ -179,7 +179,7 @@ config TRACE_PREEMPT_TOGGLE
config PREEMPTIRQ_EVENTS
bool "Enable trace events for preempt and irq disable/enable"
select TRACE_IRQFLAGS
- select TRACE_PREEMPT_TOGGLE if PREEMPT
+ select TRACE_PREEMPT_TOGGLE if PREEMPTION
select GENERIC_TRACER
default n
help
@@ -214,7 +214,7 @@ config PREEMPT_TRACER
bool "Preemption-off Latency Tracer"
default n
depends on !ARCH_USES_GETTIMEOFFSET
- depends on PREEMPT
+ depends on PREEMPTION
select GENERIC_TRACER
select TRACER_MAX_TRACE
select RING_BUFFER_ALLOW_SWAP
@@ -520,7 +520,8 @@ config BPF_EVENTS
bool
default y
help
- This allows the user to attach BPF programs to kprobe events.
+ This allows the user to attach BPF programs to kprobe, uprobe, and
+ tracepoint events.
config DYNAMIC_EVENTS
def_bool n
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index ca1255d14576..44bd08f2443b 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -142,8 +142,13 @@ BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr)
{
int ret;
+ ret = security_locked_down(LOCKDOWN_BPF_READ);
+ if (ret < 0)
+ goto out;
+
ret = probe_kernel_read(dst, unsafe_ptr, size);
if (unlikely(ret < 0))
+out:
memset(dst, 0, size);
return ret;
@@ -500,14 +505,17 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
-static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs);
-static DEFINE_PER_CPU(struct perf_sample_data, bpf_misc_sd);
+static DEFINE_PER_CPU(int, bpf_event_output_nest_level);
+struct bpf_nested_pt_regs {
+ struct pt_regs regs[3];
+};
+static DEFINE_PER_CPU(struct bpf_nested_pt_regs, bpf_pt_regs);
+static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds);
u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
{
- struct perf_sample_data *sd = this_cpu_ptr(&bpf_misc_sd);
- struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs);
+ int nest_level = this_cpu_inc_return(bpf_event_output_nest_level);
struct perf_raw_frag frag = {
.copy = ctx_copy,
.size = ctx_size,
@@ -522,12 +530,25 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
.data = meta,
},
};
+ struct perf_sample_data *sd;
+ struct pt_regs *regs;
+ u64 ret;
+
+ if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) {
+ ret = -EBUSY;
+ goto out;
+ }
+ sd = this_cpu_ptr(&bpf_misc_sds.sds[nest_level - 1]);
+ regs = this_cpu_ptr(&bpf_pt_regs.regs[nest_level - 1]);
perf_fetch_caller_regs(regs);
perf_sample_data_init(sd, 0, 0);
sd->raw = &raw;
- return __bpf_perf_event_output(regs, map, flags, sd);
+ ret = __bpf_perf_event_output(regs, map, flags, sd);
+out:
+ this_cpu_dec(bpf_event_output_nest_level);
+ return ret;
}
BPF_CALL_0(bpf_get_current_task)
@@ -569,6 +590,10 @@ BPF_CALL_3(bpf_probe_read_str, void *, dst, u32, size,
{
int ret;
+ ret = security_locked_down(LOCKDOWN_BPF_READ);
+ if (ret < 0)
+ goto out;
+
/*
* The strncpy_from_unsafe() call will likely not fill the entire
* buffer, but that's okay in this circumstance as we're probing
@@ -580,6 +605,7 @@ BPF_CALL_3(bpf_probe_read_str, void *, dst, u32, size,
*/
ret = strncpy_from_unsafe(dst, unsafe_ptr, size);
if (unlikely(ret < 0))
+out:
memset(dst, 0, size);
return ret;
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 8dfd5021b933..7950a0356042 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -276,7 +276,7 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
int index = task->curr_ret_stack;
int i;
- if (ret != (unsigned long)return_to_handler)
+ if (ret != (unsigned long)dereference_kernel_function_descriptor(return_to_handler))
return ret;
if (index < 0)
@@ -294,7 +294,7 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
{
int task_idx;
- if (ret != (unsigned long)return_to_handler)
+ if (ret != (unsigned long)dereference_kernel_function_descriptor(return_to_handler))
return ret;
task_idx = task->curr_ret_stack;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index eca34503f178..f296d89be757 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -18,6 +18,7 @@
#include <linux/clocksource.h>
#include <linux/sched/task.h>
#include <linux/kallsyms.h>
+#include <linux/security.h>
#include <linux/seq_file.h>
#include <linux/tracefs.h>
#include <linux/hardirq.h>
@@ -2814,7 +2815,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
* synchornize_rcu_tasks() will wait for those tasks to
* execute and either schedule voluntarily or enter user space.
*/
- if (IS_ENABLED(CONFIG_PREEMPT))
+ if (IS_ENABLED(CONFIG_PREEMPTION))
synchronize_rcu_tasks();
free_ops:
@@ -3095,6 +3096,14 @@ t_probe_next(struct seq_file *m, loff_t *pos)
hnd = &iter->probe_entry->hlist;
hash = iter->probe->ops.func_hash->filter_hash;
+
+ /*
+ * A probe being registered may temporarily have an empty hash
+ * and it's at the end of the func_probes list.
+ */
+ if (!hash || hash == EMPTY_HASH)
+ return NULL;
+
size = 1 << hash->size_bits;
retry:
@@ -3478,6 +3487,11 @@ static int
ftrace_avail_open(struct inode *inode, struct file *file)
{
struct ftrace_iterator *iter;
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
if (unlikely(ftrace_disabled))
return -ENODEV;
@@ -3497,6 +3511,15 @@ ftrace_enabled_open(struct inode *inode, struct file *file)
{
struct ftrace_iterator *iter;
+ /*
+ * This shows us what functions are currently being
+ * traced and by what. Not sure if we want lockdown
+ * to hide such critical information for an admin.
+ * Although, perhaps it can show information we don't
+ * want people to see, but if something is tracing
+ * something, we probably want to know about it.
+ */
+
iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
if (!iter)
return -ENOMEM;
@@ -3532,21 +3555,22 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
struct ftrace_hash *hash;
struct list_head *mod_head;
struct trace_array *tr = ops->private;
- int ret = 0;
+ int ret = -ENOMEM;
ftrace_ops_init(ops);
if (unlikely(ftrace_disabled))
return -ENODEV;
+ if (tracing_check_open_get_tr(tr))
+ return -ENODEV;
+
iter = kzalloc(sizeof(*iter), GFP_KERNEL);
if (!iter)
- return -ENOMEM;
+ goto out;
- if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX)) {
- kfree(iter);
- return -ENOMEM;
- }
+ if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX))
+ goto out;
iter->ops = ops;
iter->flags = flag;
@@ -3576,13 +3600,13 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
if (!iter->hash) {
trace_parser_put(&iter->parser);
- kfree(iter);
- ret = -ENOMEM;
goto out_unlock;
}
} else
iter->hash = hash;
+ ret = 0;
+
if (file->f_mode & FMODE_READ) {
iter->pg = ftrace_pages_start;
@@ -3594,7 +3618,6 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
/* Failed */
free_ftrace_hash(iter->hash);
trace_parser_put(&iter->parser);
- kfree(iter);
}
} else
file->private_data = iter;
@@ -3602,6 +3625,13 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
out_unlock:
mutex_unlock(&ops->func_hash->regex_lock);
+ out:
+ if (ret) {
+ kfree(iter);
+ if (tr)
+ trace_array_put(tr);
+ }
+
return ret;
}
@@ -3610,6 +3640,7 @@ ftrace_filter_open(struct inode *inode, struct file *file)
{
struct ftrace_ops *ops = inode->i_private;
+ /* Checks for tracefs lockdown */
return ftrace_regex_open(ops,
FTRACE_ITER_FILTER | FTRACE_ITER_DO_PROBES,
inode, file);
@@ -3620,6 +3651,7 @@ ftrace_notrace_open(struct inode *inode, struct file *file)
{
struct ftrace_ops *ops = inode->i_private;
+ /* Checks for tracefs lockdown */
return ftrace_regex_open(ops, FTRACE_ITER_NOTRACE,
inode, file);
}
@@ -4320,12 +4352,21 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr,
mutex_unlock(&ftrace_lock);
+ /*
+ * Note, there's a small window here that the func_hash->filter_hash
+ * may be NULL or empty. Need to be carefule when reading the loop.
+ */
mutex_lock(&probe->ops.func_hash->regex_lock);
orig_hash = &probe->ops.func_hash->filter_hash;
old_hash = *orig_hash;
hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash);
+ if (!hash) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
ret = ftrace_match_records(hash, glob, strlen(glob));
/* Nothing found? */
@@ -5020,6 +5061,8 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
mutex_unlock(&iter->ops->func_hash->regex_lock);
free_ftrace_hash(iter->hash);
+ if (iter->tr)
+ trace_array_put(iter->tr);
kfree(iter);
return 0;
@@ -5177,9 +5220,13 @@ static int
__ftrace_graph_open(struct inode *inode, struct file *file,
struct ftrace_graph_data *fgd)
{
- int ret = 0;
+ int ret;
struct ftrace_hash *new_hash = NULL;
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
if (file->f_mode & FMODE_WRITE) {
const int size_bits = FTRACE_HASH_DEFAULT_BITS;
@@ -6019,11 +6066,7 @@ clear_func_from_hash(struct ftrace_init_func *func, struct ftrace_hash *hash)
{
struct ftrace_func_entry *entry;
- if (ftrace_hash_empty(hash))
- return;
-
- entry = __ftrace_lookup_ip(hash, func->ip);
-
+ entry = ftrace_lookup_ip(hash, func->ip);
/*
* Do not allow this rec to match again.
* Yeah, it may waste some memory, but will be removed
@@ -6524,8 +6567,9 @@ ftrace_pid_open(struct inode *inode, struct file *file)
struct seq_file *m;
int ret = 0;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC))
diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h
index 0515a2096f90..0456e0a3dab1 100644
--- a/kernel/trace/ftrace_internal.h
+++ b/kernel/trace/ftrace_internal.h
@@ -6,22 +6,22 @@
/*
* Traverse the ftrace_global_list, invoking all entries. The reason that we
- * can use rcu_dereference_raw_notrace() is that elements removed from this list
+ * can use rcu_dereference_raw_check() is that elements removed from this list
* are simply leaked, so there is no need to interact with a grace-period
- * mechanism. The rcu_dereference_raw_notrace() calls are needed to handle
+ * mechanism. The rcu_dereference_raw_check() calls are needed to handle
* concurrent insertions into the ftrace_global_list.
*
* Silly Alpha and silly pointer-speculation compiler optimizations!
*/
#define do_for_each_ftrace_op(op, list) \
- op = rcu_dereference_raw_notrace(list); \
+ op = rcu_dereference_raw_check(list); \
do
/*
* Optimized for just a single item in the list (as that is the normal case).
*/
#define while_for_each_ftrace_op(op) \
- while (likely(op = rcu_dereference_raw_notrace((op)->next)) && \
+ while (likely(op = rcu_dereference_raw_check((op)->next)) && \
unlikely((op) != &ftrace_list_end))
extern struct ftrace_ops __rcu *ftrace_ops_list;
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 0564f6db0561..09b0b49f346e 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -267,7 +267,7 @@ static void ring_buffer_producer(void)
if (consumer && !(cnt % wakeup_interval))
wake_up_process(consumer);
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
/*
* If we are a non preempt kernel, the 10 second run will
* stop everything while it runs. Instead, we will call
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 525a97fbbc60..6a0ee9178365 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,6 +17,7 @@
#include <linux/stacktrace.h>
#include <linux/writeback.h>
#include <linux/kallsyms.h>
+#include <linux/security.h>
#include <linux/seq_file.h>
#include <linux/notifier.h>
#include <linux/irqflags.h>
@@ -304,6 +305,23 @@ void trace_array_put(struct trace_array *this_tr)
mutex_unlock(&trace_types_lock);
}
+int tracing_check_open_get_tr(struct trace_array *tr)
+{
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
+ if (tracing_disabled)
+ return -ENODEV;
+
+ if (tr && trace_array_get(tr) < 0)
+ return -ENODEV;
+
+ return 0;
+}
+
int call_filter_check_discard(struct trace_event_call *call, void *rec,
struct ring_buffer *buffer,
struct ring_buffer_event *event)
@@ -1567,9 +1585,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu,
/**
* update_max_tr_single - only copy one trace over, and reset the rest
- * @tr - tracer
- * @tsk - task with the latency
- * @cpu - the cpu of the buffer to copy.
+ * @tr: tracer
+ * @tsk: task with the latency
+ * @cpu: the cpu of the buffer to copy.
*
* Flip the trace of a single CPU buffer between the @tr and the max_tr.
*/
@@ -1767,7 +1785,7 @@ static void __init apply_trace_boot_options(void);
/**
* register_tracer - register a tracer with the ftrace system.
- * @type - the plugin for the tracer
+ * @type: the plugin for the tracer
*
* Register a new plugin tracer.
*/
@@ -1854,7 +1872,7 @@ int __init register_tracer(struct tracer *type)
return ret;
}
-void tracing_reset(struct trace_buffer *buf, int cpu)
+static void tracing_reset_cpu(struct trace_buffer *buf, int cpu)
{
struct ring_buffer *buffer = buf->buffer;
@@ -2230,9 +2248,9 @@ static bool tracing_record_taskinfo_skip(int flags)
/**
* tracing_record_taskinfo - record the task info of a task
*
- * @task - task to record
- * @flags - TRACE_RECORD_CMDLINE for recording comm
- * - TRACE_RECORD_TGID for recording tgid
+ * @task: task to record
+ * @flags: TRACE_RECORD_CMDLINE for recording comm
+ * TRACE_RECORD_TGID for recording tgid
*/
void tracing_record_taskinfo(struct task_struct *task, int flags)
{
@@ -2258,10 +2276,10 @@ void tracing_record_taskinfo(struct task_struct *task, int flags)
/**
* tracing_record_taskinfo_sched_switch - record task info for sched_switch
*
- * @prev - previous task during sched_switch
- * @next - next task during sched_switch
- * @flags - TRACE_RECORD_CMDLINE for recording comm
- * TRACE_RECORD_TGID for recording tgid
+ * @prev: previous task during sched_switch
+ * @next: next task during sched_switch
+ * @flags: TRACE_RECORD_CMDLINE for recording comm
+ * TRACE_RECORD_TGID for recording tgid
*/
void tracing_record_taskinfo_sched_switch(struct task_struct *prev,
struct task_struct *next, int flags)
@@ -2642,10 +2660,10 @@ static void ftrace_exports(struct ring_buffer_event *event)
preempt_disable_notrace();
- export = rcu_dereference_raw_notrace(ftrace_exports_list);
+ export = rcu_dereference_raw_check(ftrace_exports_list);
while (export) {
trace_process_export(export, event);
- export = rcu_dereference_raw_notrace(export->next);
+ export = rcu_dereference_raw_check(export->next);
}
preempt_enable_notrace();
@@ -3072,7 +3090,9 @@ static void trace_printk_start_stop_comm(int enabled)
/**
* trace_vbprintk - write binary msg to tracing buffer
- *
+ * @ip: The address of the caller
+ * @fmt: The string format to write to the buffer
+ * @args: Arguments for @fmt
*/
int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
{
@@ -4138,8 +4158,11 @@ release:
int tracing_open_generic(struct inode *inode, struct file *filp)
{
- if (tracing_disabled)
- return -ENODEV;
+ int ret;
+
+ ret = tracing_check_open_get_tr(NULL);
+ if (ret)
+ return ret;
filp->private_data = inode->i_private;
return 0;
@@ -4154,15 +4177,14 @@ bool tracing_is_disabled(void)
* Open and update trace_array ref count.
* Must have the current trace_array passed to it.
*/
-static int tracing_open_generic_tr(struct inode *inode, struct file *filp)
+int tracing_open_generic_tr(struct inode *inode, struct file *filp)
{
struct trace_array *tr = inode->i_private;
+ int ret;
- if (tracing_disabled)
- return -ENODEV;
-
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
filp->private_data = inode->i_private;
@@ -4231,10 +4253,11 @@ static int tracing_open(struct inode *inode, struct file *file)
{
struct trace_array *tr = inode->i_private;
struct trace_iterator *iter;
- int ret = 0;
+ int ret;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
/* If this file was open for write, then erase contents */
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
@@ -4249,7 +4272,7 @@ static int tracing_open(struct inode *inode, struct file *file)
if (cpu == RING_BUFFER_ALL_CPUS)
tracing_reset_online_cpus(trace_buf);
else
- tracing_reset(trace_buf, cpu);
+ tracing_reset_cpu(trace_buf, cpu);
}
if (file->f_mode & FMODE_READ) {
@@ -4350,12 +4373,15 @@ static int show_traces_open(struct inode *inode, struct file *file)
struct seq_file *m;
int ret;
- if (tracing_disabled)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
ret = seq_open(file, &show_traces_seq_ops);
- if (ret)
+ if (ret) {
+ trace_array_put(tr);
return ret;
+ }
m = file->private_data;
m->private = tr;
@@ -4363,6 +4389,14 @@ static int show_traces_open(struct inode *inode, struct file *file)
return 0;
}
+static int show_traces_release(struct inode *inode, struct file *file)
+{
+ struct trace_array *tr = inode->i_private;
+
+ trace_array_put(tr);
+ return seq_release(inode, file);
+}
+
static ssize_t
tracing_write_stub(struct file *filp, const char __user *ubuf,
size_t count, loff_t *ppos)
@@ -4393,8 +4427,8 @@ static const struct file_operations tracing_fops = {
static const struct file_operations show_traces_fops = {
.open = show_traces_open,
.read = seq_read,
- .release = seq_release,
.llseek = seq_lseek,
+ .release = show_traces_release,
};
static ssize_t
@@ -4695,11 +4729,9 @@ static int tracing_trace_options_open(struct inode *inode, struct file *file)
struct trace_array *tr = inode->i_private;
int ret;
- if (tracing_disabled)
- return -ENODEV;
-
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
ret = single_open(file, tracing_trace_options_show, inode->i_private);
if (ret < 0)
@@ -4813,15 +4845,15 @@ static const char readme_msg[] =
#endif
#endif /* CONFIG_STACK_TRACER */
#ifdef CONFIG_DYNAMIC_EVENTS
- " dynamic_events\t\t- Add/remove/show the generic dynamic events\n"
+ " dynamic_events\t\t- Create/append/remove/show the generic dynamic events\n"
"\t\t\t Write into this file to define/undefine new trace events.\n"
#endif
#ifdef CONFIG_KPROBE_EVENTS
- " kprobe_events\t\t- Add/remove/show the kernel dynamic events\n"
+ " kprobe_events\t\t- Create/append/remove/show the kernel dynamic events\n"
"\t\t\t Write into this file to define/undefine new trace events.\n"
#endif
#ifdef CONFIG_UPROBE_EVENTS
- " uprobe_events\t\t- Add/remove/show the userspace dynamic events\n"
+ " uprobe_events\t\t- Create/append/remove/show the userspace dynamic events\n"
"\t\t\t Write into this file to define/undefine new trace events.\n"
#endif
#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
@@ -4846,7 +4878,7 @@ static const char readme_msg[] =
#else
"\t $stack<index>, $stack, $retval, $comm,\n"
#endif
- "\t +|-[u]<offset>(<fetcharg>)\n"
+ "\t +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\n"
"\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string, symbol,\n"
"\t b<bit-width>@<bit-offset>/<container-size>, ustring,\n"
"\t <type>\\[<array-size>\\]\n"
@@ -5036,8 +5068,11 @@ static const struct seq_operations tracing_saved_tgids_seq_ops = {
static int tracing_saved_tgids_open(struct inode *inode, struct file *filp)
{
- if (tracing_disabled)
- return -ENODEV;
+ int ret;
+
+ ret = tracing_check_open_get_tr(NULL);
+ if (ret)
+ return ret;
return seq_open(filp, &tracing_saved_tgids_seq_ops);
}
@@ -5113,8 +5148,11 @@ static const struct seq_operations tracing_saved_cmdlines_seq_ops = {
static int tracing_saved_cmdlines_open(struct inode *inode, struct file *filp)
{
- if (tracing_disabled)
- return -ENODEV;
+ int ret;
+
+ ret = tracing_check_open_get_tr(NULL);
+ if (ret)
+ return ret;
return seq_open(filp, &tracing_saved_cmdlines_seq_ops);
}
@@ -5278,8 +5316,11 @@ static const struct seq_operations tracing_eval_map_seq_ops = {
static int tracing_eval_map_open(struct inode *inode, struct file *filp)
{
- if (tracing_disabled)
- return -ENODEV;
+ int ret;
+
+ ret = tracing_check_open_get_tr(NULL);
+ if (ret)
+ return ret;
return seq_open(filp, &tracing_eval_map_seq_ops);
}
@@ -5802,13 +5843,11 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
{
struct trace_array *tr = inode->i_private;
struct trace_iterator *iter;
- int ret = 0;
-
- if (tracing_disabled)
- return -ENODEV;
+ int ret;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
mutex_lock(&trace_types_lock);
@@ -5997,6 +6036,7 @@ waitagain:
sizeof(struct trace_iterator) -
offsetof(struct trace_iterator, seq));
cpumask_clear(iter->started);
+ trace_seq_init(&iter->seq);
iter->pos = -1;
trace_event_read_lock();
@@ -6545,11 +6585,9 @@ static int tracing_clock_open(struct inode *inode, struct file *file)
struct trace_array *tr = inode->i_private;
int ret;
- if (tracing_disabled)
- return -ENODEV;
-
- if (trace_array_get(tr))
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
ret = single_open(file, tracing_clock_show, inode->i_private);
if (ret < 0)
@@ -6579,11 +6617,9 @@ static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file)
struct trace_array *tr = inode->i_private;
int ret;
- if (tracing_disabled)
- return -ENODEV;
-
- if (trace_array_get(tr))
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
ret = single_open(file, tracing_time_stamp_mode_show, inode->i_private);
if (ret < 0)
@@ -6636,10 +6672,11 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file)
struct trace_array *tr = inode->i_private;
struct trace_iterator *iter;
struct seq_file *m;
- int ret = 0;
+ int ret;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
if (file->f_mode & FMODE_READ) {
iter = __tracing_open(inode, file, true);
@@ -6740,7 +6777,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
if (iter->cpu_file == RING_BUFFER_ALL_CPUS)
tracing_reset_online_cpus(&tr->max_buffer);
else
- tracing_reset(&tr->max_buffer, iter->cpu_file);
+ tracing_reset_cpu(&tr->max_buffer, iter->cpu_file);
}
break;
}
@@ -6784,6 +6821,7 @@ static int snapshot_raw_open(struct inode *inode, struct file *filp)
struct ftrace_buffer_info *info;
int ret;
+ /* The following checks for tracefs lockdown */
ret = tracing_buffers_open(inode, filp);
if (ret < 0)
return ret;
@@ -7103,8 +7141,9 @@ static int tracing_err_log_open(struct inode *inode, struct file *file)
struct trace_array *tr = inode->i_private;
int ret = 0;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
/* If this file was opened for write, then erase contents */
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC))
@@ -7155,11 +7194,9 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
struct ftrace_buffer_info *info;
int ret;
- if (tracing_disabled)
- return -ENODEV;
-
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
info = kzalloc(sizeof(*info), GFP_KERNEL);
if (!info) {
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 005f08629b8b..d685c61085c0 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -338,6 +338,7 @@ extern struct mutex trace_types_lock;
extern int trace_array_get(struct trace_array *tr);
extern void trace_array_put(struct trace_array *tr);
+extern int tracing_check_open_get_tr(struct trace_array *tr);
extern int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs);
extern int tracing_set_clock(struct trace_array *tr, const char *clockstr);
@@ -365,11 +366,11 @@ static inline struct trace_array *top_trace_array(void)
__builtin_types_compatible_p(typeof(var), type *)
#undef IF_ASSIGN
-#define IF_ASSIGN(var, entry, etype, id) \
- if (FTRACE_CMP_TYPE(var, etype)) { \
- var = (typeof(var))(entry); \
- WARN_ON(id && (entry)->type != id); \
- break; \
+#define IF_ASSIGN(var, entry, etype, id) \
+ if (FTRACE_CMP_TYPE(var, etype)) { \
+ var = (typeof(var))(entry); \
+ WARN_ON(id != 0 && (entry)->type != id); \
+ break; \
}
/* Will cause compile errors if type is not found. */
@@ -677,11 +678,11 @@ trace_buffer_iter(struct trace_iterator *iter, int cpu)
int tracer_init(struct tracer *t, struct trace_array *tr);
int tracing_is_enabled(void);
-void tracing_reset(struct trace_buffer *buf, int cpu);
void tracing_reset_online_cpus(struct trace_buffer *buf);
void tracing_reset_current(int cpu);
void tracing_reset_all_online_cpus(void);
int tracing_open_generic(struct inode *inode, struct file *filp);
+int tracing_open_generic_tr(struct inode *inode, struct file *filp);
bool tracing_is_disabled(void);
bool tracer_tracing_is_on(struct trace_array *tr);
void tracer_tracing_on(struct trace_array *tr);
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index fa100ed3b4de..89779eb84a07 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -47,6 +47,7 @@ int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type)
return -EINVAL;
event++;
}
+ argc--; argv++;
p = strchr(event, '/');
if (p) {
@@ -61,10 +62,13 @@ int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type)
for_each_dyn_event_safe(pos, n) {
if (type && type != pos->ops)
continue;
- if (pos->ops->match(system, event, pos)) {
- ret = pos->ops->free(pos);
+ if (!pos->ops->match(system, event,
+ argc, (const char **)argv, pos))
+ continue;
+
+ ret = pos->ops->free(pos);
+ if (ret)
break;
- }
}
mutex_unlock(&event_mutex);
@@ -170,6 +174,10 @@ static int dyn_event_open(struct inode *inode, struct file *file)
{
int ret;
+ ret = tracing_check_open_get_tr(NULL);
+ if (ret)
+ return ret;
+
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
ret = dyn_events_release_all(NULL);
if (ret < 0)
diff --git a/kernel/trace/trace_dynevent.h b/kernel/trace/trace_dynevent.h
index 8c334064e4d6..46898138d2df 100644
--- a/kernel/trace/trace_dynevent.h
+++ b/kernel/trace/trace_dynevent.h
@@ -31,8 +31,9 @@ struct dyn_event;
* @is_busy: Check whether given event is busy so that it can not be deleted.
* Return true if it is busy, otherwides false.
* @free: Delete the given event. Return 0 if success, otherwides error.
- * @match: Check whether given event and system name match this event.
- * Return true if it matches, otherwides false.
+ * @match: Check whether given event and system name match this event. The argc
+ * and argv is used for exact match. Return true if it matches, otherwides
+ * false.
*
* Except for @create, these methods are called under holding event_mutex.
*/
@@ -43,7 +44,7 @@ struct dyn_event_operations {
bool (*is_busy)(struct dyn_event *ev);
int (*free)(struct dyn_event *ev);
bool (*match)(const char *system, const char *event,
- struct dyn_event *ev);
+ int argc, const char **argv, struct dyn_event *ev);
};
/* Register new dyn_event type -- must be called at first */
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 0892e38ed6fb..a9dfa04ffa44 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -272,9 +272,11 @@ int perf_kprobe_init(struct perf_event *p_event, bool is_retprobe)
goto out;
}
+ mutex_lock(&event_mutex);
ret = perf_trace_event_init(tp_event, p_event);
if (ret)
destroy_local_trace_kprobe(tp_event);
+ mutex_unlock(&event_mutex);
out:
kfree(func);
return ret;
@@ -282,8 +284,10 @@ out:
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);
+ mutex_unlock(&event_mutex);
destroy_local_trace_kprobe(p_event->tp_event);
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index c7506bc81b75..fba87d10f0c1 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -12,6 +12,7 @@
#define pr_fmt(fmt) fmt
#include <linux/workqueue.h>
+#include <linux/security.h>
#include <linux/spinlock.h>
#include <linux/kthread.h>
#include <linux/tracefs.h>
@@ -255,12 +256,12 @@ void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer,
local_save_flags(fbuffer->flags);
fbuffer->pc = preempt_count();
/*
- * If CONFIG_PREEMPT is enabled, then the tracepoint itself disables
+ * If CONFIG_PREEMPTION is enabled, then the tracepoint itself disables
* preemption (adding one to the preempt_count). Since we are
* interested in the preempt_count at the time the tracepoint was
* hit, we need to subtract one to offset the increment.
*/
- if (IS_ENABLED(CONFIG_PREEMPT))
+ if (IS_ENABLED(CONFIG_PREEMPTION))
fbuffer->pc--;
fbuffer->trace_file = trace_file;
@@ -787,7 +788,7 @@ static int __ftrace_set_clr_event(struct trace_array *tr, const char *match,
return ret;
}
-static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
+int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
{
char *event = NULL, *sub = NULL, *match;
int ret;
@@ -1294,6 +1295,8 @@ static int trace_format_open(struct inode *inode, struct file *file)
struct seq_file *m;
int ret;
+ /* Do we want to hide event format files on tracefs lockdown? */
+
ret = seq_open(file, &trace_format_seq_ops);
if (ret < 0)
return ret;
@@ -1440,28 +1443,17 @@ static int system_tr_open(struct inode *inode, struct file *filp)
struct trace_array *tr = inode->i_private;
int ret;
- if (tracing_is_disabled())
- return -ENODEV;
-
- if (trace_array_get(tr) < 0)
- return -ENODEV;
-
/* Make a temporary dir that has no system but points to tr */
dir = kzalloc(sizeof(*dir), GFP_KERNEL);
- if (!dir) {
- trace_array_put(tr);
+ if (!dir)
return -ENOMEM;
- }
- dir->tr = tr;
-
- ret = tracing_open_generic(inode, filp);
+ ret = tracing_open_generic_tr(inode, filp);
if (ret < 0) {
- trace_array_put(tr);
kfree(dir);
return ret;
}
-
+ dir->tr = tr;
filp->private_data = dir;
return 0;
@@ -1771,6 +1763,10 @@ ftrace_event_open(struct inode *inode, struct file *file,
struct seq_file *m;
int ret;
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
ret = seq_open(file, seq_ops);
if (ret < 0)
return ret;
@@ -1795,6 +1791,7 @@ ftrace_event_avail_open(struct inode *inode, struct file *file)
{
const struct seq_operations *seq_ops = &show_event_seq_ops;
+ /* Checks for tracefs lockdown */
return ftrace_event_open(inode, file, seq_ops);
}
@@ -1805,8 +1802,9 @@ ftrace_event_set_open(struct inode *inode, struct file *file)
struct trace_array *tr = inode->i_private;
int ret;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC))
@@ -1825,8 +1823,9 @@ ftrace_event_set_pid_open(struct inode *inode, struct file *file)
struct trace_array *tr = inode->i_private;
int ret;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC))
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index c773b8fb270c..c9a74f82b14a 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -452,8 +452,10 @@ predicate_parse(const char *str, int nr_parens, int nr_preds,
switch (*next) {
case '(': /* #2 */
- if (top - op_stack > nr_parens)
- return ERR_PTR(-EINVAL);
+ if (top - op_stack > nr_parens) {
+ ret = -EINVAL;
+ goto out_free;
+ }
*(++top) = invert;
continue;
case '!': /* #3 */
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index ca6b0dff60c5..7482a1466ebf 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -7,12 +7,17 @@
#include <linux/module.h>
#include <linux/kallsyms.h>
+#include <linux/security.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/stacktrace.h>
#include <linux/rculist.h>
#include <linux/tracefs.h>
+/* for gfp flag names */
+#include <linux/trace_events.h>
+#include <trace/events/mmflags.h>
+
#include "tracing_map.h"
#include "trace.h"
#include "trace_dynevent.h"
@@ -374,7 +379,7 @@ static int synth_event_show(struct seq_file *m, struct dyn_event *ev);
static int synth_event_release(struct dyn_event *ev);
static bool synth_event_is_busy(struct dyn_event *ev);
static bool synth_event_match(const char *system, const char *event,
- struct dyn_event *ev);
+ int argc, const char **argv, struct dyn_event *ev);
static struct dyn_event_operations synth_event_ops = {
.create = synth_event_create,
@@ -422,7 +427,7 @@ static bool synth_event_is_busy(struct dyn_event *ev)
}
static bool synth_event_match(const char *system, const char *event,
- struct dyn_event *ev)
+ int argc, const char **argv, struct dyn_event *ev)
{
struct synth_event *sev = to_synth_event(ev);
@@ -674,6 +679,8 @@ static bool synth_field_signed(char *type)
{
if (str_has_prefix(type, "u"))
return false;
+ if (strcmp(type, "gfp_t") == 0)
+ return false;
return true;
}
@@ -752,6 +759,8 @@ static int synth_field_size(char *type)
size = sizeof(unsigned long);
else if (strcmp(type, "pid_t") == 0)
size = sizeof(pid_t);
+ else if (strcmp(type, "gfp_t") == 0)
+ size = sizeof(gfp_t);
else if (synth_field_is_string(type))
size = synth_field_string_size(type);
@@ -792,6 +801,8 @@ static const char *synth_field_fmt(char *type)
fmt = "%lu";
else if (strcmp(type, "pid_t") == 0)
fmt = "%d";
+ else if (strcmp(type, "gfp_t") == 0)
+ fmt = "%x";
else if (synth_field_is_string(type))
fmt = "%s";
@@ -834,9 +845,20 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
i == se->n_fields - 1 ? "" : " ");
n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
} else {
+ struct trace_print_flags __flags[] = {
+ __def_gfpflag_names, {-1, NULL} };
+
trace_seq_printf(s, print_fmt, se->fields[i]->name,
entry->fields[n_u64],
i == se->n_fields - 1 ? "" : " ");
+
+ if (strcmp(se->fields[i]->type, "gfp_t") == 0) {
+ trace_seq_puts(s, " (");
+ trace_print_flags_seq(s, "|",
+ entry->fields[n_u64],
+ __flags);
+ trace_seq_putc(s, ')');
+ }
n_u64++;
}
}
@@ -1429,6 +1451,10 @@ static int synth_events_open(struct inode *inode, struct file *file)
{
int ret;
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
ret = dyn_events_release_all(&synth_event_ops);
if (ret < 0)
@@ -1661,7 +1687,7 @@ static int save_hist_vars(struct hist_trigger_data *hist_data)
if (var_data)
return 0;
- if (trace_array_get(tr) < 0)
+ if (tracing_check_open_get_tr(tr))
return -ENODEV;
var_data = kzalloc(sizeof(*var_data), GFP_KERNEL);
@@ -2785,6 +2811,8 @@ static struct hist_field *create_alias(struct hist_trigger_data *hist_data,
return NULL;
}
+ alias->var_ref_idx = var_ref->var_ref_idx;
+
return alias;
}
@@ -5494,6 +5522,12 @@ static int hist_show(struct seq_file *m, void *v)
static int event_hist_open(struct inode *inode, struct file *file)
{
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
return single_open(file, hist_show, file);
}
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 2a2912cb4533..2cd53ca21b51 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -5,6 +5,7 @@
* Copyright (C) 2013 Tom Zanussi <tom.zanussi@linux.intel.com>
*/
+#include <linux/security.h>
#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/mutex.h>
@@ -173,7 +174,11 @@ static const struct seq_operations event_triggers_seq_ops = {
static int event_trigger_regex_open(struct inode *inode, struct file *file)
{
- int ret = 0;
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
mutex_lock(&event_mutex);
@@ -292,6 +297,7 @@ event_trigger_write(struct file *filp, const char __user *ubuf,
static int
event_trigger_open(struct inode *inode, struct file *filp)
{
+ /* Checks for tracefs lockdown */
return event_trigger_regex_open(inode, filp);
}
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index fa95139445b2..862f4b0139fc 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -150,7 +150,7 @@ void trace_hwlat_callback(bool enter)
if (enter)
nmi_ts_start = time_get();
else
- nmi_total_ts = time_get() - nmi_ts_start;
+ nmi_total_ts += time_get() - nmi_ts_start;
}
if (enter)
@@ -256,6 +256,8 @@ static int get_sample(void)
/* Keep a running maximum ever recorded hardware latency */
if (sample > tr->max_latency)
tr->max_latency = sample;
+ if (outer_sample > tr->max_latency)
+ tr->max_latency = outer_sample;
}
out:
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 9d483ad9bb6c..1552a95c743b 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -7,6 +7,7 @@
*/
#define pr_fmt(fmt) "trace_kprobe: " fmt
+#include <linux/security.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/rculist.h>
@@ -39,7 +40,7 @@ static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev);
static int trace_kprobe_release(struct dyn_event *ev);
static bool trace_kprobe_is_busy(struct dyn_event *ev);
static bool trace_kprobe_match(const char *system, const char *event,
- struct dyn_event *ev);
+ int argc, const char **argv, struct dyn_event *ev);
static struct dyn_event_operations trace_kprobe_ops = {
.create = trace_kprobe_create,
@@ -137,13 +138,36 @@ static bool trace_kprobe_is_busy(struct dyn_event *ev)
return trace_probe_is_enabled(&tk->tp);
}
+static bool trace_kprobe_match_command_head(struct trace_kprobe *tk,
+ int argc, const char **argv)
+{
+ char buf[MAX_ARGSTR_LEN + 1];
+
+ if (!argc)
+ return true;
+
+ if (!tk->symbol)
+ snprintf(buf, sizeof(buf), "0x%p", tk->rp.kp.addr);
+ else if (tk->rp.kp.offset)
+ snprintf(buf, sizeof(buf), "%s+%u",
+ trace_kprobe_symbol(tk), tk->rp.kp.offset);
+ else
+ snprintf(buf, sizeof(buf), "%s", trace_kprobe_symbol(tk));
+ if (strcmp(buf, argv[0]))
+ return false;
+ argc--; argv++;
+
+ return trace_probe_match_command_args(&tk->tp, argc, argv);
+}
+
static bool trace_kprobe_match(const char *system, const char *event,
- struct dyn_event *ev)
+ int argc, const char **argv, struct dyn_event *ev)
{
struct trace_kprobe *tk = to_trace_kprobe(ev);
return strcmp(trace_probe_name(&tk->tp), event) == 0 &&
- (!system || strcmp(trace_probe_group_name(&tk->tp), system) == 0);
+ (!system || strcmp(trace_probe_group_name(&tk->tp), system) == 0) &&
+ trace_kprobe_match_command_head(tk, argc, argv);
}
static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk)
@@ -180,20 +204,33 @@ unsigned long trace_kprobe_address(struct trace_kprobe *tk)
return addr;
}
+static nokprobe_inline struct trace_kprobe *
+trace_kprobe_primary_from_call(struct trace_event_call *call)
+{
+ struct trace_probe *tp;
+
+ tp = trace_probe_primary_from_call(call);
+ if (WARN_ON_ONCE(!tp))
+ return NULL;
+
+ return container_of(tp, struct trace_kprobe, tp);
+}
+
bool trace_kprobe_on_func_entry(struct trace_event_call *call)
{
- struct trace_kprobe *tk = (struct trace_kprobe *)call->data;
+ struct trace_kprobe *tk = trace_kprobe_primary_from_call(call);
- return kprobe_on_func_entry(tk->rp.kp.addr,
+ return tk ? kprobe_on_func_entry(tk->rp.kp.addr,
tk->rp.kp.addr ? NULL : tk->rp.kp.symbol_name,
- tk->rp.kp.addr ? 0 : tk->rp.kp.offset);
+ tk->rp.kp.addr ? 0 : tk->rp.kp.offset) : false;
}
bool trace_kprobe_error_injectable(struct trace_event_call *call)
{
- struct trace_kprobe *tk = (struct trace_kprobe *)call->data;
+ struct trace_kprobe *tk = trace_kprobe_primary_from_call(call);
- return within_error_injection_list(trace_kprobe_address(tk));
+ return tk ? within_error_injection_list(trace_kprobe_address(tk)) :
+ false;
}
static int register_kprobe_event(struct trace_kprobe *tk);
@@ -291,32 +328,68 @@ static inline int __enable_trace_kprobe(struct trace_kprobe *tk)
return ret;
}
+static void __disable_trace_kprobe(struct trace_probe *tp)
+{
+ struct trace_probe *pos;
+ struct trace_kprobe *tk;
+
+ list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
+ tk = container_of(pos, struct trace_kprobe, tp);
+ if (!trace_kprobe_is_registered(tk))
+ continue;
+ if (trace_kprobe_is_return(tk))
+ disable_kretprobe(&tk->rp);
+ else
+ disable_kprobe(&tk->rp.kp);
+ }
+}
+
/*
* Enable trace_probe
* if the file is NULL, enable "perf" handler, or enable "trace" handler.
*/
-static int
-enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
+static int enable_trace_kprobe(struct trace_event_call *call,
+ struct trace_event_file *file)
{
- bool enabled = trace_probe_is_enabled(&tk->tp);
+ struct trace_probe *pos, *tp;
+ struct trace_kprobe *tk;
+ bool enabled;
int ret = 0;
+ tp = trace_probe_primary_from_call(call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENODEV;
+ enabled = trace_probe_is_enabled(tp);
+
+ /* This also changes "enabled" state */
if (file) {
- ret = trace_probe_add_file(&tk->tp, file);
+ ret = trace_probe_add_file(tp, file);
if (ret)
return ret;
} else
- trace_probe_set_flag(&tk->tp, TP_FLAG_PROFILE);
+ trace_probe_set_flag(tp, TP_FLAG_PROFILE);
if (enabled)
return 0;
- ret = __enable_trace_kprobe(tk);
+ list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
+ tk = container_of(pos, struct trace_kprobe, tp);
+ if (trace_kprobe_has_gone(tk))
+ continue;
+ ret = __enable_trace_kprobe(tk);
+ if (ret)
+ break;
+ enabled = true;
+ }
+
if (ret) {
+ /* Failed to enable one of them. Roll back all */
+ if (enabled)
+ __disable_trace_kprobe(tp);
if (file)
- trace_probe_remove_file(&tk->tp, file);
+ trace_probe_remove_file(tp, file);
else
- trace_probe_clear_flag(&tk->tp, TP_FLAG_PROFILE);
+ trace_probe_clear_flag(tp, TP_FLAG_PROFILE);
}
return ret;
@@ -326,11 +399,14 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
* Disable trace_probe
* if the file is NULL, disable "perf" handler, or disable "trace" handler.
*/
-static int
-disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
+static int disable_trace_kprobe(struct trace_event_call *call,
+ struct trace_event_file *file)
{
- struct trace_probe *tp = &tk->tp;
- int ret = 0;
+ struct trace_probe *tp;
+
+ tp = trace_probe_primary_from_call(call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENODEV;
if (file) {
if (!trace_probe_get_file_link(tp, file))
@@ -341,12 +417,8 @@ disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
} else
trace_probe_clear_flag(tp, TP_FLAG_PROFILE);
- if (!trace_probe_is_enabled(tp) && trace_kprobe_is_registered(tk)) {
- if (trace_kprobe_is_return(tk))
- disable_kretprobe(&tk->rp);
- else
- disable_kprobe(&tk->rp.kp);
- }
+ if (!trace_probe_is_enabled(tp))
+ __disable_trace_kprobe(tp);
out:
if (file)
@@ -358,7 +430,7 @@ disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
*/
trace_probe_remove_file(tp, file);
- return ret;
+ return 0;
}
#if defined(CONFIG_KPROBES_ON_FTRACE) && \
@@ -389,6 +461,10 @@ static int __register_trace_kprobe(struct trace_kprobe *tk)
{
int i, ret;
+ ret = security_locked_down(LOCKDOWN_KPROBES);
+ if (ret)
+ return ret;
+
if (trace_kprobe_is_registered(tk))
return -EINVAL;
@@ -437,6 +513,10 @@ static void __unregister_trace_kprobe(struct trace_kprobe *tk)
/* Unregister a trace_probe and probe_event */
static int unregister_trace_kprobe(struct trace_kprobe *tk)
{
+ /* If other probes are on the event, just unregister kprobe */
+ if (trace_probe_has_sibling(&tk->tp))
+ goto unreg;
+
/* Enabled event can not be unregistered */
if (trace_probe_is_enabled(&tk->tp))
return -EBUSY;
@@ -445,12 +525,82 @@ static int unregister_trace_kprobe(struct trace_kprobe *tk)
if (unregister_kprobe_event(tk))
return -EBUSY;
+unreg:
__unregister_trace_kprobe(tk);
dyn_event_remove(&tk->devent);
+ trace_probe_unlink(&tk->tp);
return 0;
}
+static bool trace_kprobe_has_same_kprobe(struct trace_kprobe *orig,
+ struct trace_kprobe *comp)
+{
+ struct trace_probe_event *tpe = orig->tp.event;
+ struct trace_probe *pos;
+ int i;
+
+ list_for_each_entry(pos, &tpe->probes, list) {
+ orig = container_of(pos, struct trace_kprobe, tp);
+ if (strcmp(trace_kprobe_symbol(orig),
+ trace_kprobe_symbol(comp)) ||
+ trace_kprobe_offset(orig) != trace_kprobe_offset(comp))
+ continue;
+
+ /*
+ * trace_probe_compare_arg_type() ensured that nr_args and
+ * each argument name and type are same. Let's compare comm.
+ */
+ for (i = 0; i < orig->tp.nr_args; i++) {
+ if (strcmp(orig->tp.args[i].comm,
+ comp->tp.args[i].comm))
+ break;
+ }
+
+ if (i == orig->tp.nr_args)
+ return true;
+ }
+
+ return false;
+}
+
+static int append_trace_kprobe(struct trace_kprobe *tk, struct trace_kprobe *to)
+{
+ int ret;
+
+ ret = trace_probe_compare_arg_type(&tk->tp, &to->tp);
+ if (ret) {
+ /* Note that argument starts index = 2 */
+ trace_probe_log_set_index(ret + 1);
+ trace_probe_log_err(0, DIFF_ARG_TYPE);
+ return -EEXIST;
+ }
+ if (trace_kprobe_has_same_kprobe(to, tk)) {
+ trace_probe_log_set_index(0);
+ trace_probe_log_err(0, SAME_PROBE);
+ return -EEXIST;
+ }
+
+ /* Append to existing event */
+ ret = trace_probe_append(&tk->tp, &to->tp);
+ if (ret)
+ return ret;
+
+ /* Register k*probe */
+ ret = __register_trace_kprobe(tk);
+ if (ret == -ENOENT && !trace_kprobe_module_exist(tk)) {
+ pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
+ ret = 0;
+ }
+
+ if (ret)
+ trace_probe_unlink(&tk->tp);
+ else
+ dyn_event_add(&tk->devent);
+
+ return ret;
+}
+
/* Register a trace_probe and probe_event */
static int register_trace_kprobe(struct trace_kprobe *tk)
{
@@ -459,14 +609,17 @@ static int register_trace_kprobe(struct trace_kprobe *tk)
mutex_lock(&event_mutex);
- /* Delete old (same name) event if exist */
old_tk = find_trace_kprobe(trace_probe_name(&tk->tp),
trace_probe_group_name(&tk->tp));
if (old_tk) {
- ret = unregister_trace_kprobe(old_tk);
- if (ret < 0)
- goto end;
- free_trace_kprobe(old_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);
+ }
+ goto end;
}
/* Register new event */
@@ -700,7 +853,7 @@ static int trace_kprobe_create(int argc, const char *argv[])
trace_probe_log_err(0, BAD_INSN_BNDRY);
else if (ret == -ENOENT)
trace_probe_log_err(0, BAD_PROBE_ADDR);
- else if (ret != -ENOMEM)
+ else if (ret != -ENOMEM && ret != -EEXIST)
trace_probe_log_err(0, FAIL_REG_PROBE);
goto error;
}
@@ -783,6 +936,10 @@ static int probes_open(struct inode *inode, struct file *file)
{
int ret;
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
ret = dyn_events_release_all(&trace_kprobe_ops);
if (ret < 0)
@@ -835,6 +992,12 @@ static const struct seq_operations profile_seq_op = {
static int profile_open(struct inode *inode, struct file *file)
{
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
return seq_open(file, &profile_seq_op);
}
@@ -965,6 +1128,9 @@ retry:
case FETCH_OP_COMM:
val = (unsigned long)current->comm;
break;
+ case FETCH_OP_DATA:
+ val = (unsigned long)code->data;
+ break;
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
case FETCH_OP_ARG:
val = regs_get_kernel_argument(regs, code->param);
@@ -1089,7 +1255,10 @@ print_kprobe_event(struct trace_iterator *iter, int flags,
struct trace_probe *tp;
field = (struct kprobe_trace_entry_head *)iter->ent;
- tp = container_of(event, struct trace_probe, call.event);
+ tp = trace_probe_primary_from_call(
+ container_of(event, struct trace_event_call, event));
+ if (WARN_ON_ONCE(!tp))
+ goto out;
trace_seq_printf(s, "%s: (", trace_probe_name(tp));
@@ -1116,7 +1285,10 @@ print_kretprobe_event(struct trace_iterator *iter, int flags,
struct trace_probe *tp;
field = (struct kretprobe_trace_entry_head *)iter->ent;
- tp = container_of(event, struct trace_probe, call.event);
+ tp = trace_probe_primary_from_call(
+ container_of(event, struct trace_event_call, event));
+ if (WARN_ON_ONCE(!tp))
+ goto out;
trace_seq_printf(s, "%s: (", trace_probe_name(tp));
@@ -1145,23 +1317,31 @@ static int kprobe_event_define_fields(struct trace_event_call *event_call)
{
int ret;
struct kprobe_trace_entry_head field;
- struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data;
+ struct trace_probe *tp;
+
+ tp = trace_probe_primary_from_call(event_call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENOENT;
DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
- return traceprobe_define_arg_fields(event_call, sizeof(field), &tk->tp);
+ return traceprobe_define_arg_fields(event_call, sizeof(field), tp);
}
static int kretprobe_event_define_fields(struct trace_event_call *event_call)
{
int ret;
struct kretprobe_trace_entry_head field;
- struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data;
+ struct trace_probe *tp;
+
+ tp = trace_probe_primary_from_call(event_call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENOENT;
DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
- return traceprobe_define_arg_fields(event_call, sizeof(field), &tk->tp);
+ return traceprobe_define_arg_fields(event_call, sizeof(field), tp);
}
#ifdef CONFIG_PERF_EVENTS
@@ -1289,20 +1469,19 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
static int kprobe_register(struct trace_event_call *event,
enum trace_reg type, void *data)
{
- struct trace_kprobe *tk = (struct trace_kprobe *)event->data;
struct trace_event_file *file = data;
switch (type) {
case TRACE_REG_REGISTER:
- return enable_trace_kprobe(tk, file);
+ return enable_trace_kprobe(event, file);
case TRACE_REG_UNREGISTER:
- return disable_trace_kprobe(tk, file);
+ return disable_trace_kprobe(event, file);
#ifdef CONFIG_PERF_EVENTS
case TRACE_REG_PERF_REGISTER:
- return enable_trace_kprobe(tk, NULL);
+ return enable_trace_kprobe(event, NULL);
case TRACE_REG_PERF_UNREGISTER:
- return disable_trace_kprobe(tk, NULL);
+ return disable_trace_kprobe(event, NULL);
case TRACE_REG_PERF_OPEN:
case TRACE_REG_PERF_CLOSE:
case TRACE_REG_PERF_ADD:
@@ -1369,7 +1548,6 @@ static inline void init_trace_event_call(struct trace_kprobe *tk)
call->flags = TRACE_EVENT_FL_KPROBE;
call->class->reg = kprobe_register;
- call->data = tk;
}
static int register_kprobe_event(struct trace_kprobe *tk)
@@ -1432,7 +1610,9 @@ void destroy_local_trace_kprobe(struct trace_event_call *event_call)
{
struct trace_kprobe *tk;
- tk = container_of(event_call, struct trace_kprobe, tp.call);
+ tk = trace_kprobe_primary_from_call(event_call);
+ if (unlikely(!tk))
+ return;
if (trace_probe_is_enabled(&tk->tp)) {
WARN_ON(1);
@@ -1577,7 +1757,8 @@ static __init int kprobe_trace_self_tests_init(void)
pr_warn("error on getting probe file.\n");
warn++;
} else
- enable_trace_kprobe(tk, file);
+ enable_trace_kprobe(
+ trace_probe_event_call(&tk->tp), file);
}
}
@@ -1598,7 +1779,8 @@ static __init int kprobe_trace_self_tests_init(void)
pr_warn("error on getting probe file.\n");
warn++;
} else
- enable_trace_kprobe(tk, file);
+ enable_trace_kprobe(
+ trace_probe_event_call(&tk->tp), file);
}
}
@@ -1631,7 +1813,8 @@ static __init int kprobe_trace_self_tests_init(void)
pr_warn("error on getting probe file.\n");
warn++;
} else
- disable_trace_kprobe(tk, file);
+ disable_trace_kprobe(
+ trace_probe_event_call(&tk->tp), file);
}
tk = find_trace_kprobe("testprobe2", KPROBE_EVENT_SYSTEM);
@@ -1649,7 +1832,8 @@ static __init int kprobe_trace_self_tests_init(void)
pr_warn("error on getting probe file.\n");
warn++;
} else
- disable_trace_kprobe(tk, file);
+ disable_trace_kprobe(
+ trace_probe_event_call(&tk->tp), file);
}
ret = trace_run_command("-:testprobe", create_or_delete_trace_kprobe);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index cab4a5398f1d..d54ce252b05a 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -219,10 +219,10 @@ trace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len,
{
int i;
const char *ret = trace_seq_buffer_ptr(p);
+ const char *fmt = concatenate ? "%*phN" : "%*ph";
- for (i = 0; i < buf_len; i++)
- trace_seq_printf(p, "%s%2.2x", concatenate || i == 0 ? "" : " ",
- buf[i]);
+ for (i = 0; i < buf_len; i += 16)
+ trace_seq_printf(p, fmt, min(buf_len - i, 16), &buf[i]);
trace_seq_putc(p, 0);
return ret;
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index c3fd849d4a8f..d4e31e969206 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -6,6 +6,7 @@
*
*/
#include <linux/seq_file.h>
+#include <linux/security.h>
#include <linux/uaccess.h>
#include <linux/kernel.h>
#include <linux/ftrace.h>
@@ -348,6 +349,12 @@ static const struct seq_operations show_format_seq_ops = {
static int
ftrace_formats_open(struct inode *inode, struct file *file)
{
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
return seq_open(file, &show_format_seq_ops);
}
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index dbef0d135075..905b10af5d5c 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -178,6 +178,16 @@ void __trace_probe_log_err(int offset, int err_type)
if (!command)
return;
+ if (trace_probe_log.index >= trace_probe_log.argc) {
+ /**
+ * Set the error position is next to the last arg + space.
+ * Note that len includes the terminal null and the cursor
+ * appaers at pos + 1.
+ */
+ pos = len;
+ offset = 0;
+ }
+
/* And make a command string from argv array */
p = command;
for (i = 0; i < trace_probe_log.argc; i++) {
@@ -316,6 +326,29 @@ inval_var:
return -EINVAL;
}
+static int str_to_immediate(char *str, unsigned long *imm)
+{
+ if (isdigit(str[0]))
+ return kstrtoul(str, 0, imm);
+ else if (str[0] == '-')
+ return kstrtol(str, 0, (long *)imm);
+ else if (str[0] == '+')
+ return kstrtol(str + 1, 0, (long *)imm);
+ return -EINVAL;
+}
+
+static int __parse_imm_string(char *str, char **pbuf, int offs)
+{
+ size_t len = strlen(str);
+
+ if (str[len - 1] != '"') {
+ trace_probe_log_err(offs + len, IMMSTR_NO_CLOSE);
+ return -EINVAL;
+ }
+ *pbuf = kstrndup(str, len - 1, GFP_KERNEL);
+ return 0;
+}
+
/* Recursive argument parser */
static int
parse_probe_arg(char *arg, const struct fetch_type *type,
@@ -430,7 +463,8 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
ret = parse_probe_arg(arg, t2, &code, end, flags, offs);
if (ret)
break;
- if (code->op == FETCH_OP_COMM) {
+ if (code->op == FETCH_OP_COMM ||
+ code->op == FETCH_OP_DATA) {
trace_probe_log_err(offs, COMM_CANT_DEREF);
return -EINVAL;
}
@@ -444,6 +478,21 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
code->offset = offset;
}
break;
+ case '\\': /* Immediate value */
+ if (arg[1] == '"') { /* Immediate string */
+ ret = __parse_imm_string(arg + 2, &tmp, offs + 2);
+ if (ret)
+ break;
+ code->op = FETCH_OP_DATA;
+ code->data = tmp;
+ } else {
+ ret = str_to_immediate(arg + 1, &code->immediate);
+ if (ret)
+ trace_probe_log_err(offs + 1, BAD_IMM);
+ else
+ code->op = FETCH_OP_IMM;
+ }
+ break;
}
if (!ret && code->op == FETCH_OP_NOP) {
/* Parsed, but do not find fetch method */
@@ -542,8 +591,11 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
}
}
- /* Since $comm can not be dereferred, we can find $comm by strcmp */
- if (strcmp(arg, "$comm") == 0) {
+ /*
+ * Since $comm and immediate string can not be dereferred,
+ * we can find those by strcmp.
+ */
+ if (strcmp(arg, "$comm") == 0 || strncmp(arg, "\\\"", 2) == 0) {
/* The type of $comm must be "string", and not an array. */
if (parg->count || (t && strcmp(t, "string")))
return -EINVAL;
@@ -580,7 +632,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
if (!strcmp(parg->type->name, "string") ||
!strcmp(parg->type->name, "ustring")) {
if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_UDEREF &&
- code->op != FETCH_OP_IMM && code->op != FETCH_OP_COMM) {
+ code->op != FETCH_OP_IMM && code->op != FETCH_OP_COMM &&
+ code->op != FETCH_OP_DATA) {
trace_probe_log_err(offset + (t ? (t - arg) : 0),
BAD_STRING);
ret = -EINVAL;
@@ -589,9 +642,10 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM) ||
parg->count) {
/*
- * IMM and COMM is pointing actual address, those must
- * be kept, and if parg->count != 0, this is an array
- * of string pointers instead of string address itself.
+ * IMM, DATA and COMM is pointing actual address, those
+ * must be kept, and if parg->count != 0, this is an
+ * array of string pointers instead of string address
+ * itself.
*/
code++;
if (code->op != FETCH_OP_NOP) {
@@ -665,7 +719,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
fail:
if (ret) {
for (code = tmp; code < tmp + FETCH_INSN_MAX; code++)
- if (code->op == FETCH_NOP_SYMBOL)
+ if (code->op == FETCH_NOP_SYMBOL ||
+ code->op == FETCH_OP_DATA)
kfree(code->data);
}
kfree(tmp);
@@ -736,7 +791,8 @@ void traceprobe_free_probe_arg(struct probe_arg *arg)
struct fetch_insn *code = arg->code;
while (code && code->op != FETCH_OP_END) {
- if (code->op == FETCH_NOP_SYMBOL)
+ if (code->op == FETCH_NOP_SYMBOL ||
+ code->op == FETCH_OP_DATA)
kfree(code->data);
code++;
}
@@ -886,43 +942,85 @@ int traceprobe_define_arg_fields(struct trace_event_call *event_call,
return 0;
}
+static void trace_probe_event_free(struct trace_probe_event *tpe)
+{
+ kfree(tpe->class.system);
+ kfree(tpe->call.name);
+ kfree(tpe->call.print_fmt);
+ kfree(tpe);
+}
+
+int trace_probe_append(struct trace_probe *tp, struct trace_probe *to)
+{
+ if (trace_probe_has_sibling(tp))
+ return -EBUSY;
+
+ list_del_init(&tp->list);
+ trace_probe_event_free(tp->event);
+
+ tp->event = to->event;
+ list_add_tail(&tp->list, trace_probe_probe_list(to));
+
+ return 0;
+}
+
+void trace_probe_unlink(struct trace_probe *tp)
+{
+ list_del_init(&tp->list);
+ if (list_empty(trace_probe_probe_list(tp)))
+ trace_probe_event_free(tp->event);
+ tp->event = NULL;
+}
void trace_probe_cleanup(struct trace_probe *tp)
{
- struct trace_event_call *call = trace_probe_event_call(tp);
int i;
for (i = 0; i < tp->nr_args; i++)
traceprobe_free_probe_arg(&tp->args[i]);
- kfree(call->class->system);
- kfree(call->name);
- kfree(call->print_fmt);
+ if (tp->event)
+ trace_probe_unlink(tp);
}
int trace_probe_init(struct trace_probe *tp, const char *event,
const char *group)
{
- struct trace_event_call *call = trace_probe_event_call(tp);
+ struct trace_event_call *call;
+ int ret = 0;
if (!event || !group)
return -EINVAL;
- call->class = &tp->class;
- call->name = kstrdup(event, GFP_KERNEL);
- if (!call->name)
+ tp->event = kzalloc(sizeof(struct trace_probe_event), GFP_KERNEL);
+ if (!tp->event)
return -ENOMEM;
- tp->class.system = kstrdup(group, GFP_KERNEL);
- if (!tp->class.system) {
- kfree(call->name);
- call->name = NULL;
- return -ENOMEM;
+ INIT_LIST_HEAD(&tp->event->files);
+ INIT_LIST_HEAD(&tp->event->class.fields);
+ INIT_LIST_HEAD(&tp->event->probes);
+ INIT_LIST_HEAD(&tp->list);
+ list_add(&tp->event->probes, &tp->list);
+
+ call = trace_probe_event_call(tp);
+ call->class = &tp->event->class;
+ call->name = kstrdup(event, GFP_KERNEL);
+ if (!call->name) {
+ ret = -ENOMEM;
+ goto error;
+ }
+
+ tp->event->class.system = kstrdup(group, GFP_KERNEL);
+ if (!tp->event->class.system) {
+ ret = -ENOMEM;
+ goto error;
}
- INIT_LIST_HEAD(&tp->files);
- INIT_LIST_HEAD(&tp->class.fields);
return 0;
+
+error:
+ trace_probe_cleanup(tp);
+ return ret;
}
int trace_probe_register_event_call(struct trace_probe *tp)
@@ -951,7 +1049,7 @@ int trace_probe_add_file(struct trace_probe *tp, struct trace_event_file *file)
link->file = file;
INIT_LIST_HEAD(&link->list);
- list_add_tail_rcu(&link->list, &tp->files);
+ list_add_tail_rcu(&link->list, &tp->event->files);
trace_probe_set_flag(tp, TP_FLAG_TRACE);
return 0;
}
@@ -982,8 +1080,51 @@ int trace_probe_remove_file(struct trace_probe *tp,
synchronize_rcu();
kfree(link);
- if (list_empty(&tp->files))
+ if (list_empty(&tp->event->files))
trace_probe_clear_flag(tp, TP_FLAG_TRACE);
return 0;
}
+
+/*
+ * Return the smallest index of different type argument (start from 1).
+ * If all argument types and name are same, return 0.
+ */
+int trace_probe_compare_arg_type(struct trace_probe *a, struct trace_probe *b)
+{
+ int i;
+
+ /* In case of more arguments */
+ if (a->nr_args < b->nr_args)
+ return a->nr_args + 1;
+ if (a->nr_args > b->nr_args)
+ return b->nr_args + 1;
+
+ for (i = 0; i < a->nr_args; i++) {
+ if ((b->nr_args <= i) ||
+ ((a->args[i].type != b->args[i].type) ||
+ (a->args[i].count != b->args[i].count) ||
+ strcmp(a->args[i].name, b->args[i].name)))
+ return i + 1;
+ }
+
+ return 0;
+}
+
+bool trace_probe_match_command_args(struct trace_probe *tp,
+ int argc, const char **argv)
+{
+ char buf[MAX_ARGSTR_LEN + 1];
+ int i;
+
+ if (tp->nr_args < argc)
+ return false;
+
+ for (i = 0; i < argc; i++) {
+ snprintf(buf, sizeof(buf), "%s=%s",
+ tp->args[i].name, tp->args[i].comm);
+ if (strcmp(buf, argv[i]))
+ return false;
+ }
+ return true;
+}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index d1714820efe1..4ee703728aec 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -89,6 +89,7 @@ enum fetch_op {
FETCH_OP_COMM, /* Current comm */
FETCH_OP_ARG, /* Function argument : .param */
FETCH_OP_FOFFS, /* File offset: .immediate */
+ FETCH_OP_DATA, /* Allocated data: .data */
// Stage 2 (dereference) op
FETCH_OP_DEREF, /* Dereference: .offset */
FETCH_OP_UDEREF, /* User-space Dereference: .offset */
@@ -222,11 +223,18 @@ struct probe_arg {
const struct fetch_type *type; /* Type of this argument */
};
-struct trace_probe {
+/* Event call and class holder */
+struct trace_probe_event {
unsigned int flags; /* For TP_FLAG_* */
struct trace_event_class class;
struct trace_event_call call;
struct list_head files;
+ struct list_head probes;
+};
+
+struct trace_probe {
+ struct list_head list;
+ struct trace_probe_event *event;
ssize_t size; /* trace entry size */
unsigned int nr_args;
struct probe_arg args[];
@@ -240,19 +248,19 @@ struct event_file_link {
static inline bool trace_probe_test_flag(struct trace_probe *tp,
unsigned int flag)
{
- return !!(tp->flags & flag);
+ return !!(tp->event->flags & flag);
}
static inline void trace_probe_set_flag(struct trace_probe *tp,
unsigned int flag)
{
- tp->flags |= flag;
+ tp->event->flags |= flag;
}
static inline void trace_probe_clear_flag(struct trace_probe *tp,
unsigned int flag)
{
- tp->flags &= ~flag;
+ tp->event->flags &= ~flag;
}
static inline bool trace_probe_is_enabled(struct trace_probe *tp)
@@ -262,45 +270,76 @@ static inline bool trace_probe_is_enabled(struct trace_probe *tp)
static inline const char *trace_probe_name(struct trace_probe *tp)
{
- return trace_event_name(&tp->call);
+ return trace_event_name(&tp->event->call);
}
static inline const char *trace_probe_group_name(struct trace_probe *tp)
{
- return tp->call.class->system;
+ return tp->event->call.class->system;
}
static inline struct trace_event_call *
trace_probe_event_call(struct trace_probe *tp)
{
- return &tp->call;
+ return &tp->event->call;
+}
+
+static inline struct trace_probe_event *
+trace_probe_event_from_call(struct trace_event_call *event_call)
+{
+ return container_of(event_call, struct trace_probe_event, call);
+}
+
+static inline struct trace_probe *
+trace_probe_primary_from_call(struct trace_event_call *call)
+{
+ struct trace_probe_event *tpe = trace_probe_event_from_call(call);
+
+ return list_first_entry(&tpe->probes, struct trace_probe, list);
+}
+
+static inline struct list_head *trace_probe_probe_list(struct trace_probe *tp)
+{
+ return &tp->event->probes;
+}
+
+static inline bool trace_probe_has_sibling(struct trace_probe *tp)
+{
+ struct list_head *list = trace_probe_probe_list(tp);
+
+ return !list_empty(list) && !list_is_singular(list);
}
static inline int trace_probe_unregister_event_call(struct trace_probe *tp)
{
/* tp->event is unregistered in trace_remove_event_call() */
- return trace_remove_event_call(&tp->call);
+ return trace_remove_event_call(&tp->event->call);
}
static inline bool trace_probe_has_single_file(struct trace_probe *tp)
{
- return !!list_is_singular(&tp->files);
+ return !!list_is_singular(&tp->event->files);
}
int trace_probe_init(struct trace_probe *tp, const char *event,
const char *group);
void trace_probe_cleanup(struct trace_probe *tp);
+int trace_probe_append(struct trace_probe *tp, struct trace_probe *to);
+void trace_probe_unlink(struct trace_probe *tp);
int trace_probe_register_event_call(struct trace_probe *tp);
int trace_probe_add_file(struct trace_probe *tp, struct trace_event_file *file);
int trace_probe_remove_file(struct trace_probe *tp,
struct trace_event_file *file);
struct event_file_link *trace_probe_get_file_link(struct trace_probe *tp,
struct trace_event_file *file);
+int trace_probe_compare_arg_type(struct trace_probe *a, struct trace_probe *b);
+bool trace_probe_match_command_args(struct trace_probe *tp,
+ int argc, const char **argv);
#define trace_probe_for_each_link(pos, tp) \
- list_for_each_entry(pos, &(tp)->files, list)
+ list_for_each_entry(pos, &(tp)->event->files, list)
#define trace_probe_for_each_link_rcu(pos, tp) \
- list_for_each_entry_rcu(pos, &(tp)->files, list)
+ list_for_each_entry_rcu(pos, &(tp)->event->files, list)
/* Check the name is good for event/group/fields */
static inline bool is_good_name(const char *name)
@@ -370,6 +409,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(BAD_VAR, "Invalid $-valiable specified"), \
C(BAD_REG_NAME, "Invalid register name"), \
C(BAD_MEM_ADDR, "Invalid memory address"), \
+ C(BAD_IMM, "Invalid immediate value"), \
+ C(IMMSTR_NO_CLOSE, "String is not closed with '\"'"), \
C(FILE_ON_KPROBE, "File offset is not available with kprobe"), \
C(BAD_FILE_OFFS, "Invalid file offset value"), \
C(SYM_ON_UPROBE, "Symbol is not available with uprobe"), \
@@ -393,7 +434,10 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(ARG_TOO_LONG, "Argument expression is too long"), \
C(NO_ARG_BODY, "No argument expression"), \
C(BAD_INSN_BNDRY, "Probe point is not an instruction boundary"),\
- C(FAIL_REG_PROBE, "Failed to register probe event"),
+ C(FAIL_REG_PROBE, "Failed to register probe event"),\
+ C(DIFF_PROBE_TYPE, "Probe type is different from existing probe"),\
+ C(DIFF_ARG_TYPE, "Argument type or name is different from existing probe"),\
+ C(SAME_PROBE, "There is already the exact same probe event"),
#undef C
#define C(a, b) TP_ERR_##a
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 743b2b520d34..5e43b9664eca 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -579,8 +579,7 @@ probe_wakeup(void *ignore, struct task_struct *p)
else
tracing_dl = 0;
- wakeup_task = p;
- get_task_struct(wakeup_task);
+ wakeup_task = get_task_struct(p);
local_save_flags(flags);
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 5d16f73898db..4df9a209f7ca 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -5,6 +5,7 @@
*/
#include <linux/sched/task_stack.h>
#include <linux/stacktrace.h>
+#include <linux/security.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>
@@ -53,6 +54,104 @@ static void print_max_stack(void)
}
}
+/*
+ * The stack tracer looks for a maximum stack at each call from a function. It
+ * registers a callback from ftrace, and in that callback it examines the stack
+ * size. It determines the stack size from the variable passed in, which is the
+ * address of a local variable in the stack_trace_call() callback function.
+ * The stack size is calculated by the address of the local variable to the top
+ * of the current stack. If that size is smaller than the currently saved max
+ * stack size, nothing more is done.
+ *
+ * If the size of the stack is greater than the maximum recorded size, then the
+ * following algorithm takes place.
+ *
+ * For architectures (like x86) that store the function's return address before
+ * saving the function's local variables, the stack will look something like
+ * this:
+ *
+ * [ top of stack ]
+ * 0: sys call entry frame
+ * 10: return addr to entry code
+ * 11: start of sys_foo frame
+ * 20: return addr to sys_foo
+ * 21: start of kernel_func_bar frame
+ * 30: return addr to kernel_func_bar
+ * 31: [ do trace stack here ]
+ *
+ * The save_stack_trace() is called returning all the functions it finds in the
+ * current stack. Which would be (from the bottom of the stack to the top):
+ *
+ * return addr to kernel_func_bar
+ * return addr to sys_foo
+ * return addr to entry code
+ *
+ * Now to figure out how much each of these functions' local variable size is,
+ * a search of the stack is made to find these values. When a match is made, it
+ * is added to the stack_dump_trace[] array. The offset into the stack is saved
+ * in the stack_trace_index[] array. The above example would show:
+ *
+ * stack_dump_trace[] | stack_trace_index[]
+ * ------------------ + -------------------
+ * return addr to kernel_func_bar | 30
+ * return addr to sys_foo | 20
+ * return addr to entry | 10
+ *
+ * The print_max_stack() function above, uses these values to print the size of
+ * each function's portion of the stack.
+ *
+ * for (i = 0; i < nr_entries; i++) {
+ * size = i == nr_entries - 1 ? stack_trace_index[i] :
+ * stack_trace_index[i] - stack_trace_index[i+1]
+ * print "%d %d %d %s\n", i, stack_trace_index[i], size, stack_dump_trace[i]);
+ * }
+ *
+ * The above shows
+ *
+ * depth size location
+ * ----- ---- --------
+ * 0 30 10 kernel_func_bar
+ * 1 20 10 sys_foo
+ * 2 10 10 entry code
+ *
+ * Now for architectures that might save the return address after the functions
+ * local variables (saving the link register before calling nested functions),
+ * this will cause the stack to look a little different:
+ *
+ * [ top of stack ]
+ * 0: sys call entry frame
+ * 10: start of sys_foo_frame
+ * 19: return addr to entry code << lr saved before calling kernel_func_bar
+ * 20: start of kernel_func_bar frame
+ * 29: return addr to sys_foo_frame << lr saved before calling next function
+ * 30: [ do trace stack here ]
+ *
+ * Although the functions returned by save_stack_trace() may be the same, the
+ * placement in the stack will be different. Using the same algorithm as above
+ * would yield:
+ *
+ * stack_dump_trace[] | stack_trace_index[]
+ * ------------------ + -------------------
+ * return addr to kernel_func_bar | 30
+ * return addr to sys_foo | 29
+ * return addr to entry | 19
+ *
+ * Where the mapping is off by one:
+ *
+ * kernel_func_bar stack frame size is 29 - 19 not 30 - 29!
+ *
+ * To fix this, if the architecture sets ARCH_RET_ADDR_AFTER_LOCAL_VARS the
+ * values in stack_trace_index[] are shifted by one to and the number of
+ * stack trace entries is decremented by one.
+ *
+ * stack_dump_trace[] | stack_trace_index[]
+ * ------------------ + -------------------
+ * return addr to kernel_func_bar | 29
+ * return addr to sys_foo | 19
+ *
+ * Although the entry function is not displayed, the first function (sys_foo)
+ * will still include the stack size of it.
+ */
static void check_stack(unsigned long ip, unsigned long *stack)
{
unsigned long this_size, flags; unsigned long *p, *top, *start;
@@ -158,6 +257,20 @@ static void check_stack(unsigned long ip, unsigned long *stack)
i++;
}
+#ifdef ARCH_FTRACE_SHIFT_STACK_TRACER
+ /*
+ * Some archs will store the link register before calling
+ * nested functions. This means the saved return address
+ * comes after the local storage, and we need to shift
+ * for that.
+ */
+ if (x > 1) {
+ memmove(&stack_trace_index[0], &stack_trace_index[1],
+ sizeof(stack_trace_index[0]) * (x - 1));
+ x--;
+ }
+#endif
+
stack_trace_nr_entries = x;
if (task_stack_end_corrupted(current)) {
@@ -358,6 +471,12 @@ static const struct seq_operations stack_trace_seq_ops = {
static int stack_trace_open(struct inode *inode, struct file *file)
{
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
return seq_open(file, &stack_trace_seq_ops);
}
@@ -375,6 +494,7 @@ stack_trace_filter_open(struct inode *inode, struct file *file)
{
struct ftrace_ops *ops = inode->i_private;
+ /* Checks for tracefs lockdown */
return ftrace_regex_open(ops, FTRACE_ITER_FILTER,
inode, file);
}
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 75bf1bcb4a8a..9ab0a1a7ad5e 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -9,7 +9,7 @@
*
*/
-
+#include <linux/security.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
@@ -238,6 +238,10 @@ static int tracing_stat_open(struct inode *inode, struct file *file)
struct seq_file *m;
struct stat_session *session = inode->i_private;
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
ret = stat_seq_init(session);
if (ret)
return ret;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 1ceedb9146b1..352073d36585 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -7,6 +7,7 @@
*/
#define pr_fmt(fmt) "trace_uprobe: " fmt
+#include <linux/security.h>
#include <linux/ctype.h>
#include <linux/module.h>
#include <linux/uaccess.h>
@@ -44,7 +45,7 @@ static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev);
static int trace_uprobe_release(struct dyn_event *ev);
static bool trace_uprobe_is_busy(struct dyn_event *ev);
static bool trace_uprobe_match(const char *system, const char *event,
- struct dyn_event *ev);
+ int argc, const char **argv, struct dyn_event *ev);
static struct dyn_event_operations trace_uprobe_ops = {
.create = trace_uprobe_create,
@@ -248,6 +249,9 @@ process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest,
case FETCH_OP_COMM:
val = FETCH_TOKEN_COMM;
break;
+ case FETCH_OP_DATA:
+ val = (unsigned long)code->data;
+ break;
case FETCH_OP_FOFFS:
val = translate_user_vaddr(code->immediate);
break;
@@ -284,13 +288,54 @@ static bool trace_uprobe_is_busy(struct dyn_event *ev)
return trace_probe_is_enabled(&tu->tp);
}
+static bool trace_uprobe_match_command_head(struct trace_uprobe *tu,
+ int argc, const char **argv)
+{
+ char buf[MAX_ARGSTR_LEN + 1];
+ int len;
+
+ if (!argc)
+ return true;
+
+ len = strlen(tu->filename);
+ if (strncmp(tu->filename, argv[0], len) || argv[0][len] != ':')
+ return false;
+
+ if (tu->ref_ctr_offset == 0)
+ snprintf(buf, sizeof(buf), "0x%0*lx",
+ (int)(sizeof(void *) * 2), tu->offset);
+ else
+ snprintf(buf, sizeof(buf), "0x%0*lx(0x%lx)",
+ (int)(sizeof(void *) * 2), tu->offset,
+ tu->ref_ctr_offset);
+ if (strcmp(buf, &argv[0][len + 1]))
+ return false;
+
+ argc--; argv++;
+
+ return trace_probe_match_command_args(&tu->tp, argc, argv);
+}
+
static bool trace_uprobe_match(const char *system, const char *event,
- struct dyn_event *ev)
+ int argc, const char **argv, struct dyn_event *ev)
{
struct trace_uprobe *tu = to_trace_uprobe(ev);
return strcmp(trace_probe_name(&tu->tp), event) == 0 &&
- (!system || strcmp(trace_probe_group_name(&tu->tp), system) == 0);
+ (!system || strcmp(trace_probe_group_name(&tu->tp), system) == 0) &&
+ trace_uprobe_match_command_head(tu, argc, argv);
+}
+
+static nokprobe_inline struct trace_uprobe *
+trace_uprobe_primary_from_call(struct trace_event_call *call)
+{
+ struct trace_probe *tp;
+
+ tp = trace_probe_primary_from_call(call);
+ if (WARN_ON_ONCE(!tp))
+ return NULL;
+
+ return container_of(tp, struct trace_uprobe, tp);
}
/*
@@ -352,15 +397,76 @@ static int unregister_trace_uprobe(struct trace_uprobe *tu)
{
int ret;
+ if (trace_probe_has_sibling(&tu->tp))
+ goto unreg;
+
ret = unregister_uprobe_event(tu);
if (ret)
return ret;
+unreg:
dyn_event_remove(&tu->devent);
+ trace_probe_unlink(&tu->tp);
free_trace_uprobe(tu);
return 0;
}
+static bool trace_uprobe_has_same_uprobe(struct trace_uprobe *orig,
+ struct trace_uprobe *comp)
+{
+ struct trace_probe_event *tpe = orig->tp.event;
+ struct trace_probe *pos;
+ struct inode *comp_inode = d_real_inode(comp->path.dentry);
+ int i;
+
+ list_for_each_entry(pos, &tpe->probes, list) {
+ orig = container_of(pos, struct trace_uprobe, tp);
+ if (comp_inode != d_real_inode(orig->path.dentry) ||
+ comp->offset != orig->offset)
+ continue;
+
+ /*
+ * trace_probe_compare_arg_type() ensured that nr_args and
+ * each argument name and type are same. Let's compare comm.
+ */
+ for (i = 0; i < orig->tp.nr_args; i++) {
+ if (strcmp(orig->tp.args[i].comm,
+ comp->tp.args[i].comm))
+ break;
+ }
+
+ if (i == orig->tp.nr_args)
+ return true;
+ }
+
+ return false;
+}
+
+static int append_trace_uprobe(struct trace_uprobe *tu, struct trace_uprobe *to)
+{
+ int ret;
+
+ ret = trace_probe_compare_arg_type(&tu->tp, &to->tp);
+ if (ret) {
+ /* Note that argument starts index = 2 */
+ trace_probe_log_set_index(ret + 1);
+ trace_probe_log_err(0, DIFF_ARG_TYPE);
+ return -EEXIST;
+ }
+ if (trace_uprobe_has_same_uprobe(to, tu)) {
+ trace_probe_log_set_index(0);
+ trace_probe_log_err(0, SAME_PROBE);
+ return -EEXIST;
+ }
+
+ /* Append to existing event */
+ ret = trace_probe_append(&tu->tp, &to->tp);
+ if (!ret)
+ dyn_event_add(&tu->devent);
+
+ return ret;
+}
+
/*
* Uprobe with multiple reference counter is not allowed. i.e.
* If inode and offset matches, reference counter offset *must*
@@ -370,25 +476,21 @@ static int unregister_trace_uprobe(struct trace_uprobe *tu)
* as the new one does not conflict with any other existing
* ones.
*/
-static struct trace_uprobe *find_old_trace_uprobe(struct trace_uprobe *new)
+static int validate_ref_ctr_offset(struct trace_uprobe *new)
{
struct dyn_event *pos;
- struct trace_uprobe *tmp, *old = NULL;
+ struct trace_uprobe *tmp;
struct inode *new_inode = d_real_inode(new->path.dentry);
- old = find_probe_event(trace_probe_name(&new->tp),
- trace_probe_group_name(&new->tp));
-
for_each_trace_uprobe(tmp, pos) {
- if ((old ? old != tmp : true) &&
- new_inode == d_real_inode(tmp->path.dentry) &&
+ if (new_inode == d_real_inode(tmp->path.dentry) &&
new->offset == tmp->offset &&
new->ref_ctr_offset != tmp->ref_ctr_offset) {
pr_warn("Reference counter offset mismatch.");
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
}
}
- return old;
+ return 0;
}
/* Register a trace_uprobe and probe_event */
@@ -399,18 +501,22 @@ static int register_trace_uprobe(struct trace_uprobe *tu)
mutex_lock(&event_mutex);
- /* register as an event */
- old_tu = find_old_trace_uprobe(tu);
- if (IS_ERR(old_tu)) {
- ret = PTR_ERR(old_tu);
+ ret = validate_ref_ctr_offset(tu);
+ if (ret)
goto end;
- }
+ /* register as an event */
+ old_tu = find_probe_event(trace_probe_name(&tu->tp),
+ trace_probe_group_name(&tu->tp));
if (old_tu) {
- /* delete old event */
- ret = unregister_trace_uprobe(old_tu);
- if (ret)
- goto end;
+ 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);
+ }
+ goto end;
}
ret = register_uprobe_event(tu);
@@ -664,6 +770,10 @@ static int probes_open(struct inode *inode, struct file *file)
{
int ret;
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
ret = dyn_events_release_all(&trace_uprobe_ops);
if (ret)
@@ -713,6 +823,12 @@ static const struct seq_operations profile_seq_op = {
static int profile_open(struct inode *inode, struct file *file)
{
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
return seq_open(file, &profile_seq_op);
}
@@ -897,7 +1013,10 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e
u8 *data;
entry = (struct uprobe_trace_entry_head *)iter->ent;
- tu = container_of(event, struct trace_uprobe, tp.call.event);
+ tu = trace_uprobe_primary_from_call(
+ container_of(event, struct trace_event_call, event));
+ if (unlikely(!tu))
+ goto out;
if (is_ret_probe(tu)) {
trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)",
@@ -924,27 +1043,71 @@ typedef bool (*filter_func_t)(struct uprobe_consumer *self,
enum uprobe_filter_ctx ctx,
struct mm_struct *mm);
-static int
-probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file,
- filter_func_t filter)
+static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter)
+{
+ int ret;
+
+ tu->consumer.filter = filter;
+ tu->inode = d_real_inode(tu->path.dentry);
+
+ if (tu->ref_ctr_offset)
+ ret = uprobe_register_refctr(tu->inode, tu->offset,
+ tu->ref_ctr_offset, &tu->consumer);
+ else
+ ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
+
+ if (ret)
+ tu->inode = NULL;
+
+ return ret;
+}
+
+static void __probe_event_disable(struct trace_probe *tp)
{
- bool enabled = trace_probe_is_enabled(&tu->tp);
+ struct trace_probe *pos;
+ struct trace_uprobe *tu;
+
+ list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
+ tu = container_of(pos, struct trace_uprobe, tp);
+ if (!tu->inode)
+ continue;
+
+ WARN_ON(!uprobe_filter_is_empty(&tu->filter));
+
+ uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
+ tu->inode = NULL;
+ }
+}
+
+static int probe_event_enable(struct trace_event_call *call,
+ struct trace_event_file *file, filter_func_t filter)
+{
+ struct trace_probe *pos, *tp;
+ struct trace_uprobe *tu;
+ bool enabled;
int ret;
+ tp = trace_probe_primary_from_call(call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENODEV;
+ enabled = trace_probe_is_enabled(tp);
+
+ /* This may also change "enabled" state */
if (file) {
- if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE))
+ if (trace_probe_test_flag(tp, TP_FLAG_PROFILE))
return -EINTR;
- ret = trace_probe_add_file(&tu->tp, file);
+ ret = trace_probe_add_file(tp, file);
if (ret < 0)
return ret;
} else {
- if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE))
+ if (trace_probe_test_flag(tp, TP_FLAG_TRACE))
return -EINTR;
- trace_probe_set_flag(&tu->tp, TP_FLAG_PROFILE);
+ trace_probe_set_flag(tp, TP_FLAG_PROFILE);
}
+ tu = container_of(tp, struct trace_uprobe, tp);
WARN_ON(!uprobe_filter_is_empty(&tu->filter));
if (enabled)
@@ -954,18 +1117,15 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file,
if (ret)
goto err_flags;
- tu->consumer.filter = filter;
- tu->inode = d_real_inode(tu->path.dentry);
- if (tu->ref_ctr_offset) {
- ret = uprobe_register_refctr(tu->inode, tu->offset,
- tu->ref_ctr_offset, &tu->consumer);
- } else {
- ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
+ list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
+ tu = container_of(pos, struct trace_uprobe, tp);
+ ret = trace_uprobe_enable(tu, filter);
+ if (ret) {
+ __probe_event_disable(tp);
+ goto err_buffer;
+ }
}
- if (ret)
- goto err_buffer;
-
return 0;
err_buffer:
@@ -973,33 +1133,35 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file,
err_flags:
if (file)
- trace_probe_remove_file(&tu->tp, file);
+ trace_probe_remove_file(tp, file);
else
- trace_probe_clear_flag(&tu->tp, TP_FLAG_PROFILE);
+ trace_probe_clear_flag(tp, TP_FLAG_PROFILE);
return ret;
}
-static void
-probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file)
+static void probe_event_disable(struct trace_event_call *call,
+ struct trace_event_file *file)
{
- if (!trace_probe_is_enabled(&tu->tp))
+ struct trace_probe *tp;
+
+ tp = trace_probe_primary_from_call(call);
+ if (WARN_ON_ONCE(!tp))
+ return;
+
+ if (!trace_probe_is_enabled(tp))
return;
if (file) {
- if (trace_probe_remove_file(&tu->tp, file) < 0)
+ if (trace_probe_remove_file(tp, file) < 0)
return;
- if (trace_probe_is_enabled(&tu->tp))
+ if (trace_probe_is_enabled(tp))
return;
} else
- trace_probe_clear_flag(&tu->tp, TP_FLAG_PROFILE);
-
- WARN_ON(!uprobe_filter_is_empty(&tu->filter));
-
- uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
- tu->inode = NULL;
+ trace_probe_clear_flag(tp, TP_FLAG_PROFILE);
+ __probe_event_disable(tp);
uprobe_buffer_disable();
}
@@ -1007,7 +1169,11 @@ static int uprobe_event_define_fields(struct trace_event_call *event_call)
{
int ret, size;
struct uprobe_trace_entry_head field;
- struct trace_uprobe *tu = event_call->data;
+ struct trace_uprobe *tu;
+
+ tu = trace_uprobe_primary_from_call(event_call);
+ if (unlikely(!tu))
+ return -ENODEV;
if (is_ret_probe(tu)) {
DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_FUNC, 0);
@@ -1100,6 +1266,27 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
return err;
}
+static int uprobe_perf_multi_call(struct trace_event_call *call,
+ struct perf_event *event,
+ int (*op)(struct trace_uprobe *tu, struct perf_event *event))
+{
+ struct trace_probe *pos, *tp;
+ struct trace_uprobe *tu;
+ int ret = 0;
+
+ tp = trace_probe_primary_from_call(call);
+ if (WARN_ON_ONCE(!tp))
+ return -ENODEV;
+
+ list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
+ tu = container_of(pos, struct trace_uprobe, tp);
+ ret = op(tu, event);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
static bool uprobe_perf_filter(struct uprobe_consumer *uc,
enum uprobe_filter_ctx ctx, struct mm_struct *mm)
{
@@ -1213,30 +1400,29 @@ static int
trace_uprobe_register(struct trace_event_call *event, enum trace_reg type,
void *data)
{
- struct trace_uprobe *tu = event->data;
struct trace_event_file *file = data;
switch (type) {
case TRACE_REG_REGISTER:
- return probe_event_enable(tu, file, NULL);
+ return probe_event_enable(event, file, NULL);
case TRACE_REG_UNREGISTER:
- probe_event_disable(tu, file);
+ probe_event_disable(event, file);
return 0;
#ifdef CONFIG_PERF_EVENTS
case TRACE_REG_PERF_REGISTER:
- return probe_event_enable(tu, NULL, uprobe_perf_filter);
+ return probe_event_enable(event, NULL, uprobe_perf_filter);
case TRACE_REG_PERF_UNREGISTER:
- probe_event_disable(tu, NULL);
+ probe_event_disable(event, NULL);
return 0;
case TRACE_REG_PERF_OPEN:
- return uprobe_perf_open(tu, data);
+ return uprobe_perf_multi_call(event, data, uprobe_perf_open);
case TRACE_REG_PERF_CLOSE:
- return uprobe_perf_close(tu, data);
+ return uprobe_perf_multi_call(event, data, uprobe_perf_close);
#endif
default:
@@ -1330,7 +1516,6 @@ static inline void init_trace_event_call(struct trace_uprobe *tu)
call->flags = TRACE_EVENT_FL_UPROBE | TRACE_EVENT_FL_CAP_ANY;
call->class->reg = trace_uprobe_register;
- call->data = tu;
}
static int register_uprobe_event(struct trace_uprobe *tu)
@@ -1399,7 +1584,7 @@ void destroy_local_trace_uprobe(struct trace_event_call *event_call)
{
struct trace_uprobe *tu;
- tu = container_of(event_call, struct trace_uprobe, tp.call);
+ tu = trace_uprobe_primary_from_call(event_call);
free_trace_uprobe(tu);
}